Artificial
Intelligence In
Electrical Power
System
Presented by:
- Samay Rajput
- Manoj Pawar
Under the Guidance of,
Dr. Swati Bhasme (HOD)
Table Of Contents
1 2 3 4
Introduction Different AI Comparison of
to AI Need of AI.
Techniques AI methods
5 6 7 8
Transmission Problem Power System
solving with AI Control
Conclusion
Line
1. Introduction
• What Is AI?
- Artificial Intelligence is a ability of
a computer to act or think like a
human being.
• What Is Power system?
2. Need of AI in power
System.. ?
• Power System analysis by conventional
techniques becomes more difficult because
of :
1. Complex, versatile and large amount of
information which is used in data calculation,
diagnosis and learning.
2. Increase in the computational time period and
accuracy due to extensive and vast data
handling.
3. Different AI techniques
1. XPSs 3. FLs
Expert System Fuzzy Logic
techniques. System.
2. ANNs 4. GAs
Generating
Artificial Neural
Algorithms,
Networks. etc.
_ Expert System techniques
- An Expert System obtains the knowledge of a
human expert in a narrow specified domain into a
machine implementable form.
- Expert systems are the computer programs and
they are also called as the knowledge based systems
or the rule based systems.
- Expert systems use the interface mechanism and
the knowledge to solve the problems that cannot be
solved by the human skills and intellect.
Operation of Expert System
• These technique can be installed
in the system with the help of
codes and programs.
• Modifications can be done
easily even while the system is
operating.
• Virtually, estimation research
for the efficiency can be done Block diagram of an Expert System
_ Artificial Neural Networks
• Biologically inspired systems.
• Converts set of inputs into set of outputs with the help of
NEURONS.
• An individual neuron can be considered as a processor
which produces one output for one input .
• These neurons which are capable of solving real life
problems are interconnected in a specified way to
construct a computer.
Operation of Artificial Neural Networks
• For example,
the value of inductance,
capacitance and resistance in a
transmission line can be
numerically calculated.
• Considering all the factors
like,
- Unbalancing
Block diagram of an Artificial Neural Network
- Losses
- Environmental factors, etc.
_ Fuzzy Logic Systems
• These are logical systems for standardization and
formalization.
• It same as the human ability to produce exact and
accurate decision with certain or even
approximate information and data.
• Can be used
- for designing the physical components of
power system.
- for increasing the efficiency of components
- to derive stable, exact and ambiguity free
output.
Operation of Fuzzy Logic
4. Comparison of Different techniques
5. Block Diagram of Transmission line using AI
6 . Problem Solving with AI
2. Generator 3. Optimal
1. Economic Load
Maintenance
Dispatch Power Flow
Scheduling
• ELD is the process where electricity • GMS is one of the major problems for • OPF helps to find the best
generation is allocated to the units, settings for control
all the power providers.
to meet the demand efficiently and parameters, like voltage and
• The maintenance is mainly divided
economically. reactive controls.
into three different time horizons.
• Techniques like Genetic
• The main aim is to reduce the cost of • Different AI like GA, ANN are used
algorithms artificial neural
generation as much as possible. for GMS.
networks (GA-ANN) and
• Various AI methods are used like, • But the PSO (particle swarm
Adaptive neuro fuzzy
GA, ANN, ACO, etc. optimization) shows evolutionary inference system (ANFIS) are
• Mainly used is ABC (artificial bee categories. used to optimize the power
colony)
flow efficiently.
7. Control of Power System
Parameters with AI
1. Voltage Control 2. Reactive Power
Proportional-Integral- 3. Load Shedding
Genetic Algorithms are used
Derivative (PID) controllers Fuzzy Logic Control is used.
for this controlling purpose.
are used for this purpose.
5. Transmission line 6. Capacitor
4. Fault Detection
Switching Placement Control
Neural Networks are used for Ant Colony optimization are Particle Swarm optimization
this purpose. used. technique is used.
8. Conclusion.
• A lot of research is yet to be performed
to perceive full advantages of this
upcoming electricity market.
• In the upcoming decades almost every
parameter, component and grid will be
controlled by the AI with a little
Human touch
Thank you!
.…for listening carefully.
ANY
QUERIES..?
