SS5: Artificial Intelligence Enhanced Reliability, Resilience and Stability of Smart Grid

Abstract:

The rapid advances of cloud computing, big data and Internet-of-Things (IoT) technologies have significantly increased the implementation and application of advanced artificial intelligence (AI) methods to address security and reliability challenges in smart grid. Thus, the data exchange between grid components and data-driven solutions will help to enable a high stability and resilience level in smart grid operation. Data gathering devices such as smart meters and phasor measurement units (PMUs) are widely deployed into the grid, which gives a great opportunity for such data-driven AI algorithms. However, the rapid penetration of renewable energy sources and electrified transportation (e.g., electrified railway, urban rail transit and electric vehicle, etc.) brings more power electronics and more uncertainty to the grid. It is harmful to both the accuracy and the online computational efficiency of the AI-based diagnostics, prognostics and assessment models. Furthermore, the critical and vulnerable cyber conditions are constantly influencing the data quality, leading to much more accuracy degradation of the AI models. Therefore, highly robust prediction and decision-making AI models that improve the reliability, resilience and stability of smart grid which is integrated by large-scale renewable energy sources and electrified transportation draws high importance.

Topics of this special session include, but are not limited to the following:

  • AI methods for reliability assessment and prediction of both power equipment and power grid.
  • AI methods for stability and dynamic security assessment of power grid.
  • AI methods for resilience-oriented development of power system protection and control.
  • Real-time power grid situational awareness and anomaly detection based on AI.
  • Renewable energy generation and electrified transportation load behavior prediction based on AI.
  • Intelligent and predictive maintenance of power equipment and power grid based on AI.
  • Power data cleansing for complex cyber-physical power systems.
  • Grid state estimation toward false data injection attack and other uncertainty conditions based on AI.
  • Power data visualization and digital twin based on AI.

Organizer:

Dr. Qi Wang, Assistant Professor, Southwest Jiaotong University, Email: wangqi@swjtu.edu.cn.

Dr. Qi Wang received the B.S. and Ph.D. degrees in Electrical Engineering & Its Automation and in Electrical Engineering, from Southwest Jiaotong University, Chengdu, China, in 2012 and 2018, respectively. From 2016-2017, he worked as a Visiting Doctoral Scholar with University of Tennessee, Knoxville, TN, USA. From 2018-2020, he worked as a Postdoctoral Fellow with The Hong Kong Polytechnic University, Kowloon, Hong Kong. He is currently an Assistant Professor with the School of Electrical Engineering, Southwest Jiaotong University, Chengdu, China. His research interests include data mining, deep learning and artificial intelligence applications in both the electric power system and the high-speed railway traction power supply system.