International Journal of Sustainable Energy

ISSN: (Print) (Online) Journal homepage: www.tandfonline.com/journals/gsol20

A systematic literature review on machine learning

applications at coal-fired thermal power plants for
improved energy efficiency

C. Bisset, P. V. Z. Venter & R. Coetzer

To cite this article: C. Bisset, P. V. Z. Venter & R. Coetzer (2023) A systematic literature
review on machine learning applications at coal-fired thermal power plants for improved
energy efficiency, International Journal of Sustainable Energy, 42:1, 845-872, DOI:
10.1080/14786451.2023.2244618

To link to this article: https://doi.org/10.1080/14786451.2023.2244618

© 2023 The Author(s). Published by Informa

UK Limited, trading as Taylor & Francis
Group

Published online: 22 Aug 2023.

Submit your article to this journal

Article views: 2208

View related articles

View Crossmark data

Citing articles: 4 View citing articles

Full Terms & Conditions of access and use can be found at

https://www.tandfonline.com/action/journalInformation?journalCode=gsol20
INTERNATIONAL JOURNAL OF SUSTAINABLE ENERGY
2023, VOL. 42, NO. 1, 845–872
https://doi.org/10.1080/14786451.2023.2244618

A systematic literature review on machine learning applications

at coal-fired thermal power plants for improved energy efficiency
a b c
C. Bisset , P. V. Z. Venter and R. Coetzer
a
School of Industrial Engineering, North-West University, Potchefstroom, South Africa; bSchool of Mechanical
Engineering, North-West University, Potchefstroom, South Africa; cSchool of Mathematical and Statistical Sciences,
North-West University, Potchefstroom, South Africa

ABSTRACT ARTICLE HISTORY

Power generation comprises high environmental and ecological impacts. Received 16 March 2023
The global power industry is under pressure to develop more efficient Accepted 17 July 2023
ways to operate and reduce the impacts of inherent process variability.
KEYWORDS
With the rapid development of technologies within the energy sector, Coal-fired thermal power
large volumes of data are available due to in-time operational plant; energy efficiency;
measurements. With increased computer processing capabilities, machine learning; systematic
machine learning is applied to explore these in-time operational literature review
measurements for improved process understanding. This research paper
investigates machine learning algorithms for energy efficiency
improvement at coal-fired thermal power plants by conducting a
systematic literature review. This research is essential since it provides
guidelines for applying machine learning towards sustainable energy
supply and improved decision-making. Subsequently, efficient processes
result in the reduction of fuel usage, which results in lower emission
levels for equivalent power generation capacity. Furthermore, this study
contributes towards future research by providing valuable insights from
academic and industry-related studies.

1. Introduction
The global power industry is under pressure to develop more efficient ways to operate and to reduce
the impact of variable operations on market supply and the environment (Sleiti, Kapat, and Vesely
2022). Minimal attention was given to energy management during the early 1970s (Petrecca 2014).
However, energy security was a big concern after the oil crisis, leading to more energy-efficient tech-
nologies and operations (Kaya and Keyes IV 1980). Studies published over the last few decades
focused predominantly on energy management, emphasising the need for more effective ways to
generate and use energy resources globally (Bunse et al. 2011; Narisco and Martins 2020; Schulze
et al. 2016). This need originates from the challenges that emerge by balancing the use of valuable
resources, the human population and providing proper living conditions (Narisco and Martins
2020).
Energy efficiency is the attempt to decrease the recourses used while considering resource
depletion, monetary savings, environmental impacts, and resource security (Lovins 2017; Patterson
1996). Energy efficiency is considered one of the primary contributors to a sustainable society and is

CONTACT C. Bisset [email protected]; [email protected]

© 2023 The Author(s). Published by Informa UK Limited, trading as Taylor & Francis Group
This is an Open Access article distributed under the terms of the Creative Commons Attribution-NonCommercial License (http://creativecommons.
org/licenses/by-nc/4.0/), which permits unrestricted non-commercial use, distribution, and reproduction in any medium, provided the original work
is properly cited. The terms on which this article has been published allow the posting of the Accepted Manuscript in a repository by the author(s) or
with their consent.
846 C. BISSET ET AL.

considered a critical aspect in all industries and countries. In South Africa, 2003 data indicate that
the mining sector consumes more than 175 PJ of energy annually. Thus, it is identified as the high-
est consumer of electricity (Oladiran and Meyer 2007). These energy-intensive operations could be
more sustainable, provided the government’s regulations on carbon emissions (Awuah-Offei 2016).
Numerous initiatives have been launched globally over the last few years to highlight the impor-
tance of energy efficiency (Narisco and Martins 2020), including, but not limited to, climate and
energy initiatives by the European environment agency (Climate & Energy Package 2020), and
the energy star programme (Energy Star Overview 2016). Given this high electricity demand, the
Chinese government and various other countries, including India (Mishra 2004) and Zimbabwe
(Murehwa et al. 2012), focus explicitly on thermal power plants for electricity generation. A thermal
plant consists of various boilers that feed into common steam receivers (Murehwa et al. 2012).
These feed sources are mainly coal, oil, nuclear or gas. Most power plants use coal to generate elec-
tricity (Bi et al. 2014; Murehwa et al. 2012).
A coal-fired boiler converts water into steam (Jagarnath 2019). Two boilers exist in coal-fired
thermal plants: the pulverised coal-fired boiler and the fluidised bed combustion boiler. In India,
70% of electricity is produced by coal-fired power plants, and in China, thermal power generation
contributes 73.4% to the total capacity (Bi et al. 2014; Mishra 2004). Coal generally has a low calo-
rific value and a high ash content (Mishra 2004). The problem is that the electricity generated from
these thermal power plants produces greenhouse gases, including nitrogen oxides (NOx ) and car-
bon monoxide (CO) (Bi et al. 2014). Therefore, the impact of power generation globally comprises
high environmental and ecological risks.
From an engineering viewpoint, Haddadin et al. (2023) indicated that a balance could be reached
by maintaining the current structure while increasing the use of renewable energy within power
plants. This prospect will provide a dual benefit for a cleaner environment amid a few changes
to the power system’s components and framework (Haddadin et al. 2023). Despite the need to
shift from coal to other renewable energy sources, the generation and production of electricity in
coal-fired thermal power plants will continue for at least another twelve years (Zima et al. 2022).
Coal-fired power plants generate 38% of electrical power worldwide (Kitto 1996). For this reason,
the focus should be on technological improvements, behavioural changes and the price or policy
tools to induce these changes towards optimal efficiency (Lovins 2017).
One operational objective of the coal-fired boiler is to reach optimal operating efficiency while
considering reliability and cost (Rambalee et al. 2011). Various technologies have been
implemented to optimise and stabilise these thermal plants. These technologies include model pre-
dictive control (MPC) and advanced process control (APC), which have been introduced to ensure
stable control of the boiler and to balance the burner management system (Rambalee et al. 2011).
These technologies contribute to reducing harmful emissions (i.e., NOx and CO).
With the rapid development of these technologies, a large quantity of data has been captured
(Sleiti, Kapat, and Vesely 2022). The volume of data is increasing in all sectors, which results in
more opportunities for improved efficiency (Narisco and Martins 2020). However, the structure
and volume of the datasets are becoming more complex and newer methods are required to deal
with these complexities (Sleiti, Kapat, and Vesely 2022). Most enterprises focus on machine learn-
ing (ML) to explore and operate these volumes of data (Narisco and Martins 2020). Machine learn-
ing is a subset of artificial intelligence (AI) (Shinde and Shah 2018). Ayodele (2010) stated that
analysing machine learning algorithms is classified as computational learning theory. Subsequently,
the learning is not considered consciousness learning but finding patterns in the data instead.
Machine learning algorithms provide valuable insight into the difficulty of learning relationships
in various environments (Ayodele 2010).
Machine learning techniques have been developed since the 1950s, and many advancements
have been made within the last few decades. Prominent machine learning applications include
the following industries: manufacturing (Wuest et al. 2016), retail (Jia, Zhao, and Tong 2013),
finance (Goodell et al. 2021), and the energy sector (Nabavi et al. 2020). There has been an increase
 INTERNATIONAL JOURNAL OF SUSTAINABLE ENERGY 847

in academic papers on energy management and various new developments focusing specifically on
machine learning and sustainability. However, Prashar (2017) stated that there is still a lack of
knowledge on implementing these concepts for energy efficiency.
For this reason, this research study aims to investigate machine learning applications at coal-
fired thermal power plants for improved energy efficiency by conducting a systematic literature
review. To achieve the aim, the following objectives have been formulated:

1. To provide an overview of the fundamentals of machine learning theory followed by an overview

of how these techniques are currently applied for energy efficiency.
2. To investigate which machine learning techniques are applied at coal-fired thermal power plants
for improved energy efficiency.
3. To investigate how these machine learning techniques are applied at coal-fired thermal power
plants for improved energy efficiency.
4. To identify the current literature limitations and to provide valuable future research
recommendations.

The research paper is outlined as follows. First, a detailed literature study on machine learning
algorithms is provided in Section 2, specifically on supervised, unsupervised, semi-supervised and
reinforcement learning. Section 3 outlines the search protocol developed for the systematic litera-
ture review and discusses the results in Section 4. Conclusions and future recommendations based
on the results obtained in this study are provided in Sections 5 and 6, respectively.

2. Literature review: the application of machine learning for energy efficiency

improvements
Artificial intelligence (AI), in general, impacts the energy sector since it can assist in the develop-
ment of clean, cheap, and reliable energy (Makala and Bakovic 2020). Furthermore, AI eliminates
energy waste and reduces energy costs by improving the planning, operations, and control of var-
ious power systems (Makala and Bakovic 2020). Machine learning is a subset of AI closely related to
statistics (Ongsulee 2017). First, an overview of the fundamentals of machine learning is provided,
followed by a few case studies on how some of these algorithms are applied for improved energy
efficiency in the industry.

2.1. An overview of machine learning

Machine learning techniques are divided into supervised, unsupervised, semi-supervised, and
reinforcement learning (Bhatt 2019). Supervised learning develops an artificial system that maps
the relationships or the patterns between the input and the output variables (Liu 2011). Based
on these findings, the system predicts outcomes based on new information by referring to the
relationships and patterns identified during the learning process. Classification of the input data
is determined if the output takes a finite set of discrete values. In contrast, regression of the
input data is identified if the output takes continuous values. With supervised learning, the
input-output relationships are based on specific parameters. These unknown parameters must
first be determined by training the algorithms (Liu 2011). The structure of supervised learning is
demonstrated in Figure 1 (Liu 2011):
With supervised learning, the training data need to be labelled (Liu 2011). Labelled data are
already tagged with the specific output (Javatpoint 2022). The training sample is identified as
{Xi , Yi }. The variable (Xi ) is the system input, and (Yi ) is the system’s output.
The indices (i) is defined as the index of the training sample. First, (Xi ) is fed to the learning sys-
tem, and an output (Ỹ i )
is generated. The output variable (Ỹ i ) is compared to the labelling (Yi ) by
an arbitrator. This arbitrator computes the difference between the (Yi ) and (Ỹ i )variables. The
848 C. BISSET ET AL.

Figure 1. Supervised learning algorithm (Liu 2011).

difference between the two variables, which is the error signal, is sent back to the learning system.
The system evaluates the difference and adjusts the parameters accordingly to minimise the error
signal, the difference between the (Yi ) and(Ỹ i )variables. The primary purpose of this learning pro-
cess is to minimise the error signal of the training set, and to obtain the optimal set of learning sys-
tem parameters (Liu 2011).
The objective of training the artificial system is to estimate the parameters based on known data,
whereas testing aims to assess the predictions on unseen data. The data used in the training process
are not used in the testing of the system. For this reason, it is not guaranteed that the system will
perform the same in both instances. In addition, the training process is complex and lacks general-
izability. Generalizability is defined when the system is trained to minimise training error and com-
plexity (Liu 2011).
Supervised learning algorithms include, but are not limited to, linear classifiers such as the sup-
port vector machine, decision tree, and Bayesian networks (Ayodele 2010). Supervised learning can
be used for discriminative pattern classification since the classes can be manipulated. However, with
supervised learning, collecting and labelling unlabelled data is challenging. Various mistakes can
occur, and it is time-consuming (Liu 2011). In the following sections, various machine learning
algorithms are explained.

2.1.1. The support vector machine

A support vector machine is an algorithm that assigns labels to objects in the dataset (Boser, Guyon,
and Vapnik 1992). The purpose is to find an optimal hyperplane within a specific N-dimensional
space (Gandhi 2018). In this N-dimensional space, the data points are classified accordingly, as
demonstrated in Figure 2 (Gandhi 2018).

Figure 2. The support vector machine: Potential hyperplane (Gandhi 2018).

 INTERNATIONAL JOURNAL OF SUSTAINABLE ENERGY 849

The hyperplanes in N-dimensional space separate two classes from each other. The primary goal
is to select the hyperplane with the maximum margin. A maximum margin is defined as the maxi-
mum distance between the two classes.
Gandhi (2018) stated that future data points could be classified with more confidence by max-
imising the distance. A hyperplane depends on the number of features. The hyperplane is a line if
the support vector machine has two features. However, if the number of features is three, the hyper-
plane is two-dimensional. A support vector is a data point closest to the hyperplane. Subsequently,
this vector influences the position and orientation of the hyperplane (Lovins 2017).

2.1.2. The decision tree

A decision tree is applied to solve classification and regression problems (Gupta 2017). An upside
tree represents the decision-making process. The tree consists of internal nodes, which are split into
branches. A decision is made at the end of each branch. A classification tree primarily aims to clas-
sify the data points according to the classes, whereas a regression tree predicts continuous values
(Gupta 2017).
With a decision tree, all the features and attributes are considered in the decision-making pro-
cess. The cost is linked to the accuracy of the prediction. For example, a function calculates how
much accuracy each decision tree split will cost. The split with the least cost is selected. A cost func-
tion is typically used for both classification and regression problems. For regression, the following
cost function is formulated:

Regression: (Yi − Ỹ i )2 (1)

The average response of the training data of the group is considered the prediction for that group.
The function is applied to all the data, and the cost is calculated accordingly. For classification, the
following cost function is formulated:

K
Classification:G = ( pk (1 − pk )) (2)
k=1

The variable (pk ) is the proportion within each class k, k = 1, 2, . . . , K. A perfect class purity is
defined when the (pk ) value is either 1 or 0, meaning the group contains all inputs from a similar
class. A minimum number of training inputs on each leaf can be defined for a decision tree. This
will ensure that the tree stops splitting after reaching a specific number of splits. Subsequently, the
parameter known as the maximum depth can also be set, which is defined as the length of the long-
est path from the tree’s root to the leaf (Gupta 2017).
Other supervised machine learning techniques include the Bayesian network, Naive Bayes and
the Gaussian Process (GP). The Bayesian network is a probabilistic model that mainly uses Bayesian
inference to compute probabilities. The model consists of nodes and directed edges (Brownlee
2019). These models consider conditionally dependent and independent relationships between ran-
dom data points. Like the rest of the algorithms discussed in this section, these models are also
trained before predicting the probabilities of events.
The Naïve Bayes is defined as a probabilistic model based on the Bayes Theorem. The Naïve
Bayes algorithm is mainly applied to solve classification problems. Bayes Theorem is defined as fol-
lows (Chauhan 2022):
P(B|A)P(A)
P(A|B) = (3)
P(B)
where P(A|B) is the probability of A occurring, given B has already occurred. P(B|A) is the prob-
ability of B occurring given A has already occurred. P(A) is defined as the probability of A occur-
ring, and P(B) is the probability of B occurring.
850 C. BISSET ET AL.

The Gaussian Process (GP) is designed specifically to solve regression and probabilistic classifi-
cation problems. These processes are versatile, so various kernels can be specified, and the predic-
tion interpolates the observations. However, these processes lose efficiency in high-dimensional
spaces (Yi 2022).
Unlike supervised learning, unsupervised learning algorithms do not use labelled data (Ayodele
2010). Unsupervised learning is complex since the hidden patterns and relationships between the
data points are unknown. Unsupervised learning algorithms primarily aim to identify hidden pat-
terns and group similarities (Javatpoint 2022).
The unsupervised learning algorithm mainly addresses three problems (IBM Cloud Education
2020b): clustering, association, and dimensionality reduction. Clustering is defined as a method
that clusters or groups objects in one specific group that has similarities (Javatpoint 2022). An
association rule is a method that identifies the relationships between various variables in a dataset
(Javatpoint 2022). The size of the datasets used influences the performance. However, overfitting is
a common challenge when working with large data sets. Dimension reduction is applied to reduce
the number of features. This algorithm also preserves the integrity of the data while reducing the
variables to a reasonable size (IBM Cloud Education 2020b).
Unsupervised learning algorithms can solve complex problems in a considerable amount of
time. However, the output might not be as accurate as supervised learning since the data is not
labelled, and no result is known in advance (javatpoint 2022). One of the most popular unsuper-
vised learning algorithms is neural networks (NN). This algorithm is discussed in the following
section.

2.1.3. Neural networks

Neural networks (NN) are also known as artificial neural networks (ANN) or simulated neural net-
works (SNN) (IBM Cloud Education 2020a). These networks are a subset of machine learning at the
centre of deep learning. Neural networks consist of node layers (input, hidden, and output layers).
The structure of a deep neural network is presented in Figure 3 (IBM Cloud Education 2020a).
Each node or artificial neuron consists of a weight and threshold. As stated in Section 2.1, each
algorithm must be trained to improve accuracy over time. Training of the algorithm contributes
towards the accuracy of the prediction. Once properly trained, the algorithm can be employed as

Figure 3. The deep neural networks (IBM Cloud Education 2020a).

 INTERNATIONAL JOURNAL OF SUSTAINABLE ENERGY 851

a powerful machine learning tool, specifically for image and speech recognition. A node is similar to
a linear regression model, consisting mainly of data, weights, a threshold value, and an output. A
node’s equation is defined as follows (IBM Cloud Education 2020a):

m
wi xi + bias = w1 x1 + w2 x2 + w3 x3 + . . . + wm xm + bias (4)
i=1

Weights (wi ) are assigned to the node when the input layer is determined. The weight depends
on the importance of the provided variable (IBM Cloud Education 2020a). An activation function is
used to determine the output. An activation function is defined as follows (IBM Cloud Education
2020a):
⎧ 
⎨ 1 if wi xi + b ≥ 0
Output = f (x) = i
(5)
⎩ 0 if wi xi + b , 0
i

If the predicted output of a specific node is above the threshold value, the node is activated, and data
is sent to the following layer of the entire network. Therefore, the output of one node becomes the
input of another. A feedforward neural network is defined when data is passed from one node to
another in the network (IBM Cloud Education 2020a).
There exist various types of artificial neural networks. Only the most common types are dis-
cussed in this paper. Figure 4 depicts the most basic neural network as demonstrated by Frank
Rosenblatt in 1958 (Rosenblatt 1958):
Feedforward neural networks are also referred to as multi-layer perceptions (MLPs). They are
comprised of sigmoid neurons and not perceptions since most real-world problems are non-linear.
Convolutional neural networks (CNN) typically use principles from linear algebra, specifically
matrix multiplication, to identify specific relationships in the data. Recurrent neural networks
(RNN) consist of various feedback loops. Time-series data are used to make precise predictions
(Rosenblatt 1958).
Johnson (2022) stated that one of the most common ways to train neural networks is to use the
backpropagation method. This method is applied by tuning the neural network weights by consid-
ering the error rate obtained from the previous epoch. As explained in Section 2.1, the primary pur-
pose of training any machine learning algorithm is to reduce the error rate to deliver a more reliable
model for accurate predictions. This approach is mostly followed in training neural networks since
it is fast and easy to programme. There are no parameters to tune except the number of inputs, and
it is considered flexible (Johnson 2022).
A study conducted by Smrekar et al. (2009) employed machine learning by developing an artifi-
cial neural network (ANN) model that predicts steam properties from a coal-fired boiler. The
authors considered three input parameters: steam pressure, temperature, and flow. The models

Figure 4. The neural networks (Rosenblatt 1958).

852 C. BISSET ET AL.

developed in this study yielded high accuracy on both the training and testing data. Furthermore,
the study demonstrated the usefulness of ANN modelling for coal-fired boilers. The authors stated
that some boiler processes, such as pulverises and combustion, are challenging to develop physical
models since the relations between these variables are not always known. For this reason, ANN
models are applicable since these types of models can consider most things known and unknown
(Smrekar et al. 2009).
Other unsupervised machine learning techniques include the K-Nearest Neighbor and the K-
means clustering. The K-Nearest Neighbor is applied to solve both classification and regression pro-
blems. The K-Nearest Neighbor assumes that similar characteristics exist between data points near
each other. The euclidean distance is used to calculate the distance between the data points (Har-
rison 2018).
The K-means clustering technique divides data points into K groups, where K is defined as the
number of clusters (IBM Cloud Education 2020b). The number of clusters is based on the distance
from each group’s centroid. All points allocated near the centroid are clustered into one category. A
small K-value indicates large groupings with less granularity, and a large K-value means smaller
groupings with more granularity.
Semi-supervised learning is defined when the data is only half labelled (IBM Cloud Education
2020b). Subsequently, unsupervised and semi-supervised learning is mainly applied to prevent
data from being incorrectly labelled.

2.1.4. Reinforcement learning

Supervised and reinforcement learning utilises a function that maps the dependency between the
input and output data (Song et al. 2013). However, supervised learning provides a correct set of
actions to obtain a specific output, whereas reinforcement learning uses rewards and punishments
to obtain a particular result (Bhatt 2019).
Unsupervised learning and reinforcement learning’s objectives are different. Unsupervised
learning recognises the patterns between data points, whereas reinforcement learning identifies
an action model. This action model aims to maximise the total cumulative rewards of the system.
Figure 5 provides an overview of the action-reward feedback loop of reinforcement learning (Bhatt
2019):
The state (St ) is defined as the agent’s current state. The reward variable (Rt ) indicates the feed-
back from the environment, and a policy refers to the method used to map the agent’s actions (Bhatt
2019). The environment is defined as the space the agent operates in, and the value (Rt+1 ) is defined
as the future reward the agents may receive if a specific action (At ) is followed. The primary objec-
tive is to build an optimal policy while maximising the reward. In reinforcement learning,

Figure 5. Reinforcement learning algorithm (Bhatt 2019).

 INTERNATIONAL JOURNAL OF SUSTAINABLE ENERGY 853

exploration and exploitation are prevalent definitions. A decision must be made where both are
balanced (Bhatt 2019).

2.1.5. Errors and evaluation criteria

The performance of a machine learning model is analysed based on the prediction error against
the validation dataset. This study presents and discusses the coefficient of determination (R2 ),
root-mean-square error (RMSE), normalised RMSE, mean absolute error (MAE) and mean
absolute percentage error (MAPE). The values obtained from these performance metrics provide
information on the machine learning model’s robustness and effectiveness (Muhammad Ashraf
et al. 2020).
Assume (n) presents the sample size used as input, (yi ) and (ŷi ) denote the predicted values and
the actual values, respectively. The maximum and minimum value of (yi ) are denoted by (ymax ) and
(ymin ), respectively. The coefficient of determination (R2 ) is given in Equation (6).
n
i=1 (yi − ŷi )
2
SRESIDUAL
R =1−
2
=1−  (6)
STOTAL n 1 n 2

i=1 yi − y
i=1 i
n
Nagelkerke (1991) indicated that the coefficient of determination estimates the percentage of
variance explained in a given dataset. The root-mean-square error (RMSE) and the normalised
RMSE are estimated as illustrated in Equations (7–8)

1 n
RMSE = (yi − ŷi )2 (7)
n i=1

RMSE
NRMSE = × 100% (8)
ymax − ymin
The root-mean-square error (RMSE) estimates the standard deviation of the residuals between
the predicted values and the actual values of an observation (Otto 2019). Furthermore, the normal-
ised RMSE (NRMSE) enables comparing various models with different scales (Otto 2019). The
mean absolute error (MAE) and mean absolute percentage error (MAPE) are illustrated in
Equations (9–10)
1 n
MAE = |yi − ŷi | (9)
n i=1

1 n
yi − ŷi
MAPE = × 100% (10)
n i=1 yi

The mean absolute error (MAE) presents the error obtained between the predicted values and the
real values of the specific dataset (Qi et al. 2020). Furthermore, the mean absolute percentage error
(MAPE) estimates the average magnitude of the error between the predicted value and the actual
values of a specific dataset (De Myttenaere et al. 2016).
Baressi Šegota et al. (2020) stated that the K-fold cross-validation is part of the training pro-
cess of a machine learning model, specifically when the data sets used are small. First, the data is
split into k splits, where (k−1) subsets of the dataset are used for training, and the remaining
subset is used for testing. This process is repeated k times until all the splits have been used
as the testing split precisely once. Subsequently, this allows the entire dataset to be used as a test-
ing set systematically and provides more information on the model’s performance (Baressi
Šegota et al. 2020).
854 C. BISSET ET AL.

2.2. The application of machine learning for improved energy efficiency

Machine learning applications also include, but are not limited to, renewable energy predictions,
fault detection and power quality monitoring. Renewable energy resources, including wind
power, hydropower, and photovoltaic energy, have gained attention over the last few years and
are considered alternative energy supply (Sogabe et al. 2018). The problem encountered with
renewable energy resources is often a mismatch between the electricity supply and demand, result-
ing in instability and limited power output (Sogabe et al. 2018). Virtualitics (2021) added that the
power demand and generation must always be equivalent to prevent blackouts due to inefficient
energy.
However, machine learning algorithms can predict the electricity required for any renewable
source for a specific period to satisfy demand. Virtualitics (2021) argued that these predictions
and evaluations will contribute towards reducing harmful emissions by encouraging the use of
reliable renewable energy sources as an alternative to coal or other non-renewable energy. Sogabe
et al. (2018) indicated that there is a need for a practical approach to address these types of issues.
Khan and Khan (2013) proposed smart grids due to their ability for intelligent, robust, and func-
tional power grids. Sogabe et al. (2018) applied two deep reinforcement learning techniques for
smart grid optimisation. These techniques captured the supply and demand feature and selected
the appropriate behaviour, maximising the reward of the deep reinforcement learning model
(Sogabe et al. 2018). The beforementioned studies provide a general overview of how these algor-
ithms can assist with better decision-making.
Despite using renewable energy sources, clean coal power plants are still one of the dominant
choices for power generation by developing energy-efficient operations and ensuring carbon cap-
ture and storage (Haddadin et al. 2023). Haddad and Mohamed (2022) stated that, with the new-
est advancements in clean coal technologies, it is essential to gain a fundamental and
comprehensive understanding of these modelling philosophies. For this reason, this study focuses
on machine learning applications at coal-fired thermal power plants for improved energy
efficiency.
One of the leading causes of failure in a steam power plant is defined as boiler waterwall tube
leakage (Khalid et al. 2020). In 2021, Khalid, Hwang, and Kim (2021) stated that the primary
reason for failure in thermal power plants is equipment, specifically boiler and turbine faults
(Khalid, Hwang, and Kim 2021). Based on these two studies, the authors indicated that devel-
oping efficient fault-detection processes in power plants is required. These intelligent tube leak-
detection systems can improve the efficiency and reliability of modern power plants (Khalid
et al. 2020; Khalid, Hwang, and Kim 2021). Khalid, Hwang, and Kim (2021) proposed a
novel machine learning-based optimal sensor selection to analyse the turbine and boiler faults
in the power plant. The results of this study demonstrated that the machine learning models’
computational efficiency was enhanced by reducing the number of sensors for both scenarios.
Furthermore, the performance of these models was improved by up to 97% and 92.60% in
the water wall tube leakage and the turbine motor fault, respectively (Khalid, Hwang, and
Kim 2021).
Alvarez Quiñones, Lozano-Moncada, and Bravo Montenegro (2023) proposed a methodology to
schedule predictive maintenance of distribution transformers using machine learning. The authors
focused explicitly on classification predictive modelling to obtain the minimal number of distri-
bution transformers prone to fail. In conclusion, the machine learning methodology was
implemented and saved 13% in corrective maintenance expenses in one specific year (Alvarez Qui-
ñones, Lozano-Moncada, and Bravo Montenegro 2023).
In the study conducted by Haddadin et al. (2023), the Elman neural network (ENN) and the gen-
eralised regression neural network (GRNN) were proposed for a cleaner coal-fired supercritical
unit. These models obtained more accurate results than previously published models. Subsequently,
the authors predicted the supercritical pressure, the production, and the steam temperature. It is
 INTERNATIONAL JOURNAL OF SUSTAINABLE ENERGY 855

important to note that these variables have been selected since they represent energy efficiency and
cleaner production. The Mean Square Error was used as a performance metric to evaluate the
models’ effectiveness and performance (Haddadin et al. 2023).
From these case studies, it is evident that the application of machine learning is extended to
solve a wide range of problems in various areas, including renewable energy predictions, fault
detection and optimal power generation in coal-fired thermal power plants. Furthermore,
machine learning provides the ability to make more accurate decisions in real-time and deliver
sustainable solutions (Ghosh 2017). To further extend the machine learning analysis, an in-
depth investigation is conducted on the type of machine learning algorithms and how these algor-
ithms were applied in coal-fired thermal power plants for improved energy efficiency from 2012 -
2022. First, the research method of the systematic literature review is outlined, followed by a dis-
cussion of the results.

3. A systematic literature review: the review protocol

The number of published papers in various research fields exponentially increases, resulting in
information overload. Pejić-Bach and Cerpa (2019) stated that there is a gap between the number
of published articles and the time to review these studies. A systematic literature review addresses
this gap by providing insight into only the relevant papers and their scientific development (Pejić-
Bach and Cerpa 2019).
A systematic literature review is considered evidence-based research and originated in the medi-
cal industry (Kitchenham et al. 2009). Kitchenham et al. (2009) defined the word evidence as a syn-
thesis of the best quality studies in the academic literature of a particular topic or research field. A
systematic literature review is different from a formal literature review since a methodologically rig-
orous method is followed to obtain research results (Kitchenham et al. 2009).
In this paper, a systematic literature review is conducted to investigate machine learning appli-
cations at coal-fired thermal power plants for improved energy efficiency. The systematic literature
review conducted in this study is based on the guidelines proposed by Kitchenham et al. (2009) and
Kumar and Garg (2020). Kitchenham et al. (2009) conducted a systematic literature review to ident-
ify the status of Evidence-based Software Engineering (EBSE) papers since 2004, and Kumar and
Garg (2020) conducted a systematic literature review on context-based sentiment analysis in social
multimedia.
Kitchenham et al. (2009) method consists of seven stages, including the formulation of
research questions, search process, inclusion and exclusion criteria, quality assessment, data col-
lection, data analysis and deviations from the protocol. The review process by Kumar and Garg
(2020) was divided into six stages: formulating the research questions, search strategy, study
selection, quality assessment, data extraction and data synthesis. The search protocol followed
in this paper consists of five stages: Formulating the research questions, the search process,
study selection: Inclusion and exclusion criteria, quality assessment, data extraction, and data
synthesis.

3.1. Research question formulation

The following research questions were formulated to collect and collate research evidence from
existing studies:

I. Research Question 1: Which machine learning algorithms were applied at coal-fired thermal
power plants for improved energy efficiency?
II. Research Question 2: How were these machine learning algorithms applied at coal-fired ther-
mal power plants for improved energy efficiency?
856 C. BISSET ET AL.

3.2. Search process

The search process consists of defining keywords in locating only the relevant studies. Scientific
papers that contain all three keywords were selected:

1. Machine learning
2. Energy efficiency
3. Coal-fired thermal power plant

A manual search was conducted, and only published scientific journal articles were selected. The
following databases were used to identify the relevant studies:

1. Science Direct
2. Scopus
3. Web of Science
4. IEEE Explore
5. Emerald Insight

3.3. Study selection: inclusion and exclusion criteria

The following studies were included in the search process:

1. Only published journal articles were included in the search process.

2. Journal articles containing the following three keywords: Machine learning, energy efficiency
and coal-fired thermal power plant. These studies may include any review study or studies
that refer to other studies containing the relevant keywords.
3. Journal articles that were published between 2012 and 2022.

The following studies were excluded from the search process:

1. Non-English articles

3.4. Quality assessment process

For the quality assessment, Kitchenham et al. (2009) followed the database of abstracts of reviews of
effects (DARE) criterion outlined by York University. This criterion is explicitly defined for studies
that evaluate other studies that conducted a systematic literature review. The systematic literature
review conducted in this study identified all types of studies. For this reason, quality assessment cri-
teria are used as outlined by Albliwi et al. (2014) and Mangaroo-Pillay and Coetzee (2022). This
assessment consists of four phases: Identification, screening, eligibility, and inclusion. Each phase
is described in Table 1.

3.5. Data extraction

The data extracted from each study were the following:

1. The fundamentals of each study (Table 2).

2. The type of machine learning algorithm applied (Table 2).
3. The year of publication (Table 2).
4. The databases (Table 2).
 INTERNATIONAL JOURNAL OF SUSTAINABLE ENERGY 857

Table 1. The quality assessment process.

Phases Description of each phase
Identification The databases were searched using the defined keywords in each study’s title, abstract and keywords. The
following results were obtained:
1. Science Direct = 2
2. Scopus = 11
3. Web of Science = 0
4. IEEE Explore = 1
5. Emerald Insight = 0
Total = 14
Screening The following results were obtained by screening the studies to ensure that each study adheres to the inclusion
and exclusion criteria, as outlined in Section 3.3.
1. Science Direct = 2
2. Scopus = 11
3. Web of Science = 0
4. IEEE Explore = 1
5. Emerald Insight = 0
Total = 14

Eligibility All duplicates were removed after screening each study to ensure the studies met the inclusion and exclusion
criteria. No duplicates were identified.
1. Science Direct = 2
2. Scopus = 11
3. Web of Science = 0
4. IEEE Explore = 1
5. Emerald Insight = 0
Total = 14
Inclusion A full-text assessment was done on all 14 studies to investigate machine learning applications at coal-fired
thermal power plants for improved energy efficiency. The results are discussed in Section 4.

One researcher extracted the data, and the other checked the extraction. All three researchers
evaluated the selected studies to ensure that the studies adhered to the quality assessment
process.

3.6. Data analysis

Each study identified is summarised in Table 2 to show:

1. The title of each study

2. The type of machine learning algorithm applied in coal-fired thermal power plants for energy
efficiency.
3. Each database the study was published in.
4. The year of publication.
5. Reference.

4. Discussion of results
In this section, the results are discussed.

4.1. Search results

As indicated in Section 3, the review results are collected by the following information: Title, the
type of machine learning model applied, published year, database, and reference. The studies ident-
ified were divided into three sections: Those that applied machine learning models, review papers
and others. Others are defined as papers that did not apply machine learning models; however, the
858 C. BISSET ET AL.

Table 2. Systematic literature review results.

Type of machine learning model
# Title of the study applied Year Database Reference
1 Digital twin in the energy industry: A deep reinforcement learning (DLR) 2022 Science Sleiti, Kapat, and
Proposed a robust digital twin for model Direct Vesely (2022)
power plants and other complex
capital-intensive large engineering
systems.
2 Energy digital twin technology for Review paper: The existing literature 2022 Science Yu et al. (2022)
industrial energy management: on energy digital twin technology Direct
Classification, challenges, and was investigated in this study. The
future. authors highlighted the advantages,
including improvements in energy
management and optimisation,
improved maintenance and
servicing, and enhanced renewable
energy. This study proposes an
original multi-dimensional digital
twin with guidelines demonstrating
how these technologies can be
applied to reduce the carbon
footprint
3 Thermal calculations of a natural Other – A methodology was 2022 Scopus Zima et al. (2022)
circulation power boiler operating developed specifically for the
under a wide range of loads. thermal flow of a natural circulation
power boiler and contributed
towards the power boiler’s design
process. Various in-house methods
were formulated and used in
conjunction with the literature. This
method is developed to compute
the heat transfer in the combustion
gas duct’s wall superheaters and
hanger tubes. Following these
calculations, a computer
programme was developed. Various
other CFD computations were
performed that focused explicitly on
the boiler furnace chamber. The
results were compared to the data
provided by the manufacturer. Only
slight differences were observed,
and the models were verified.
4 A Review on the Adoption of AI, BC, Review paper: Artificial intelligence 2022 Scopus Wu et al. (2022)
and IoT in Sustainability Research (AI), blockchain (BC), and the
internet of Things (IoT) are the
factors influencing the
advancement of sustainability the
most. This study aimed to
investigate how digital
transformation drives natural and
human systems by conducting a
bibliometric analysis. The authors
assessed 960 studies, concluding
that most advancements were
made in the following sectors: Smart
cities, energy systems and supply
chain management. Artificial
intelligence contributed towards
these advancements by assisting
with scheduling, predicting, and
monitoring energy systems within
smart cities. In conclusion, these
authors stated that there is an
increase in the technological

(Continued )
 INTERNATIONAL JOURNAL OF SUSTAINABLE ENERGY 859

Table 2. Continued.
Type of machine learning model
# Title of the study applied Year Database Reference
integration of AI and IoT, specifically
in the smart city and energy sectors.
5 The Implementation of K-Means K-Means clustering 2022 Scopus Wahyuningtyas and
Clustering in Coal-fired Power Plant Asrol (2022)
Performance.
6 A systematic review of big data in Review paper: Energy computing 2022 Scopus Dhanalakshmi and
energy analytics using energy techniques in the energy-orientated Ayyanathan
computing techniques domain were investigated in this (2022)
study. The authors indicated an
increase in energy analytics due to
the rapid increase in data. In
conclusion, this study highlighted
that the thermal power plant, smart
grid, and power systems datasets
were extensively utilised, and the
artificial neural network (ANN) was
mainly applied.
7 Repowering Industrial Combined Other – This study is classified as a 2022 Scopus Variny and
Heat and Power Units: a gas turbine-based repowering Kšiňanová (2022)
contribution to Cleaner Energy study. Repowering industrial units
Production results in a reduction of greenhouse
gas emissions. This study specifically
focused on fuel and carbon
monoxide reduction. In conclusion,
two conservative repowering
options were identified, and both
indicated feasible economics with a
simple payback period.
8 Improvement of marine steam An Artificial neural network – A multi- 2020 Scopus Baressi Šegota et al.
turbine conventional exergy layered perceptron (MLP) (2020)
analysis by neural network
application
9 Optimisation of a 660 MWE The following machine learning 2020 Scopus Muhammad Ashraf
supercritical power plant methods were developed in this et al. (2020)
performance: A case of industry 4.0 study: 1. Artificial neural network
in the data-driven operational (ANN): 2. Multiple linear regression
management. Part 2: power (MLR): 3. The least-square vector
generation machine (LSSVM)
10 Artificial neural network and its Review paper: This study aimed to 2020 Scopus Babatunde (2020)
applications in the energy sector – summarise artificial intelligence
An overview methods’ significance in the energy
sector. The authors indicated that
artificial neural networks are
effective methods designed to solve
complex problems within
modelling, control, and
optimisation.
11 Data-driven framework for boiler Other – This study aimed to propose 2016 Scopus Nikula, Ruusunen,
performance monitoring a framework for monitoring a steam and Leiviskä
boiler’s real-time operations. The (2016)
boiler’s actual efficiency was
compared and monitored with the
expected efficiency. The
performance of the boiler is
measured using a statistical process
control chart. The framework was
verified using fluidised bed boiler
and corner-fired boiler historical
data. In conclusion, the strongest
correlations between the variables
and boiler efficiency were consistent
in both cases.

(Continued )
860 C. BISSET ET AL.

Table 2. Continued.
Type of machine learning model
# Title of the study applied Year Database Reference
12 Neuro-genetic model for crude oil An artificial neural network model 2016 Scopus Chiroma and
price prediction while considering combined with the genetic Abdulkareem
the impact of uncertainties algorithm (neuro-genetic) (2016)
13 A methodology for energy savings An Artificial neural network (ANN) 2015 Scopus Rossi and Velázquez
verification in the industry with the (2015)
application for a CHP (combined
heat and power) plant
14 Control Strategy for Denitrification A deep reinforcement learning (DLR) 2020 IEEE Fu et al. (2020)
Efficiency of a Coal-Fired Power model Explore
Plant Based on Deep Reinforcement
Learning

authors of these studies referred to other studies that contained the keywords used in this systematic
literature review. Therefore, these studies were included in the search. All reviews and other studies
are explained. The studies that applied machine learning models are further discussed in Table 3.
For this reason, only an overview of the model type is provided in Table 2.
Table 2 provides an overview of each study identified in the search by referring to the following:
Title, type of machine learning model applied in each study, published year, database, and the refer-
ence. According to the search protocol developed, the studies were further analysed by addressing
the two research questions.

4.1.1. Research question 1: which machine learning algorithms were applied in coal-fired
thermal power plants for improved energy efficiency?
Fourteen studies contained all three keywords: Machine learning, energy efficiency and coal-fired
thermal power plant. Two studies were identified in Science Direct, 11 in Scopus and one in
IEEE Xplore. Seven of these studies were published in 2022, four in 2020, two in 2016 and one
in 2015. These results are summarised in Figure 6.
Figure 6 demonstrates that most studies were identified in Scopus, and zero studies were
identified in Web of Science and Emerald Insight. Furthermore, most studies were published
recently, in 2022, and fewer studies were published before 2015. These results indicate the
increased attention machine learning applications have gained over the last decade at coal-
fired thermal power plants for improved energy efficiency. Various machine learning algorithms
were developed and applied in the 14 studies identified. Figure 7 provides an outline of these
types of algorithms.
The types of machine learning algorithms developed in these studies were identified as follows:

Figure 6. Search results: Publications per year and database.

 INTERNATIONAL JOURNAL OF SUSTAINABLE ENERGY 861

Figure 7. The type of machine learning algorithms applied in each study.

. K-Means clustering
. The artificial neural networks (ANN)
. Multiple linear regression (MLR)
. The least-square vector machine (LSSVM)
. Deep reinforcement learning (DRL) and deep learning.

Muhammad Ashraf et al. (2020) applied three different machine learning algorithms. For this
reason, 16 algorithms are identified in Figure 7. These results showed that artificial neural networks
were the most popular algorithm to solve the identified problems. The multi-layered perceptron
(MLP) was mainly developed and applied within these.
Four studies conducted a review: Yu et al. (2022), Wu et al. (2022), Dhanalakshmi and Ayya-
nathan (2022), and Babatunde (2020). These reviews did not particularly apply or develop machine
learning models but provided an overview of these algorithms. The ‘other’ studies identified in
Figure 7 did not apply or develop machine learning models: Zima et al. (2022), Variny and Kšiňa-
nová (2022), and (Nikula, Ruusunen, and Leiviskä 2016). However, the authors of these studies
referred to other studies that contained the keywords used in this systematic literature review.
Therefore, these studies were included in the search. From the studies identified, it is also important
to note that no review, like the one conducted in this study, was identified. Research question two is
addressed in the next section.

4.1.2. Research question 2: how were these machine learning algorithms applied in coal-
fired thermal power plants for energy efficiency?
A further review of the seven studies provided insight into how these algorithms were applied in
industry to address specific problems by focusing on the datasets, input parameters, training
method and results. Furthermore, to provide a more comprehensive overview of the current litera-
ture, a detailed overview is provided of each study’s contribution and potential future recommen-
dations. A description of each is provided in Table 3.
Table 3 provides an overview of how the different machine learning algorithms were applied in
each study, followed by an overview of each study’s contribution and future recommendations. The
seven studies developed and implemented machine learning models in various forms. As discussed
in Section 2, a specific process is followed in training supervised, unsupervised and reinforcement
learning algorithms.
Table 3 shows that four studies developed unsupervised learning algorithms, including artificial
neural networks and the K-means clustering algorithm. One study applied one supervised algor-
ithm (the least square vector machine), and two focused on deep learning or deep reinforcement
learning.
 862
Table 3. Describes how machine learning models were applied in each study.
# Title of the study An overview of each machine learning application Contribution(s) and Future Research
1 Digital twin in energy industry: Proposed a robust This study did not specifically apply to machine learning. The contributions of this study include the following:

C. BISSET ET AL.
digital twin for power plants and other complex However, deep learning is used to assist the authors in
capital-intensive large engineering systems developing a database model. To achieve high reliability while 1. A comprehensive overview of digital twins subject to the
considering cost, a digital twin (DT) architecture is required for application, frameworks, and architectures for power plants.
future power plants. The paper consists of three sections: 2. Research related to digital twins and how these can
contribute towards energy savings applications.
. The authors provide an overview of digital twins and research 3. The authors also proposed a robust digital twin for power
regarding energy applications. plants.
. The design requirements for the digital twin are established
by considering physics-based formulation, sensor data Future research includes the following:
analysis, statistical analysis, and the system Genome.
. Valuable future recommendations are provided. 1. Any digital twin requires actual data and a description
representing a holistic view of the system, focusing explicitly
The authors highlighted that a data-driven approach alone is not on each part and connection.
sufficient for achieving improved reliability. They recommended 2. The authors suggested that data-driven algorithms capable of
that a low-order physics model should operate with the updated predicting dynamic system behaviour are still lacking in the
system parameters to enhance the results of the data-driven literature.
approach. 3. A data-driven model alone is not sufficient. For this reason,
The database model is designed to use ADL to detect and identify the authors proposed that a physics-based model must be
the differences between the dynamic systems model (DSM) and integrated with system parameters to improve the
the digital twin (DT). The sensor failures are identified using deep interpretation of the results from the data-driven processes.
learning and are sent back to the sensor database. The sensor 4. The authors noted that research related to cyber security with
database is updated accordingly. digital twins had not been reported in the literature, which
In conclusion, this study demonstrated the discrepancies between can be a future research study.
the dynamic system models (DSM), anomaly detection, and deep
learning (ADL). Using operational data, the vector autoregressive
model was applied for anomaly detection in utility gas turbines.
2 The Implementation of K-Means Clustering in Coal- The k-Means Clustering algorithm is developed for coal-fired The contributions of this study include the following:
fired Power Plant Performance power plant performance. Two attributes are required for
power plant performance: Equivalent Availability Factor (EAF) 1. The authors demonstrated the ability of machine learning to
and Equivalent Outage Rate (EFOR) The data set used in this analyse current power plant conditions successfully.
study is from 2020, and the data performance indices in these
investigations are the abovementioned attributes. The authors Future research includes the following:
obtained the data set from the Generation Availability
Information System (GAIS) database. The authors pre-processed 1. A real dataset is required to control current conditions to
the data to ensure data integrity. A number of 576 numerical improve the decision-making process.
datasets of the two attributes were pre-processed. The 2. Furthermore, the authors illustrated that a decision-support
relationship between the EAF and the EFOR was investigated to system may facilitate the decision-maker in making faster and
determine the characteristics of the power plant. The analysis more reliability decisions.

(Continued)
 concluded a negative correlation between the two attributes,
and the authors did a further investigation. The features of the
input data determined the number of clusters, and the Elbow
method was applied to analyse the total number of clusters
used explicitly for power plant clustering. After an in-depth
investigation, 4 clusters were selected for optimal power plant
performance. This number of clusters produced each cluster’s
highest EAF value and the lowest EFOR value In conclusion, the
higher the EAF value and the lower the EFOR value, the better
the plant performs. For this reason, the authors evaluated these
values and made conclusions accordingly. Applying this
machine learning technique, the results indicated which plant
needs to be prioritised for maintenance.
3 Improvement of marine steam turbine conventional Neural networks were applied to improve the steam turbine’s The contributions of this study include the following:
exergy analysis by neural network application. conventional exergy. Subsequently, a multi-layered perceptron
(MLP) model is developed in Python programming language 1. Developing a neural network to improve the marine steam
using the Scikit-Learn library. The data set comprised 125 points turbine conventional exergy analysis.
for the ambient temperature, pressure, steam mass flow rate, 2. This study demonstrated the usefulness of Artificial
and exergy destruction and efficiency values for the high- intelligence and that these algorithms could be applied to
pressure cylinder, low-pressure cylinder, and the entire turbine. calculate the exergy destruction and exergy efficiency of a
The input variables were the steam temperature, pressure, and marine steam turbine.

INTERNATIONAL JOURNAL OF SUSTAINABLE ENERGY

mass flow rate. The weights of the inter-neuron connection and
the values of the hidden layers are randomly defined. The Future research includes the following:
output values are compared to the input values by focusing
explicitly on exergy destruction or efficiency. Each data point 1. The authors suggested that a future study can be conducted
has 23 input values and approximately six output values. The to determine the optimal turbine operating points, precisely
backward propagation algorithm is used to train the neural steam temperature, pressure, and mass flow rate. These
network, and this method is specifically used to adjust the optimal operating points may be integrated with the MLP to
weights based on the gradient of the error. The training process analyse exergy parameter prediction focusing on the entire
is repeated until a very low error is obtained for the training turbine.
model. It is important to note that two models were trained for 2. This study’s same approach and technique can be applied to
each possible output: exergy destruction and exergy efficiency. other marine steam turbines.
For this reason, this study had a total of 72 final models. One of 3. To improve the prediction of the turbine exergy analysis
the purposes of training the model is to identify the optimal parameter, the authors suggested that a study be conducted
hyperparameter values. The hyperparameters selected were the where extensive measurements over a long period are
activation function of the hidden layer neurons, the total collected on the turbine and the turbine’s cylinders. Using
number of hidden layers, the total number of neurons per these measurements, a more accurate prediction can be made
hidden layer, and the solver, which estimates the weights, the based on the operating period.
learning rate and the L2 regularisation parameter.
In this study, Grid Search was used using the GridSearchCV
Function in Python. The training of the model took place on a
supercomputer. The coefficient of correlation (R2 ) and the mean
absolute error (MAE) were used to determine the model’s

863
performance. The K-fold cross-validation method was applied
 864
Table 3. Continued.
# Title of the study An overview of each machine learning application Contribution(s) and Future Research
with ten folds, and the data set was randomly split into training
and testing data.

C. BISSET ET AL.
4 Optimisation of a 660 MWE supercritical power plant This study considers 24 thermo-electric parameters of a specific The contributions of this study include the following:
performance: A case of industry 4.0 in the data- power plant to model the generator power under different
driven operational management. Part 2: power power generation scenarios. These operating parameters were 1. The ability of a least-square vector machine (LSSVM) model is
generation. obtained from the power plant’s turbine, boiler, and generator demonstrated in this study. This model outperformed the
sides. The data set consisted of 1900 data points. The following multiple linear regression (MLR) models and the artificial
machine learning methods were developed in this study: neural network (ANN). This model’s reliable performance in
modelling generator power has been highlighted in this
1. Artificial neural network (ANN): The feedforward study.
backpropagation algorithm is developed in this study. The 2. In this study, the power plant’s operation control has been
authors used the gradient descent with momentum as a improved by employing data-driven optimisation strategies.
training function. The tangent hyperbolic and purelin were
employed as transfer functions in both the hidden and output
layer of the ANN model.
2. Multiple linear regression (MLR): The least square vector
machine (LSSVM) was used to develop this model. First, the
difference (referred to as residuals) between the actual and
observed values was calculated. Second, the sum of the
square of residuals is minimised to obtain the best fit i.e. least
squares minimisation was employed.
3. The least-square vector machine (LSSVM): This model was
trained based on the structure risk minimisation (SRM)
principle. The relationship between the input and output
variables is determined by using a Gaussian kernel function.
All variables were standardised for model training. The
authors used the Bayesian optimiser and the expected
improvement per second in conjunction with the acquisition
function to optimise the model under 30 epochs.

After training the MLR, ANN and LSSVM models, the models were
validated using new (unseen) data. The unseen data were defined
as generator power data and were not included in the training
dataset. The coefficient of determination, mean absolute
percentage error (MAE), root-mean-square error (RMSE),
normalised RMSE (NRMSE), and the mean absolute percentage
error (MAPE) were estimated to analyse the model’s robustness
and effectiveness. The results demonstrated that the LSSVM
outperformed the other two models in predicting the plant’s

(Continued)
 generator power. This model was further used to predict the
generator power of the plant while considering numerous
operating strategies.
5 Neuro-genetic model for crude oil price prediction The authors proposed a neural network model combined with the The contributions of this study include the following:
while considering the impact of uncertainties genetic algorithm (neuro-genetic) to predict the crude oil price
while considering uncertainty. The parameters optimised are 1. The authors proposed an artificial intelligence approach to
the neural network’s bias, weights, and hidden layer nodes. The predict the crude oil price while considering uncertainties. The
values for the input neurons, the output neurons, the activation neuro-genetic model developed outperformed the neural
function, the weights, and the hidden layers were defined prior network (NN) and the support vector machine (SVM).
to training the model. The model was trained by splitting the 2. Considering uncertainty in decision-making provides a more
dataset into 80% training and 20% testing. The optimal realistic and practical application of crude oil prediction.
parameter values were obtained through trial and error, and the
sensitivity of the neuro-genetic model was analysed. The Future research includes the following:
models were trained on two datasets obtained from the Energy
Information Administration of the US Department of Energy. 1. Advancing and updating the current model to consider the
The first dataset used in this study was obtained from May 1987 prediction of crude oil in different prediction horizons.
to July 1991, excluding uncertainties. The second data set, 2. The framework may be modified to be applied to optimise
including uncertainties, was obtained from August 1990 to nuclear data libraries and nitride fuel.
February 1991. The proposed method was implemented using
Matlab 2012b.
The performance of the neuro-genetic model was investigated

INTERNATIONAL JOURNAL OF SUSTAINABLE ENERGY

and compared to the neural network and support vector
machine. It was concluded that the neuro-genetic model
performance is better due to accuracy and CPU processing time.
6 A methodology for energy savings verification in the A methodology to assess the savings achieved from developing The contributions of this study include the following:
industry with the application for a CHP (combined and implementing energy conservation measures (ECM) in
heat and power) plant specific industrial plants was developed. An artificial neural 1. The authors proposed a methodology to evaluate the savings
network was developed in this study. Historical data were from implementing energy conservation measures in
obtained from the plant’s distributed control system and are industrial plants.
pre-processed to ensure data integrity. The data were cleaned
by eliminating invalid and non-representative data points. The Future research includes the following:
applicable variables were defined, and the non-applicable
variables were removed from the dataset. The authors indicated 1. The authors suggested evaluating other techniques,
that the ANN is famous for detecting non-linear patterns and excluding the ANN model, including the feature selection
controlling many industrial processes and power plants. The method. These methods could improve the screening stage of
ANN is also capable of replicating these processes with the dataset. It is also important to note that feature selection
satisfactory levels of accuracy. The data samples were is essential when working with large datasets and ranking all
determined for training, followed by the selection of input variables’ relevance to the target variable.
variables. The ANN was trained using the back error
propagation algorithm. The model’s performance was analysed
using the coefficient of determination, the root mean square
error (RMSE), and the mean absolute error (MAE). Acceptable
model performance was confirmed.

865
Table 3. Continued.

866
# Title of the study An overview of each machine learning application Contribution(s) and Future Research
7 Control Strategy for Denitrification Efficiency of a Coal- In this study, a 1000MW unit is used as a case study. A deep The contributions of this study include the following:
Fired Power Plant Based on Deep Reinforcement reinforcement learning (DLR) model is developed with a long

C. BISSET ET AL.
Learning short-term memory model, the Asynchronous Advantage Actor- 1. One of the primary contributions is that the approach
Critic algorithm (A3C). The data used in this study was obtained proposed in this study demonstrates the ability to be feasible
from the plant’s Distributed Control System (DCS). The authors and universally applicable in industry.
used 10000 sets of data from a 1000MW coal-fired boiler.
Variables, including, but not limited to, spray ammonia mass Future research includes the following:
flow, Inlet mass concentration, boiler load, inlet mass and inlet
flue gas temperature, were identified. The data was pre- 1. The authors indicated that the following should be further
processed, followed by using this data as input for the Long investigated: the control method of the combustion process,
short-term memory neural network (LSTM). Subsequently, this the system cost of coal-fired power plants and the
LSTM model was used for the DRL’s environment. The DLR denitrification process. These elements should be investigated
method used the state value output by the environment as an to improve the stability and reliability of control strategies.
input to produce a new updated action value. By conducting
several iterations, a new control strategy of SCR was obtained.
The Back Propagation algorithm was used to train the LSTM. For
the training, six main variables were defined as input variables;
the model consisted of 3 LSTM layers and 64 nodes per layer.
The model was optimised using the Adam optimiser algorithm,
and the data were split into 20% testing and 80% training data.
Two performance metrics were used: the root mean square
error (RMSE) and the R-squared. The accuracy of the efficiency
calculated was 91.7%. In conclusion, it was shown that the
approach is feasible and universally applicable.
 INTERNATIONAL JOURNAL OF SUSTAINABLE ENERGY 867

There are similarities between the studies that applied unsupervised learning algorithms.
Muhammad Ashraf et al. (2020), Baressi Šegota et al. (2020) and Rossi and Velázquez (2015)
used the backpropagation algorithm to train the artificial neural networks. Typical performance
metrics used to determine the performance of the ANN included the following: The coefficient
of determination, the root mean square error (RMSE), and the mean absolute error (MAE).
Most other algorithms followed a similar approach, as explained in Section 2.
Multiple researchers emphasised the value of artificial neural networks. Artificial neural network
models are flexible and can be applied to problems even if much of the information is unknown
(Smrekar et al. 2009). These algorithms are designed to solve complex problems related explicitly
to modelling, control and optimisation (Babatunde 2020). Furthermore, these algorithms can
model complex non-linear relationships between inputs and outputs, which is much more challen-
ging than traditional models (Chiroma and Abdulkareem 2016).
Wu et al. (2022) highlighted that the articles identified in their review demonstrated the impor-
tance and the applicability of various machine learning algorithms, including decision trees, sup-
port vector machines (SVM), and artificial neural networks (ANN), specifically feedforward deep
neural networks and recurrent neural networks. Another systematic review conducted by Dhana-
lakshmi and Ayyanathan (2022) revealed that the artificial neural network (ANN) was mostly
applied in the identified studies.
The type of machine learning model employed depends on the volume of data and the pro-
blem identified. However, as these different studies are evaluated, it is evident that there is a
common thread across all these research studies identified from conducting the review. Specifi-
cally, most researchers suggested that artificial neural networks be used when working with
large datasets and complex problems, especially those related to industrial processes and
power plants.
Evidently, each study contributed to academia and industry by incorporating realistic and prac-
tical approaches. The studies by Sleiti, Kapat, and Vesely (2022) and Wahyuningtyas and Asrol
(2022) indicated the importance of a decision support system for optimal decision-making.
These studies illustrated that a data-driven approach alone is insufficient, and a tool is required
to integrate it with system parameters for optimal decision-making. Furthermore, the importance
of actual data is highlighted in Table 3 by Sleiti, Kapat, and Vesely (2022) and Wahyuningtyas and
Asrol (2022). Real data will improve decision-making and provide an accurate view of the system
and its components, specifically when applying machine learning.

5. Summary and conclusions

This research paper investigated machine learning algorithms utilised for energy efficiency
improvement at coal-fired thermal power plants by conducting a systematic literature review. Sub-
sequently, this paper provided an overview of the identified relevant studies, focusing on the type of
machine learning algorithms and the application thereof. This paper contributed towards research
by providing guidelines for sustainable energy supply and improved decision-making towards more
efficient processes. Efficient processes result in the reduction of fuel usage, which results in lower
emission levels for equivalent power generation capacity. This research paper adds value to the
industry and academia by identifying all scientific articles that applied machine learning algorithms
in the power industry.
First, an overview of machine learning was provided, explicitly focused on supervised, unsuper-
vised, semi-supervised and deep reinforcement learning algorithms. Second, a systematic literature
review followed the same method as Kitchenham et al. (2009). A search protocol was developed by
formulating research questions, identifying keywords, databases, inclusion and exclusion criteria,
and a quality assessment. From the search process, only 14 studies contained the three keywords.
Two studies were identified in Science Direct, 11 in Scopus and one in IEEE Xplore. Seven of these
studies were published in 2022, four in 2020, two in 2016 and one in 2015.
868 C. BISSET ET AL.

From the review, three studies mentioned machine learning: Zima et al. (2022), Variny and Kši-
ňanová (2022), and Nikula, Ruusunen, and Leiviskä (2016), four conducted a review: Yu et al.
(2022), Wu et al. (2022), Dhanalakshmi and Ayyanathan (2022), and Babatunde (2020), and
seven applied machine learning at a coal-fired thermal power plant for energy efficiency (Baressi
Šegota et al. 2020; Chiroma and Abdulkareem 2016; Fu et al. 2020; Rossi and Velázquez 2015; Sleiti,
Kapat, and Vesely 2022; Wahyuningtyas and Asrol 2022). The seven studies applied different
machine learning algorithms, including K-means clustering, multiple linear regression (MLR),
the least-square vector machine (LSSVM), deep reinforcement learning (RL) and artificial neural
networks (ANN). Typical performance metrics used to determine the performance of the ANN
included the following: The coefficient of determination, the root mean square error (RMSE),
and the mean absolute error (MAE).
Various researchers emphasised the value of artificial neural networks. Artificial neural network
models are flexible and can be applied to problems even if all the information is unknown (Smrekar
et al. 2009). The models can solve complex problems related explicitly to process modelling, control
and optimisation. Furthermore, these algorithms can model complex non-linear relationships
between inputs and outputs, which is much more challenging than traditional models (Chiroma
and Abdulkareem 2016). The studies by Sleiti, Kapat, and Vesely (2022) and Wahyuningtyas and
Asrol (2022) indicated the importance of a decision support system for optimal decision-making.
These studies illustrate that a data-driven approach alone is insufficient, and a tool is required to
integrate with system parameters for optimal decision-making. The results obtained from this
study underline the significance of some applications of machine learning algorithms. For instance,
the artificial neural network is famous for detecting non-linear patterns and predicting the behav-
iour of most industrial processes and power plants (Rossi and Velázquez 2015). The potential future
recommendations are identified and explained in Section 6.

6. Limitations and future recommendations

One limitation identified from the systematic literature review conducted in this study is that the
keywords are particular, resulting in fewer studies identified on the selected databases. For future
research, it is recommended to broaden the search by removing the keyword: coal-fired thermal
power plant. By eliminating this keyword, over 3000 studies are identified from Scopus. This will
provide insight into how various machine learning algorithms are applied to solve related energy
problems in other industries. For example, technologies may be investigated to improve asset failure
prediction, resulting in optimised plant production and enhanced energy efficiency.
It is further recommended that a review is conducted that does not only focus on coal-fired ther-
mal power plants but also on the application of machine learning for gas turbines and other fossil
fuel plants, including gas-fired and oil-fired power plants. An extensive amount of research has been
conducted on machine learning, and a comprehensive review that includes all power plants may
further pave the way for future researchers and the industry.
The review showed that various supervised, unsupervised and reinforcement learning models
are applied to solve industry-related problems. Based on the systematic literature review conducted
and reported on in this paper, limited industry-related applications were identified for machine
learning applications at coal-fired thermal power plants under investigation, especially to improve
the operational efficiency of the status quo operations. Furthermore, Decision trees, Gaussian pro-
cesses (GP), and the Naïve Bayes techniques were typically not found in the literature for the
research question. It is, therefore, proposed that researchers investigate these techniques for the
identified research question, i.e. the aim to improve energy efficiency at coal-fired thermal power
plants while reducing fuel usage. Further research should also include comparing these identified
techniques with that of an artificial neural network for energy-improved operations at coal-fired
thermal power plants. It must be noted that coal-fired refers to coal being utilised within a boiler
house to generate steam; therefore, emphasise must be placed on the coal-fired boiler.
 INTERNATIONAL JOURNAL OF SUSTAINABLE ENERGY 869

Another limitation identified in the literature is applying the long short-term memory network
(LSTM) technique. The LSTM has been developed and applied in various industries because it can
process time series data (Pan et al. 2021). Furthermore, the LSTM can remember previous infor-
mation and use this memory to calculate the current output (Pan et al. 2021).
For future research, it is recommended that this modelling technique is applied for optimal oper-
ational control of various units at coal-fired thermal power plants. Applying the LSTM may also
contribute towards improving the energy efficiency of coal-fired boilers.
Furthermore, neural network predictive control (NNPC) is a model integrated with predictive
control (MPC). One of the primary contributors of this model is its ability to be employed in
real-time for simple controls and disturbance reduction (Megahed, Abdelkader, and Zakaria
2019). No such model has been identified in this review. For this reason, it may be valuable to inves-
tigate the application of such a model to enhance a power plant’s automation and operational
decision-making. It is recommended that the readers refer to Table 3 for a more comprehensive
overview of each study’s potential future research opportunities. These opportunities highlight
the limitations of current literature and may be investigated for future research.

Disclosure statement
No potential conflict of interest was reported by the author(s).

ORCID
C. Bisset http://orcid.org/0000-0001-5296-5945
P. V. Z. Venter http://orcid.org/0000-0003-4963-6248
R. Coetzer http://orcid.org/0000-0002-7505-3911

References
Albliwi, S., J. Antony, S. A. H. Lim, and T. van der Wiele. 2014. “Critical Failure Factors of Lean Six Sigma: A
Systematic Literature Review.” International Journal of Quality & Reliability Management 31 (9): 1012–1030.
Alvarez Quiñones, L. I., C. A. Lozano-Moncada, and D. A. Bravo Montenegro. 2023. “Machine Learning for
Predictive Maintenance Scheduling of Distribution Transformers.” Journal of Quality in Maintenance
Engineering 29 (1): 188–202. https://doi.org/10.1108/JQME-06-2021-0052
Awuah-Offei, K. 2016. “Energy Efficiency in Mining: A Review with Emphasis on the Role of Operators in Loading
and Hauling Operations.” Journal of Cleaner Production 117: 89–97. https://doi.org/10.1016/j.jclepro.2016.01.035
Ayodele, T. O. 2010. Types of Machine Learning Algorithms. In www.intechopen.com. IntechOpen. https://www.
intechopen.com/chapters/10694.
Babatunde, D. E. 2020. Artificial Neural Network and Its Applications in the Energy Sector: An Overview. 670216917.
Baressi Šegota, S., I. Lorencin, N. Anđelić, V. Mrzljak, and Z. Car. 2020. “Improvement of Marine Steam Turbine
Conventional Exergy Analysis by Neural Network Application.” Journal of Marine Science and Engineering 8
(11): 884. https://doi.org/10.3390/jmse8110884
Bhatt, S. 2019. Reinforcement Learning 101. [online] Medium. https://towardsdatascience.com/reinforcement-
learning-101-e24b50e1d292.
Bi, G. B., W. Song, P. Zhou, and L. Liang. 2014. “Does Environmental Regulation Affect Energy Efficiency in China’s
Thermal Power Generation? Empirical Evidence from a Slacks-Based DEA Model.” Energy Policy 66: 537–546.
https://doi.org/10.1016/j.enpol.2013.10.056
Boser, B. E., I. M. Guyon, and V. N. Vapnik. 1992. “A Training Algorithm for Optimal Margin Classifiers.” In
Proceedings of the Fifth Annual Workshop on Computational Learning Theory, 144–152, July.
Brownlee, J. 2019. A Gentle Introduction to Bayesian Belief Networks. [online] Machine Learning Mastery. https://
machinelearningmastery.com/introduction-to-bayesian-belief-networks/.
Bunse, K., M. Vodicka, P. Schönsleben, M. Brülhart, and F. O. Ernst. 2011. “Integrating Energy Efficiency
Performance in Production Management–gap Analysis Between Industrial Needs and Scientific Literature.”
Journal of Cleaner Production 19 (6–7): 667–679. https://doi.org/10.1016/j.jclepro.2010.11.011
Chauhan, N. 2022. Naïve Bayes Algorithm: Everything You Need to Know. [online] KDnuggets. https://www.
kdnuggets.com/2020/06/naive-bayes-algorithm-everything.html.
870 C. BISSET ET AL.

Chiroma, H., and S. Abdulkareem. 2016. “Neuro-genetic Model for Crude oil Price Prediction While Considering the
Impact of Uncertainties.” International Journal of Oil, Gas and Coal Technology 12 (3): 302–333.
Climate & energy package. 2020. Climate.ec.europa.eu. https://climate.ec.europa.eu/eu-action/climate-strategies-
targets/2020-climate-energy-package_en.
De Myttenaere, A., B. Golden, B. Le Grand, and F. Rossi. 2016. “Mean Absolute Percentage Error for Regression
Models.” Neurocomputing 192: 38–48. https://doi.org/10.1016/j.neucom.2015.12.114
Dhanalakshmi, J., and N. Ayyanathan. 2022. “A Systematic Review of Big Data in Energy Analytics Using Energy
Computing Techniques.” Concurrency and Computation: Practice and Experience 34 (4): e6647. https://doi.org/
10.1002/cpe.6647
Energy Star Overview. 2016. Energystar.gov. https://www.energystar.gov/about.
Fu, J., H. Xiao, H. Wang, and J. Zhou. 2020. “Control Strategy for Denitrification Efficiency of Coal-Fired Power Plant
Based on Deep Reinforcement Learning.” IEEE Access 8: 65127–65136. https://doi.org/10.1109/ACCESS.2020.
2985233
Gandhi, R. 2018. Support Vector Machine — Introduction to Machine Learning Algorithms. Towards Data Science;
Towards Data Science, June 7. https://towardsdatascience.com/support-vector-machine-introduction-to-
machine-learning-algorithms-934a444fca47.
Ghosh, P. 2017. The Value of Machine Learning: Benefits and Best Practices - Dataversity. Los Angeles, CA:
Dataversity, June 8. https://www.dataversity.net/value-machine-learning-benefits-best-practices/
Goodell, J. W., S. Kumar, W. M. Lim, and D. Pattnaik. 2021. “Artificial Intelligence and Machine Learning in Finance:
Identifying Foundations, Themes, and Research Clusters from Bibliometric Analysis.” Journal of Behavioral and
Experimental Finance 32: 100577. https://doi.org/10.1016/j.jbef.2021.100577.
Gupta, P. 2017. Decision Trees in Machine Learning. [online] Towards Data Science. Available at: https://
towardsdatascience.com/decision-trees-in-machine-learning-641b9c4e8052.
Haddad, A., and O. Mohamed. 2022. “Qualitative and Quantitative Comparison of Three Modeling Approaches for a
Supercritical Once-Through Generation Unit.” International Journal of Energy Research 46 (14): 20780–20800.
https://doi.org/10.1002/er.8330
Haddadin, M., O. Mohamed, W. Abu Elhaija, and M. Matar. 2023. “Performance Prediction of a Clean Coal Power
Plant via Machine Learning and Deep Learning Techniques.” Energy & Environment. 0958305X231160590.
Harrison, O. 2018. Machine Learning Basics with the K-Nearest Neighbors Algorithm. [online] Medium. https://
towardsdatascience.com/machine-learning-basics-with-the-k-nearest-neighbors-algorithm-6a6e71d01761.
IBM Cloud Education. 2020a. What are Neural Networks? [online] www.ibm.com. Accessed 05 August 05, 2023.
Available at: https://www.ibm.com/topics/neural-networks.
IBM Cloud Education. 2020b. What is Unsupervised Learning? Www.ibm.com; IBM Cloud Education, September 21.
https://www.ibm.com/cloud/learn/unsupervised-learning#:~:text=Unsupervised%20learning%2C%20also%
20known%20as.
Jagarnath Mahato. 2019. Jagarnath Mahato. [online] Coal Handling Plants. https://www.coalhandlingplants.com/
boiler-in-thermal-power-plant/.
javatpoint. 2022. “Supervised Machine Learning - Javatpoint.” Www.javatpoint.com, 2022, www.javatpoint.com/
supervised-machine-learning.
Jia, L., Q. Zhao, and L. Tong. 2013. Retail pricing for stochastic demand with unknown parameters: An online
machine learning approach. In 2013 51st Annual Allerton Conference on Communication, Control, and
Computing (Allerton) (pp. 1353-1358). IEEE. 2013, October.
Johnson, D. 2022. Back Propagation Neural Network: Explained With Simple Example. [online] www.guru99.com.
https://www.guru99.com/backpropogation-neural-network.html.
Kaya, A., and M. A. Keyes IV. 1980. “Energy Management Technology in Pulp, Paper and Allied Industries.” IFAC
Proceedings Volumes 13 (12): 609–622. https://doi.org/10.1016/S1474-6670(17)69499-0
Khalid, S., H. Hwang, and H. S. Kim. 2021. “Real-world Data-Driven Machine-Learning-Based Optimal Sensor
Selection Approach for Equipment Fault Detection in a Thermal Power Plant.” Mathematics 9 (21): 2814.
https://doi.org/10.3390/math9212814
Khalid, S., W. Lim, H. S. Kim, Y. T. Oh, B. D. Youn, H. S. Kim, and Y. C. Bae. 2020. “Intelligent Steam Power Plant
Boiler Waterwall Tube Leakage Detection via Machine Learning-Based Optimal Sensor Selection.” Sensors 20 (21):
6356. https://doi.org/10.3390/s20216356
Khan, R. H., and J. Y. Khan. 2013. “A Comprehensive Review of the Application Characteristics and Traffic
Requirements of a Smart Grid Communications Network.” Computer Networks 57 (3): 825–845. https://doi.
org/10.1016/j.comnet.2012.11.002
Kitchenham, B., O. P. Brereton, D. Budgen, M. Turner, J. Bailey, and S. Linkman. 2009. “Systematic Literature
Reviews in Software Engineering–a Systematic Literature Review.” Information and Software Technology 51 (1):
7–15. https://doi.org/10.1016/j.infsof.2008.09.009
Kitto, J. B. 1996. “Developments in Pulverized Coal-Fired Boiler Technology.” In Missouri Valley Electric Association
Engineering Conference, 1–11, April.
 INTERNATIONAL JOURNAL OF SUSTAINABLE ENERGY 871

Kumar, A., and G. Garg. 2020. “Systematic Literature Review on Context-Based Sentiment Analysis in Social
Multimedia.” Multimedia Tools and Applications 79 (21–22): 15349–15380. https://doi.org/10.1007/s11042-019-
7346-5
Liu, B. 2011. “Supervised Learning.” In Web Data Mining, 63–132. Berlin, Heidelberg: Springer.
Lovins, A. 2017. “Energy Efficiency.” Energy Economics 1: 234–258.
Makala, B., and T. Bakovic. 2020. Artificial Intelligence in the Power Sector. EMCompass No. 81. Washington,
DC: International Finance Corporation. https://openknowledge.worldbank.org/handle/10986/34303.
Mangaroo-Pillay, M., and R. Coetzee. 2022. “Lean Frameworks: A Systematic Literature Review (SLR) Investigating
Methods and Design Elements.” Journal of Industrial Engineering and Management 15 (2): 202–214. https://doi.
org/10.3926/jiem.3677
Megahed, T. F., S. M. Abdelkader, and A. Zakaria. 2019. “Energy Management in Zero-Energy Building Using Neural
Network Predictive Control.” IEEE Internet of Things Journal 6 (3): 5336–5344. https://doi.org/10.1109/JIOT.
2019.2900558
Mishra, U. C. 2004. “Environmental Impact of Coal Industry and Thermal Power Plants in India.” Journal of
Environmental Radioactivity 72 (1-2): 35–40. https://doi.org/10.1016/S0265-931X(03)00183-8
Muhammad Ashraf, W., G. Moeen Uddin, A. Hassan Kamal, M. Haider Khan, A. A. Khan, H. Afroze Ahmad, F.
Ahmed, et al. 2020. “Optimisation of a 660 MWe Supercritical Power Plant Performance—a Case of Industry
4.0 in the Data-Driven Operational Management. Part 2. Power Generation.” Energies 13 (21): 5619. https://
doi.org/10.3390/en13215619
Murehwa, G., D. Zimwara, W. Tumbudzuku, and S. Mhlanga. 2012. “Energy Efficiency Improvement in Thermal
Power Plants.” International Journal of Innovative Technology and Exploring Engineering (IJITEE) 2 (1): 20–25.
Nabavi, S. A., A. Aslani, M. A. Zaidan, M. Zandi, S. Mohammadi, and N. Hossein Motlagh. 2020. “Machine Learning
Modeling for Energy Consumption of Residential and Commercial Sectors.” Energies 13 (19): 5171. https://doi.
org/10.3390/en13195171
Nagelkerke, N. J. 1991. “A Note on a General Definition of the Coefficient of Determination.” Biometrika 78 (3): 691–
692. https://doi.org/10.1093/biomet/78.3.691
Narciso, D. A., and F. G. Martins. 2020. “Application of Machine Learning Tools for Energy Efficiency in Industry: A
Review.” Energy Reports 6: 1181–1199.
Nikula, R. P., M. Ruusunen, and K. Leiviskä. 2016. “Data-driven Framework for Boiler Performance Monitoring.”
Applied Energy 183: 1374–1388. https://doi.org/10.1016/j.apenergy.2016.09.072
Oladiran, M. T., and J. P. Meyer. 2007. “Energy and Exergy Analyses of Energy Consumptions in the Industrial Sector
in South Africa.” Applied Energy 84 (10): 1056–1067. https://doi.org/10.1016/j.apenergy.2007.02.004
Ongsulee, P. 2017. “Artificial Intelligence, Machine Learning and Deep Learning.” In 2017 15th International
Conference on ICT and Knowledge Engineering (ICT&KE), 1–6. IEEE. November.
Otto, S. 2019. How to normalise the RMSE. Www.marinedatascience.co, January 7. https://www.marinedatascience.
co/blog/2019/01/07/normalizing-the-rmse/.
Pan, H., T. Su, X. Huang, and Z. Wang. 2021. “LSTM-based Soft Sensor Design for Oxygen Content of Flue gas in
Coal-Fired Power Plant.” Transactions of the Institute of Measurement and Control 43 (1): 78–87. https://doi.org/
10.1177/0142331220932390
Patterson, M. G. 1996. “What is Energy Efficiency?: Concepts, Indicators and Methodological Issues.” Energy Policy
24 (5): 377–390. https://doi.org/10.1016/0301-4215(96)00017-1
Pejić-Bach, M., and N. Cerpa. 2019. “Planning, Conducting and Communicating Systematic Literature Reviews.”
Journal of Theoretical and Applied Electronic Commerce Research 14 (3): 1–4. https://doi.org/10.4067/S0718-
18762019000300101
Petrecca, G. 2014. “Energy Conversion and Management.” Cham, Switzerland, 101–103.
Prashar, A. 2017. “Energy Efficiency Maturity (EEM) Assessment Framework for Energy-Intensive SMEs: Proposal
and Evaluation.” Journal of Cleaner Production 166: 1187–1201. https://doi.org/10.1016/j.jclepro.2017.08.116
Qi, J., J. Du, S. M. Siniscalchi, X. Ma, and C. H. Lee. 2020. “On Mean Absolute Error for Deep Neural Network Based
Vector-to-Vector Regression.” IEEE Signal Processing Letters 27: 1485–1489. https://doi.org/10.1109/LSP.2020.
3016837
Rambalee, P., G. Gous, P. G. R. De Villiers, N. Mcculloch, and G. Humphries. 2011. Power Control: Advanced Process
Control. Control Engineering, June 20. https://www.controleng.com/articles/power-control-advanced-process-
control/
Rosenblatt, F. 1958. “The Perceptron: A Probabilistic Model for Information Storage and Organisation in the Brain.”
Psychological Review 65 (6): 386. https://doi.org/10.1037/h0042519
Rossi, F., and D. Velázquez. 2015. “A Methodology for Energy Savings Verification in Industry with Application for a
CHP (Combined Heat and Power) Plant.” Energy 89: 528–544. https://doi.org/10.1016/j.energy.2015.06.016
Schulze, M., H. Nehler, M. Ottosson, and P. Thollander. 2016. “Energy Management in Industry–a Systematic Review
of Previous Findings and an Integrative Conceptual Framework.” Journal of Cleaner Production 112: 3692–3708.
https://doi.org/10.1016/j.jclepro.2015.06.060
872 C. BISSET ET AL.

Shinde, P. P., and S. Shah. 2018. “A Review of Machine Learning and Deep Learning Applications.” In 2018 Fourth
international conference on computing communication control and automation (ICCUBEA) (pp. 1–6). IEEE,
August.
Sleiti, A. K., J. S. Kapat, and L. Vesely. 2022. “Digital Twin in Energy Industry: Proposed Robust Digital Twin for
Power Plant and Other Complex Capital-Intensive Large Engineering Systems.” Energy Reports 8: 3704–3726.
https://doi.org/10.1016/j.egyr.2022.02.305
Smrekar, J., M. Assadi, M. Fast, I. Kuštrin, S. De, 2009. “Development of Artificial Neural Network Model for a Coal-
Fired Boiler Using Real Plant Data.” Energy 34 (2): 144–152.
Sogabe, T., D. B. Malla, S. Takayama, S. Shin, K. Sakamoto, K. Yamaguchi, T. P. Singh, M. Sogabe, T. Hirata, and Y.
Okada. 2018. Smart grid optimisation by deep reinforcement learning over discrete and continuous action space.
In 2018 IEEE 7th World Conference on Photovoltaic Energy Conversion (WCPEC)(A Joint Conference of 45th IEEE
PVSC, 28th PVSEC & 34th EU PVSEC) (pp. 3794-3796). IEEE, June.
Song, M. L., L. Yang, J. Wu, and W. D. Lv. 2013. “Energy Saving in China: Analysis on the Energy Efficiency via
Bootstrap-DEA Approach.” Energy Policy 57: 1–6. https://doi.org/10.1016/j.enpol.2012.11.001
Variny, M., and M. Kšiňanová. 2022. “Repowering Industrial Combined Heat and Power Units: A Contribution to
Cleaner Energy Production.” Polish Journal of Environmental Studies 31 (3): 2861–2879. https://doi.org/10.15244/
pjoes/144096
Virtualitics. 2021. Using Machine Learning in the Energy Sector. Blog.virtualitics.com, November 24. https://blog.
virtualitics.com/using-machine-learning-in-the-energy-sector.
Wahyuningtyas, D., and M. Asrol. 2022. “The Implementation of K-Means Clustering in Coal-Fired Power Plant
Performance.” International Journal of Emerging Technology and Advanced Engineering 12 (3): 1–8. https://doi.
org/10.46338/ijetae0322_01
Wu, S. R., G. Shirkey, I. Celik, C. Shao, and J. Chen. 2022. “A Review on the Adoption of AI, BC, and IoT in
Sustainability Research.” Sustainability 14 (13): 7851. https://doi.org/10.3390/su14137851
Wuest, T., D. Weimer, C. Irgens, and K.-D. Thoben. 2016. “Machine Learning in Manufacturing: Advantages,
Challenges, and Applications.” Production & Manufacturing Research, [Online] 4 (1): 23–45. https://doi.org/10.
1080/21693277.2016.1192517.
Yi, W. 2022. Understanding Gaussian Process, the Socratic Way. [online] Medium. https://towardsdatascience.com/
understanding-gaussian-process-the-socratic-way-ba02369d804.
Yu, W., P. Patros, B. Young, E. Klinac, and T. G. Walmsley. 2022. “Energy Digital Twin Technology for Industrial
Energy Management: Classification, Challenges and Future.” Renewable and Sustainable Energy Reviews 161:
112407. https://doi.org/10.1016/j.rser.2022.112407
Zima, W., J. Taler, S. Grądziel, M. Trojan, A. Cebula, P. Ocłoń, P. Dzierwa, et al. 2022. “Thermal Calculations of a
Natural Circulation Power Boiler Operating Under a Wide Range of Loads.” Energy 261: 125357. https://doi.org/
10.1016/j.energy.2022.125357