Energy Management of Multi-mode Hybrid Electric Vehicles based on Hand-shaking Multi-agent Learning

Min Hua; Zhi Li; Quan Zhou

Energy Management of Multi-mode Hybrid Electric Vehicles based on Hand-shaking Multi-agent Learning

Machine Learning 2022-11-29 v3 Multiagent Systems Systems and Control Systems and Control

Authors: Min Hua , Zhi Li , Quan Zhou

Abstract

The future transportation system will be a multi-agent network where connected AI agents can work together to address the grand challenges in our age, e.g., mitigation of real-world driving energy consumption. Distinguished from the existing research on vehicle energy management, which decoupled multiple inputs and multiple outputs (MIMO) control into single-output(MISO) control, this paper studied a multi-agent deep reinforcement learning (MADRL) framework to deal with multiple control outputs simultaneously. A new hand-shaking strategy is proposed for the DRL agents by introducing an independence ratio, and a parametric study is conducted to obtain the best setting for the MADRL framework. The study suggested that the MADRL with an independence ratio of 0.2 is the best, and more than 2.4% of energy can be saved over the conventional DRL framework.

Keywords

energy management hybrid electric vehicles multi-agent deep reinforcement learning hand-shaking strategy independence ratio multiple control outputs energy saving

Cite

@article{arxiv.2209.02633,
  title  = {Energy Management of Multi-mode Hybrid Electric Vehicles based on Hand-shaking Multi-agent Learning},
  author = {Min Hua and Zhi Li and Quan Zhou},
  journal= {arXiv preprint arXiv:2209.02633},
  year   = {2022}
}

Energy Management of Multi-mode Hybrid Electric Vehicles based on Hand-shaking Multi-agent Learning

Abstract

Keywords

Cite

Related papers