Artificial Intelligence-based Smart Power Systems

Sanjeevikumar Padmanaban, PhD, is a Full Professor with the Department of Electrical Engineering, IT and Cybernetics, at the University of South-Eastern Norway, Porsgrunn, Norway. He serves as an Editor/Associate Editor/Editorial Board Member of many refereed journals, in particular, the IEEE Systems Journal, the IEEE Access Journal, IEEE Transactions on Industry Applications, the Deputy Editor/Subject Editor of IET Renewable Power Generation, and IET Generation, Transmission and Distribution Journal, Subject Editor of FACETS and Energies MDPI Journal.Sivaraman Palanisamy is a Program Manager - EV Charging Infrastructure in WRI India. He is an IEEE Senior Member, a Member of CIGRE, and Life Member of the Institution of Engineers (India). He is an active participant in the IEEE Standards Association.Sharmeela Chenniappan, PhD, is a Professor in the Department of EEE, CEG campus, Anna University, Chennai, India. She is an IEEE Senior Member, a Life Member of CBIP, and Member of the Institution of Engineers (India), ISTE, and SSI.Jens Bo Holm-Nielsen, PhD, is the Head of the Esbjerg Energy Section with the Department of Energy Technology at Aalborg University. He has been an organizer of various international conferences, workshops, and training programs.

• Editor Biography xvList of Contributors xvii1 Introduction to Smart Power Systems 1Sivaraman Palanisamy, Zahira Rahiman, and Sharmeela Chenniappan1.1 Problems in Conventional Power Systems 11.2 Distributed Generation (DG) 11.3 Wide Area Monitoring and Control 21.4 Automatic Metering Infrastructure 41.5 Phasor Measurement Unit 61.6 Power Quality Conditioners 81.7 Energy Storage Systems 81.8 Smart Distribution Systems 91.9 Electric Vehicle Charging Infrastructure 101.10 Cyber Security 111.11 Conclusion 11References 112 Modeling and Analysis of Smart Power System 15Madhu Palati, Sagar Singh Prathap, and Nagesh Halasahalli Nagaraju2.1 Introduction 152.2 Modeling of Equipment’s for Steady-State Analysis 162.2.1 Load Flow Analysis 162.2.1.1 Gauss Seidel Method 182.2.1.2 Newton Raphson Method 182.2.1.3 Decoupled Load Flow Method 182.2.2 Short Circuit Analysis 192.2.2.1 Symmetrical Faults 192.2.2.2 Unsymmetrical Faults 202.2.3 Harmonic Analysis 202.3 Modeling of Equipments for Dynamic and Stability Analysis 222.4 Dynamic Analysis 242.4.1 Frequency Control 242.4.2 Fault Ride Through 262.5 Voltage Stability 262.6 Case Studies 272.6.1 Case Study 1 272.6.2 Case Study 2 282.6.2.1 Existing and Proposed Generation Details in the Vicinity of Wind Farm 292.6.2.2 Power Evacuation Study for 50 MW Generation 302.6.2.3 Without Interconnection of the Proposed 50 MW Generation from Wind Farm on 66 kV Level of 220/66 kV Substation 312.6.2.4 Observations Made from Table 2.6 312.6.2.5 With the Interconnection of Proposed 50 MW Generation from Wind Farm on 66 kV level of 220/66 kV Substation 312.6.2.6 Normal Condition without Considering Contingency 322.6.2.7 Contingency Analysis 322.6.2.8 With the Interconnection of Proposed 60 MW Generation from Wind Farm on 66 kV Level of 220/66 kV Substation 332.7 Conclusion 34References 343 Multilevel Cascaded Boost Converter Fed Multilevel Inverter for Renewable Energy Applications 37Marimuthu Marikannu, Vijayalakshmi Subramanian, Paranthagan Balasubramanian, Jayakumar Narayanasamy, Nisha C. Rani, and Devi Vigneshwari Balasubramanian3.1 Introduction 373.2 Multilevel Cascaded Boost Converter 403.3 Modes of Operation of MCBC 423.3.1 Mode-1 Switch S A Is ON 423.3.2 Mode-2 Switch S A Is ON 423.3.3 Mode-3-Operation – Switch S A Is ON 423.3.4 Mode-4-Operation – Switch S A Is ON 423.3.5 Mode-5-Operation – Switch S A Is ON 423.3.6 Mode-6-Operation – Switch S A Is OFF 423.3.7 Mode-7-Operation – Switch S A Is OFF 423.3.8 Mode-8-Operation – Switch S A Is OFF 433.3.9 Mode-9-Operation – Switch S A Is OFF 443.3.10 Mode 10-Operation – Switch S A is OFF 453.4 Simulation and Hardware Results 453.5 Prominent Structures of Estimated DC–DC Converter with Prevailing Converter 493.5.1 Voltage Gain and Power Handling Capability 493.5.2 Voltage Stress 493.5.3 Switch Count and Geometric Structure 493.5.4 Current Stress 523.5.5 Duty Cycle Versus Voltage Gain 523.5.6 Number of Levels in the Planned Converter 523.6 Power Electronic Converters for Renewable Energy Sources (Applications of MLCB) 543.6.1 MCBC Connected with PV Panel 543.6.2 Output Response of PV Fed MCBC 543.6.3 H-Bridge Inverter 543.7 Modes of Operation 553.7.1 Mode 1 553.7.2 Mode 2 553.7.3 Mode 3 563.7.4 Mode 4 563.7.5 Mode 5 563.7.6 Mode 6 563.7.7 Mode 7 583.7.8 Mode 8 583.7.9 Mode 9 593.7.10 Mode 10 593.8 Simulation Results of MCBC Fed Inverter 603.9 Power Electronic Converter for E-Vehicles 613.10 Power Electronic Converter for HVDC/Facts 623.11 Conclusion 63References 634 Recent Advancements in Power Electronics for Modern Power Systems-Comprehensive Review on DC-Link Capacitors Concerning Power Density Maximization in Power Converters 65Naveenkumar Marati, Shariq Ahammed, Kathirvel Karuppazaghi, Balraj Vaithilingam, Gyan R. Biswal, Phaneendra B. Bobba, Sanjeevikumar Padmanaban, and Sharmeela Chenniappan4.1 Introduction 654.2 Applications of Power Electronic Converters 664.2.1 Power Electronic Converters in Electric Vehicle Ecosystem 664.2.2 Power Electronic Converters in Renewable Energy Resources 674.3 Classification of DC-Link Topologies 684.4 Briefing on DC-Link Topologies 694.4.1 Passive Capacitive DC Link 694.4.1.1 Filter Type Passive Capacitive DC Links 704.4.1.2 Filter Type Passive Capacitive DC Links with Control 724.4.1.3 Interleaved Type Passive Capacitive DC Links 744.4.2 Active Balancing in Capacitive DC Link 754.4.2.1 Separate Auxiliary Active Capacitive DC Links 764.4.2.2 Integrated Auxiliary Active Capacitive DC Links 784.5 Comparison on DC-Link Topologies 824.5.1 Comparison of Passive Capacitive DC Links 824.5.2 Comparison of Active Capacitive DC Links 834.5.3 Comparison of DC Link Based on Power Density, Efficiency, and Ripple Attenuation 864.6 Future and Research Gaps in DC-Link Topologies with Balancing Techniques 944.7 Conclusion 95References 955 Energy Storage Systems for Smart Power Systems 99Sivaraman Palanisamy, Logeshkumar Shanmugasundaram, and Sharmeela Chenniappan5.1 Introduction 995.2 Energy Storage System for Low Voltage Distribution System 1005.3 Energy Storage System Connected to Medium and High Voltage 1015.4 Energy Storage System for Renewable Power Plants 1045.4.1 Renewable Power Evacuation Curtailment 1065.5 Types of Energy Storage Systems 1095.5.1 Battery Energy Storage System 1095.5.2 Thermal Energy Storage System 1105.5.3 Mechanical Energy Storage System 1105.5.4 Pumped Hydro 1105.5.5 Hydrogen Storage 1105.6 Energy Storage Systems for Other Applications 1115.6.1 Shift in Energy Time 1115.6.2 Voltage Support 1115.6.3 Frequency Regulation (Primary, Secondary, and Tertiary) 1125.6.4 Congestion Management 1125.6.5 Black Start 1125.7 Conclusion 112References 1136 Real-Time Implementation and Performance Analysis of Supercapacitor for Energy Storage 115Thamatapu Eswararao, Sundaram Elango, Umashankar Subramanian, Krishnamohan Tatikonda, Garika Gantaiahswamy, and Sharmeela Chenniappan6.1 Introduction 1156.2 Structure of Supercapacitor 1176.2.1 Mathematical Modeling of Supercapacitor 1176.3 Bidirectional Buck–Boost Converter 1186.3.1 FPGA Controller 1196.4 Experimental Results 1206.5 Conclusion 123References 1257 Adaptive Fuzzy Logic Controller for MPPT Control in PMSG Wind Turbine Generator 129Rania Moutchou, Ahmed Abbou, Bouazza Jabri, Salah E. Rhaili, and Khalid Chigane7.1 Introduction 1297.2 Proposed MPPT Control Algorithm 1307.3 Wind Energy Conversion System 1317.3.1 Wind Turbine Characteristics 1317.3.2 Model of PMSG 1327.4 Fuzzy Logic Command for the MPPT of the PMSG 1337.4.1 Fuzzification 1347.4.2 Fuzzy Logic Rules 1347.4.3 Defuzzification 1347.5 Results and Discussions 1357.6 Conclusion 139References 1398 A Novel Nearest Neighbor Searching-Based Fault Distance Location Method for HVDC Transmission Lines 141Aleena Swetapadma, Shobha Agarwal, Satarupa Chakrabarti, and Soham Chakrabarti8.1 Introduction 1418.2 Nearest Neighbor Searching 1428.3 Proposed Method 1448.3.1 Power System Network Under Study 1448.3.2 Proposed Fault Location Method 1458.4 Results 1468.4.1 Performance Varying Nearest Neighbor 1478.4.2 Performance Varying Distance Matrices 1478.4.3 Near Boundary Faults 1488.4.4 Far Boundary Faults 1498.4.5 Performance During High Resistance Faults 1498.4.6 Single Pole to Ground Faults 1508.4.7 Performance During Double Pole to Ground Faults 1518.4.8 Performance During Pole to Pole Faults 1518.4.9 Error Analysis 1528.4.10 Comparison with Other Schemes 1538.4.11 Advantages of the Scheme 1548.5 Conclusion 154Acknowledgment 154References 1549 Comparative Analysis of Machine Learning Approaches in Enhancing Power System Stability 157Md. I. H. Pathan, Mohammad S. Shahriar, Mohammad M. Rahman, Md. Sanwar Hossain, Nadia Awatif, and Md. Shafiullah9.1 Introduction 1579.2 Power System Models 1599.2.1 PSS Integrated Single Machine Infinite Bus Power Network 1599.2.2 PSS-UPFC Integrated Single Machine Infinite Bus Power Network 1609.3 Methods 1619.3.1 Group Method Data Handling Model 1619.3.2 Extreme Learning Machine Model 1629.3.3 Neurogenetic Model 1629.3.4 Multigene Genetic Programming Model 1639.4 Data Preparation and Model Development 1659.4.1 Data Production and Processing 1659.4.2 Machine Learning Model Development 1659.5 Results and Discussions 1669.5.1 Eigenvalues and Minimum Damping Ratio Comparison 1669.5.2 Time-Domain Simulation Results Comparison 1709.5.2.1 Rotor Angle Variation Under Disturbance 1709.5.2.2 Rotor Angular Frequency Variation Under Disturbance 1719.5.2.3 DC-Link Voltage Variation Under Disturbance 1739.6 Conclusions 173References 17410 Augmentation of PV-Wind Hybrid Technology with Adroit Neural Network, ANFIS, and PI Controllers Indeed Precocious DVR System 179Jyoti Shukla, Basanta K. Panigrahi, and Monika Vardia10.1 Introduction 17910.2 PV-Wind Hybrid Power Generation Configuration 18010.3 Proposed Systems Topologies 18110.3.1 Structure of PV System 18110.3.2 The MPPTs Technique 18310.3.3 NN Predictive Controller Technique 18310.3.4 ANFIS Technique 18410.3.5 Training Data 18610.4 Wind Power Generation Plant 18710.5 Pitch Angle Control Techniques 18910.5.1 PI Controller 18910.5.2 NARMA-L2 Controller 19010.5.3 Fuzzy Logic Controller Technique 19210.6 Proposed DVRs Topology 19210.7 Proposed Controlling Technique of DVR 19310.7.1 ANFIS and PI Controlling Technique 19310.8 Results of the Proposed Topologies 19610.8.1 PV System Outputs (MPPT Techniques Results) 19610.8.2 Main PV System outputs 19610.8.3 Wind Turbine System Outputs (Pitch Angle Control Technique Result) 19810.8.4 Proposed PMSG Wind Turbine System Output 19910.8.5 Performance of DVR (Controlling Technique Results) 20310.8.6 DVRs Performance 20310.9 Conclusion 204References 20411 Deep Reinforcement Learning and Energy Price Prediction 207Deepak Yadav, Saad Mekhilef, Brijesh Singh, and Muhyaddin RawaAbbreviations 20711.1 Introduction 20811.2 Deep and Reinforcement Learning for Decision-Making Problems in Smart Power Systems 21011.2.1 Reinforcement Learning 21011.2.1.1 Markov Decision Process (MDP) 21011.2.1.2 Value Function and Optimal Policy 21111.2.2 Reinforcement Learnings to Deep Reinforcement Learnings 21211.2.3 Deep Reinforcement Learning Algorithms 21211.3 Applications in Power Systems 21311.3.1 Energy Management 21311.3.2 Power Systems’ Demand Response (DR) 21511.3.3 Electricity Market 21611.3.4 Operations and Controls 21711.4 Mathematical Formulation of Objective Function 21811.4.1 Locational Marginal Prices (LMPs) Representation 21911.4.2 Relative Strength Index (RSI) 21911.4.2.1 Autoregressive Integrated Moving Average (ARIMA) 21911.5 Interior-point Technique & KKT Condition 22011.5.1 Explanation of Karush–Kuhn–Tucker Conditions 22011.5.2 Algorithm for Finding a Solution 22111.6 Test Results and Discussion 22111.6.1 Illustrative Example 22111.7 Comparative Analysis with Other Methods 22311.8 Conclusion 22411.9 Assignment 224Acknowledgment 225References 22512 Power Quality Conditioners in Smart Power System 233Zahira Rahiman, Lakshmi Dhandapani, Ravi Chengalvarayan Natarajan, Pramila Vallikannan, Sivaraman Palanisamy, and Sharmeela Chenniappan12.1 Introduction 23312.1.1 Voltage Sag 23412.1.2 Voltage Swell 23412.1.3 Interruption 23412.1.4 Under Voltage 23412.1.5 Overvoltage 23412.1.6 Voltage Fluctuations 23412.1.7 Transients 23512.1.8 Impulsive Transients 23512.1.9 Oscillatory Transients 23512.1.10 Harmonics 23512.2 Power Quality Conditioners 23512.2.1 STATCOM 23512.2.2 Svc 23512.2.3 Harmonic Filters 23612.2.3.1 Active Filter 23612.2.4 UPS Systems 23612.2.5 Dynamic Voltage Restorer (DVR) 23612.2.6 Enhancement of Voltage Sag 23612.2.7 Interruption Mitigation 23712.2.8 Mitigation of Harmonics 24112.3 Standards of Power Quality 24412.4 Solution for Power Quality Issues 24412.5 Sustainable Energy Solutions 24512.6 Need for Smart Grid 24512.7 What Is a Smart Grid? 24512.8 Smart Grid: The “Energy Internet” 24512.9 Standardization 24612.10 Smart Grid Network 24712.10.1 Distributed Energy Resources (DERs) 24712.10.2 Optimization Techniques in Power Quality Management 24712.10.3 Conventional Algorithm 24812.10.4 Intelligent Algorithm 24812.10.4.1 Firefly Algorithm (FA) 24812.10.4.2 Spider Monkey Optimization (SMO) 25012.11 Simulation Results and Discussion 25412.12 Conclusion 257References 25713 The Role of Internet of Things in Smart Homes 259Sanjeevikumar Padmanaban, Mostafa Azimi Nasab, Mohammad Ebrahim Shiri, Hamid Haj Seyyed Javadi, Morteza Azimi Nasab, Mohammad Zand, and Tina Samavat13.1 Introduction 25913.2 Internet of Things Technology 26013.2.1 Smart House 26113.3 Different Parts of Smart Home 26213.4 Proposed Architecture 26413.5 Controller Components 26513.6 Proposed Architectural Layers 26613.6.1 Infrastructure Layer 26613.6.1.1 Information Technology 26613.6.1.2 Information and Communication Technology 26613.6.1.3 Electronics 26613.6.2 Collecting Data 26713.6.3 Data Management and Processing 26713.6.3.1 Service Quality Management 26713.6.3.2 Resource Management 26713.6.3.3 Device Management 26713.6.3.4 Security 26713.7 Services 26713.8 Applications 26813.9 Conclusion 269References 26914 Electric Vehicles and IoT in Smart Cities 273Sanjeevikumar Padmanaban, Tina Samavat, Mostafa Azimi Nasab, Morteza Azimi Nasab, Mohammad Zand, and Fatemeh Nikokar14.1 Introduction 27314.2 Smart City 27514.2.1 Internet of Things and Smart City 27514.3 The Concept of Smart Electric Networks 27514.4 IoT Outlook 27614.4.1 IoT Three-layer Architecture 27614.4.2 View Layer 27614.4.3 Network Layer 27714.4.4 Application Layer 27814.5 Intelligent Transportation and Transportation 27814.6 Information Management 27814.6.1 Artificial Intelligence 27814.6.2 Machine Learning 27914.6.3 Artificial Neural Network 27914.6.4 Deep Learning 28014.7 Electric Vehicles 28114.7.1 Definition of Vehicle-to-Network System 28114.7.2 Electric Cars and the Electricity Market 28114.7.3 The Role of Electric Vehicles in the Network 28214.7.4 V2G Applications in Power System 28214.7.5 Provide Baseload Power 28314.7.6 Courier Supply 28314.7.7 Extra Service 28314.7.8 Power Adjustment 28314.7.9 Rotating Reservation 28414.7.10 The Connection between the Electric Vehicle and the Power Grid 28414.8 Proposed Model of Electric Vehicle 28414.9 Prediction Using LSTM Time Series 28514.9.1 LSTM Time Series 28614.9.2 Predicting the Behavior of Electric Vehicles Using the LSTM Method 28714.10 Conclusion 287Exercise 288References 28815 Modeling and Simulation of Smart Power Systems Using HIL 291Gunapriya Devarajan, Puspalatha Naveen Kumar, Muniraj Chinnusamy, Sabareeshwaran Kanagaraj, and Sharmeela Chenniappan15.1 Introduction 29115.1.1 Classification of Hardware in the Loop 29115.1.1.1 Signal HIL Model 29115.1.1.2 Power HIL Model 29215.1.1.3 Reduced-Scaled HIL Model 29215.1.2 Points to Be Considered While Performing HIL Simulation 29315.1.3 Applications of HIL 29315.2 Why HIL Is Important? 29315.2.1 Hardware-In-The-Loop Simulation 29415.2.2 Simulation Verification and Validation 29515.2.3 Simulation Computer Hardware 29515.2.4 Benefits of Using Hardware-In-The-Loop Simulation 29615.3 HIL for Renewable Energy Systems (RES) 29615.3.1 Introduction 29615.3.2 Hardware in the Loop 29715.3.2.1 Electrical Hardware in the Loop 29715.3.2.2 Mechanical Hardware in the Loop 29715.4 HIL for HVDC and FACTS 29915.4.1 Introduction 29915.4.2 Modular Multi Level Converter 30015.5 HIL for Electric Vehicles 30115.5.1 Introduction 30115.5.2 EV Simulation Using MATLAB, Simulink 30215.5.2.1 Model-Based System Engineering (MBSE) 30215.5.2.2 Model Batteries and Develop BMS 30215.5.2.3 Model Fuel Cell Systems (FCS) and Develop Fuel Cell Control Systems (FCCS) 30315.5.2.4 Model Inverters, Traction Motors, and Develop Motor Control Software 30415.5.2.5 Deploy, Integrate, and Test Control Algorithms 30415.5.2.6 Data-Driven Workflows and AI in EV Development 30515.6 HIL for Other Applications 30615.6.1 Electrical Motor Faults 30615.7 Conclusion 307References 30816 Distribution Phasor Measurement Units (PMUs) in Smart Power Systems 311Geethanjali Muthiah, Meenakshi Devi Manivannan, Hemavathi Ramadoss, and Sharmeela Chenniappan16.1 Introduction 31116.2 ComparisonofPMUsandSCADA 31216.3 Basic Structure of Phasor Measurement Units 31316.4 PMU Deployment in Distribution Networks 31416.5 PMU Placement Algorithms 31516.6 Need/Significance of PMUs in Distribution System 31516.6.1 Significance of PMUs – Concerning Power System Stability 31616.6.2 Significance of PMUs in Terms of Expenditure 31616.6.3 Significance of PMUs in Wide Area Monitoring Applications 31616.7 Applications of PMUs in Distribution Systems 31716.7.1 System Reconfiguration Automation to Manage Power Restoration 31716.7.1.1 Case Study 31716.7.2 Planning for High DER Interconnection (Penetration) 31916.7.2.1 Case Study 31916.7.3 Voltage Fluctuations and Voltage Ride-Through Related to DER 32016.7.4 Operation of Islanded Distribution Systems 32016.7.5 Fault-Induced Delayed Voltage Recovery (FIDVR) Detection 32216.8 Conclusion 322References 32317 Blockchain Technologies for Smart Power Systems 327A. Gayathri, S. Saravanan, P. Pandiyan, and V. Rukkumani17.1 Introduction 32717.2 Fundamentals of Blockchain Technologies 32817.2.1 Terminology 32817.2.2 Process of Operation 32917.2.2.1 Proof of Work (PoW) 32917.2.2.2 Proof of Stake (PoS) 32917.2.2.3 Proof of Authority (PoA) 33017.2.2.4 Practical Byzantine Fault Tolerance (PBFT) 33017.2.3 Unique Features of Blockchain 33017.2.4 Energy with Blockchain Projects 33017.2.4.1 Bitcoin Cryptocurrency 33117.2.4.2 Dubai: Blockchain Strategy 33117.2.4.3 Humanitarian Aid Utilization of Blockchain 33117.3 Blockchain Technologies for Smart Power Systems 33117.3.1 Blockchain as a Cyber Layer 33117.3.2 Agent/Aggregator Based Microgrid Architecture 33217.3.3 Limitations and Drawbacks 33217.3.4 Peer to Peer Energy Trading 33317.3.5 Blockchain for Transactive Energy 33517.4 Blockchain for Smart Contracts 33617.4.1 The Platform for Smart Contracts 33717.4.2 The Architecture of Smart Contracting for Energy Applications 33817.4.3 Smart Contract Applications 33917.5 Digitize and Decentralization Using Blockchain 34017.6 Challenges in Implementing Blockchain Techniques 34017.6.1 Network Management 34117.6.2 Data Management 34117.6.3 Consensus Management 34117.6.4 Identity Management 34117.6.5 Automation Management 34217.6.6 Lack of Suitable Implementation Platforms 34217.7 Solutions and Future Scope 34217.8 Application of Blockchain for Flexible Services 34317.9 Conclusion 343References 34418 Power and Energy Management in Smart Power Systems 349Subrat Sahoo18.1 Introduction 34918.1.1 Geopolitical Situation 34918.1.2 Covid-19 Impacts 35018.1.3 Climate Challenges 35018.2 Definition and Constituents of Smart Power Systems 35118.2.1 Applicable Industries 35218.2.2 Evolution of Power Electronics-Based Solutions 35318.2.3 Operation of the Power System 35518.3 Challenges Faced by Utilities and Their Way Towards Becoming Smart 35618.3.1 Digitalization of Power Industry 35918.3.2 Storage Possibilities and Integration into Grid 36018.3.3 Addressing Power Quality Concerns and Their Mitigation 36218.3.4 A Path Forward Towards Holistic Condition Monitoring 36318.4 Ways towards Smart Transition of the Energy Sector 36618.4.1 Creating an All-Inclusive Ecosystem 36618.4.1.1 Example of Sensor-Based Ecosystem 36718.4.1.2 Utilizing the Sensor Data for Effective Analytics 36818.4.2 Modular Energy System Architecture 37018.5 Conclusion 371References 373Index 377