Nirma University

Institute of Technology
M.Tech. in Electrical Engineering (Electrical Power Systems)
Semester - II
L T P C
3 0 2 4
Course Code 3EE22D103
Course Title Applications of AI and Optimization in Power
Systems

Course Learning Outcomes (CLO):

At the end of the course, students will be able to-
1. Make use of classical and advanced techniques in optimization
2. apply knowledge of optimization theory in electrical power systems
3. develop AI / optimization based solutions for power system problems

Syllabus Teaching Hours:

45
Unit-1: Fundamentals of Optimization Techniques 03
Definition - classification of optimization problems-Unconstrained and constrained
optimization - Optimality conditions - classical optimization techniques (Lamda
Iteration method, Linear programming)

Unit-2: Lamda Iteration Method 04

Brief introduction to lamda iteration method, formulation of Lagrange function,
Lamda iteration method to solve optimal dispatch problem

Unit-3: Linear Programming 04

Fundamentals of linear programming, simplex method I, weak and strong duality
theorems, integer programming, network flow, develop a linear programming
model from problem description

Unit-4: Genetic Algorithm 05

Introduction to Evolutionary computation, advantages and limitations of
evolutionary computation, fundamentals of genetic algorithm, working principle,
principles of genetic algorithm - genetic operators, selection, crossover and
mutation fitness function, GA operators, similarities and differences between GA
and traditional methods, unconstrained and constrained optimization using Genetic
Algorithm

Unit-5: Particle Swarm Optimization 04

Principle, velocity updating, advanced operators- parameter selection, hybrid
approaches - binary, discrete and combinatorial

Unit-6: Fuzzy Logic 06

Introduction, Concepts in Fuzzy logic and relevance with the power system
problems, approaches and types of fuzzy logic systems, typical actions in Fuzzy
systems, Integration of fuzzy systems with evolutionary techniques
 Unit-7: Artificial Neural Network Approaches 07
Introduction to artificial neural networks, artificial neuron model, and types of
activation functions. Learning in neural networks, feed forward and feedback
neural networks, backpropagation training algorithm, Hopfield network,
Boltzmann machine

Unit-8: Applications in Power Systems 12

Applications to Power System Scheduling - algorithms and flow chart of various
optimization techniques for solving economic load dispatch and hydro-thermal
scheduling problem; Model Identification - Dynamic Load Modeling, Short-Term
Load Forecasting; Distribution system applications - Network reconfiguration for
loss reduction, Optimal protection and switching devices placement, Prioritizing
investments in distribution networks; Applications to system planning; Solving
optimal power flow problems; etc.

Self-Study Component:
The self-study content(s) will be declared at the commencement of semester. Around 10% of
the questions will be asked from self-study contents.
Laboratory Work:
This shall consist of at least 08 simulations / laboratory experiments based on the syllabus.
Suggested Readings:
1. S. S. Rao, Engineering Optimization Theory and Practice, John Wiley & Sons
2. K. Y. Lee and M.A. El-Sharkawi (eds.), Modern Heuristic Optimization Techniques with
Applications to Power Systems, IEEE Press
3. D. E. Goldberg, Genetic Algorithm in Search, Optimization and Machine Learning,
Wesley Longman Publishing Co., Inc. Boston, MA, USA
4. S.N. Sivanandam, S. N. Deepa, Principles of Soft Computing, Wiley India Pvt. Ltd.
5. Chaturvedi Devendra K., Soft Computing Techniques and Applications in Electrical
Engineering, Springer-Verlag Berlin Heidelberg
6. Jizhong Zhu, Optimization of Power System Operation, John Wiley & Sons
7. Edwin K. P. Chong, Stanislaw H. Zak, An Introduction to Optimization, John Wiley &
Sons

L = Lecture, T = Tutorial, P = Practical, C = Credit

w.e.f. academic year 2019-20 and onwards