Abstract

In this paper, a novel control scheme based on Reinforcement Learning (RL) controller for the Static Synchronous Compensator (STATCOM) is presented for inter-area multi-machine power system. It is a common criterion to develop an improved control strategy for STATCOM to enhance the voltage stability of multi-machine power system. To exemplify on this purpose, a STATCOM controller has been designed which does not depend on the structure and parameters of power system. Moreover, the proposed strategy also replaces the conventional PI controller by RL controller and provides more reliable controlling environment. In addition, the Twin-Delayed Deep Deterministic Policy Gradient (TD3) algorithm is adopted for this work and the parameters of the controller are being updated by TD3 algorithm using only local information. Finally, a simulated result of inter-area multi-machine power system is given, where the result shows the effectiveness of stable voltage maintenance and preventing voltage collapse.

Full Text
Published version (Free)

Talk to us

Join us for a 30 min session where you can share your feedback and ask us any queries you have

Schedule a call