Topology aware machine learning for transmission system operation

11/30/2023  9:45 am-10:45 am ET

This event has passed.

Questions? Contact

Hosted by MIT Laboratory for Information and Decision Systems

The energy transition (decarbonization/defossilization) is transforming power systems into cyber-physical systems of systems. The adoption of smaller dispersed generations, active consumptions, power electronics, and the trend towards local supply and autonomy require a reevaluation of control designs and coordination approaches. The grid topology (power line switching and substation reconfiguration) offers degrees of freedom that are underutilized to find non-asset based solutions to efficiently implement the energy transition. Grid topology optimization is a very complex problem, and machine learning could certainly help to find implementable solutions at scale (several thousand nodes). The presentation will address this issue, give an overview of current R&D projects at RTE (Réseau de Transport d’Electricité, French TSO) on this topic, and present some perspectives and open questions.

About the speaker

Patrick Panciatici is a graduate of Supélec (French electrical engineering school). He joined EDF R&D in 1985 and then RTE in 2003 when he participated in the creation of an internal R&D department at RTE. He has more than 35 years of experience in power systems: modeling, simulation, control, and optimization. Currently, as Senior Scientific Advisor, he inspires and coordinates RTE’s long-term research in the “system” dimension. He interacts with a large network of international experts and academic teams worldwide on these topics. He is a member of CIGRE, Fellow of IEEE, RTE representative in PSERC and Bits & Watts.

We're hiring! Learn more and apply