Deep reinforcement learning with deep-Q-network based energy management for fuel cell hybrid electric truck

Zhifu Wang, Shunshun Zhang, Wei Luo and Song Xu

Energy, 2024, vol. 306, issue C

Abstract: To better utilize hydrogen energy from fuel cell electric vehicles (FCEVs), an investigation is conducted into how a proton exchange membrane fuel cell (PEMFC) hybrid vehicle's 100-km hydrogen consumption rate is affected by a dynamic programming-based energy management method. The Dueling Deep Q-Network (Dueling DQN) algorithm's energy management approach is proposed. The DQN algorithm is optimized to increase the method's stability and quicken its pace of convergence. The simulation results show that the fuel economy of DQN and Dueling DQN algorithm are 94.28 % and 95.7 % respectively, both of which are improved, while the Dueling DQN algorithm converges at 480 steps higher than the DQN algorithm converges at 800 steps, and the algorithm comparison verifies the two algorithms' The validity of both algorithms was verified by algorithm comparison. In China Truck Driving Conditions (CHTC-LT), the hardware-in-the-loop simulation of CAN communication protocol using NI-PXI hardware-in-the-loop test system achieves the target vehicle speed following and verifies the real-time performance of the strategy.

Keywords: Fuel cell; Dynamic programming; Deep reinforcement learning; Energy management strategy (search for similar items in EconPapers)
Date: 2024
References: View references in EconPapers View complete reference list from CitEc
Citations:

Downloads: (external link)
http://www.sciencedirect.com/science/article/pii/S0360544224023053
Full text for ScienceDirect subscribers only

Related works:
This item may be available elsewhere in EconPapers: Search for items with the same title.

Export reference: BibTeX RIS (EndNote, ProCite, RefMan) HTML/Text

Persistent link: https://EconPapers.repec.org/RePEc:eee:energy:v:306:y:2024:i:c:s0360544224023053

DOI: 10.1016/j.energy.2024.132531

Access Statistics for this article

Energy is currently edited by Henrik Lund and Mark J. Kaiser

More articles in Energy from Elsevier
Bibliographic data for series maintained by Catherine Liu ().