“Machine Learning for Physical Simulation: the Powergrid Usecase”: and the winners are..

This competition, launched by SystemX in collaboration with RTE, NVIDA and Inria, hosted by Codalab and powered by the LIPS platform, has been a resounding success with over 76 participants and over 600 submissions!

This contest invited the competing teams to address the challenge of developing new ML surrogate models to speed-up power-flow simulations by several order of magnitude with realistic criteria, in order to run advanced near real-time congestion risk assessment!

After several months of intense competition, IRT SystemX announced on November 18th the winning teams:

• 1st prize: Amarsagar Reddy Ramapuram Matavalam, Shaban Satti – Arizona State University, United States : HyPowerFlow: Hypersparse Message Passing for Parallel Power Flow on GPUs
• 2d prize: Jianglin Feng, Qingbin Jiang, Yang Liu, Yuheng Li, Zijun Wang – Xi`an Jiaotong University, China : LEAPNet and KKT-hPINN
• 3rd prize: Dean Ninalga – University of Toronto, Canada (independant participation): Power Grid Self-Attention

Congratulations to all!