.png){kind=icon}
返回
Soft Actor-Critic Algorithm Based Reinforcement Learning Controller for Single-Inductor Dual-Output DC-DC Converter
.png){kind=icon}
PRE
AI
DOI：10.1109/JESTIE.2025.3596982.png)
.png){kind=icon}
原文求助.png){kind=icon}
分享.png){kind=icon}
收藏
摘要
En 中文
This article proposes the use of a soft actor-critic (SAC) algorithm-based reinforcement learning (RL) controller as the only primary controller to mitigate cross-regulation issues between the two output voltages of the single-inductor dual-output (SIDO) converter operating in continuous conduction mode. The advantages of maximum entropy learning are discussed, and the principles of the SAC algorithm are elucidated. Design schemes for neural networks and reward functions are provided. The SAC-based RL agent is trained offline and the stability analysis is conducted at the operating point. The agent is deployed on a physical platform for testing. Comparative analysis with existing methods demonstrates the effectiveness of this approach in mitigating cross-regulation issues in the SIDO converter while exhibiting strong robustness to variations in input voltage, reference values, and loads.
Keyword:
Switches
Training
Inductors
Entropy
Artificial neural networks
Artificial intelligence
Aerospace electronics
Steady-state
Stability analysis
Data mining
Cross-regulation
reinforcement learning (RL)
single-inductor dual-output (SIDO) converter
soft actor-critic (SAC)
期刊
I
IF:
0
论文数:
138
被引数:
0
机构
引用论文
Artificial Intelligence Applications in High-Frequency Magnetic Components Design for Power Electronics Systems: An Overview人工智能在电力电子系统高频磁性元件设计中的应用: 综述
PREAI
分享收藏A Ripple Control Dual-Mode Single-Inductor Dual-Output Buck Converter With Fast Transient Response
PREAI
分享收藏
Deep Reinforcement Learning for Smart Grid Operations: Algorithms, Applications, and Prospects智能电网运营的深度强化学习: 算法、应用和前景.png)
PROCEEDINGS OF THE IEEE
PROCEEDINGS OF THE IEEEIF25.9
PREAI
分享收藏
查看更多内容