Course Outcome
| CO1 | Apply foundational and advanced Reinforcement Learning (RL) algorithms for modeling intelligent energy systems |
| CO2 | Analyze and implement Generative AI models for synthetic data generation and intelligent forecasting in Smart Grid and Electric Vehicle (EV) applications. |
| CO3 | Implement Generative Adversarial Network (GAN) architectures in energy systems |
| CO4 | Demonstrate scalable data-driven pipelines for monitoring and decision-making in energy systems |
Course Articulation Matrix: Correlation level [ 1: low, 2: medium, 3: High]
| PO | PO1 | PO2 | PO3 | PSO1 | PSO2 |
| CO | |||||
| CO1 | 2 | 1 | 3 | 3 | 1 |
| CO2 | 2 | 1 | 3 | 2 | |
| CO3 | 3 | 1 | 2 | 2 | |
| CO4 | 1 | 1 | 1 | 2 |
Reinforcement Learning (RL) in Energy Systems: RL basics: agent, environment, reward, policy, Tabular methods: Q-Learning, SARSA, Policy gradient methods, Deep Reinforcement Learning: DQN (Deep Q Network), DDPG (Deep Deterministic Policy Gradient), PPO (Proximal Policy Optimization)? Generative AI for Smart Grids & EVs: Introduction to generative AI: concepts & significance Transformer models- BERT, GPT, Diffusion models and multimodal learning? Generative Adversarial Networks: GAN architecture: generator vs discriminator, Loss functions and training challenges, Variants: Conditional GAN (CGAN), CycleGAN, TimeGAN? Big Data Architectures for Energy, Data Ingestion and Storage Real-time data pipelines, Data Cleaning & Preprocessing Techniques. Analytics and Visualization Tools