A Neural Network Direct Control of STATCOM: Design and Experimental Validation
With the development of artificial intelligence, neural network technology has been applied in the power system. In this letter, a neural network direct control of static synchronous compensator (STATCOM) is proposed, which can improve the dynamic and steady-state performance. First, a simulation model of STATCOM under direct reactive power control is established, and the simulation data are collected as the training dataset for the neural network. Then, the neural network architecture and training algorithm are designed according to the input and output variables, and the neural network direct controller of STATCOM is obtained through training. Compared with direct reactive power control, the proposed neural network direct control can significantly improve the dynamic and steady-state performance of STATCOM due to the direct and fast input–output characteristics of the neural network. Finally, the effectiveness of the proposed control strategy is verified through the experiments based on TMS320F28377 chip.