Preface xv 1 Optimization Algorithm for Renewable Energy Integration 1Bikash Das, SoumyabrataBarik, Debapriya Das and V Mukherjee 1.1 Introduction 2 1.2 Mixed Discrete SPBO 5 1.2.1 SPBO Algorithm 5 1.2.2 Performance of SPBO for Solving Benchmark Functions 8 1.2.3 Mixed Discrete SPBO 11 1.3 Problem Formulation 12 1.3.1 Objective Functions 12 1.3.2 Technical Constraints Considered 14 1.4 Comparison of the SPBO Algorithm in Terms of CEC-2005 Benchmark Functions 17 1.5 Optimum Placement of RDG and Shunt Capacitor to the Distribution Network 18 1.5.1 Optimum Placement of RDGs and Shunt Capacitors to 33-Bus Distribution Network 25 1.5.2 Optimum Placement of RDGs and Shunt Capacitors to 69-Bus Distribution Network 29 1.6 Conclusions 33 References 34 2 Chaotic PSO for PV System Modelling 41Souvik Ganguli, Jyoti Gupta and Parag Nijhawan 2.1 Introduction 42 2.2 Proposed Method 43 2.3 Results and Discussions 43 2.4 Conclusions 72 References 72 3 Application of Artificial Intelligence and Machine Learning Techniques in Island Detection in a Smart Grid 79Soham Dutta, Pradip Kumar Sadhu, Murthy Cherikuri and Dusmanta Kumar Mohanta 3.1 Introduction 80 3.1.1 Distributed Generation Technology in Smart Grid 81 3.1.2 Microgrids 81 3.3.1.1 Problems with Microgrids 81 3.2 Islanding in Power System 82 3.3 Island Detection Methods 83 3.3.1 Passive Methods 83 3.3.2 Active Methods 85 3.3.3 Hybrid Methods 86 3.3.4 Local Methods 87 3.3.5 Signal Processing Methods 87 3.3.6 Classifer Methods 88 3.4 Application of Machine Learning and Artificial Intelligence Algorithms in Island Detection Methods 89 3.4.1 Decision Tree 89 3.4.1.1 Advantages of Decision Tree 91 3.4.1.2 Disadvantages of Decision Tree 91 3.4.2 Artificial Neural Network 91 3.4.2.1 Advantages of Artificial Neural Network 93 3.4.2.2 Disadvantages of Artificial Neural Network 93 3.4.3 Fuzzy Logic 93 3.4.3.1 Advantages of Fuzzy Logic 94 3.4.3.2 Disadvantages of Fuzzy Logic 94 3.4.4 Artificial Neuro-Fuzzy Inference System 95 3.4.4.1 Advantages of Artificial Neuro-Fuzzy Inference System 95 3.4.4.2 Disadvantages of Artificial Neuro-Fuzzy Inference System 96 3.4.5 Static Vector Machine 96 3.4.5.1 Advantages of Support Vector Machine 97 3.4.5.2 Disadvantages of Support Vector Machine 97 3.4.6 Random Forest 97 3.4.6.1 Advantages of Random Forest 98 3.4.6.2 Disadvantages of Random Forest 98 3.4.7 Comparison of Machine Learning and Artificial Intelligence Based Island Detection Methods with Other Methods 99 3.5 Conclusion 99 References 101 4 Intelligent Control Technique for Reduction of Converter Generated EMI in DG Environment 111Ritesh Tirole, R R Joshi, Vinod Kumar Yadav, Jai Kumar Maherchandani and Shripati Vyas 4.1 Introduction 112 4.2 Grid Connected Solar PV System 113 4.2.1 Grid Connected Solar PV System 113 4.2.2 PhotoVoltaic Cell 114 4.2.3 PhotoVoltaic Array 114 4.2.4 PhotoVoltaic System Configurations 114 4.2.4.1 Centralized Configurations 115 4.2.4.2 Master Slave Configurations 115 4.2.4.3 String Configurations 115 4.2.4.4 Modular Configurations 115 4.2.5 Inverter Integration in Grid Solar PV System 115 4.2.5.1 Voltage Source Inverter 116 4.2.5.2 Current Source Inverter 117 4.3 Control Strategies for Grid Connected Solar PV System 117 4.3.1 Grid Solar PV System Controller 117 4.3.1.1 Linear Controllers 117 4.3.1.2 Non-Linear Controllers 117 4.3.1.3 Robust Controllers 118 4.3.1.4 Adaptive Controllers 118 4.3.1.5 Predictive Controllers 118 4.3.1.6 Intelligent Controllers 118 4.4 Electromagnetic Interference 118 4.4.1 Mechanisms of Electromagnetic Interference 119 4.4.2 Effect of Electromagnetic Interference 120 4.5 Intelligent Controller for Grid Connected Solar PV System 120 4.5.1 Fuzzy Logic Controller 120 4.6 Results and Discussion 121 4.6.1 Generated EMI at the Input Side of Grid SPV System 122 4.7 Conclusion 125 References 125 5 A Review of Algorithms for Control and Optimization for Energy Management of Hybrid Renewable Energy Systems 131Megha Vyas, Vinod Kumar Yadav, Shripati Vyas, R.R Joshi and Ritesh Tirole 5.1 Introduction 132 5.2 Optimization and Control of HRES 134 5.3 Optimization Techniques/Algorithms 135 5.3.1 Genetic Algorithms (GA) 136 5.4 Use of Ga In Solar Power Forecasting 140 5.5 PV Power Forecasting 142 5.5.1 Short-Term Forecasting 143 5.5.2 Medium Term Forecasting 144 5.5.3 Long Term Forecasting 144 5.6 Advantages 145 5.7 Disadvantages 146 5.8 Conclusion 146 Appendix A: List of Abbreviations 146 References 147 6 Integration of RES with MPPT by SVPWM Scheme 157Busireddy Hemanth Kumar and Vivekanandan Subburaj 6.1 Introduction 158 6.2 Multilevel Inverter Topologies 158 6.2.1 Cascaded H-Bridge (CHB) Topology 159 6.2.1.1 Neutral Point Clamped (NPC) Topology 160 6.2.1.2 Flying Capacitor (FC) Topology 160 6.3 Multilevel Inverter Modulation Techniques 161 6.3.1 Fundamental Switching Frequency (FSF) 162 6.3.1.1 Selective Harmonic Elimination Technique for MLIs 162 6.3.1.2 Nearest Level Control Technique 163 6.3.1.3 Nearest Vector Control Technique 164 6.3.2 Mixed Switching Frequency PWM 164 6.3.3 High Level Frequency PWM 164 6.3.3.1 CBPWM Techniques for MLI 164 6.3.3.2 Pulse Width Modulation Algorithms Using Space Vector Techniques for Multilevel Inverters 167 6.4 Grid Integration of Renewable Energy Sources (RES) 167 6.4.1 Solar PV Array 167 6.4.2 Maximum Power Point Tracking (MPPT) 169 6.4.3 Power Control Scheme 170 6.5 Simulation Results 171 6.6 Conclusion 176 References 176 7 Energy Management of Standalone Hybrid Wind-PV System 179Raunak Jangid, Jai Kumar Maherchandani, Vinod Kumar and Raju Kumar Swami 7.1 Introduction 180 7.2 Hybrid Renewable Energy System Configuration & Modeling 180 7.3 PV System Modeling 181 7.4 Wind System Modeling 183 7.5 Modeling of Batteries 185 7.6 Energy Management Controller 186 7.7 Simulation Results and Discussion 186 7.7.1 Simulation Response at Impulse Change in Wind Speed, Successive Increase in Irradiance Level and Impulse Change in Load 187 7.8 Conclusion 193 References 194 8 Optimization Technique Based Distribution Network Planning Incorporating Intermittent Renewable Energy Sources 199Surajit Sannigrahi and Parimal Acharjee 8.1 Introduction 200 8.2 Load and WTDG Modeling 204 8.2.1 Modeling of Load Demand 204 8.2.2 Modeling of WTDG 205 8.3 Objective Functions 207 8.3.1 System Voltage Enhancement Index (SVEI) 208 8.3.2 Economic Feasibility Index (EFI) 208 8.3.3 Emission Cost Reduction Index (ECRI) 211 8.4 Mathematical Formulation Based on Fuzzy Logic 212 8.4.1 Fuzzy MF for SVEI 212 8.4.2 Fuzzy MF for EFI 213 8.4.3 Fuzzy MF for ECRI 214 8.5 Solution Algorithm 215 8.5.1 Standard RTO Technique 215 8.5.2 Discrete RTO (DRTO) Algorithm 217 8.5.3 Computational Flow 219 8.6 Simulation Results and Analysis 221 8.6.1 Obtained Results for Different Planning Cases 223 8.6.2 Analysis of Voltage Profile and Power Flow Under the Worst Case Scenarios: 230 8.6.3 Comparison Between Different Algorithms 231 8.6.3.1 Solution Quality 234 8.6.3.2 Computational Time 234 8.6.3.3 Failure Rate 234 8.6.3.4 Convergence Characteristics 234 8.6.3.5 Wilcoxon Signed Rank Test (WSRT) 236 8.7 Conclusion 237 References 239 9 User Interactive GUI for Integrated Design of PV Systems 243SushmitaSarkar, K UmaRao, Prema V, Anirudh Sharma C A, Jayanth Bhargav and ShrikeshSheshaprasad 9.1 Introduction 244 9.2 PV System Design 245 9.2.1 Design of a Stand-Alone PV System 245 9.2.1.1 Panel Size Calculations 246 9.2.1.2 Battery Sizing 247 9.2.1.3 Inverter Design 248 9.2.1.4 Loss of Load 249 9.2.1.5 Average Daily Units Generated 249 9.2.2 Design of a Grid-Tied PV System 250 9.2.3 Design of a Large-Scale Power Plant 251 9.3 Economic Considerations 252 9.4 PV System Standards 252 9.5 Design of GUI 252 9.6 Results 255 9.6.1 Design of a Stand-Alone System Using GUI 255 9.6.2 GUI for a Grid-Tied System 257 9.6.3 GUI for a Large PV Plant 259 9.7 Discussions 260 9.8 Conclusion and Future Scope 260 9.9 Acknowledgment 261 References 261 10 Situational Awareness of Micro-Grid Using Micro-PMU and Learning Vector Quantization Algorithm 267Kunjabihari Swain and Murthy Cherukuri 10.1 Introduction 268 10.2 Micro Grid 269 10.3 Phasor Measurement Unit and Micro PMU 270 10.4 Situational Awareness: Perception, Comprehension and Prediction 272 10.4.1 Perception 273 10.4.2 Comprehension 274 10.4.3 Projection 280 10.5 Conclusion 280 References 280 11 AI and ML for the Smart Grid 287Dr M K Khedkar and B Ramesh Abbreviations 288 11.1 Introduction 288 11.2 AI Techniques 291 11.2.1 Expert Systems (ES) 291 11.2.2 Artificial Neural Networks (ANN) 291 11.2.3 Fuzzy Logic (FL) 292 11.2.4 Genetic Algorithm (GA) 292 11.3 Machine Learning (ML) 293 11.4 Home Energy Management System (HEMS) 294 11.5 Load Forecasting (LF) in Smart Grid 295 11.6 Adaptive Protection (AP) 297 11.7 Energy Trading in Smart Grid 298 11.8 AI Based Smart Energy Meter (AI-SEM) 300 References 302 12 Energy Loss Allocation in Distribution Systems with Distributed Generations 307Dr Kushal Manohar Jagtap 12.1 Introduction 308 12.2 Load Modelling 311 12.3 Mathematicl Model 312 12.4 Solution Algorithm 317 12.5 Results and Discussion 317 12.6 Conclusion 341 References 341 13 Enhancement of Transient Response of Statcom and VSC Based HVDC with GA and PSO Based Controllers 345Nagesh Prabhu, R Thirumalaivasan and M.Janaki 13.1 Introduction 346 13.2 Design of Genetic Algorithm Based Controller for STATCOM 347 13.2.1 Two Level STACOM with Type-2 Controller 348 13.2.1.1 Simulation Results with Suboptimal Controller Parameters 349 13.2.1.2 PI Controller Without Nonlinear State Variable Feedback 349 13.2.1.3 PI Controller with Nonlinear State Variable Feedback 351 13.2.2 Structure of Type-1 Controller for 3-Level STACOM 354 13.2.2.1 Transient Simulation with Suboptimal Controller Parameters 357 13.2.3 Application of Genetic Algorithm for Optimization of Controller Parameters 357 13.2.3.1 Boundaries of Type-2 Controller Parameters in GA Optimization 359 13.2.3.2 Boundaries of Type-1 Controller Parameters in GA Optimization 360 13.2.4 Optimization Results of Two Level STATCOM with GA Optimized Controller Parameters 360 13.2.4.1 Transient Simulation with GA Optimized Controller Parameters 361 13.2.5 Optimization Results of Three Level STATCOM with Optimal Controller Parameters 362 13.2.5.1 Transient Simulation with GA Optimized Controller Parameters 363 13.3 Design of Particle Swarm Optimization Based Controller for STATCOM 364 13.3.1 Optimization Results of Two Level STATCOM with GA and PSO Optimized Parameters 365 13.4 Design of Genetic Algorithm Based Type-1 Controller for VSCHVDC 371 13.4.1 Modeling of VSC HVDC 371 13.4.1.1 Converter Controller 374 13.4.2 A Case Study 375 13.4.2.1 Transient Simulation with Suboptimal Controller Parameters 376 13.4.3 Design of Controller Using GA and Simulation Results 378 13.4.3.1 Description of Optimization Problem and Application of GA 378 13.4.3.2 Transient Simulation 379 13.4.3.3 Eigenvalue Analysis 379 13.5 Conclusion 379 References 386 14 Short Term Load Forecasting for CPP Using ANN 391Kirti Pal and Vidhi Tiwari 14.1 Introduction 392 14.1.1 Captive Power Plant 394 14.1.2 Gas Turbine 394 14.2 Working of Combined Cycle Power Plant 395 14.3 Implementation of ANN for Captive Power Plant 396 14.4 Training and Testing Results 397 14.4.1 Regression Plot 397 14.4.2 The Performance Plot 398 14.4.3 Error Histogram 399 14.4.4 Training State Plot 399 14.4.5 Comparison between the Predicted Load and Actual Load 401 14.5 Conclusion 403 14.6 Acknowlegdement 403 References 404 15 Real-Time EVCS Scheduling Scheme by Using GA 409Tripti Kunj and Kirti Pal 15.1 Introduction 410 15.2 EV Charging Station Modeling 413 15.2.1 Parts of the System 413 15.2.2 Proposed EV Charging Station 414 15.2.3 Proposed Charging Scheme Cycle 414 15.3 Real Time System Modeling for EVCS 415 15.3.1 Scenario 1 415 15.3.2 Design of Scenario 1 418 15.3.3 Scenario 2 419 15.3.4 Design of Scenario 2 421 15.3.5 Simulation Settings 422 15.4 Results and Discussion 424 15.4.1 Influence on Average Waiting Time 424 15.4.1.1 Early Morning 425 15.4.1.2 Forenoon 425 15.4.1.3 Afternoon 426 15.4.2 Influence on Number of Charged EV 426 15.5 Conclusion 428 References 428 About the Editors 435 Index 437

This collection of papers on artificial intelligence and other methods for improving renewable energy systems, written by industry experts, is a reflection of the state of the art, a must-have for engineers, maintenance personnel, students, and anyone else wanting to stay abreast with current energy systems concepts and technology. Renewable energy is one of the most important subjects being studied, researched, and advanced in today’s world. From a macro level, like the stabilization of the entire world’s economy, to the micro level, like how you are going to heat or cool your home tonight, energy, specifically renewable energy, is on the forefront of the discussion. This book illustrates modelling, simulation, design and control of renewable energy systems employed with recent artificial intelligence (AI) and optimization techniques for performance enhancement. Current renewable energy sources have less power conversion efficiency because of its intermittent and fluctuating behavior. Therefore, in this regard, the recent AI and optimization techniques are able to deal with data ambiguity, noise, imprecision, and nonlinear behavior of renewable energy sources more efficiently compared to classical soft computing techniques. This book provides an extensive analysis of recent state of the art AI and optimization techniques applied to green energy systems. Subsequently, researchers, industry persons, undergraduate and graduate students involved in green energy will greatly benefit from this comprehensive volume, a must-have for any library. Audience Engineers, scientists, managers, researchers, students, and other professionals working in the field of renewable energy.