2020
DOI: 10.1016/j.energy.2020.118931
|View full text |Cite
|
Sign up to set email alerts
|

Stochastic model predictive control for energy management of power-split plug-in hybrid electric vehicles based on reinforcement learning

Abstract: In this paper, a stochastic model predictive control (MPC) method based on reinforcement learning is proposed for energy management of plug-in hybrid electric vehicles (PHEVs). Firstly, the power transfer of each component in a power-split PHEV is described in detail. Then an effective and convergent reinforcement learning controller is trained by the Q-learning algorithm according to the driving power distribution under multiple driving cycles. By constructing a multi-step Markov velocity prediction model, th… Show more

Help me understand this report

Search citation statements

Order By: Relevance

Paper Sections

Select...
2
1
1
1

Citation Types

0
29
0

Year Published

2021
2021
2024
2024

Publication Types

Select...
7
2
1

Relationship

2
8

Authors

Journals

citations
Cited by 86 publications
(29 citation statements)
references
References 38 publications
0
29
0
Order By: Relevance
“…The panoramic analysis on electric powertrain behaviors and energy consumption in the real vehicle and the built model proves that the novel model validation method can prompt the accuracy of the control module in the constructed forward model, contributing to optimal design of vehicle control strategy. [33], parallel [34] and power-split [35] configurations. According to the investigation results, the developed novel method can comprehensively validate the forward model with different configurations coherently.…”
Section: B Model Validation In Simulationmentioning
confidence: 99%
“…The panoramic analysis on electric powertrain behaviors and energy consumption in the real vehicle and the built model proves that the novel model validation method can prompt the accuracy of the control module in the constructed forward model, contributing to optimal design of vehicle control strategy. [33], parallel [34] and power-split [35] configurations. According to the investigation results, the developed novel method can comprehensively validate the forward model with different configurations coherently.…”
Section: B Model Validation In Simulationmentioning
confidence: 99%
“…In the energy sector, the combination of the MPC and DQN methods has been applied to respond effectively to disturbances in power generation of DERs [35][36][37] and uncertain behavior in DR programs [38,39]. Nevertheless, there is a scarcity of studies applying the DQN-based MPC approach to DCMs with integrated voltage-based DR and From Figure 2, the proposed control strategy is carried out in the following steps:…”
Section: Reinforcement Learning-based Model Predictive Controlmentioning
confidence: 99%
“…They used DQN to approximate the optimal actionvalue function. To contribute to the fuel efficiency of plug-in hybrid EVs, Chen et all [27] propose a stochastic model predictive control strategy for energy management, based on Reinforcement Learning. Furthermore, the authors employ the Q-learning algorithm to set a RL controller used in the optimization process.…”
Section: State Of the Artmentioning
confidence: 99%