Big Data Application in Power Systems

2nd Edition - July 1, 2024
Imprint: Elsevier Science
Editors: Reza Arghandeh, Yuxun Zhou
Language: English
Paperback ISBN:
9 7 8 - 0 - 4 4 3 - 2 1 5 2 4 - 7
eBook ISBN:
9 7 8 - 0 - 4 4 3 - 2 1 9 5 1 - 1

Big Data Application in Power Systems, Second Edition presents a thorough update of the previous volume, providing readers with step-by-step guidance in big data analytics… 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

Big Data Application in Power Systems, Second Edition presents a thorough update of the previous volume, providing readers with step-by-step guidance in big data analytics utilization for power system diagnostics, operation, and control. Divided into three parts, this book begins by breaking down the big picture for electric utilities before zooming in to examine theoretical problems and solutions in detail. Finally, the third section provides case studies and applications, demonstrating solution troubleshooting and design from a variety of perspectives and for a range of technologies.

Bringing back a team of global experts and drawing on fresh, emerging perspectives, this book provides cutting-edge advice for meeting today’s challenges in this rapidly accelerating area of power engineering.
Readers will develop new strategies and techniques for leveraging data towards real-world outcomes.

Cover image
Title page
Table of Contents
Copyright
Contributors
About the editors
Preface, objective, and overview of the book
Acknowledgments for the second edition
Section A: Harness the big data from power systems
Chapter One A holistic approach to becoming a data-driven utility
Abstract
1.1 Introduction
1.2 Aligning internal and external stakeholders
1.3 Taking a holistic approach
1.4 “Strong” first, then “smarter”
1.5 Implementing an “Observability Strategy”
1.6 Increasing visibility with IEDs
1.7 Network response requirements
1.8 Integration before automation
1.9 Functional data paths: Keep it simple
1.10 From sensor to end user: The process
1.11 Customers > consumers > prosumers
1.12 New sources of data: Robotics and UAVs
1.13 Extracting value from data and presenting it
1.14 The transformation
1.15 Three case studies
1.16 Frankfort, Kentucky, and greenfield SCADA, SA
1.17 Unmanned aerial vehicles for vegetation management
1.18 Robotics for substation asset management
1.19 Conclusion
1.20 Looking ahead
References
Chapter Two Security and data privacy challenges for data-driven utilities
Abstract
2.1 Introduction
2.2 Case studies: The state and scope of the threat
2.3 The digitized network increases vulnerability
2.4 The role of data analytics
2.5 Conclusion
References
Chapter Three The role of big data and analytics in utilities innovation
Abstract
3.1 Introduction of big data and analytics as an accelerator of innovation
3.2 Approaches to data-driven innovation
3.3 Integration of renewable energy
3.4 Grid operations
3.5 Cognitive computing on big data
3.6 Weather, the biggest data topic for power systems
References
Further reading
Chapter Four Big data integration for the digitalization and decarbonization of distribution grids
Abstract
4.1 Introduction: Challenges toward a net-zero economy
4.2 Grid observability and controllability
4.3 Key drivers of the digital transformation in distribution grids
4.4 Losses and fault detection
4.5 Conclusions
References
Further reading
Section B: Put the power of big data into power systems
Chapter Five Topology detection in distribution networks with machine learning
Abstract
5.1 Introduction
5.2 Distribution grid: Structure and power flows
5.3 Properties of voltage magnitudes in radial grids
5.4 Topology learning with full observation
5.5 Topology learning with missing data
5.6 Experiments
5.7 Conclusions
References
Chapter Six Grid topology identification via distributed statistical hypothesis testing
Abstract
6.1 Introduction
6.2 Power distribution grid model
6.3 Voltage conditional correlation analysis
6.4 A distributed topology test
6.5 Conclusions
References
Chapter Seven Learning stable local Volt/Var controllers in distribution grids
Abstract
Acknowledgments
7.1 Introduction
7.2 Grid modeling and problem formulation
7.3 Equilibrium functions depending only on voltage
7.4 Equilibrium functions with reactive power as an additional argument
7.5 Learning equilibrium functions from data
7.6 Case study
7.7 Conclusions
Chapter Eight Grid-edge optimization and control with machine learning
Abstract
8.1 Introduction
8.2 Optimal power flow methods for grid-edge coordination
8.3 Learning-based control/optimization at the grid edge
8.4 Future research directions
References
Chapter Nine Fault detection in distribution grid with spatial-temporal recurrent graph neural networks
Abstract
9.1 Introduction
9.2 Use case and data description
9.3 Methodology
9.4 Results and discussions
9.5 Conclusion and future work
References
Further reading
Chapter Ten Supervised learning-based fault location in power grids
Abstract
10.1 Fundamentals of SVM
10.2 Power system applications of SVM
10.3 Fault classification and location for three-terminal transmission lines
10.4 Fault location for hybrid HVAC transmission lines
10.5 Summary
References
Chapter Eleven Transient stability predictions in modern power systems using transfer learning
Abstract
11.1 Introduction
11.2 Background
11.3 The proposed framework
11.4 Numerical tests and analysis
11.5 Conclusions
References
Chapter Twelve Misconfiguration detection of inverter-based units in power distribution grids using machine learning
Abstract
12.1 Introduction
12.2 Monitoring and detection framework
12.3 Employed approaches
12.4 Use case example
12.5 Conclusions
References
Chapter Thirteen Virtual inertia provision from distribution power systems using machine learning
Abstract
13.1 Introduction
13.2 Inertia support framework
13.3 Conclusions
References
Chapter Fourteen Electricity demand flexibility estimation in warehouses using machine learning
Abstract
Acknowledgment
14.1 Introduction
14.2 Methodology
14.3 Machine learning algorithms, correlation index, and utilized accuracy metrics
14.4 Results and discussion
14.5 Conclusion
References
Chapter Fifteen The role of eXplainable Artificial Intelligence (XAI) in smart grids
Abstract
Acknowledgment
15.1 Introduction
15.2 A brief overview of XAI and its tools
15.3 XAI-based big data applications in electric power systems
15.4 Explainability to end users and control room operators
15.5 Challenges and opportunities of XAI in electric power systems
15.6 Conclusion
References
Chapter Sixteen Data-driven photovoltaic and wind power forecasting for distribution grids
Abstract
16.1 Introduction
16.2 The role of RES power forecasting in modern power systems
16.3 Classification of PV and wind power forecasting approaches based on models, time horizon, and data
16.4 Accuracy of the PV/wind power forecasting models
16.5 Day-ahead residual load forecasting in a distribution grid with distributed PV generation
16.6 Conclusions
References
Chapter Seventeen Grid resilience against wildfire with machine learning
Abstract
Acknowledgment
17.1 Introduction
17.2 Impact of wildfires on power systems
17.3 Current wildfire management techniques
17.4 Enabling power grid resilience to wildfire
17.5 Conclusion and future work
References
Index

Reza Arghandeh

Prof. Reza Arghandeh is the Director of Connectivity, Information & Intelligence Lab (Ci2Lab.com) and a Full Professor in Data Science and Machine Learning in the Department of Computer Science, Electrical Engineering, and Mathematical Sciences at the Western Norway University of Applied Sciences (HVL), Bergen, Norway. He is also the HVL Data Science Group (HVL.no/ai). Additionally, he is a Research Professor in the Electrical and Computer Department at Florida State University, USA, where he was an assistant professor from 2015 to 2018. Prior to FSU, he was a postdoctoral scholar at the University of California, Berkeley, EECS Dept 2013-2015. His research interests include data analysis and decision support for smart grids and smart cities. His research has been supported by IBM, the U.S. National Science Foundation, the U.S. Department of Energy, the European Space Agency, the European Commission, and the Research Council of Norway.

Affiliations and expertise

Director of Connectivity, Information and Intelligence Lab, Professor, Data Science and Machine Learning, Western Norway University of Applied Sciences, Norway, Research Professor, Electrical Computer Department, Florida State University, USA

Yuxun Zhou

Yuxun Zhou received his B.S. degree in electrical engineering from Xi’an Jiaotong University, Xi’an, China, in 2009, the Diplome d’Ingénieur degree in applied mathematics from École Centrale Paris, Paris, France, in 2012, and a Ph.D. degree from the Department of Electrical Engineering and Computer Sciences, University of California at Berkeley, Berkeley, CA, USA, in 2017. He has been an author on over 60 research articles and conference proceedings published in peer-reviewed journals. Dr Zhou’s research interests include statistical learning theory and paradigms for modern information-rich, large-scale, and human-involved systems.

Affiliations and expertise

Department of Electrical Engineering and Computer Sciences, University of California, Berkeley, USA

Life Sciences

Physical Sciences & Engineering

Social Sciences & Humanities

Health