A decentralized multi-agent energy management strategy based on a look-ahead reinforcement learning approach

Khalatbarisoltani, A., Kandidayeni, M., Boulon, L. et Hu, X. (2022). A decentralized multi-agent energy management strategy based on a look-ahead reinforcement learning approach. SAE International Journal of Electrified Vehicles, 11 (2). ISSN 2691-3747 DOI 10.4271/14-11-02-0012

Prévisualisation

PDF Télécharger (1MB) | Prévisualisation

Résumé

An energy management strategy (EMS) has an essential role in ameliorating the efficiency and lifetime of the powertrain components in a hybrid fuel cell vehicle (HFCV). The EMS of intelligent HFCVs is equipped with advanced data-driven techniques to efficiently distribute the power flow among the power sources, which have heterogeneous energetic characteristics. Decentralized EMSs provide higher modularity (plug and play) and reliability compared to the centralized data-driven strategies. Modularity is the specification that promotes the discovery of new components in a powertrain system without the need for reconfiguration. Hence, this article puts forward a decentralized reinforcement learning (Dec-RL) framework for designing an EMS in a heavy-duty HFCV. The studied powertrain is composed of two parallel fuel cell systems (FCSs) and a battery pack. The contribution of the suggested multi-agent approach lies in the development of a fully decentralized learning strategy composed of several connected local modules. The performance of the proposed approach is investigated through several simulations and experimental tests. The results indicate the advantage of the established Dec-RL control scheme in convergence speed and optimization criteria. © 2021 SAE International Journal of Electrified Vehicles.

Type de document:	Article
Mots-clés libres:	Electric load flow Energy efficiency Fuel cells Multi agent systems Powertrains Reinforcement learning Data driven technique Decentralised Energetic characteristics Fuel cell vehicles Hybrid fuels Multi agent energy management Power flows Power sources Powertrain components Reinforcement learning approach Energy management
Date de dépôt:	14 févr. 2022 13:48
Dernière modification:	14 févr. 2022 13:51
Version du document déposé:	Post-print (version corrigée et acceptée)
URI:	https://depot-e.uqtr.ca/id/eprint/9962

Actions (administrateurs uniquement)

Éditer la notice