PES Webinar - Deep Learning and its Application to Power System Analysis
IEEE Power & Energy Society Technical Webinar Series
Deep Learning and its Application to Power System Analysis
21 November 2017 • 10:00 am Eastern
Presented by Dr. Mike Zhou, Chief Scientist, State Grid EPRI China
After the AlphaGo winning game, there is a renewed interest in artificial intelligence, especially in the area of Deep Learning. This Webinar will give a general overview of Deep Learning and its potential application to power system analysis. It will include two parts. In the first part, an open platform for exploring the application of Deep Learning to power system analysis will be introduced, including the discussion of its system architecture, and some sample application scenarios. The platform is based on the integration of InterPSS, an open source power system simulation software project, and TensorFlow, Google's Deep Learning engine; In the second part, some of our recent research work in the area of applying Deep Learning to perform fast power system stability assessment will be presented. Different types of neural networks model, both steady-state and dynamic power system operation information as the neural networks model prediction input are studied for the assessment. Some preliminary results of applying Deep Learning to assess the stability of large-scale power networks will be presented.
Dr. Mike Zhou obtained his B.S. from Hunan University, M.S. and PhD. from Tsinghua University. He was an assistant professor at University of Saskatchewan 1990-1992, served as the VP in charging of power distribution system software development at EDSA Micro Corporation 1992-1997. He was a Senior Computer System Architect with TIBCO Software Inc. 2000-2014. He joined State Grid Electric Power Research Institute of China as a Chief Scientist in 2014, sponsored by the "Thousand Talents Plan" program. His current research interests include Big Data and deep learning technologies, and their application to large-scale power grid on-line analysis.