Sustainable Developments by Artificial Intelligence and Machine Learning for Renewable Energies

Front Cover
Sustainable Developments by Artificial Intelligence and Machine Learning for Renewable Energies
Copyright
Dedication
Contents
Contributors
About the editors
Preface
Chapter 1: Application of alternative clean energy
	1.1. Introduction
	1.2. Solar energy
		1.2.1. Photovoltaic systems
		1.2.2. Solar thermal energy systems
		1.2.3. Solar water heating (SWH) systems
		1.2.4. Solar cooker
			1.2.4.1. Box type solar cooker
			1.2.4.2. Parabolic concentrating type solar cooker
		1.2.5. Solar water pumps
		1.2.6. Solar space heating
			1.2.6.1. Active space heating
			1.2.6.2. Passive space heating
	1.3. Geothermal energy
		1.3.1. Geothermal power generation
			1.3.1.1. Direct steam power plants
			1.3.1.2. Single flash system power plants
			1.3.1.3. Double flash steam power plants
			1.3.1.4. Binary cycle power plants
		1.3.2. Direct uses of geothermal energy
	1.4. Wind energy
		1.4.1. Horizontal Axis wind turbine
		1.4.2. Vertical axis wind turbine
		1.4.3. Wind turbine applications
	1.5. Biomass energy
		1.5.1. Method of biomass energy extraction
			1.5.1.1. Pyrolysis
		1.5.2. Gasification
		1.5.3. Anaerobic digestion
		1.5.4. Biofuels
		1.5.5. Bioethanol production
			1.5.5.1. Sugar or starch fermentation
			1.5.5.2. Bioethanol from lignocellulose fermentation
		1.5.6. Biodiesel
	1.6. Ocean and tidal energy
		1.6.1. Wave energy
		1.6.2. OTEC
		1.6.3. TIC
	1.7. Small, micro, and mini hydro plants
	1.8. Case study
	1.9. Conclusion
	References
Chapter 2: Optimization of hybrid energy generation
	2.1. Introduction
	2.2. RES data and uncertainty statistical analysis
		2.2.1. Wind source analysis
		2.2.2. Solar source analysis
	2.3. Test case modifications and solution methodology
		2.3.1. Test case modifications
		2.3.2. Configuration of cases
		2.3.3. Solution methodology
		2.3.4. Sensitivity factors
		2.3.5. Locational marginal pricing (LMP)
		2.3.6. Reliability parameters
	2.4. Results
		2.4.1. Impact of probabilistic nature and location of RES on sensitivity factors
		2.4.2. Impact of probabilistic nature and location of RES on LMP
		2.4.3. Impact of the probabilistic nature and location of RES on TTC and TRM
	2.5. Discussion and conclusion, future scope
		2.5.1. Discussion
		2.5.2. Conclusion
		2.5.3. Future scope
	Acknowledgment
	References
Chapter 3: IoET-SG: Integrating internet of energy things with smart grid
	3.1. Introduction
	3.2. Traditional grid
	3.3. Smart grid
	3.4. Internet of energy things (IoET)
	3.5. IoET-SG system
	3.6. Research challenges and future guidelines
	3.7. Conclusion
	References
Chapter 4: Evolution of high efficiency passivated emitter and rear contact (PERC) solar cells
	4.1. Introduction
	4.2. Photon absorption and optical generation
	4.3. Loss mechanisms in PERC solar cells
		4.3.1. Optical losses
		4.3.2. Electrical losses
			4.3.2.1. Loss due to reflection
			4.3.2.2. Incomplete absorption
				Interband absorption
				Intraband absorption
				Free-carrier absorption
			4.3.2.3. Shadowing
			4.3.2.4. Resistive losses
			4.3.2.5. Recombination losses
				Radiative recombination
				Auger recombination
				Shockley-Read-Hall (SRH) recombination
				Surface recombination
	4.4. Carrier transport equations
		4.4.1. Solar cell parameters
	4.5. PERC technology
		4.5.1. PERC process flow
		4.5.2. Surface passivation
			4.5.2.1. Passivation by SiO2
			4.5.2.2. Passivation by SiNx
			4.5.2.3. Passivation by Al2O3
			4.5.2.4. Dielectric stack passivation
		4.5.3. LBSF and rear local contact
		4.5.4. Rear polishing
		4.5.5. PERC performance
		4.5.6. Improvements of PERC solar cells
		4.5.7. Further improvements
		4.5.8. Bifacial PERC
	4.6. Fabrication of PERC solar cells
		4.6.1. Saw damage removal, texturization, and cleaning
			4.6.1.1. Saw damage removal
			4.6.1.2. Texturization
			4.6.1.3. Wafer cleaning
		4.6.2. Diffusion and oxidation
			4.6.2.1. Phosphorus diffusion
				Process steps for phosphorus diffusion
				PSG removal
			4.6.2.2. Thermal oxidation
		4.6.3. Reactive ion etching
		4.6.4. Plasma-enhanced chemical vapor deposition (PECVD)
		4.6.5. Atomic layer deposition (ALD)
		4.6.6. Laser ablation
		4.6.7. Metallization
	4.7. Characterization equipment
		4.7.1. Scanning electron microscopy (SEM)
		4.7.2. Four point probe measurement
		4.7.3. Thickness profilometer
		4.7.4. I-V and C-V measurement
		4.7.5. X-ray photo electron spectroscopy (XPS)
		4.7.6. Lifetime and Suns-Voc measurement
		4.7.7. Reflectance and external quantum efficiency (EQE) measurement
			4.7.7.1. Reflectance measurement
			4.7.7.2. External quantum efficiency (EQE) measurement
		4.7.8. Current-voltage (I-V) measurement
	4.8. Conclusion
	References
Chapter 5: Online-based approach for frequency control of microgrid using biologically inspired intelligent controller
	5.1. Introduction
	5.2. Test system description
		5.2.1. Photovoltaic model
		5.2.2. Wind energy
		5.2.3. Diesel engine generator (DEG) model
		5.2.4. Fuel cell, BESS, and FESS
	5.3. Fuzzy logic controller
	5.4. Particle swarm optimization (PSO)
	5.5. Gray wolf optimization (GWO)
	5.6. Results analysis
	5.7. Conclusion
	References
Chapter 6: Optimal allocation of renewable energy sources in electrical distribution systems based on technical and econo ...
	6.1. Introduction
		6.1.1. Motivation
		6.1.2. Literature review
		6.1.3. Contribution and chapter organization
	6.2. Problem formulation
		6.2.1. Multiobjective function
		6.2.2. Equality constraints
		6.2.3. Inequality constraints of distribution line
		6.2.4. Inequality constraints of DG units
	6.3. Cosine adapted whale optimization algorithm (CAWOA)
	6.4. Results and discussion
		6.4.1. Test systems
		6.4.2. Analysis of optimal results
		6.4.3. Comparison results
		6.4.4. Impact of DG on branch currents
		6.4.5. Impact of loadability variation on EDS
	6.5. Conclusions
	Abbreviations
	References
Chapter 7: Optimization of renewable energy sources using emerging computational techniques
	Abbreviations
	7.1. Introduction
	7.2. Sources of renewable energy
		7.2.1. Bioenergy (BE)
		7.2.2. Geothermal energy (GE)
		7.2.3. Hydropower energy (HPE)
		7.2.4. Hydrogen energy (HE)
		7.2.5. Solar energy (SE)
		7.2.6. Wind energy (WE)
		7.2.7. Ocean energy (OE)
	7.3. Artificial intelligence (AI)
		7.3.1. Artificial intelligence in bioenergy
		7.3.2. Artificial intelligence in geothermal energy
		7.3.3. Artificial intelligence in hydro energy
		7.3.4. Artificial intelligence in hydrogen energy
		7.3.5. Artificial intelligence in solar energy
		7.3.6. Artificial intelligence in wind energy
		7.3.7. Artificial intelligence in ocean energy
	7.4. Conclusion
	References
Chapter 8: Advanced renewable dispatch with machine learning-based hybrid demand-side controller: The state of the art an ...
	8.1. Introduction
	8.2. Building energy demand forecasting with machine learning
		8.2.1. Predictions on cooling/heating/electrical loads
		8.2.2. Machine learning modeling techniques
	8.3. Flexible demand-side management strategies
		8.3.1. Smart appliances
		8.3.2. HVAC systems
		8.3.3. Plug-in loads and storages
	8.4. Machine learning-based advanced controllers
	Acknowledgment
	References
Chapter 9: A machine learning-based design approach on PCMs-PV systems with multilevel scenario uncertainty
	9.1. Introduction
	9.2. Overview on PCMs-PV systems and operations
		9.2.1. Passive PCMs-PV systems
		9.2.2. Active PCMs-PV systems
		9.2.3. Combined passive/active PCMs-PV systems
	9.3. Mechanism for machine learning on performance prediction of nonlinear systems
	9.4. Application of machine learning in PCMs-PV systems
		9.4.1. Surrogate model for performance prediction
		9.4.2. System optimization
			9.4.2.1. Single-objective optimization
			9.4.2.2. Multiobjective optimization of the hybrid renewable system using the Pareto NSGA-II
		9.4.3. Robust optimization with multilevel scenario uncertainty
	9.5. Challenges and outlooks
		9.5.1. Uncertainty quantification and probability density function
		9.5.2. Stochastic sampling size and uncertainty-based optimization function
		9.5.3. Hybrid learning and advanced optimization algorithms
		9.5.4. Multicriteria decision-marking for trade-off solutions
	Acknowledgment
	References
Chapter 10: Agent-based peer-to-peer energy trading between prosumers and consumers with cost-benefit business models
	10.1. Introduction
	10.2. Agent-based peer-to-peer energy trading with dynamic internal pricing
		10.2.1. P2P energy trading modes with different energy forms
		10.2.2. Mechanisms and mathematical models for dynamic internal pricing
			10.2.2.1. Theoretical mechanisms
			10.2.2.2. Mathematical models
	10.3. Blockchain and machine learning technologies in P2P energy trading
		10.3.1. Blockchain in P2P energy trading
		10.3.2. Machine learning technologies in P2P energy trading
	10.4. Electricity market and techno-economic incentives for P2P energy market
		10.4.1. Decentralized electricity market design
		10.4.2. Techno-economic incentives
	10.5. Challenges and outlook
	Acknowledgment
	References
Chapter 11: Machine learning-based hybrid demand-side controller for renewable energy management
	11.1. Introduction
		11.1.1. Renewable and hybrid energy system
		11.1.2. Demand-side management
	11.2. Machine learning at a glance
		11.2.1. Machine learning meets model-based control
		11.2.2. The application of machine learning in hybrid demand-side controllers
		11.2.3. Support vector machine
		11.2.4. K-means clustering
		11.2.5. Extreme learning machine
		11.2.6. Linear regression
		11.2.7. Partial least squares
		11.2.8. Challenges and future research direction
	11.3. Conclusion
	References
Chapter 12: Prediction of energy generation target of hydropower plants using artificial neural networks
	12.1. Introduction
	12.2. Artificial neural network (ANN)
	12.3. Performance measurement parameters
	12.4. Modeling and analysis
	12.5. Conclusion
	References
Chapter 13: Response surface methodology-based optimization of parameters for biodiesel production
	13.1. Introduction
	13.2. Problem formulation
	13.3. Mathematical model of biodiesel production
		13.3.1. Optimization of the mathematical model
		13.3.2. Proposed methodology
		13.3.3. Basic elephant swarm water search algorithm (ESWSA)
	13.4. Methodology
	13.5. Reaction conditions by RSM
	13.6. Surface plot by different combinations in RSM model
	13.7. Conclusion
	References
Chapter 14: Reservoir simulation model for the design of irrigation projects
	14.1. Introduction
	14.2. System description
	14.3. Cost-benefit functions
	14.4. Methodology
		14.4.1. Linear programming model (LP model)
		14.4.2. Reservoir simulation
			14.4.2.1. The simulation model
			14.4.2.2. System design variables, parameters, and constants
	14.5. Simulation computations
	14.6. Results and discussion
	14.7. Response of Harabhangi irrigation project
		14.7.1. Support for the use of simulation
	14.8. Conclusion
	References
Chapter 15: Effect of hydrofoils on the starting torque characteristics of the Darrieus hydrokinetic turbine
	Abbreviations
	15.1. Introduction
	15.2. Investigated parameters for the Darrieus hydrokinetic turbine
	15.3. Numerical simulation analysis
		15.3.1. Turbine model development
		15.3.2. Grid generation
		15.3.3. Boundary conditions and turbulence modeling
	15.4. Results and discussion
		15.4.1. Performance characteristics
		15.4.2. Flow contours
	15.5. Conclusions
	References
Index
Back Cover