.png){kind=icon}
返回
Level-Increased iSHE Modulation Method for Modular Multilevel Converters Based on DDPG
.png){kind=icon}
PRE
AI
DOI：10.1109/TPEL.2024.3486816.png)
.png){kind=icon}
原文求助.png){kind=icon}
分享.png){kind=icon}
收藏
摘要
En 中文
The output waveform quality of modular multilevel converters (MMCs) may not be good enough when there are only a few submodules (SMs). This article proposes a technique to increase the quantity of equivalent output voltage levels of MMC by changing the capacitor voltage of certain SMs. This method significantly improves the performance of the MMC. In addition, the method combines a level-increased MMC with an improved selected harmonic elimination (iSHE) modulation, aiming to minimize the total harmonic distortion of the MMC output. The primary challenge of the iSHE modulation lies in solving a complex nonlinear mathematical model to determine the optimal switching angles. Deep reinforcement learning has proven to be effective in addressing intricate multidimensional optimization problems within a continuous action space. Therefore, this article utilizes the deep deterministic policy gradient (DDPG) algorithm to calculate the optimal switching angles of the MMC. The integration of DDPG algorithm enhances the operational performance of the MMC, thereby contributing to the progress of power electronics using artificial intelligence.
Keyword:
Modulation
Switches
Harmonic analysis
Voltage
Mathematical models
Bridge circuits
Artificial intelligence
Total harmonic distortion
Topology
Multilevel converters
Deep deterministic policy gradient (DDPG)
level-increased
modular multilevel converter (MMC)
selective harmonic elimination (SHE)
total harmonics distortion (THD)
期刊
IF:
6.5
论文数:
1.7W
被引数:
8.3W
机构
暂无机构信息
引用论文
分享收藏Multi-Agent Reinforcement Learning-Based Decentralized Controller for Battery Modular Multilevel Inverter Systems基于多智能体强化学习的电池模块化多电平逆变器系统分散控制器.png)
ELECTRICITY
OAAI
ELECTRICITYIF1.8
OAAI分享收藏
查看更多内容