Bi-level energy management strategy for power-split plug-in hybrid electric vehicles: A reinforcement learning approach for prediction and control

Yang, Xueping and Jiang, Chaoyu and Zhou, Ming and Hu, Hengjie (2023) Bi-level energy management strategy for power-split plug-in hybrid electric vehicles: A reinforcement learning approach for prediction and control. Frontiers in Energy Research, 11. ISSN 2296-598X

[thumbnail of pubmed-zip/versions/1/package-entries/fenrg-11-1153390/fenrg-11-1153390.pdf] Text
pubmed-zip/versions/1/package-entries/fenrg-11-1153390/fenrg-11-1153390.pdf - Published Version

Download (5MB)

Abstract

The implementation of an energy management strategy plays a key role in improving the fuel economy of plug-in hybrid electric vehicles (PHEVs). In this article, a bi-level energy management strategy with a novel speed prediction method leveraged by reinforcement learning is proposed to construct the optimization scheme for the inner energy allocation of PHEVs. First, the powertrain transmission model of the PHEV in a power-split type is analyzed in detail to obtain the energy routing and its crucial characteristics. Second, a Q-learning (QL) algorithm is applied to establish the speed predictor. Third, the double QL algorithm is introduced to train an effective controller offline that realizes the optimal power distribution. Finally, given a reference battery's state of charge (SOC), a model predictive control framework solved by the reinforcement learning agent with a novel speed predictor is proposed to build the bi-level energy management strategy. The simulation results show that the proposed method performs with a satisfying fuel economy in different driving scenarios while tracking the corresponding SOC references. Moreover, the calculation performance also implies the potential online capability of the proposed method.

Item Type: Article
Subjects: STM Digital Library > Energy
Depositing User: Unnamed user with email support@stmdigitallib.com
Date Deposited: 25 Apr 2023 05:31
Last Modified: 25 Jul 2024 07:41
URI: http://archive.scholarstm.com/id/eprint/968

Actions (login required)

View Item
View Item