TD3 Deep Reinforcement Learning Control Approach for a DC-DC Multiport Converter Used in Low-Power EV Applications

Amirhossein Hosseini; Saeed Hosseinnataj; Ali Arzani

doi:10.1049/ses2.70027

English Version Journal Login

您当前的位置：

首页 >

文章列表页 >

TD3 Deep Reinforcement Learning Control Approach for a DC-DC Multiport Converter Used in Low-Power EV Applications

更新时间：2026-06-24

- TD3 Deep Reinforcement Learning Control Approach for a DC-DC Multiport Converter Used in Low-Power EV Applications
- IET Smart Energy Systems Vol. 2, Issue 2, (2026)
- 作者机构：
  
  1. Electrical Engineering Department, Noshirvani University of Technology, Babol,Iran
  2. Contribution: Software, Data curation, Formal analysis, Visualization, Resources, Investigation, Methodology, Writing - review & editing, Writing - original draft, Conceptualization, Validation
  3. University Lille, Arts et Metiers Institute of Technology,Lille,France
  4. Contribution: Conceptualization, Methodology, Validation, Formal analysis, Resources, Writing - original draft, Writing - review & editing, Visualization
  5. Center for Energy Systems Research (CESR), Tennessee Technological University, Cookeville,Tennessee,USA
  6. Contribution: Conceptualization, Validation, Formal analysis, Writing - review & editing, Supervision
- 作者简介：
- 基金信息：
- DOI：10.1049/ses2.70027
  CLC：
- Published：2026
- 稿件说明：
移动端阅览
Amirhossein Hosseini, Saeed Hosseinnataj, Ali Arzani. TD3 Deep Reinforcement Learning Control Approach for a DC-DC Multiport Converter Used in Low-Power EV Applications[J]. IET Smart Energy Systems, 2026, 2(2).
DOI：

Amirhossein Hosseini, Saeed Hosseinnataj, Ali Arzani. TD3 Deep Reinforcement Learning Control Approach for a DC-DC Multiport Converter Used in Low-Power EV Applications[J]. IET Smart Energy Systems, 2026, 2(2). DOI： 10.1049/ses2.70027.

摘要

Abstract

This paper presents a deep reinforcement learning (DRL)-based control framework for a bidirectional dual-input single-output (BDISO) converter applied to low-power electric vehicles (EVs). The study addresses the dynamic instability introduced by constant power loads (CPLs)

which emulate the negative impedance behaviour of EV motor drives. A twin delayed deep deterministic policy gradient (TD3) algorithm is employed to directly generate control signals

thereby eliminating reliance on explicit converter models and intermediate control layers. The proposed model-free approach enables fast voltage regulation and stable bidirectional power flow between sources and load

particularly under regenerative operating conditions. Simulation results obtained in MATLAB/Simulink demonstrate that the proposed strategy achieves up to 4–7 times faster settling time and 30%–90% lower voltage error compared with conventional proportional-integral (PI) and super-twisting algorithm (STA) controllers. These findings establish DRL-based TD3 control as a scalable

model-free solution for robust and efficient energy management in next-generation EV powertrains.

关键词

Keywords

references

Views

下载量

CSCD

Alert me when the article has been cited

提交

Tools

Publicity Resources

Source–Grid Coordinated Optimal Control Strategy Integrating Green Power Tracing and Power Flow Sensitivity

Prospects for Developing Compressed Air Energy Storage in Saudi Arabia

Cyberattack Detection, Fault Estimation, and Fault-Tolerant Control of Smart-Grid Cyber-Physical Systems

A GSDF-Based Renewable Energy Carbon Emission Reduction Calculation Method Considering Network Losses

A Control Strategy for Variable Speed Condenser Based on Doubly-Fed Machine

Related Author

No data

Related Institution

No data

AI问答

⁰