An illuminating and up-to-date exploration of the latest advances in AI-empowered smart energy systems
In Artificial Intelligence Empowered Smart Energy Systems, the editors along with a team of distinguished researchers deliver an original and comprehensive discussion of artificial intelligence enabled smart energy systems. The book offers a deep dive into AI’s integration with energy, examining critical topics like renewable energy forecasting, load monitoring, fault diagnosis, resilience-oriented optimization, and efficiency-driven control.
The contributors discuss the real-world applications of AI in smart energy systems, showing you AI’s transformative effects on energy landscapes. It provides practical solutions and strategies to address complicated problems in energy systems.
The book also includes:
- A thorough introduction to cybersecurity, privacy, and virtual power plants
- Comprehensive demonstrations of the effective leveraging of AI technologies in energy systems
- Practical discussions of the potential of AI to create sustainable, efficient, and resilient energy systems
- Detailed case studies and real-world examples of AI’s implementation in smart energy systems
Perfect for researchers, data scientists, and policymakers, Artificial Intelligence Empowered Smart Energy Systems will also benefit graduate and senior undergraduate students in both the tech and energy industries.
Table of Contents:
List of Contributors xv
About the Editors xxi
Foreword xxiii
Preface xxv
Acknowledgments xxvii
1 Machine Learning-Based Applications for Cyberattack and Defense in Smart Energy Systems 1
Sha Peng, Mengxiang Liu, Zhenyong Zhang, and Ruilong Deng
1.1 Introduction to Machine Learning 1
1.1.1 Overview of Machine Learning Approaches 1
1.1.1.1 Unsupervised Learning 1
1.1.1.2 Supervised Learning 3
1.1.1.3 Semi-Supervised Learning 4
1.1.1.4 Reinforcement Learning 4
1.1.2 Advantages of Machine Learning 5
1.2 Machine Learning in Attack Design 6
1.2.1 System Information Inference 7
1.2.2 Attack Resource Allocation 9
1.3 Machine Learning in Attack Protection 10
1.3.1 Data Security 10
1.3.2 Vulnerability Analysis 11
1.4 Machine Learning in Attack Detection 12
1.4.1 Anomaly Detection 13
1.4.2 Line Outage Detection 18
1.4.3 Electricity Theft Detection 18
1.5 Machine Learning in Impact Mitigation 19
1.5.1 Compromised Measurement Clearing 19
1.6 Future Directions 20
References 22
2 Enhancing Cybersecurity in Power Communication Networks: An Approach to Resilient CPPS Through Channel Expansion and Defense Resource Allocation 27
Yingjun Wu, Yingtao Ru, Jinfan Chen, Hao Xu, Zhiwei Lin, Chengjun Liu, and Xinyi Liang
2.1 Introduction 27
2.2 Mechanisms for the Classification and Propagation of Cyberattacks 28
2.2.1 Popularity in Academic Research and Frequency of Actual Cyberattacks 30
2.2.2 Propagation Mechanism of Hotspot Cyberattacks 30
2.2.2.1 Denial of Service (DoS) Attack 30
2.2.2.2 False Data Injection Attacks (FDIAs) 32
2.2.2.3 The Black Hole Attack (BHA) 34
2.2.2.4 Address Resolution Protocol (ARP) Spoofing Attack 35
2.2.2.5 Man-In-The-Middle (MITM) Attack 36
2.2.2.6 Eavesdropping Attack (EA) 37
2.2.2.7 Replay Attack 38
2.2.2.8 Load Altering Attack (LAA) 39
2.2.3 Propagation Mechanism of Non-Hotspot Cyberattacks 41
2.2.3.1 Active Non-Hotspot Cyberattack 41
2.2.3.2 Passive Non-Hotspot Cyberattack 42
2.2.4 Targeting Equipment of Cyberattacks in TAL 43
2.3 Power Communication Network Planning Based on Information Transmission Reachability Against Cyberattacks 47
2.3.1 Introduction 47
2.3.2 Planning Framework for Grid Communication Network Planning Object 48
2.3.2.1 Planning Goals 49
2.3.2.2 Planning Framework 50
2.3.3 Topology Planning Model of Power Communication Network 51
2.3.3.1 Planning Goal of the TP to Ensure Information Transmission of Regular Operation 51
2.3.3.2 Enhancing Cyberattack Defense Capabilities in ACAP Planning Goals 53
2.3.4 A Game Theory-Based Planning Method 59
2.3.4.1 Criterion Derived from the Nash Equilibrium 59
2.3.4.2 Model Solution Using Enhanced Particle Swarm-Based Optimization Algorithm 60
2.3.5 Simulations 61
2.3.5.1 System Overview Under Study 61
2.3.5.2 Cyberattacks Factored in During the Planning Phase 63
2.3.5.3 Planning Results in Different Cases 63
2.3.5.4 Relative to Planning Methods that Disregard Cyberattacks 65
2.3.5.5 Practical Case Application 67
2.3.5.6 PSO-Based Analysis of Planning Outcomes 69
2.4 Survivability-Oriented Defensive Resource Allocation for Communication and Information Systems Under Cyberattack 71
2.4.1 Introduction 71
2.4.2 Systematic Evaluation of Survivability for CPPS Communication and Information Systems 73
2.4.2.1 Breaking Down Power Businesses into Atomic Services 73
2.4.2.2 Indexes for Evaluating the Survivability of Atomic Services 74
2.4.2.3 Survivability Evaluation Framework 74
2.4.2.4 Calculation Method for Survivability Evaluation Indices 74
2.4.2.5 Calculation Method for Survivability Evaluation Indexes 79
2.4.3 Defensive Resource Allocation Model for Enhancing CPPS Survivability Against Cyber Threats 79
2.4.3.1 Objective Function 80
2.4.3.2 Constraints 80
2.4.4 Modified Genetic Algorithm for the Proposed Model 80
2.4.5 Simulations 82
2.4.5.1 Introduction of the Studied System 82
2.4.5.2 Simulation Results and Analysis 85
References 91
3 Multi-Objective Real-Time Control of Operating Conditions Using Deep Reinforcement Learning 101
Ruisheng Diao, Tu Lan, Zhiwei Wang, Haifeng Li, Chunlei Xu, Fangyuan Sun, Bei Zhang, Yishen Wang, Siqi Wang, Jiajun Duan, andDiShi
3.1 Introduction 101
3.2 Principles of Deep Reinforcement Learning 102
3.2.1 Deep Q Network (DQN) 103
3.2.2 Proximal Policy Optimization (PPO) 104
3.2.3 Soft Actor-Critic (SAC) 106
3.3 Real-Time Line Flow Control Using PPO 107
3.3.1 Problem Formulation 107
3.3.1.1 State Space 107
3.3.1.2 Action Space 107
3.3.1.3 Reward Function 107
3.3.1.4 Training Process of PPO-Based Agents 108
3.3.2 Case Studies 109
3.4 Dueling DQN-Based Topology Control for Maximizing Available Transfer Capabilities 110
3.4.1 Problem Formulation 112
3.4.1.1 Architecture Design 113
3.4.1.2 Dueling DQN Agent 113
3.4.1.3 Imitation Learning 114
3.4.1.4 Guided Exploration Training 115
3.4.1.5 Early Warning 116
3.4.2 Case Studies 116
3.4.2.1 Environment and Framework 116
3.4.2.2 Effectiveness of Imitation Learning 117
3.4.2.3 Improved Performance with Guided Exploration 117
3.4.2.4 Performance Comparison of Different Agents 118
3.5 Real-Time Multi-Objective Power Flow Control Using Soft Actor-Critic 119
3.5.1 Problem Formulation 119
3.5.1.1 Architecture Design 120
3.5.1.2 Episode and Terminating Conditions 122
3.5.1.3 State Space 122
3.5.1.4 Control Space 122
3.5.1.5 Reward Definition 122
3.5.2 Case Studies 123
References 124
4 Smart Generation Control Based on Multi-Agents 127
Lei Xi, Yixiao Wang, Lu Dong, and Jianyu Ren
4.1 Overview 127
4.2 Research on Intelligent Power Generation Control Based on Multi-Agents 128
4.2.1 Function and Architecture of Multi-Agent System 128
4.2.2 Virtual Power Generation Tribe Control Based on Multi-Agent Theory 129
4.2.2.1 First-Order Multi-Agent Consistency Algorithm 130
4.2.2.2 Consistent AGC Power Allocation Algorithm 132
4.2.2.3 Robust Consistency Algorithm in Nonideal Communication Networks 136
4.3 Intelligent Power Generation Control for Islands and Microgrids 139
4.3.1 AGC Cooperative Control Based on Equal Incremental Rate Consistency Algorithm 141
4.3.1.1 Intelligent Distribution Network Decentralized Autonomy Framework 141
4.3.1.2 AGC Power Allocation Model of Smart Distribution Network 142
4.3.1.3 Consistency Algorithm of Equal Incremental Rate 143
References 147
5 Power System Fault Diagnosis Method Under Disaster Weather Based on Random Self-Regulating Algorithm 149
Tao Wang, Liyuan Liu, Ruixuan Ying, Chunyu Zhou, Hanyan Wu, and Quanlin Leng
5.1 Introduction 149
5.2 Analytic Model for Fault Diagnosis 151
5.2.1 Three Types of Self-Regulating Trust Factors 153
5.2.1.1 Self-Regulating Expectation Trust Factor and Self-Regulating Warning Trust Factor 153
5.2.1.2 Self-Regulating Weather Trust Factor 155
5.2.2 Expected States of Protection Devices 156
5.2.2.1 Expected States of Main Protective Relays 157
5.2.2.2 Expected States of Primary Backup Protective Relays 157
5.2.2.3 Expected States of Secondary Backup Protective Relays 157
5.2.2.4 Expected States of Breaker Failure Protective Relays 157
5.2.2.5 Expected States of Circuit Breakers 157
5.3 Random Self-Regulating Algorithm 157
5.3.1 Random Self-Regulating Algorithm 158
5.3.2 Bionic Self-Regulating Function 160
5.3.2.1 Increment Operator of Guiding Probability 160
5.3.2.2 Iterative Mutation Operator 162
5.3.3 Fault Diagnosis Process 164
5.4 Experiment and Analysis 165
5.4.1 Case Study 166
5.4.2 Accuracy Test 169
References 171
6 Statistical Machine Learning Model for Production Simulation of Power Systems with a High Proportion of Photovoltaics 173
Xueqian Fu, Feifei Yang, Qiaoyu Ma, Na Lu, and Chunyu Zhang
6.1 Introduction 173
6.2 Methodology 174
6.2.1 Long Time Scale 174
6.2.1.1 Bidirectional LSTM Style-Based Generative Adversarial Networks 174
6.2.1.2 Clustering with Adaptive Neighbors 176
6.2.2 Short Time Scale 180
6.2.2.1 Decomposition Strategy and Attention-Based Long Short-Term Memory Network 180
6.2.2.2 Forecasting with Dynamic Mask 183
6.3 Case Studies 185
6.3.1 Long Time Scale 185
6.3.1.1 Year-Round Photovoltaic Scenario Generation 185
6.3.1.2 Typical Scenarios Extraction 188
6.3.2 Short Time Scale 191
6.3.2.1 Power Load Forecast 191
6.3.2.2 Photovoltaic Power Generation Forecast 193
References 195
7 Dynamic Reconfiguration of PV-TEG Hybrid Systems via Improved Whale Optimization Algorithm 199
Bo Yang, Jiarong Wang, and Yulin li
7.1 Introduction 199
7.2 PV-TEG Hybrid System Model 202
7.2.1 PV System Model 202
7.2.2 TEG System Model 204
7.2.3 PV-TEG Hybrid System Model 206
7.2.4 Objective Function 207
7.2.5 Performance Evaluation 208
7.3 Improved Whale Optimization Algorithm 208
7.3.1 Whale Optimization Algorithm 208
7.3.1.1 Encircling Prey 208
7.3.1.2 Bubble-Net Attack 209
7.3.1.3 Random Search 209
7.3.2 Design of Improved Whale Optimization Algorithm 210
7.3.2.1 The Roulette Mechanism 210
7.3.2.2 Nonlinear Convergence Factor 212
7.4 Case Study 212
7.4.1 6 × 6SquareArray 213
7.4.2 6 × 10 Non-Square Array 219
7.5 Conclusion 226
References 228
8 Coordinating Transactive Energy and Carbon Emission Trading Among Multi-Energy Virtual Power Plants for Distributed Learning 233
Peiling Chen and Yujian Ye
8.1 Introduction 233
8.1.1 Background and Motivation 233
8.1.2 Review of Previous Work 234
8.2 Overall Transactive Trading Market in Heterogeneous Networked MEVPPs 236
8.3 Mathematical Formulation of MEVPP Coordination Problem 238
8.3.1 Objective Function 238
8.3.2 Constraints 239
8.3.2.1 Energy Balance Constraint 239
8.3.2.2 CER Balance Constraint 239
8.3.2.3 Operating Constraints of Conversion Devices 241
8.3.2.4 Constraints of Energy Storage Devices 242
8.3.2.5 Trading Constraints 242
8.3.2.6 Network Constraints 242
8.4 Adaptive Consensus ADMM 243
8.4.1 Consensus ADMM 243
8.4.2 Adaptive Tuning of Penalty Parameters 244
8.4.3 AC-ADMM-Based Energy and CER Trading for Networked MEVPPs 244
8.5 Case Studies 249
8.5.1 Experimental Setup 249
8.5.2 Impact of Transactive Trading 251
8.5.2.1 Impact of Transactive CER Trading 252
8.5.2.2 Impact of Transactive Heat Trading 254
8.5.3 Impact of Network Constraints 255
8.5.4 Convergence Analysis 256
8.6 Conclusions 258
References 258
9 Cluster-Based Heuristic Algorithm for Collection System Topology Generation of a Large-Scale Offshore Wind Farm 263
Jincheng Li, Zhengxun Guo, and Xiaoshun Zhang
9.1 Introduction 263
9.1.1 Background and Importance 263
9.1.2 Research Status 264
9.1.2.1 Radial Topologys Optimization Methods 264
9.1.2.2 Graph Theory-Based Methods 265
9.1.2.3 Meta-Heuristic Optimization Methods 265
9.2 Mathematical Model for CS Optimization in LSOWFs 266
9.2.1 Composition of the LSOWF 266
9.2.2 Objective Function 267
9.2.3 Constraints 268
9.2.3.1 Constraint on the Number of WTs per Feeder 268
9.2.3.2 Constraint on the Load Capacity of Submarine Cable 269
9.2.3.3 Non-Crossing Constraint of Submarine Cables 269
9.2.3.4 Voltage Constraint 270
9.3 Cluster-Based Topology Generation Method 270
9.3.1 Polar Coordinate Clustering 270
9.3.2 Radial Clustering 271
9.3.2.1 Fuzzy C-Means Algorithm 272
9.3.2.2 Radial Fuzzy C-Means Algorithm 272
9.3.3 Dynamic Minimum Spanning Tree 274
9.3.4 Firefly Algorithm-Based Optimization 276
9.4 Case Study 277
9.4.1 Test Case # 1 277
9.4.2 Test Case # 2 278
9.4.3 Cost Comparison 280
9.5 Conclusion 282
References 283
10 Transmission Line Multi-Fitting Detection Method Based on Implicit Space Knowledge Fusion 287
Qianming Wang, Congbin Guo, Xuan Liu, and Yongjie Zhai
10.1 Introduction 287
10.2 Overall Overview of Methods 292
10.3 Implicit Spatial Knowledge Fusion Structure 294
10.3.1 Spatial Box Setting Module 295
10.3.2 Spatial Context Extraction Module 297
10.3.3 Spatial Context Memory Module 298
10.4 Improved Post-Processing Structure 301
10.5 Experimental Results and Analysis 303
10.5.1 Experimental Dataset and Environment 303
10.5.2 Comprehensive Comparative Experiment 304
10.5.3 Ablation Experiment 307
10.5.4 Visual Comparison Experiment 309
10.6 Summary 311
References 312
Index 315
About the Author :
Qiang Yang, PhD, is a Full Professor at the College of Electrical Engineering at Zhejiang University, China. He is a Senior Member of the IEEE and a Distinguished Member of the China Computer Federation. His primary research interests include smart energy systems, learning-based optimization and control.
Gang Huang, PhD, is an Assistant Professor at the College of Electrical Engineering at Zhejiang University, China. He is a Senior Member of the IEEE and a Senior Member of the China Computer Federation. His primary research interests include artificial intelligence for power and energy systems.
