Artificial Intelligence & Machine Learning for Demand-Side Response
In the recent years, there has been a growing interest for the use of Distributed Demand-Side-Response (DDSR) to regulate the power system. DDSR consists in the coordination of distributed loads such as industrial, commercial and recently residential end-users to contribute to electricity suppliers’ portfolio balance or frequency regulation. The integration of commercial and residential end-users into DDSR comes with the need for Big Data Analysis and Artificial Intelligence (AI) solutions to optimize the contribution of these distributed assets. In this webinar, we describe what the key challenges of DDSR are, and how AI and Machine Learning (ML) solutions can address these challenges. Based on a recent review of research works and industrial projects, we will detail the principles of the most relevant AI techniques and will explain how they are used in the context of DDSR. Finally, we discuss a number of directions for future research in this area.
Ioannis Antonopoulos is a PhD student currently working on building a demand response model using machine learning and AI tools. He has been awarded an ETP studentship, combining expert supervision from both Heriot-Watt University, Edinburgh and the University of Edinburgh, art funded by Upside Energy Ltd. (an innovative aggregator company providing demand response services to the UK National Grid) as an industrial partner.
Benoit Couraud is an engineer with a PhD in telecommunication and energy systems, currently working as a Research Associate in Responsive Flexibility (the UK’s largest smart energy demonstrator project, based on the island of Orkney) and the Community-scale Energy Demand Reduction (CEDRI) project in India on distribution grid modeling and smart grid solutions, including demand-side response. His research interest includes using artificial intelligence-based solutions to support the operation of smarter power grids, with high renewable penetration.
Valentin Robu is an Associate Professor at Heriot-Watt University, Edinburgh and a research affiliate at Center for Collective Intelligence at MIT. His core research interests include artificial intelligence and machine learning and their application in building next-generation energy and grid systems. He is a Co- Investigator in a number of large UK research projects in this area, including the EPSRC National Center for Energy Systems Integration (CESI), Responsive Flexibility, CEDRI etc. He has over 100 publications in international conferences and journals, and has collaborated extensively with commercial partners and network operators developing solutions in these areas.
Publication Year: 2020
Earn 1 Professional Development Hour (PDH) for completing the webinar