Optimization, Uncertainty and Machine Learning in Wind Energy Conversion Systems

This book presents state-of-the-art technologies in wind farm layout optimization and control to improve the current industry/research practice. The contents take readers towards a different kind of uncertainty handling through the discussion on several techniques enabling maximum energy harnessing out of uncertain situations. The book aims to give a detailed overview of such concepts in the first part, where the recent advancements in the fields of (i) Wind farm layout optimization, (ii) Multi-objective Optimization and Uncertainty handling in optimization methods, (iii) Development of Machine Learning-based surrogate models in optimization, and (iv) Different types of wake models for wind farms will be discussed. The second part will cover the application of the aforementioned techniques on the wind farm layout optimization and control through several chapters such as (i) Wind farm performance assessment using Computational Fluid Dynamics (CFD) tools, (ii) Artificial Neural Network (ANN) based hybrid wake models, (iii) Long Short-term Memory (LSTM) & Support Vector Regression (SVR) based forecasting and micro-siting, (iv) windfarm micro-siting using data-driven Robust Optimization (RO) as well as Generative Adversarial Networks (GANs), (v) Reinforcement learning (RL) based wind farm control and (vi) Application of eXplainable AI (XAI) tools for interpreting wind time-series data. In this manner, the book provides state-of-the-art techniques in the fields of multi-objective optimization, Evolutionary Algorithms, Machine Learning surrogate models, Bayesian Optimization, Data Analysis, and Optimization under Uncertainty and their applications in the field of wind energy generation that can be extremely generic and can be applied to many other engineering fields. This volume will be of interest to those in academia and industry.

Focusing on renewable energy research handling wind farm optimization under uncertainty Discusses novel concepts of deep learning-based techniques and uncertainty handling techniques Presents state-of-the-art technologies in wind farm layout optimization & control to improve industry/research practice

Auteur

Prof. Kishalay Mitra received his B.E. from the National Institute of Technology (NIT) Durgapur, India, in 1995, M. Tech. from Indian Institute of Technology (IIT) Kanpur, India, in 1997, and Ph.D. from the Indian Institute of Technology (IIT) Bombay, India, in 2009 (all in Chemical Engineering). He is a Professor in the Department of Chemical Engineering and associated faculty in the Departments of Artificial Intelligence and Climate Change at IIT Hyderabad, India. His work interests lie in the interface of data analysis and process optimization such as machine learning, evolutionary optimization, optimization under uncertainty, planning and scheduling of supply chain, and analysis of systems involving biology, climate change, and renewable energy. He worked in several engineering leadership positions at General Electric Global Research, Bangalore, and Tata Research Development & Design Centre, Pune for close to 15 years. His research has been supported by several leading agencies in India like the Department of Science & Technology, Department of Bio-Technology, Ministry of Education, Defence Research & Development Organization, and Tata Steel through several nationally important projects (~ INR 50 million). He has over 200 international journal and conference publications to his credit. Apart from serving on the editorial board of several reputed journals and conferences, he has been visiting Washington University in St. Louis, USA, and the University of Washington, Seattle as a visiting professor on several occasions. He has been named among the World's top 2% scientists according to the latest profile review conducted by a group from Stanford University since its inception.

Prof. Richard Everson is a Professor of Machine Learning and Director of the Institute for Data Science and Artificial Intelligence at the University of Exeter. He is a Fellow of The Alan Turing Institute and the Turing University Lead for Exeter. His research interests focus on statistical machine learning, multi-objective optimization, and the interactions between them. Particularly relevant is his work on measuring and accounting for uncertainty in evolutionary and robust Bayesian optimization. He was the principal investigator for the EPSRC `Data-Driven Surrogate-Assisted Evolutionary Fluid Dynamic Optimisation' which pioneered Bayesian optimization methods for Computational Fluid Dynamics problems.

Prof. Jonathan Fieldsend received a BA in Economics from Durham University in 1998, an MSc in Computational Intelligence from the University of Plymouth in 1999, and a PhD in Computer Science from the University of Exeter in 2003. He is a Professor of Computational Intelligence at the University of Exeter. He primarily works on the interface of optimization heuristics and machine learning. This includes both fundamental advances, as well as solving immediate and near-term problems with partners from industry and the public sector. He has particular interests in multi-objective, expensive, and uncertain design optimization problems, along with search landscape characterization. He has contributed to several professional activities, including acting as Editor-in-Chief for the ACM Genetic and Evolutionary Computation Conference in 2022.

Contenu
Part 1 State-of-the-art in Optimization, Uncertainty handling, Machine Learning methods, and Wake models.- Chapter 1. Introduction.- Chpater 2. Multi-objective optimisation with uncertainty: considerations for wind farm optimisation.- Chapter 3. Offline Multi-Objective Optimisation using Surrogate-Assisted Evolutionary Algorithms with Uncertainty Quantification.- Chapter 4. Bayesian optimisation for expensive computational fluid dynamics design problems.- Chapter 5. Multidisciplinary uncertainty modelling using Copulas.