Predictive Control of Voltage Source Inverter: An Online Reinforcement Learning Solution

被引:30
作者
Liu, Xing [1 ,2 ]
Qiu, Lin [2 ]
Fang, Youtong [2 ]
Wang, Kui [3 ]
Li, Yongdong [3 ]
Rodriguez, Jose [4 ]
机构
[1] Shanghai Dianji Univ, Coll Elect Engn, Shanghai 201306, Peoples R China
[2] Zhejiang Univ, Coll Elect Engn, Hangzhou 310027, Peoples R China
[3] Tsinghua Univ, Dept Elect Engn, State Key Lab Power Syst, Beijing 100084, Peoples R China
[4] Univ San Sebastian Santiago, Fac Engn, Santiago 8420524, Chile
基金
国家重点研发计划;
关键词
Finite control-set model predictive control (FCS-MPC); neural network (NN); power converters; reinforcement learning (RL); CONVERTERS; MPC;
D O I
10.1109/TIE.2023.3303626
中图分类号
TP [自动化技术、计算机技术];
学科分类号
0812 ;
摘要
The focus of this article is to introduce the concept of an online reinforcement learning (RL) solution and to propose a novel finite control-set model predictive control framework subject to system uncertainties, which possesses the excellent applicative potential for power converter systems with unknown perturbations. In this framework, the control task is performed by incorporating an adaptive neural network approximation-based RL and neural predictor-based predictive current control solution. To be more precise, a critic neural network is responsible for learning a strategic utility function online, and an actor network is developed to derive control behaviors by approximating the unknown model dynamics and optimizing the learned utility function obtained from the critic network. Compared to previous works, it not only attenuates the inherent issues of system uncertainties and unknown disturbances, but also provides a flexible framework and allows the enhancement of control property. Furthermore, by deploying the Lyapunov approach, it shows that all signals in the closed-loop system are uniformly ultimately bounded. Finally, numerical simulation and experiments validate our theoretical findings.
引用
收藏
页码:6591 / 6600
页数:10
相关论文
共 24 条
[1]   Model Predictive Current Control of Grid-Connected Neutral-Point-Clamped Converters to Meet Low-Voltage Ride-Through Requirements [J].
Calle-Prado, Alejandro ;
Alepuz, Salvador ;
Bordonau, Josep ;
Nicolas-Apruzzese, Joan ;
Cortes, Patricio ;
Rodriguez, Jose .
IEEE TRANSACTIONS ON INDUSTRIAL ELECTRONICS, 2015, 62 (03) :1503-1514
[2]   Delay Compensation in Model Predictive Current Control of a Three-Phase Inverter [J].
Cortes, Patricio ;
Rodriguez, Jose ;
Silva, Cesar ;
Flores, Alexis .
IEEE TRANSACTIONS ON INDUSTRIAL ELECTRONICS, 2012, 59 (02) :1323-1325
[3]   Weighting Factor Design in Model Predictive Control of Power Electronic Converters: An Artificial Neural Network Approach [J].
Dragicevic, Tomislav ;
Novak, Mateja .
IEEE TRANSACTIONS ON INDUSTRIAL ELECTRONICS, 2019, 66 (11) :8870-8880
[4]   Reinforcement-Learning-Based Optimal Control of Hybrid Energy Storage Systems in Hybrid AC-DC Microgrids [J].
Duan, Jiajun ;
Yi, Zhehan ;
Shi, Di ;
Lin, Chang ;
Lu, Xiao ;
Wang, Zhiwei .
IEEE TRANSACTIONS ON INDUSTRIAL INFORMATICS, 2019, 15 (09) :5355-5364
[5]   Deep Neural Network-Based Approximate Optimal Tracking for Unknown Nonlinear Systems [J].
Greene, Max L. ;
Bell, Zachary I. ;
Nivison, Scott ;
Dixon, Warren E. .
IEEE TRANSACTIONS ON AUTOMATIC CONTROL, 2023, 68 (05) :3171-3177
[6]  
KhalilNonlinear H. K., 2002, SYSTEMS-BASEL
[7]   Finite Control-Set Learning Predictive Control for Power Converters [J].
Liu, Xing ;
Qiu, Lin ;
Fang, Youtong ;
Wang, Kui ;
Li, Yongdong ;
Rodriguez, Jose .
IEEE TRANSACTIONS ON INDUSTRIAL ELECTRONICS, 2024, 71 (07) :8190-8196
[8]   Reinforcement Learning-Based Event-Triggered FCS-MPC for Power Converters [J].
Liu, Xing ;
Qiu, Lin ;
Fang, Youtong ;
Rodriguez, Jose .
IEEE TRANSACTIONS ON INDUSTRIAL ELECTRONICS, 2023, 70 (12) :11841-11852
[9]   Predictor-Based Data-Driven Model-Free Adaptive Predictive Control of Power Converters Using Machine Learning [J].
Liu, Xing ;
Qiu, Lin ;
Fang, Youtong ;
Rodriguez, Jose .
IEEE TRANSACTIONS ON INDUSTRIAL ELECTRONICS, 2023, 70 (08) :7591-7603
[10]   Learning-Based Neural Dynamic Surface Predictive Control for MMC [J].
Liu, Xing ;
Qiu, Lin ;
Rodriguez, Jose ;
Wang, Kui ;
Li, Yongdong ;
Fang, Youtong .
IEEE TRANSACTIONS ON POWER ELECTRONICS, 2023, 38 (01) :53-59