Tao Chen (Southeast University, China)

Talk: Learning-assisted Management and Pricing Methods for Demand Side Resources and Energy Critical Infrastructure

The key of power system operation and pricing mechanism design is using the price signal to guide reasonable allocation of power flow at system level and customer level at the same time. There should be a reasonable energy-price coupling mechanism and management methods for the demand side resources and energy critical infrastructure at the distribution side near energy end-users, which could ultimately improve the utilization efficiency of distributed energy resources (DERs). By considering AI technology applications in energy system and critical infrastructure, we can reform the traditional expert knowledge and rule-based optimization framework as a learning-assisted framework, such as reinforcement learning and deep learning, to guide the intelligent decision-making process of less manpower involved operation of energy critical infrastructure. 

Bio: Tao Chen is currently an Associate Professor in School of Electrical Engineering, Southeast University, China. His research interests are about power energy system and Artificial Intelligence applications. He worked as Postdoctoral Associate in Advanced Research Institute, Virginia Tech, Washington D.C., USA, 2018-2019 and Engineer in GEIRINA, California, USA, 2017-2018. He received MSc and PhD form Tampere University of Technology, Finland, and University of Michigan, USA, respectively. He received the Best Paper Award for IEEE ISGT-Asia 2019, IEEE iSPEC 2021, IEEE CIEEC 2022. He was a guest editor for IET Renewable Power Generation, Engineering Reports, Frontiers in Energy Research and many other journals. He has (co)authored more than 100 publications and PI for 20+ R&D projects.

Wei Lin (The University of Hong Kong)

Talk: Trustworthy Machine Learning Techniques for Power System Optimization

Power system optimization is fundamental for various applications in power sectors, such as power system economic dispatch and reliability evaluation. As global power sectors are undergoing a renewable-based decarbonization process, the uncertainties from renewable integration (e.g., wind power, rooftop PV) require tremendous scenario-based power system optimization to ensure safe operations of power sectors. However, existing iterative methods face challenges in addressing tremendous power system optimization problems within limited operational time in power sectors. As an alternative, this talk will introduce machine learning-based power system optimization, i.e., end-to-end predictions of optimization solutions. Currently, a critical issue is the trustworthiness worries of deploying machine learning approaches for power system optimization in the real world, which arises from the black-box nature of machine learning techniques to prevent their ensured performance. Consequently, this talk will further focus on trustworthy machine learning techniques for power system optimization, whose core is the theoretical evaluation and ensured improvements for the performance of machine learning-based power system optimization.

Bio: Wei Lin received his B.E. and Ph.D. degrees from Chongqing University, China, in 2016 and 2021, respectively. He was a visiting scholar at the University of Connecticut, from Sep. 2019 to Oct. 2020. From Aug. 2022 to Feb. 2024, He served as a postdoctoral fellow at the Chinese University of Hong Kong and the Hong Kong Polytechnic University. He is currently a postdoctoral fellow at the University of Hong Kong.  His research interests include trustworthy AI techniques in energy, operations research in energy systems,  and energy markets. He is an Associate Editor of IET Renewable Power Generation, and a member of IEEE PES Composite System Reliability. He served as committee members and tutorial speakers at various international conferences (e.g., a series of IEEE conferences) and invited speakers in various affiliations (e.g., Alibaba DAMO Academy). He won the 2022 Power Science and Technology Progress Award (Third-class Prize) of the Chinese Society for Electrical Engineering.