Green Machine Learning and Big Data for Smart Grids

Practices and Applications

1st Edition - November 13, 2024
Imprint: Elsevier
Editors: V. Indragandhi, R. Elakkiya, V. Subramaniyaswamy
Language: English
Paperback ISBN:
9 7 8 - 0 - 4 4 3 - 2 8 9 5 1 - 4
eBook ISBN:
9 7 8 - 0 - 4 4 3 - 2 8 9 5 2 - 1

Green Machine Learning and Big Data for Smart Grids: Practices and Applications is a guidebook to the best practices and potential for green data analytics when generating innova… Read more

Purchase options

World Book Day Celebration!

Save up to 30% on books and eBooks!

Shop now

Institutional subscription on ScienceDirect

Request a sales quote

Green Machine Learning and Big Data for Smart Grids: Practices and Applications is a guidebook to the best practices and potential for green data analytics when generating innovative solutions to renewable energy integration in the power grid. This book begins with a solid foundation in the concept of “green” machine learning and the essential technologies for utilizing data analytics in smart grids. A variety of scenarios are examined closely, demonstrating the opportunities for supporting renewable energy integration using machine learning, from forecasting and stability prediction to smart metering and disturbance tests.

Uses for control of physical components including inverters and converters are examined, along with policy implications. Importantly, real-world case studies and chapter objectives are combined to signpost essential information, and to support understanding and implementation.

Title of Book
Cover image
Title page
Table of Contents
Copyright
List of contributors
Preface
Chapter 1. Introduction to smart grid and the need for green solutions
Abstract
1.1 Introduction
1.2 Sustainable development for smart grid
1.3 Environmental impacts of smart grid
1.4 Applying artificial intelligence and machine learning for enhancing green solutions
1.5 Strategies for implementing artificial intelligence and machine learning in smart grids
1.6 Case studies
1.7 Conclusion
References
Further Reading and Useful Web Sites
Chapter 2. Smart grid technologies through data preprocessing and feature engineering: role in demand response and green machine learning
Abstract
2.1 Introduction
2.2 Smart grids and the data revolution
2.3 Data preprocessing: unveiling the insights
2.4 Smart grid at present: technical architecture
2.5 Feature engineering: crafting intelligence from raw data
2.6 Demand response: enabling smart energy management
2.7 Green machine learning: a path to sustainability
2.8 Case studies: realizing potential
2.9 Challenges and future prospects
2.10 Conclusion
Chapter 3. An analysis of smart grid and management through data analytical models
Abstract
3.1 Introduction
3.2 Methodology
3.3 Setting the stage
3.4 Illuminating the future—load forecasting and demand response models
3.5 Safeguarding reliability—unveiling anomaly detection and predictive maintenance models
3.6 Converging horizons-fusion of renewable energy and grid optimization
3.7 Balancing the currents—unmasking voltage stability assessment and fault detection
3.8 Unveiling personalized power-exploring customer segmentation and energy efficiency programs
3.9 Unmasking unfair play-harnessing data analytics to combat energy theft
3.10 Conclusion
Chapter 4. Analysis and real-time implementation of power line disturbances test in smart grid
Abstract
4.1 Introduction
4.2 Related work
4.3 The working mechanism of smart grids
4.4 Simulation of voltage disturbances
4.5 Comparative analysis and implementation of different ai mitigation techniques
4.6 Conclusion
References
Chapter 5. Energy efficiency and conservation using machine learning
Abstract
5.1 Introduction
5.2 Predicting energy demand
5.3 Optimizing energy systems
5.4 Identifying energy inefficiencies
5.5 A case study with oneAPI
5.6 Conclusion
References
Chapter 6. Smart grid stability prediction using binary manta ray foraging-based machine learning
Abstract
6.1 Introduction
6.2 Related works
6.3 Proposed methodology
6.4 Results and discussion
6.5 Conclusion
References
Chapter 7. CO2 emissions: machine learning models for assessing the economic & environmental impact of fossil fuels and electric vehicles
Abstract
7.1 Introduction
7.2 Literature survey
7.3 System architecture and workflow
7.4 Experimental investigation and findings
7.5 Conclusion
References
Chapter 8. Detection of electricity theft in Chinese power utility state grid corporation using hybrid deep learning model
Abstract
8.1 Introduction
8.2 Related works
8.3 Proposed methodology
8.4 Results and discussion
8.5 Conclusion
References
Chapter 9. Paradigm shift from machine learning to federated learning
Abstract
9.1 Introduction
9.2 Background
9.3 Multiple FL model
9.4 Key consideration for federated learning
9.5 Application of FL
9.6 Challenges
9.7 Conclusion and future work
References
Chapter 10. Blockchain-backed design for an indestructible electric vehicle charging system
Abstract
10.1 Introduction
10.2 Blockchain high level EV charging architecture
10.3 Benefits of EV charging on blockchain
10.4 Discussions
10.5 Conclusion
References
Chapter 11. Thermal management of battery for electric vehicle
Abstract
11.1 Introduction
11.2 Existing system
11.3 Proposed system
11.4 Hardware results and discussion
11.5 Conclusion
References
Chapter 12. Optimal DG placement and FCL sizing using fuzzy-SSOA algorithm
Abstract
12.1 Introduction
12.2 Problem formulation
12.3 Fuzzy logic
12.4 Index for voltage appropriate index(IVA)
12.5 Salp swarm optimization algorithm
12.6 Results and analysis
12.7 Conclusion
References
Chapter 13. Drive control strategies for PMSM drives in electric vehicles
Abstract
13.1 Introduction
13.2 Vector control
13.3 Direct torque control
13.4 Proportional-integral-derivative/maximum torque per ampere controller
13.5 Adaptive fuzzy logic controller
13.6 Artificial neural networks-based control
13.7 Model reference adaptive current control/adaptive neuro-fuzzy inference system control
13.8 Conclusion
References
Chapter 14. Power management system for electric traction integrated with microgrid
Abstract
14.1 Introduction
14.2 System description
14.3 Proposed work
14.4 Simulation results
14.5 Hardware results
14.6 Conclusion
References
Chapter 15. A vehicle-to-grid and grid-to-vehicle off-board DC fast charger for an electric vehicle
Abstract
15.1 Introduction
15.2 Structure of the proposed system
15.3 Development of control mechanism
15.4 Results and analysis
15.5 Conclusion
References
Chapter 16. The global energy landscape and the smart grid: a paradigm shift towards sustainability
Abstract
16.1 Introduction
16.2 The role of smart grids
16.3 Grid modernization
16.4 Role of data analytics in smart grid
16.5 Challenges and barriers in smart grid implementation
16.6 The changing energy landscape: future trends and innovations
References
Chapter 17. Empowering a sustainable future: unleashing the potential of machine learning for energy efficiency and conservation
Abstract
17.1 Introduction: navigating energy challenges with machine learning
17.2 Methodology
17.3 The role of machine learning in energy efficiency: analyzing, predicting, and optimizing consumption
17.4 Analyzing and predicting energy consumption patterns
17.5 Case studies in optimizing energy usage
17.6 Benefits of machine learning in energy efficiency
17.7 Advanced data analytics for energy conservation: from collection to forecasting
17.8 Smart buildings and Internet of Things integration: enabling energy efficiency through connectivity
17.9 Role of IoT devices in real-time data collection
17.10 Integration of machine learning algorithms with smart building systems
17.11 Case studies demonstrating energy savings
17.12 Renewable energy integration: empowering the power grid through machine learning
17.13 Facilitating integration of renewable energy sources
17.14 Machine learning in energy storage management
17.15 Energy-efficient industrial processes: transforming efficiency through machine learning
17.16 Optimizing energy-intensive industrial processes with machine learning
17.17 Machine learning-driven predictive maintenance
17.18 Examples of successful implementations
17.19 Challenges and future directions in implementing machine learning for energy efficiency
17.20 Challenges in implementing machine learning for energy efficiency
17.21 Future developments and strategies
17.22 Policy implications and societal benefits of machine learning in energy efficiency
17.23 Policy implications of machine learning adoption
17.24 Societal benefits of machine learning-driven energy efficiency
17.25 Conclusion: harnessing machine learning for a sustainable energy future
17.26 Key takeaway
17.27 Transformative potential
References
Further Reading
Chapter 18. An analysis of IoT and machine learning–enabled smart grids for sustainable and future–pro energy management
Abstract
18.1 Introduction
18.2 IoT architecture
18.3 Advantage of IoT-enabled smart grid over conventional grid
18.4 Integration of IoT with machine learning to create smart grid
18.5 Requirements for using IoT with machine learning in SG
18.6 Obstacles and prospects for further research
18.7 Conclusion
References
Chapter 19. Grid integration of renewable energy sources: challenges and solutions
Abstract
19.1 Introduction
19.2 Renewable energy sources and their characteristics
19.3 Grid infrastructure and its limitations
19.4 Technical challenges in grid integration
19.5 Technological advancements in grid integration
19.6 Grid integration models
19.7 Grid Resilience and Reliability
19.8 Forecasting and predictive analytics
19.9 Environmental and socioeconomic impact of renewable energy integration
19.10 Future trends and emerging technologies
19.11 Conclusion
References
Index

V. Indragandhi

Dr. V. Indragandhi obtained a PhD from Anna University, Chennai, and is currently employed by VIT as a Professor at the School of Electrical Engineering. She has engaged in teaching and research work for the past 15 years, with a focus on power electronics and renewable energy systems. She has published articles in high-impact factor journals, holds 4 patents to her name, and is a prolific book author/editor for Wiley, Elsevier, and MDPI. She has successfully organized many international conferences and workshops, partnering with leading universities around the world. Recently, she has been engaged as co-PI on a joint research project with Teesside University, funded by the UK Royal Academy of Engineering.

Affiliations and expertise

Professor, Dept. of Energy and Power Electronics, School of Electrical Engineering, Vellore Institute of Technology, Vellore, India

R. Elakkiya

R. Elakkiya is an Assistant Professor in the Department of Computer Science, at Birla Institute of Technology and Science, Dubai. She has acted as a machine learning and data analytics consultant, delivering many solutions to a variety of industries. During the COVID-19 pandemic, she developed an Artificial Intelligence-based screening tool for preliminary screening and deployed it as an open-source tool in three Government Hospitals in Tamilnadu, India. She holds three patents, has published two books, and has authored more than 50 research articles in reputable international journals on topics including AI enhancement of conductor reliability and optimization algorithms for machine learning.

Affiliations and expertise

Assistant Professor, Department of Computer Science, Birla Institute of Technology & Science, Dubai

V. Subramaniyaswamy

V. Subramaniyaswamy is currently working as a Professor in the School of Computer Science and Engineering, Vellore Institute of Technology, Vellore, India. In total, he has 18 years of experience in academia. He has published more than 120 papers in reputed international journals and conferences, and filed 5 patents. His technical competencies lie in recommender systems, Artificial Intelligence, the Internet of Things, reinforcement learning, big data analytics, and cognitive analytics. He has edited two books, including Electric Motor Drives and their Applications, with Simulation Practice (Elsevier: 2022, ISBN: 9780323911627).

Affiliations and expertise

Professor, School of Computer Science and Engineering, Vellore Institute of Technology, Vellore, India.

Life Sciences

Physical Sciences & Engineering

Social Sciences & Humanities

Health

Green Machine Learning and Big Data for Smart Grids

Practices and Applications

Purchase options

World Book Day Celebration!

Institutional subscription on ScienceDirect

V. Indragandhi

R. Elakkiya

V. Subramaniyaswamy

Related books