Physics-Aware Machine Learning for Integrated Energy Systems Management

Physics-Aware Machine Learning for Integrated Energy Systems Management guides the reader through this state-of-the-art approach to computational methods, from data input and training to application opportunities in integrated energy systems. This book begins by establishing the principles, design, and needs of integrated energy systems in the modern sustainable grid, before moving into assessing aspects such as sustainability, energy storage, and physical-economic models. Detailed, step-by-step procedures for utilizing a variety of physics-aware machine learning models are provided, including reinforcement learning, feature learning, and neural networks.

Supporting students, researchers, and industry engineers to make renewable-integrated grids a reality, Physics-Aware Machine Learning for Integrated Energy Systems Management is a holistic introduction to an exciting new approach in energy systems management.

• Outlines the challenges, opportunities, and applications in utilising physics-aware machine learning to support renewable energy integration to the modern grid
• Covers a wide variety of techniques, from the fundamental principles to security concerns
• Represents the latest offering in the cutting-edge series ‘Advances in Intelligent Energy Systems’, which introduces these essential multidisciplinary skills to modern energy engineers