LAUSR

The present study applies reinforcement learning strategy for controller design to improve the low voltage ride through (LVRT) capability of a hybrid power system through convertible static compensator (CSC). This article considers different configurations of CSC such as static synchronous series compensator (SSSC), one static synchronous compensator (STATCOM), two STATCOMs, and unified power flow controller (UPFC). Both Q-learning and dynamic fuzzy Q-learning (DFQL)-based controllers are designed and their performances were compared with classical proportional-integral derivative (PID) controller considering a 3-machine system consisting of 2-synchronous and 1-wind energy systems. The results of simulation show that the performance of DFQL-based controller is better compared to other 2-controllers in improving the LVRT capability. Further, it is shown that the UPFC and two STATCOMs configurations of CSC provide higher voltage support compared to other configurations.