Session 1:
Tuesday, 1st November
1:00PM - 3:00PM (SGT, UTC+8)

Delivery Mode:
Physical – Marina Bay Sands Convention Hall (Melati 4101AB)

Topic of the session: “How to develop cloud computing frameworks for using real-time data streams in large-scale distribution system simulations”

Speaker: Dr. Sayonsom Chanda

Abstract: Real-time data streams from sensors and smart meters deployed at the distribution feeders provide valuable insights about future operations of the grid, and opportunities to optimize the network. However, bringing together data points from multiple domains, formats, and of varying time resolutions into power system simulation models is a challenging task. In this tutorial, Dr. Chanda will provide a framework for researchers to effectively bring together real-time energy demand data from customer meter, hyper-local weather data, and sensor data for further

Learning Outcomes:

    • Become familiar with cloud architecture/frameworks and open-source libraries that can be used to bring together machine learning and electric power grid simulations into cloud platforms.
    • Exercise intelligence extraction from real-time AMI datastreams.
    • Learn from three case studies of cloud-based power grid simulations – for scenarios like DER hosting capacity and EV infrastructure planning.

Sayonsom Chanda, Ph.D. is a senior researcher of Energy Systems Integration at National Renewable Energy Laboratory in Denver, Colorado, USA. He is also  the founder of clean-tech start-up companies like Plexflo and Sync Energy. As a renowned expert in developing AI-powered grid analytics technologies to combat climate change, he has been called to deliver lectures in conferences and panel sessions, including a TEDx talk in 2021. Dr. Chanda has a decade-long experience in working with large utilities and US Department of Energy national laboratories on mission-critical projects.

Dr. Chanda has three patents in cloud-computing for the power grid. He has published 18 peer-reviewed papers in high impact power systems journals.

Session 2:
Tuesday, 1st November
3:30PM - 5:30PM (SGT, UTC+8)

Delivery Mode:
Physical – Marina Bay Sands Convention Hall (Melati 4101AB)

Topic of the session: “Machine Learning and Optimization for Smart Grid”

Speakers: Professor Yan Zhang and Dr. Yushua Li

Abstract: Smart grid has been proposed to deeply use state-of-the-art energy generation, transportation, conversion, utilization and communication technologies to enhance system resilience, improve energy efficiency and adopt higher penetration of renewable energy, etc. With the development of multi-energy network structure, widespread electric vehicles and unmanned aerial vehicle, there are many unprecedented challenges for intelligent modelling, operation and control in smart grid.

Learning Outcomes: Mainly focus on advanced machine learning and optimization technologies with application in smart grid. We first will introduce  the new features, requirements and challenges of the future generation smart grid. Then, multiple state-of-the-art machine learning methods will be presented and introduced. We will also show how to exploit machine learning approaches to address the challenges, including load scheduling, load monitoring and frequency control. Next, we will present energy P2P trading and sharing based on distributed optimization and game theory. We also explore the problem of placement and routing optimization for wind farm by using UAV. Finally, we will conclude and point out related open issues.

Speaker 1
Yan Zhang (IEEE Fellow) is currently a Full Professor at the Department of Informatics, University of Oslo, Norway. He received a PhD degree from School of Electrical & Electronics Engineering, Nanyang Technological University, Singapore. Dr. Zhang is an Editor (or Area Editor, Associate Editor) for 11 IEEE top-ranked Transactions/Magazines, e.g., IEEE Internet of Things, IEEE Transactions on Sustainable Computing, IEEE Transactions on Vehicular Technology, IEEE Network Magazine and IEEE Transactions on Industrial Informatics, etc. He is a symposium/track chair in a number of conferences, e.g., IEEE ICC 2021, IEEE Globecom 2017, IEEE VTC-Spring 2017, IEEE PIMRC 2016, IEEE CloudCom 2016, IEEE CCNC 2016, and IEEE SmartGridComm 2015, etc. He is the Chair of IEEE Communications Society Technical Committee on Green Communications and Computing. Since 2018, Prof. Zhang was a recipient of the global “Highly Cited Researcher” Award. His current research interests include: Energy Internet, Big Data (energy, wireless) and next-generation communications networks. His works in these areas have received more than 28000+ citations and his H-index is 89. He is Fellow of IEEE, Fellow of IET, elected member of Academia Europaea, and elected member of Norwegian Academy of Technological Sciences.

Speaker 2
Yushua Li is currently a Marie Curie Research Fellow at the Department of Informatics, University of Oslo, Norway. He received the Ph.D. degree in control theory and control engineering from the Northeastern University, China. From 2019 to 2021, he was a postdoctoral research scholar in the Department of Electrical and Computer Engineering, University of Denver, Colorado, USA. Dr. Li is an editor for Frontiers in Energy Research, and a Guest Editor for Complexity on the Special Issue “Theory and Applications of Cyber-Physical Systems”. He serves as the section Chair for IEEE 4th Conference on Energy Internet and Energy System Integration and the Vice Secretary-General for IEEE Computational Intelligence Society China Council. He is the member of IEEE and IEEE PES. He has published 12+ papers in Top-ranked IEEE Transactions/Magazines, such as IEEE Transactions on Power System, IEEE Transactions on Smart Grid and IEEE Transactions on Industrial Informatics, etc. Therein, two of them are “Hot Papers” and four of them are “Highly Cited Papers”. He received the Most Popular Academic Works Award at CCDC 2021. His main research interests include distributed modelling, control, energy management and optimization for smart grid and multi-energy systems, as well as distributed machine learning algorithm with applications in microgrids.