Reinforcement learning for Energies of the future and carbon neutrality: a Challenge Design

—Current rapid changes in climate increase the ur- gency to change energy production and consumption management, in order to reduce carbon and other greenhouse gas production. In this context, the French electricity network management company RTE (R´eseau de Transport d’´Electricit´e) has recently published the results of an extensive study outlining var- ious scenarios for tomorrow’s French power management [10]. We propose a challenge that will test the viability of such scenarios [1]. The goal is to control electricity transportation in power networks while pursuing multiple objectives: balanc- ing production and consumption, minimizing energetic losses, keeping people and equipment safe, and particularly avoiding catastrophic failures. While the importance of the application provides a goal in itself, this challenge also aims to push the state-of-the-art in a branch of Artificial Intelligence (AI) called Reinforcement Learning (RL), which offers new possibilities to tackle control problems. In particular, various aspects of the combination of Deep Learning and RL called Deep Reinforce- ment Learning remain to be harnessed in this application domain. This challenge belongs to a series started in 2019 under the name ”Learning to run a power network” (L2RPN). In this new edition, we introduce new more realistic scenarios proposed by RTE to reach carbon neutrality by 2050, retiring fossil fuel electricity production, increasing proportions of renewable and nuclear energy and introducing batteries. Furthermore, we provide a baseline using a state-of-the-art reinforcement learning algorithm to stimulate future participants.