Cyberphysical Smart Cities Infrastructures: Optimal Operation and Intelligent Decision Making

Description

Learn to deploy novel algorithms to improve and secure smart city infrastructure In Cyberphysical Smart Cities Infrastructures: Optimal Operation and Intelligent Decision Making, accomplished researchers Drs. M. Hadi Amini and Miadreza Shafie-Khah deliver a crucial exploration of new directions in the science and engineering of deploying novel and efficient computing algorithms to enhance the efficient operation of the networks and communication systems underlying smart city infrastructure. The book covers special issues on the deployment of these algorithms with an eye to helping readers improve the operation of smart cities. The editors present concise and accessible material from a collection of internationally renowned authors in areas as diverse as computer science, electrical engineering, operation research, civil engineering, and the social sciences. They also include discussions of the use of artificial intelligence to secure the operations of cyberphysical smart city infrastructure and provide several examples of the applications of novel theoretical algorithms. Readers will also enjoy: Thorough introductions to fundamental algorithms for computing and learning, large-scale optimizations, control theory for large-scale systems Explorations of machine learning and intelligent decision making in cyberphysical smart cities, including smart energy systems and intelligent transportation networks In-depth treatments of intelligent decision making in cyberphysical smart city infrastructure and optimization in networked smart cities Perfect for senior undergraduate and graduate students of electrical and computer engineering, computer science, civil engineering, telecommunications, information technology, and business, Cyberphysical Smart Cities Infrastructures is an indispensable reference for anyone seeking to solve real-world problems in smart cities. Cover Title Page Copyright Contents Biography List of Contributors Chapter 1 Artificial Intelligence and Cybersecurity: Tale of Healthcare Applications 1.1 Introduction 1.2 A Brief History of AI 1.3 AI in Healthcare 1.4 Morality and Ethical Association of AI in Healthcare 1.5 Cybersecurity, AI, and Healthcare 1.6 Future of AI and Healthcare 1.7 Conclusion References Chapter 2 Data Analytics for Smart Cities: Challenges and Promises 2.1 Introduction 2.2 Role of Machine Learning in Smart Cities 2.3 Smart Cities Data Analytics Framework 2.3.1 Data Capturing 2.3.2 Data Analysis 2.3.2.1 Big Data Algorithms and Challenges 2.3.2.2 Machine Learning Process and Challenges 2.3.2.3 Deep Learning Process and Challenges 2.3.2.4 Learning Process and Emerging New Type of Data Problems 2.3.3 Decision‐Making Problems in Smart Cities 2.3.3.1 Traffic Decision‐Making System 2.3.3.2 Safe and Smart Environment 2.4 Conclusion References Chapter 3 Embodied AI‐Driven Operation of Smart Cities: A Concise Review 3.1 Introduction 3.2 Rise of the Embodied AI 3.3 Breakdown of Embodied AI 3.3.1 Language Grounding 3.3.2 Language Plus Vision 3.3.3 Embodied Visual Recognition 3.3.4 Embodied Question Answering 3.3.5 Interactive Question Answering 3.3.6 Multi‐agent Systems 3.4 Simulators 3.4.1 MINOS 3.4.2 Habitat 3.5 Future of Embodied AI 3.5.1 Higher Intelligence 3.5.2 Evolution 3.6 Conclusion References Chapter 4 Analysis of Different Regression Techniques for Battery Capacity Prediction 4.1 Introduction 4.2 Data Preparation 4.2.1 Dataset 4.2.2 Feature Extraction 4.2.3 Noise Addition 4.3 Experiment Design and Machine Learning Algorithms 4.4 Result and Analysis 4.5 Threats to Validity 4.6 Conclusions References Chapter 5 Smart Charging and Operation of Electric Fleet Vehicles in a Smart City 5.1 Smart Charging in Transportation 5.1.1 Available EV Charging Technologies 5.1.1.1 Inductive Charging 5.1.1.2 Battery Swapping 5.1.1.3 Automatic Robotic Charging Connector 5.1.1.4 Automatic Ground‐Based Docking Connector 5.1.2 Current Regulations on Smart Charging 5.2 Cyber‐Physical Aspects of EV Networks 5.2.1 Sensing and Cooperative Data Collection 5.2.2 Data‐Driven Control and Optimization 5.3 Charging of Electric Fleet Vehicles in Smart Cities 5.3.1 Intelligent Management of Fleets of Electric Vehicles 5.3.1.1 Charging of EV Fleets 5.3.1.2 Route Mapping with Charging 5.3.2 Electricity Grid Support Services 5.3.2.1 Demand Response 5.3.2.2 Frequency Response 5.3.2.3 Emergency Power 5.3.2.4 Emergency Response 5.4 Data and Cyber Security of EV Networks 5.4.1 Attack Schemes 5.4.1.1 Data Injection 5.4.1.2 Distributed Denial of Service 5.4.1.3 Data and Identity Theft 5.4.1.4 Man‐in‐the‐Middle Attack 5.4.2 Attack Detection Methods 5.4.2.1 Abnormal State Estimation 5.4.2.2 Message Encryption and Authentication 5.4.2.3 Denial‐of‐Service Attacks 5.4.3 Privacy Concerns and Privacy‐Preserving Methods 5.5 EV Smart Charging Strategies 5.5.1 Optimization Approaches 5.5.1.1 Future Scheduling 5.5.1.2 Battery Health Optimization 5.5.1.3 Energy Loss Minimization 5.5.2 Artificial Intelligence Approaches 5.5.2.1 Deep Learning for Smart Charging 5.5.2.2 Predicting Charging Profiles 5.5.3 Coordinated Charging 5.5.3.1 Centralized Optimization 5.5.3.2 Distributed Optimization 5.5.4 Population‐Based Approaches 5.5.4.1 Case Study 5.6 Conclusion Acknowledgments References Chapter 6 Risk‐Aware Cyber‐Physical Control for Resilient Smart Cities 6.1 Introduction 6.2 System Model 6.2.1 Communication Latency in Smart Grid Systems 6.2.2 Risk Model for Communication Links 6.2.3 History of Communication Links 6.3 Risk‐Aware Quality of Service Routing Using SDN 6.3.1 Constrained Shortest Path Routing Problem Formulation 6.3.2 SDN Architecture and Implementation 6.3.3 Risk‐Aware Routing Algorithm 6.4 Risk‐Aware Adaptive Control 6.4.1 Smart Grid Model 6.4.2 Parametric Feedback Linearization Control 6.4.3 Risk‐Aware Routing and Latency‐Adaptive Control Scheme 6.5 Simulation Environment and Numerical Analysis 6.5.1 Avoiding Vulnerable Communication Links While Meeting QoS Constraint 6.5.2 Algorithm Overhead Comparison 6.5.3 Impact of QoS Constraints 6.5.4 Impact on Distributed Control 6.6 Conclusions References Chapter 7 Wind Speed Prediction Using a Robust Possibilistic C‐Regression Model Method: A Case Study of Tunisia 7.1 Introduction 7.2 Data Collection and Method 7.2.1 Data Description 7.2.2 Robust Possibilistic C‐Regression Models 7.2.3 Wind Speed Data Analysis Procedure 7.3 Experiment and Discussion 7.4 Conclusion References Chapter 8 Intelligent Traffic: Formulating an Applied Research Methodology for Computer Vision and Vehicle Detection 8.1 Introduction 8.1.1 Introduction 8.1.2 Background 8.1.3 Problem Statement 8.1.3.1 Purpose of Research 8.1.3.2 Research Questions 8.1.3.3 Study Aim and Objectives 8.1.3.4 Significance and Structure of the Research 8.2 Literature Review 8.2.1 Introduction 8.2.2 Machine Learning, Deep Learning, and Computer Vision 8.2.2.1 Machine Learning 8.2.2.2 Deep Learning 8.2.2.3 Computer Vision 8.2.3 Object Recognition, Object Detection, and Object Tracking 8.2.3.1 Object Recognition 8.2.3.2 Object Detection 8.2.3.3 Object Tracking 8.2.4 Edge Computing, Fog Computing, and Cloud Computing 8.2.4.1 Edge Computing 8.2.4.2 Fog Computing 8.2.4.3 Cloud Computing 8.2.5 Benefits of Computer Vision‐Driven Traffic Management 8.2.6 Challenges of Computer Vision‐Driven Traffic Management 8.2.6.1 Big Data Issues 8.2.6.2 Privacy Issues 8.2.6.3 Technical Barriers 8.3 Research Methodology 8.3.1 Research Questions and Objectives 8.3.2 Study Design 8.3.2.1 Selection Rationale 8.3.2.2 Potential Challenges 8.3.3 Adapted Study Design Research Approach 8.3.4 Selected Hardware and Software 8.3.4.1 Hardware: The NVIDIA Jetson Nano Developer Kit and Accompanying Items 8.3.5 Hardware Proposed 8.3.5.1 Software Stack: NVIDIA Jetpack SDK and Accompanying Requirements (All Iterations) 8.3.6 Software Proposed 8.4 Conclusion References Chapter 9 Implementation and Evaluation of Computer Vision Prototype for Vehicle Detection 9.1 Prototype Setup 9.1.1 Introduction 9.1.2 Environment Setup 9.2 Testing 9.2.1 Design and Development: The Default Model and the First Iteration 9.2.2 Testing (Multiple Images) 9.2.3 Analysis (Multiple Images) 9.2.4 Testing (MP4 File) 9.2.5 Testing (Livestream Camera) 9.3 Iteration 2: Transfer Learning Model 9.3.1 Design and Development 9.3.2 Test (Multiple Images) 9.3.3 Analysis (Multiple Images) 9.3.4 Test (MP4 File) 9.3.5 Analysis (MP4 File) 9.3.6 Test (Livestream Camera) 9.3.7 Analysis (Livestream Camera) 9.3.8 Redesign 9.4 Iteration 3: Increased Sample Size and Change of Accuracy Analysis (Images) 9.4.1 Design and Development 9.4.2 Testing 9.4.3 Analysis 9.4.3.1 Confusion Matrices 9.4.3.2 Precision, Recall, and F‐score 9.5 Findings and Discussion 9.5.1 Findings: Vehicle Detection Across Multiple Images 9.5.2 Findings: Vehicle Detection Performance on an MP4 File 9.5.3 Findings: Vehicle Detection on Livestream Camera 9.5.4 Findings: Iteration 3 9.5.5 Addressing the Research Questions 9.5.6 Assessment of Suitability 9.5.7 Future Improvements 9.6 Conclusion References Chapter 10 A Review on Applications of the Standard Series IEC 61850 in Smart Grid Applications 10.1 Introduction 10.2 Overview of IEC 61850 Standards 10.3 IEC 61850 Protocols and Substandards 10.3.1 IEC 61850 Standards and Classifications 10.3.2 Basics of IEC 61850 Architecture Model 10.3.3 IEC 61850 Class Model 10.3.4 IEC 61850 Logical Interfaces (Functional Hierarchy of IEC 61850) 10.4 IEC 61850 Features 10.4.1 MMS 10.4.2 GOOSE 10.4.3 Sampled Measured Value (SMV) or SV 10.4.4 R‐GOOSE and R‐SV 10.4.4.1 Application in Transmission Systems 10.4.4.2 Application in Distribution Systems 10.4.5 Web Services 10.5 Relevant Application 10.5.1 Substation Automation System (SAS) 10.5.2 Energy Management System (EMS) 10.5.3 Distribution Management System (DMS) 10.5.3.1 Feeder Balancing and Loss Minimization Distribution 10.5.3.2 Voltage/VAR Optimization (VVO) and Conservation Voltage Reduction 10.5.3.3 Fault Location, Isolation, and Service Restoration 10.5.4 Distribution Automation (DA) 10.5.4.1 Voltage/VAR Control 10.5.4.2 Fault Detection and Isolation 10.5.4.3 Service Restoration Use Case 10.5.5 Distributed Generation and Demand Response Management (Distributed Energy Resource [DER]) 10.5.5.1 Storage 10.5.5.2 Solar Panels 10.5.5.3 Wind Farm 10.5.5.4 Virtual Power Plant (VPP) 10.5.6 Advanced Metering Infrastructure (AMI) 10.5.7 Electric Vehicle (EV) 10.6 Advantages of IEC 61850 (Requirements of Smart Grid IEC 61850) 10.6.1 Communications Bandwidth 10.6.2 Interoperability 10.6.3 Cybersecurity 10.6.4 Information Security and Privacy 10.6.5 Security Aspects of IEC 61850 in Smart Grid Applications 10.6.5.1 How Security Can Be Breached 10.6.5.2 Effects on the Security 10.6.5.3 Efforts to Address the Security Issues 10.6.6 Reliability of Technology 10.7 Conclusion and Perspective Acknowledgments References Chapter 11 Electric Vehicles in Smart Cities 11.1 Introduction 11.2 Autonomous Vehicle 11.2.1 Classification of Vehicle Automation 11.2.2 Advantages of CAEVs 11.3 IoT Technology and CAEV 11.4 CAEV Applications and Services 11.4.1 CAEV Charging Management System 11.4.2 CAEV Taxi Service 11.5 Cybersecurity Issues of Internet of EVs 11.5.1 UPCEV Architecture 11.5.2 IoV Communication Technologies 11.5.3 IoEV Vulnerabilities 11.5.3.1 V2S Attacks 11.5.3.2 V2V Attacks 11.5.3.3 V2I Attack 11.5.3.4 V2N Attacks 11.6 IoT‐Based EV State Estimation and Control Under Cyberattacks 11.6.1 State Estimation Problem 11.6.2 Vehicle State Space and IoT Sensing Systems 11.6.3 State Estimation Under Cyberattack 11.7 Effect of EV Charging Behavior on Power System 11.7.1 Behavior of Electric Vehicle Parking Lots as Demand Response Aggregation Agents 11.7.2 Parking Lots in Demand Response Programs 11.7.3 Application of IoT in Demand Response Programs Based on Parking Lots 11.8 Charging Scheme for EVs Using IoT 11.8.1 System Model and IoT Architecture References Author Index EULA