Artificial Intelligence for Renewable Energy Systems

Ajay Kumar Vyas, PhD is an assistant professor at Adani Institute of Infrastructure Engineering, Ahmedabad, India. He has authored several research papers in peer-reviewed international journals and conferences, three books, and two Indian patents.S. Balamurugan, PhD SMIEEE, ACM Distinguished Speaker, received his PhD from Anna University, India. He has published 57 books, 300+ international journals/conferences, and 100 patents. He is the Director of the Albert Einstein Engineering and Research Labs. He is also the Vice-Chairman of the Renewable Energy Society of India (RESI). He is serving as a research consultant to many companies, startups, SMEs, and MSMEs. He has received numerous awards for research at national and international levels. Kamal Kant Hiran, PhD is an assistant professor at the School of Engineering, Sir Padampat Singhania University (SPSU), Udaipur, Rajasthan, India, as well as a research fellow at the Aalborg University, Copenhagen, Denmark. He has published more than 35 scientific research papers in SCI/Scopus/Web of Science and IEEE Transactions Journal, conferences, two Indian patents, one Australian patent granted, and nine books. Harsh S. Dhiman, PhD is an assistant professor in the Department of Electrical Engineering at Adani Institute of Infrastructure Engineering, Ahmedabad, India. He has published 12 SCI-indexed journal articles and two books, and his research interests include hybrid operation of wind farms, hybrid wind forecasting techniques, and anomaly detection in wind turbines.

• Preface xi1 Analysis of Six-Phase Grid Connected Synchronous Generator in Wind Power Generation 1Arif Iqbal and Girish Kumar Singh1.1 Introduction 21.2 Analytical Modeling of Six-Phase Synchronous Machine 41.2.1 Voltage Equation 51.2.2 Equations of Flux Linkage Per Second 51.3 Linearization of Machine Equations for Stability Analysis 101.4 Dynamic Performance Results 121.5 Stability Analysis Results 151.5.1 Parametric Variation of Stator 161.5.2 Parametric Variation of Field Circuit 191.5.3 Parametric Variation of Damper Winding, Kd 221.5.4 Parametric Variation of Damper Winding, Kq 241.5.5 Magnetizing Reactance Variation Along q-axis 261.5.6 Variation in Load 281.6 Conclusions 29References 30Appendix 31Symbols Meaning 322 Artificial Intelligence as a Tool for Conservation and Efficient Utilization of Renewable Resource 37Vinay N., Ajay Sudhir Bale, Subhashish Tiwari and Baby Chithra R.2.1 Introduction 382.2 AI in Water Energy 392.2.1 Prediction of Groundwater Level 392.2.2 Rainfall Modeling 462.3 AI in Solar Energy 472.3.1 Solar Power Forecasting 472.4 AI in Wind Energy 532.4.1 Wind Monitoring 532.4.2 Wind Forecasting 542.5 AI in Geothermal Energy 552.6 Conclusion 60References 613 Artificial Intelligence–Based Energy-Efficient Clustering and Routing in IoT-Assisted Wireless Sensor Network 79Nitesh Chouhan3.1 Introduction 803.2 Related Study 813.3 Clustering in WSN 843.4 Research Methodology 853.4.1 Creating Wireless Sensor–Based IoT Environment 853.4.2 Clustering Approach 863.4.3 AI-Based Energy-Aware Routing Protocol 873.5 Conclusion 89References 894 Artificial Intelligence for Modeling and Optimization of the Biogas Production 93Narendra Khatri and Kamal Kishore Khatri4.1 Introduction 934.2 Artificial Neural Network 964.2.1 ANN Architecture 964.2.2 Training Algorithms 984.2.3 Performance Parameters for Analysis of the ANN Model 984.2.4 Application of ANN for Biogas Production Modeling 994.3 Evolutionary Algorithms 1034.3.1 Genetic Algorithm 1034.3.2 Ant Colony Optimization 1044.3.3 Particle Swarm Optimization 1064.3.4 Application of Hybrid Models (ANN and Evolutionary Algorithms) for Biogas Production Modeling 1064.4 Conclusion 107References 1115 Battery State-of-Charge Modeling for Solar PV Array Using Polynomial Regression 115Siddhi Vinayak Pandey, Jeet Patel and Harsh S. Dhiman5.1 Introduction 1155.2 Dynamic Battery Modeling 1195.2.1 Proposed Methodology 1205.3 Results and Discussion 1225.4 Conclusion 126References 1276 Deep Learning Algorithms for Wind Forecasting: An Overview 129M. Lydia and G. Edwin Prem KumarNomenclature 1296.1 Introduction 1316.2 Models for Wind Forecasting 1336.2.1 Persistence Model 1336.2.2 Point vs. Probabilistic Forecasting 1336.2.3 Multi-Objective Forecasting 1346.2.4 Wind Power Ramp Forecasting 1346.2.5 Interval Forecasting 1346.2.6 Multi-Step Forecasting 1346.3 The Deep Learning Paradigm 1356.3.1 Batch Learning 1366.3.2 Sequential Learning 1366.3.3 Incremental Learning 1366.3.4 Scene Learning 1366.3.5 Transfer Learning 1366.3.6 Neural Structural Learning 1366.3.7 Multi-Task Learning 1376.4 Deep Learning Approaches for Wind Forecasting 1376.4.1 Deep Neural Network 1376.4.2 Long Short-Term Memory 1386.4.3 Extreme Learning Machine 1386.4.4 Gated Recurrent Units 1396.4.5 Autoencoders 1396.4.6 Ensemble Models 1396.4.7 Other Miscellaneous Models 1396.5 Research Challenges 1396.6 Conclusion 141References 1427 Deep Feature Selection for Wind Forecasting-I 147C. Ramakrishnan, S. Sridhar, Kusumika Krori Dutta, R. Karthick and C. Janamejaya7.1 Introduction 1487.2 Wind Forecasting System Overview 1527.2.1 Classification of Wind Forecasting 1537.2.2 Wind Forecasting Methods 1537.2.2.1 Physical Method 1547.2.2.2 Statistical Method 1547.2.2.3 Hybrid Method 1557.2.3 Prediction Frameworks 1557.2.3.1 Pre-Processing of Data 1557.2.3.2 Data Feature Analysis 1567.2.3.3 Model Formulation 1567.2.3.4 Optimization of Model Structure 1567.2.3.5 Performance Evaluation of Model 1577.2.3.6 Techniques Based on Methods of Forecasting 1577.3 Current Forecasting and Prediction Methods 1587.3.1 Time Series Method (TSM) 1597.3.2 Persistence Method (PM) 1597.3.3 Artificial Intelligence Method 1607.3.4 Wavelet Neural Network 1617.3.5 Adaptive Neuro-Fuzzy Inference System (ANFIS) 1627.3.6 ANFIS Architecture 1637.3.7 Support Vector Machine (SVM) 1657.3.8 Ensemble Forecasting 1667.4 Deep Learning–Based Wind Forecasting 1667.4.1 Reducing Dimensionality 1687.4.2 Deep Learning Techniques and Their Architectures 1697.4.3 Unsupervised Pre-Trained Networks 1697.4.4 Convolutional Neural Networks 1707.4.5 Recurrent Neural Networks 1707.4.6 Analysis of Support Vector Machine and Decision Tree Analysis (With Computation Time) 1707.4.7 Tree-Based Techniques 1727.5 Case Study 173References 1768 Deep Feature Selection for Wind Forecasting-II 181S. Oswalt Manoj, J.P. Ananth, Balan Dhanka and Maharaja Kamatchi8.1 Introduction 1828.1.1 Contributions of the Work 1848.2 Literature Review 1858.3 Long Short-Term Memory Networks 1868.4 Gated Recurrent Unit 1908.5 Bidirectional Long Short-Term Memory Networks 1948.6 Results and Discussion 1968.7 Conclusion and Future Work 197References 1989 Data Falsification Detection in AMI: A Secure Perspective Analysis 201Vineeth V.V. and S. Sophia9.1 Introduction 2019.2 Advanced Metering Infrastructure 2029.3 AMI Attack Scenario 2049.4 Data Falsification Attacks 2059.5 Data Falsification Detection 2069.6 Conclusion 207References 20810 Forecasting of Electricity Consumption for G20 Members Using Various Machine Learning Techniques 211Jaymin Suhagiya, Deep Raval, Siddhi Vinayak Pandey, Jeet Patel, Ayushi Gupta and Akshay Srivastava10.1 Introduction 21110.1.1 Why Electricity Consumption Forecasting Is Required? 21210.1.2 History and Advancement in Forecasting of Electricity Consumption 21210.1.3 Recurrent Neural Networks 21310.1.3.1 Long Short-Term Memory 21410.1.3.2 Gated Recurrent Unit 21410.1.3.3 Convolutional LSTM 21510.1.3.4 Bidirectional Recurrent Neural Networks 21610.1.4 Other Regression Techniques 21610.2 Dataset Preparation 21710.3 Results and Discussions 21810.4 Conclusion 225Acknowledgement 225References 22511 Use of Artificial Intelligence (AI) in the Optimization of Production of Biodiesel Energy 229Manvinder Singh Pahwa, Manish Dadhich, Jaskaran Singh Saini and Dinesh Kumar Saini11.1 Introduction 23011.2 Indian Perspective of Renewable Biofuels 23011.3 Opportunities 23211.4 Relevance of Biodiesel in India Context 23311.5 Proposed Model 23411.6 Conclusion 236References 237Index 239