Reinforcement Learning Based on Energy Management Strategy for HEVs

Inuzuka, Shota; Xu, Fuguo; Zhang, Bo; Shen, Tielong

doi:10.1109/vppc46532.2019.8952511

Cited by 13 publications

(3 citation statements)

References 5 publications

Supporting

Mentioning

Contrasting

Order By: Relevance

“…Markov chain [104] Integrate the Markov chain, GA and radial basis function neural network to obtain a real-time EMS PPO [105] Join the information of V2V and V2I in state variables, utilize the PPO to predict the future behavior a real-time optimal control strategy for a hybrid excavator [100]. An integrated framework was proposed in [101], the first part of the structure is the off-line training use DP, then the optimal results derived from DP were embedded into the ECMS to optimize the power split strategy online.…”

Section: Algorithms References Content Descriptionmentioning

confidence: 99%

“…The information of the V2V and V2I environment was employed as a part of state variables for the training of the PPO algorithm, and the local controller was utilized to improve the learning process by correcting the bad actions [105], Table 3 describes a detailed overview of the literature on the application of RL algorithms to the energy management of HEVs.…”

Section: Algorithms References Content Descriptionmentioning

confidence: 99%

See 1 more Smart Citation

Driving conditions-driven energy management strategies for hybrid electric vehicles: A review

Tan

Tang

et al. 2021

Renewable and Sustainable Energy Reviews

108

View full text Add to dashboard Cite

Section: Algorithms References Content Descriptionmentioning

confidence: 99%

Section: Algorithms References Content Descriptionmentioning

confidence: 99%

Driving conditions-driven energy management strategies for hybrid electric vehicles: A review

Tan

Tang

et al. 2021

Renewable and Sustainable Energy Reviews

108

View full text Add to dashboard Cite

“…In recent years, a growing number of tabular and approximate RL-based solutions have been applied to EMS tasks. They can be broadly classified into value based [13][14][15], policy based [16] and mixed value and policy methods [17][18]. All the approaches above are typically viewed as online RL, which requires the controller to interact with the environment while learning the policy.…”

Section: Introductionmentioning

confidence: 99%

A Data-Driven Solution for Energy Management Strategy of Hybrid Electric Vehicles Based on Uncertainty-Aware Model-Based Offline Reinforcement Learning

Xiao

Zhang

et al. 2023

IEEE Trans. Ind. Inf.

View full text Add to dashboard Cite

Energy management strategy (EMS) is the key technology to improving the fuel efficiency of hybrid electric vehicles (HEV). In recent years, the development of artificial intelligence has enabled tremendous advances by utilizing reinforcement learning (RL) for training and deploying deep neural network-based EMS. However, in contrast to the fields of deep learning such as computer vision and natural language processing which mainly rely on large-scale offline datasets, most RL-based policies must be trained online by trial-and-error with the initial performance being almost arbitrary. Such a paradigm is considered inefficient and unsafe for industrial automation and can only be used to tackle the EMS problems in the simulation world. Considering large historical interactive datasets are readily available in EMS domain, if a RL algorithm can be used to extract a policy purely offline from the prior collected dataset and improve upon data logging policy, the current issues including sample inefficiency, unsafe exploration, and simulation-to-real gap that prevent the widespread use of RL methods could be mitigated to a great extent. To this end, this paper presents a feasible algorithmic framework for model-based offline RL. Unlike vanilla RL approaches without any consideration against distributional shift, a data-driven dynamic model is built before the policy training using RL. After that, two techniques namely conservative MDP and state regularization are augmented which is proved to be effective against model over exploitation. A hardware-inthe-loop (HIL) test is used to evaluate the real-time performance and effectiveness of different strategies on a real controller, and it is found that the proposed naïve datadriven model-based offline RL algorithm can already solve the distributional shift problem inherent in vanilla RL to a large extent. Furthermore, by incorporating the guidance of uncertainty-awareness, a near optimal policy can be obtained by using only the dataset from a sub-optimal controller.

show abstract

Recent Progress in Learning Algorithms Applied in Energy Management of Hybrid Vehicles: A Comprehensive Review

Zheng

Cui

et al. 2022

Int. J. of Precis. Eng. and Manuf.-Green Tech.

View full text Add to dashboard Cite

Reinforcement Learning Based on Energy Management Strategy for HEVs

Cited by 13 publications

References 5 publications

Driving conditions-driven energy management strategies for hybrid electric vehicles: A review

Driving conditions-driven energy management strategies for hybrid electric vehicles: A review

A Data-Driven Solution for Energy Management Strategy of Hybrid Electric Vehicles Based on Uncertainty-Aware Model-Based Offline Reinforcement Learning

Recent Progress in Learning Algorithms Applied in Energy Management of Hybrid Vehicles: A Comprehensive Review

Contact Info

Product

Resources

About