Deep reinforcement learning-based proportional–integral control for dual-active-bridge converter

You, Won-Hee; Yang, Genke; Chu, Jian; Changjiang, JU

doi:10.1007/s00521-023-08667-x

Search citation statements

Order By: Relevance

Paper Sections

Select...

Citation Types

Supporting

Mentioning

Contrasting

Year Published

2024

Publication Types

Select...

Other2

Preprint1

Article1

Relationship

Self Cite0

Independent4

Authors

Journals

Cited by 4 publications

References 25 publications

Supporting

Mentioning

Contrasting

Order By: Relevance

Hybrid Control Scheme for More Efficient Charging of Two Electric Vehicle Batteries Simultaneously

Ahmad,

Thirumarai-Chelvan

2024

2024 IEEE Canadian Conference on Electrical and Computer Engineering (CCECE)

View full text Add to dashboard Cite

Hybrid Control Scheme for More Efficient Charging of Two Electric Vehicle Batteries Simultaneously

Ahmad,

Thirumarai-Chelvan

2024

2024 IEEE Canadian Conference on Electrical and Computer Engineering (CCECE)

View full text Add to dashboard Cite

H₂/H_∞ Dynamic Output Synthesis Based on Regularized Reinforcement Learning

Rajabalifardi,

Sojoodi,

Badri

2024

2024 10th International Conference on Control, Instrumentation and Automation (ICCIA)

View full text Add to dashboard Cite

Reinforcement Learning-Based Modulation Strategy for Dual Active Bridge Converter

Zhang,

Wang,

Zhao

et al. 2024

Preprint

View full text Add to dashboard Cite

With the continuous growth of global energy demand and the depletion of non-renewable resources, the role of power electronic converters in energy conversion and distribution has become increasingly significant. This paper addresses the modulation strategy for the Dual Active Bridge (DAB) converter under complex operating conditions, proposing an optimization method based on reinforcement learning (RL). By incorporating Deep Q-Network (DQN) and Double Deep Q-Network (DDQN) algorithms, an intelligent agent control system is designed. The agent learns and optimizes the phase-shift modulation strategy through interactions with the DAB circuit environment, aiming to achieve high efficiency and stability in power transmission. Simulations conducted using MATLAB demonstrate that the RL-based DAB modulation strategy significantly enhances stability and self-stability compared to traditional control strategies across various operating conditions. The proposed RL-based control strategy for DAB converters offers a novel approach to overcoming the limitations of conventional control methods in complex scenarios. It not only enhances the performance of DAB converters but also provides new research perspectives and theoretical foundations for the intelligent control of power electronic converters.

show abstract

Deep reinforcement learning-based proportional–integral control for dual-active-bridge converter

Cited by 4 publications

References 25 publications

Hybrid Control Scheme for More Efficient Charging of Two Electric Vehicle Batteries Simultaneously

Hybrid Control Scheme for More Efficient Charging of Two Electric Vehicle Batteries Simultaneously

H₂/H_∞ Dynamic Output Synthesis Based on Regularized Reinforcement Learning

Reinforcement Learning-Based Modulation Strategy for Dual Active Bridge Converter

Contact Info

Product

Resources

About

Deep reinforcement learning-based proportional–integral control for dual-active-bridge converter

Cited by 4 publications

References 25 publications

Hybrid Control Scheme for More Efficient Charging of Two Electric Vehicle Batteries Simultaneously

Hybrid Control Scheme for More Efficient Charging of Two Electric Vehicle Batteries Simultaneously

H2/H∞ Dynamic Output Synthesis Based on Regularized Reinforcement Learning

Reinforcement Learning-Based Modulation Strategy for Dual Active Bridge Converter

Contact Info

Product

Resources

About

H₂/H_∞ Dynamic Output Synthesis Based on Regularized Reinforcement Learning