Sustainable Energy Solutions with Artificial Intelligence, Blockchain Technology, and Internet of Things

Cover
Half Title
Series Page
Title Page
Copyright Page
Contents
Preface
Acknowledgments
Editors' Biography
Contributors
Chapter 1: Recent Developments of Artificial Intelligence for Renewable Energy: Accelerated Material and Process Design
	1.1 Introduction
	1.2 Role of AI in Renewable Energy
	1.3 Advancements of AI towards Sustainable Energy
		1.3.1 Improved Machine Learning Models
		1.3.2 DL Models
		1.3.3 Optimization Techniques
	1.4 Digital Transformation of Renewable Energy Industry
		1.4.1 Hydrogen Production from Biomass
			1.4.1.1 Background and Motivation
			1.4.1.2 Catalytic Conversion of Biomass to Hydrogen through Gasification
				1.4.1.2.1 Alkaline Earth Metallic Catalysts
				1.4.1.2.2 Metal and Metallic Oxides Catalysts
				1.4.1.2.3 Natural Mineral Catalysts
				1.4.1.2.4 Hybrid Catalysts
			1.4.1.3 Current Challenges in Biomass Conversion to Hydrogen
			1.4.1.4 Intervention of AI/ML in H2 Production from Biomass
			1.4.1.5 Conclusions and Future Directions
		1.4.2 Hydrogen Generation from Photocatalytic Water Splitting
			1.4.2.1 Materials Development Photocatalytic Water Splitting
				1.4.2.1.1 Metal-Modified TiO2
				1.4.2.1.2 Non-Metal-Modified TiO2
				1.4.2.1.3 Semiconductor Coupling TiO2
				1.4.2.1.4 Ternary TiO2
				1.4.2.1.5 Carbon-Based Photocatalyst
			1.4.2.2 ML Aided Photocatalyst Development
			1.4.2.3 Conclusions and Future Directions
		1.4.3 Geothermal Energy Applications
	1.5 Challenges of AI in the Renewable Energy Industry
		1.5.1 Lack of Theoretical Background
		1.5.2 Lack of Practical Expertise
		1.5.3 Outdated Infrastructure
		1.5.4 Financial Pressure
	1.6 Outlook and Future Perspectives
	References
Chapter 2: Recent Advancements in Artificial Intelligence and Machine Learning in Sustainable Energy Management
	2.1 Introduction
	2.2 Literature Survey
	2.3 Different Forms of Sustainable Energy
		2.3.1 Solar Energy/Solar Farms
		2.3.2 Wind Energy
	2.4 Sustainable Energy Management
	2.5 Recent Advancements in Energy Management Using AI and ML
		2.5.1 Solar Related Methodological Approaches
		2.5.2 Related Models of Predicting Algorithms
		2.5.3 Wind System Related Methodological Approaches
	2.6 Pros and Cons of Current Scenario
	2.7 Conclusion
	References
Chapter 3: Role of Machine Learning in Renewable Energy
	3.1 Introduction
	3.2 Machine Learning
	3.3 Renewable Energy
	3.4 Solar Energy
		3.4.1 Current Usage of Solar Energy
		3.4.2 Role of ML in Solar Power Forecasting
	3.5 Wind Energy
		3.5.1 Current Use of Wind Energy
		3.5.2 Role of ML in Wind Energy
	3.6 Hydroelectric Power
		3.6.1 Current Use of Hydroelectric Power
		3.6.2 Role of ML in Hydroelectric Energy
	3.7 Biomass
		3.7.1 Current Usage of Biomass
		3.7.2 Role of ML in Biomass Gasification
		3.7.3 Role of ML in Biomass Production in the Wastewater Treatment System
	3.8 Geothermal Energy
		3.8.1 Current use of Geothermal Energy
		3.8.2 Role of ML in Geothermal Oil and Gas Well Subsurface Temperature Prediction
	3.9 Conclusion
	References
Chapter 4: Smart Home Energy Management Using Non-intrusive Load Monitoring: A Deep Learning Perspective
	4.1 Introduction
		4.1.1 Supervised Algorithms
		4.1.2 Unsupervised Algorithms
		4.1.3 Semi-Supervised Algorithm
	4.2 Datasets and Algorithms
		4.2.1 Datasets
			4.2.1.1 REDD
			4.2.1.2 UK - DALE
			4.2.1.3 REFIT
			4.2.1.4 SynD
		4.2.2 Algorithms
			4.2.2.1 Combinatorial Optimization (CO)
			4.2.2.2 Factorial HMM
			4.2.2.3 Denoising Auto Encoder (DAE)
			4.2.2.4 Recurrent Neural Network (RNN)
			4.2.2.5 Gated Recurrent Unit (GRU) and Window GRU
			4.2.2.6 Short Sequence to Point (SS2P)
			4.2.2.7 Sequence to Sequence (S2S)
			4.2.2.8 Bidirectional Encoder Representation for Transformers (BERT)
	4.3 Experimental Results and Discussion
		4.3.1 Case 1: REDD with Five Appliances (Fridge, Light, Sockets, Microwave, and Dishwasher)
		4.3.2 Case 2: UK - DALE with Five Appliances (Washer Dryer, Kettle, Fridge Freezer, Microwave, and Dish washer)
		4.3.3 Case 3: SynD with five appliances (Electric space heater, Clothes iron, Dish washer, Washing machine, and Fridge)
		4.3.4 Case 4: REFIT with five appliances (Dish washer, Kettle, Fridge freezer, Washing machine, and Audio system)
	4.4 Conclusion
	References
Chapter 5: New Scheme of Cost-Load Optimization by Appliance Scheduling in Smart Homes
	5.1 Introduction
	5.2 Mathematical Modelling
		5.2.1 Objective Functions
		5.2.2 Operational Constraints
	5.3 Solution Methods
		5.3.1 Cuckoo Search (CS) Method
		5.3.2 Adaptive Cuckoo Search (ACS) Method
		5.3.3 Hybrid GA-PSO Algorithm
	5.4 Results and Discussion
		5.4.1 Analysis of Results for Case Study I (Waterloo North Hydro Inc., Canada)
			5.4.1.1 Scenario 1: Individual Smart Home Residents Reschedule His/Her Power Consumption in Order to Minimize Electricity Bill Cost
			5.4.1.2 Scenario 2: Individual Smart Home Residents Reschedule His/Her Power Consumption in Order to Minimize the Peak to Average Ratio (PAR)
			5.4.1.3 Scenario 3: Individual Smart Home Residents Reschedule His/Her Power Consumption in Order to Optimize the Electricity Bill Cost and Peak Demand Together
		5.4.2 Result Analysis for Case Study II (Gulf Power's Company, Northwest Florida)
			5.4.2.1 Scenario 1: Individual Smart Home Residents Reschedule His/Her Power Consumption in Order to Minimize Electricity Bill Cost
			5.4.2.2 Scenario 2: Individual Smart Home Residents Reschedule His/Her Power Consumption in Order to Minimize the Peak to Average Ratio (PAR)
			5.4.2.3 Scenario 3: Individual Smart Home Residents Reschedule His/Her Power Consumption in Order to Optimize the Electricity Bill Cost and Peak Demand Together
	5.5 Conclusion and Future Scope
	References
Chapter 6: A Comparison of Metaheuristic Algorithms for Estimating Solar Cell Parameters Using a Single Diode Model
	6.1 Introduction
	6.2 Problem Formulation
		6.2.1 Single-Diode Model
		6.2.2 Objective Function
	6.3 Metaheuristic Algorithms
		6.3.1 Particle Swarm Optimization
		6.3.2 Gray Wolf Optimization
		6.3.3 Atom Search Optimization
	6.4 Results and Discussion
	6.5 Conclusion
	References
Chapter 7: Review on Controlling of BLDC Motor via Optimization Techniques for Renewable Energy Applications
	7.1 Introduction
	7.2 Mathematical Model of BLDC
	7.3 PID and PD Controller
	7.4 Optimization Techniques
		7.4.1 Different Optimization Techniques
			7.4.1.1 Particles Swarm Optimization
			7.4.1.2 Grey Wolf Optimization
			7.4.1.3 Whale Optimization Algorithm
			7.4.1.4 COOT Algorithm
			7.4.1.5 Sine Cos Algorithm
			7.4.1.6 Moth Flame Optimization
		7.4.2 Common Optimization Steps
	7.5 Simulation and Results
	7.6 Conclusion
	References
Chapter 8: Energy-Efficient Task Offloading in Edge Computing with Energy Harvesting
	8.1 Introduction
		8.1.1 An Overview of the Energy-Harvesting Capabilities of the IoT
		8.1.2 Energy Efficient IoT Protocols
	8.2 The Reasons for Energy Optimization
		8.2.1 Hardware and Software for Mobile Devices
		8.2.2 Offloading Strategies for Computation
		8.2.3 Offload Computation from Devices
		8.2.4 Energy Aware Computing Offloading
		8.2.5 Offloading over Device to Device
	8.3 Task Offloading Scheme
	8.4 Offloading Algorithm
	8.5 Conclusion
	References
Chapter 9: Blockchain Application in Sustainable Energy Solution
	9.1 Introduction
	9.2 Blockchain
		9.2.1 Blockchain Term Definition
		9.2.2 The Making of a Blockchain
		9.2.3 The Blockchain Technology Architecture
		9.2.4 The Grouping of Blockchain
		9.2.5 Blockchain's Core Technologies
	9.3 Specification of Blockchain
		9.3.1 Decentralization
		9.3.2 Accessibility
		9.3.3 An Automatic Execution Agreement
		9.3.4 Credibility, Security, Data Integrity, and Traceability
		9.3.5 Anonymity
	9.4 Blockchain Technology: Development and Applications
	9.5 EI Introduction and Definition
		9.5.1 Features of the EI
			9.5.1.1 Accurate Calculation
			9.5.1.2 Regional Multi-source Collaboration
			9.5.1.3 Intelligent Command
			9.5.1.4 Open Trading
			9.5.1.5 EI and Blockchain Technology Compatibility
		9.5.2 Blockchain in the EI: Application Scenarios and Use Cases
			9.5.2.1 Blockchain in the EI: Application Scenarios
			9.5.2.2 P2P Energy Transaction
			9.5.2.3 The Electric Vehicles
			9.5.2.4 Physical Information Security
			9.5.2.5 Carbon Emissions Trading and Certification
			9.5.2.6 Virtual Power Plant
			9.5.2.7 The Multiple Energy System's Synergy
			9.5.2.8 Customer Demand Response
	9.6 Practical Applications
	9.7 EI-Related Blockchain Technology Challenges
		9.7.1 Some Barriers in Blockchain Technology Still Exist
		9.7.2 Applying Blockchain Technology to the Complicated EI is Insufficient in Terms of Dependability and Security
		9.7.3 Blockchain Technology's Standards and Oversight Systems Require Improvement
		9.7.4 The Blockchain Industry is Lacking in Skill
	9.8 Conclusions
	References
Index