Reinforcement learning for Energies of the future and carbon neutrality: a Challenge Design - Inria - Institut national de recherche en sciences et technologies du numérique Access content directly
Conference Papers Year : 2022

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

Abstract

Current rapid changes in climate increase the urgency to change energy production and consumption management, to reduce carbon and other green-house gas production. In this context, the French electricity network management company RTE (Réseau de Transport d’Électricité) has recently published the results of an extensive study outlining various scenarios for tomorrow’s French power management. We propose a challenge that will test the viability of such a scenario. The goal is to control electricity transportation in power networks, while pursuing multiple objectives: balancing production and consumption, minimizing energetic losses, and 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 Reinforcement 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 state-of-the-art reinforcement learning algorithm to stimulate the future participants.
Fichier principal
Vignette du fichier
Reinforcement learning for Energies of the future and carbon neutrality.pdf (956.53 Ko) Télécharger le fichier
2019_winner_scheme.pdf (132.92 Ko) Télécharger le fichier
2022_em.pdf (13.53 Ko) Télécharger le fichier
agent_archi.pdf (2.92 Ko) Télécharger le fichier
archi_nn.pdf (414.83 Ko) Télécharger le fichier
baseline_vs_dn.pdf (17.66 Ko) Télécharger le fichier
grid_operation_scheme.png (72.88 Ko) Télécharger le fichier
ppo1.pdf (6.15 Ko) Télécharger le fichier
ppo2.pdf (6.05 Ko) Télécharger le fichier
score_barplot.pdf (15.8 Ko) Télécharger le fichier
score_margin.pdf (14.77 Ko) Télécharger le fichier
score_safe-max-rho.pdf (16.11 Ko) Télécharger le fichier
set_agents.pdf (21.04 Ko) Télécharger le fichier
time_series.png (223.34 Ko) Télécharger le fichier
Origin Files produced by the author(s)
Origin Files produced by the author(s)
Origin Files produced by the author(s)

Dates and versions

hal-03726294 , version 1 (20-07-2022)
hal-03726294 , version 2 (02-08-2022)

Identifiers

Cite

Gaëtan Serré, Eva Boguslawski, Benjamin Donnot, Adrien Pavão, Isabelle Guyon, et al.. Reinforcement learning for Energies of the future and carbon neutrality: a Challenge Design. SSCI 2022 - IEEE Symposium Series on Computational Intelligence, IEEE, Dec 2022, Singapour, Singapore. ⟨hal-03726294v2⟩
163 View
264 Download

Altmetric

Share

Gmail Mastodon Facebook X LinkedIn More