HPC and machine learning framework and applications for power systems
* 21PESGM0785, Accelerating massive simulations of power systems and deep learning simultaneously on GPUs: Y. CHEN, Tsinghua University * 21PESGM0786, Leveraging HPC and ML to enhance power system cascading failure analysis: Y. CHEN, PNNL * 21PESGM0787, Hot-Starting the Ac Power Flow with Convolutional Neural Networks: Z. TATE, University of Toronto * 21PESGM0788, Demonstration of Grid Mind in Multiple Pilot Projects in Real-world Power Systems: D. SHI, Global Energy Interconnection Research Institute
-
Members: $5.00PES
IEEE Members: $10.00
Non-members: $20.00
26 Jul 2021
To address the challenges brought by the unprecedented development of power systems, high-performance computing (HPC) and machine learning (ML) techniques have been applied to different types of power system applications. To better leverage the advantages of both HPC and ML, this panel will bring experts to help to understand the challenges to merge HPC and ML to increase the overall system efficiencies such as how to connect HPC to ML efficiently, how to accelerate massive scenario-based simulations and multi-agent learning algorithms, and how these two techniques can work together for online learning and control applications. The panelists will also share their experiences on how to address the challenges through different applications.
Chairs:
Yousu Chen, PNNL, Ying Chen, Tsinghua University
Sponsor Committees:
(AMPS) Computer Analytical Methods
