Syllabus

Introduction to Machine Learning and Neural Networks (8 Hours)
• Overview of Artificial Intelligence (AI), Machine Learning (ML), and Deep Learning.
• Scope of ML in Electrical and Power Engineering.
• Types of Learning: Supervised, Unsupervised, Reinforcement Learning.
• Data representation, feature engineering, training and testing datasets.
• Neural Network fundamentals: Biological neuron model and artificial neuron, Activation functions, Perceptron learning rule, Multilayer Perceptron (MLP), Backpropagation algorithm.

Learning Theory and Supervised Learning Methods (10 Hours)
• Introduction to learning theory, Bayesian inference and Bayes theorem, Naïve Bayes classifier, Bias-variance tradeoff, Generalization and overfitting, Regularization techniques, Concentration inequalities and VC dimension, Unconstrained optimization using Steepest Descent method.
• Regression methods: Simple Linear Regression, feature scaling, regularization, Multiple Linear Regression, Polynomial Regression.
• Classification methods: Logistic Regression, Generative Models, Gaussian Discriminant Analysis,
• Support Vector Machine (SVM): Hard margin, soft margin, Kernel concept and kernel functions, Kernel SVM.

Advanced Machine Learning Models (8 Hours)
• Gaussian Processes, Decision Trees, Random Forests, Ensemble Learning, Boosting and Gradient Boosting methods, Hyperparameter tuning,
• Performance evaluation metrics: Accuracy, Precision, Recall, F1-score. RMSE, MAE, Confusion Matrix.
• Model validation: Cross-validation, Training/testing split.

Unsupervised Learning and Reinforcement Learning (8 Hours)
• Clustering concepts and applications, K-Means clustering algorithm, Gaussian Mixture Models (GMM), Expectation Maximization (EM),
• Dimensionality reduction techniques: Principal Component Analysis (PCA), Independent Component Analysis (ICA), Factor Analysis.
• Variational Autoencoders (VAE).
• Reinforcement Learning: Markov Decision Process (MDP), Bellman equations, Value Iteration and Policy Iteration, Q-learning.

Machine Learning Applications in Power Engineering (8 Hours)
• Load forecasting using ML.
• Renewable energy forecasting: Solar power forecasting, Wind power forecasting.
• Energy market price prediction.
• Fault detection, classification, and localization in power systems.
• ML-based predictive maintenance for electrical drives.
• False data injection attack detection in smart grids.
• Machine learning in power electronics: MPPT control for photovoltaic systems, Intelligent control of converters and inverters, Condition monitoring of motors and drives.
• Case studies and industrial applications.

To introduce machine learning fundamentals and their relevance to power engineering applications.

To familiarize students with supervised, unsupervised, and reinforcement learning techniques.

To develop skills in data-driven modeling for electrical and power engineering systems.

To enable application of machine learning techniques in renewable energy, power converters, fault diagnosis, and intelligent control.

Explain the fundamentals of machine learning, neural networks, and learning paradigms relevant to power engineering applications.

Analyze supervised learning techniques for regression and classification problems in electrical and power engineering datasets.

Apply unsupervised learning methods for clustering, dimensionality reduction, and feature extraction from power system data.

Evaluate reinforcement learning approaches for intelligent decision-making and control in energy and power electronics systems.

Develop machine learning models using software tools for prediction, diagnostics, and performance assessment.

Design ML-based solutions for practical power engineering problems such as load forecasting, fault diagnosis, renewable energy prediction, and intelligent converter control.

Christopher M. Bishop, Pattern Recognition and Machine Learning, Springer , 2011

Ethem Alpaydin, Machine Learning, MIT Press , 2010

Anuradha Srinivasaraghavan and Vincy Joseph, Machine Learning, Wiley , 2019

Tom M. Mitchell, Machine Learning, McGraw Hill , 1997

Giuseppe Bonaccorso, Machine Learning Algorithms, Packt Publishing , 2018

Aurélien Géron, Hands-On Machine Learning with Scikit-Learn, Keras & TensorFlow, O’Reilly

Machine Learning for Engineering and science applications, IIT Madras, Prof. Balaji Srinivasan Prof. Ganapathy Krishnamurthi https://nptel.ac.in/courses/106106198

Machine Learning for Core Engineering Disciplines, IISc Bangalore,
Prof. Ananth Govind Rajan https://nptel.ac.in/courses/127108778