IoT Enabled Multi-Energy Systems: From Isolated Energy Grids to Modern Interconnected Networks

Front Cover
IoT Enabled Multi-Energy Systems
Copyright Page
Contents
List of contributors
Preface
1 Overview of Internet of Things-based multi-energy management of cleaner multi-energy mix
	Chapter Outline
	1.1 Introduction
	1.2 Applications of Internet of Things
	1.3 Characteristics of Internet of Things
	1.4 Opportunities of Internet of Things
	1.5 Challenges of Internet of Things
	1.6 Summary
	References
2 Overview of multi-energy interconnected systems in different energy grids
	Chapter Outline
	Abbreviations
	2.1 Introduction
	2.2 Modern interconnected energy networks
		2.2.1 Independent multi-energy system
		2.2.2 Interconnected multi-energy systems
	2.3 Internet of Things technologies for transactive energy systems
	2.4 Control methods of interconnected energy networks
		2.4.1 Centralized approach
		2.4.2 Decentralized approach
		2.4.3 Distributed approach
	2.5 Modeling methods of interconnected multi-energy systems: a survey on state-of-the-art
		2.5.1 Deterministic approach
		2.5.2 Nondeterministic approach
			2.5.2.1 Scenarios-based approach
			2.5.2.2 Robust optimization
			2.5.2.3 Information gap decision theory
			2.5.2.4 Chance constraints
			2.5.2.5 Fuzzy method
			2.5.2.6 Z-number
			2.5.2.7 Interval analysis
	2.6 Advantages and challenges of interconnected multi-energy systems
		2.6.1 Advantages
			2.6.1.1 Economic efficiency
			2.6.1.2 Emission abatement
			2.6.1.3 Resiliency improvement
			2.6.1.4 Reliability enhancement
			2.6.1.5 Flexibility improvement
		2.6.2 Challenges
			2.6.2.1 Economic risk
			2.6.2.2 Social challenges
			2.6.2.3 Technological challenges
	2.7 Conclusion
	References
3 Overview of Internet of Things-based fault positioning cyber-physical systems in smart cleaner multi-energy systems
	Chapter Outline
	3.1 Introduction
	3.2 Structure of Internet of Things-based fault monitoring cyber-physical system for clean multi-energy mixes
		3.2.1 Perception (sensor) layer
		3.2.2 Network layer
		3.2.3 Application layer
	3.3 Advantages and opportunities of Internet of Things-based fault monitoring system
		3.3.1 Location awareness
		3.3.2 Low latency
		3.3.3 Machine-to-machine communication
		3.3.4 Self-healing networks
		3.3.5 Burgeoning renewable energy units’ integration
	3.4 Challenges of Internet of Things-based fault monitoring system
		3.4.1 Device attack
		3.4.2 Data attack
		3.4.3 Network attack
	3.5 Applicability of Internet of Things technology with conventional methods
	3.6 The future development path for Internet of Things-based fault detection systems for clean multi-energy mixes
	3.7 Summary
	References
4 Architecture and applications of Internet of Things in smart grids
	Chapter Outline
	4.1 Introduction
	4.2 Internet of Things in smart grid
	4.3 Internet of Things in generation level
		4.3.1 Internet of Things and wind energy
		4.3.2 Internet of Things and solar energy
		4.3.3 Internet of Things and thermal generation
	4.4 Internet of Things in transmission level
	4.5 Internet of Things in distribution level
		4.5.1 Internet of Things in microgrids
		4.5.2 Internet of Things in smart cities and homes
	4.6 Internet of Things in transportation networks
	4.7 Summary
	References
5 Artificial intelligence–enabled Internet of Things technologies in modern energy grids
	Chapter Outline
	5.1 Introduction
		5.1.1 Internet of Things basics in smart grids
		5.1.2 The relationships between Internet of Things and intelligent grids
		5.1.3 Internet of Things in power systems
		5.1.4 Smart grid roles and drawbacks in power systems
	5.2 Communication infrastructure
		5.2.1 Smart grid internet infrastructure
		5.2.2 Power electronic components
			5.2.2.1 Volt-VAR control
			5.2.2.2 Ramp-rate control
			5.2.2.3 Frequency and voltage
		5.2.3 Communication challenge and cyber-security
			5.2.3.1 Communication role in smart grid
			5.2.3.2 Cyber-security role in smart grid
		5.2.4 Internet of Things components
			5.2.4.1 Advanced sensing and intelligent measurement system
			5.2.4.2 Mechanized monitoring and control
			5.2.4.3 Renewable resources consuming prediction
			5.2.4.4 Information and communication technology
			5.2.4.5 Power distribution industrialization
	5.3 Key features in energy internet
		5.3.1 Internet of Energy
		5.3.2 Modern methods for computation
	5.4 Internet of Things challenges in energy systems
		5.4.1 Internet of Things attacks
	5.5 Future research potentials
		5.5.1 Blockchain for Internet of Things
		5.5.2 Green Internet of Things
	5.6 Conclusion
	References
6 Data science leverage and big data analysis for Internet of Things energy systems
	Chapter Outline
	6.1 Introduction
	6.2 Data science
		6.2.1 Understanding data science modeling in smart grids
		6.2.2 Steps of data science modeling in smart grid
		6.2.3 Advanced data analytics and smart computing in smart grids
		6.2.4 Supervised and unsupervised learning in smart grids
			6.2.4.1 Classification
			6.2.4.2 Regression
			6.2.4.3 Clustering
			6.2.4.4 Association rules learning
			6.2.4.5 Prediction and analytics for time-series data
			6.2.4.6 Behavioral data analysis
			6.2.4.7 Anomaly detection
			6.2.4.8 Factor analysis
			6.2.4.9 Logs analytics
			6.2.4.10 Deep learning and artificial neural networks
	6.3 Big data
		6.3.1 Big data in smart grid literature
		6.3.2 Big data architecture in smart grids
		6.3.3 Big data technologies in smart grids
		6.3.4 Big data tools in smart grids
			6.3.4.1 Apache Drill
			6.3.4.2 Hadoop
			6.3.4.3 Game Theory
			6.3.4.4 Data centers
		6.3.5 Big data applications in smart grids
	6.4 Future research potentials
		6.4.1 Security and privacy
		6.4.2 Internet of Things big data challenges
		6.4.3 Deep learning implementation challenges and limitations
		6.4.4 Smart grid data–driven planning, cost management, and quality of service
	6.5 Conclusion
	References
7 Battery cloud with advanced algorithms
	Chapter Outline
	7.1 Introduction
	7.2 Battery in the cloud
		7.2.1 Data sources and connections
		7.2.2 Database
		7.2.3 Data visualization
		7.2.4 Algorithms and analytics
	7.3 Onboard state of charge estimation with cloud-trained ANNs
		7.3.1 Requirements, definition, and design
		7.3.2 Artificial neural network training with cloud data
		7.3.3 Hardware-in-the-loop and vehicle testing results
	7.4 Online state-of-health estimation
		7.4.1 Degradation mechanisms and modes of Li-ion batteries
			7.4.1.1 Anode
			7.4.1.2 Cathode
			7.4.1.3 Separator, electrolyte, and current collectors
		7.4.2 State of health and end of life
		7.4.3 Advanced online state-of-health estimation methods
			7.4.3.1 Methods
			7.4.3.2 Differential voltage analysis/ICA-based state-of-health estimation method
	7.5 Cloud-based thermal runaway prediction
		7.5.1 Cause and effects of thermal runaway
		7.5.2 Methods for thermal runaway detection
		7.5.3 Data-driven thermal anomaly detection
			7.5.3.1 Workflow
			7.5.3.2 Case study
	7.6 Conclusion
	References
8 Applicability of federated learning for securing critical energy infrastructures
	Chapter Outline
	8.1 Introduction
	8.2 Review of cyberattacks in smart grids
		8.2.1 Major cyberattacks in power systems and smart grids
		8.2.2 Suitability of Internet of Things-based technologies in modern grids
	8.3 Federated learning and challenges
		8.3.1 Federated learning
		8.3.2 Challenges of federated learning
			8.3.2.1 Statistical heterogeneity
			8.3.2.2 System heterogeneity
		8.3.3 Survey of threats, attacks, and defense strategies
	8.4 Simulated system model
		8.4.1 System architecture
		8.4.2 HAI dataset
	8.5 Simulation results
		8.5.1 Model fitness evolution
		8.5.2 Confusion matrix
	8.6 Insights on federated learning security countermeasures
	8.7 Conclusion
	References
9 A lightweight string-matching technique for secure communication within IoT energy systems technology
	Chapter Outline
	9.1 Introduction
	9.2 Background
		9.2.1 Knuth–Morris–Pratt algorithm
		9.2.2 Aho–Corasick algorithm
		9.2.3 Data loss prevention in cloud service
	9.3 Literature review
	9.4 Proposed architecture and design
	9.5 Result, discussion, and findings
		9.5.1 Performance test result
		9.5.2 Comparative analysis of Aho–Corasick versus Knuth–Morris–Pratt
	9.6 Conclusion
	Acknowledgments
	References
Index
Back Cover