Energy management strategies based on soft actor critic reinforcement learning with a proper reward function design based on battery state of charge constraints
Year: 2024
Type: article
Abstract: The environmental concerns have pushed our society to find solutions to reduce the emission of transportation systems. Onepromising solution is the fuel cell hybrid electric vehicle (FCHEV), with a proton exchange membrane fuel cell (PEMFC) anda lithium-ion battery. The presence of two different energy sources requires a smart energy management strategy (EMS) whichmust not only optimize energy consumption (conventional approaches), but also the mitigation of component’s degradation (Newapproaches : Health-conscious strategies). For that, a wide range of techniques has been proposed in the literature, and the mostrecent techniques are based on machine learning. Reinforcement learning (RL) is usually the most chosen strategy, but as in theoptimization techniques, a strong design of the objective (called reward function in RL) is required. The main challenge in thereward function is to encourage a proper battery state of charge (SOC) management, while reducing the energy consumption. Thecurrent advancement in the literature shows satisfactory results, but the reward function design have great improvement potentialin the chosen approach. This paper proposes a new approach in the reward function design that allows much better optimization inenergy consumption and degradation than the existing strategies.
Source: Journal of Energy Storage
Language: English
Subfield: Automotive Engineering
Field: Engineering
Domain: Physical Sciences
Open Access status: hybrid
Estimated APC paid: $3,030
OpenAlex ID: W4396631391