Reinforcement Learning Based PID Control of Wind Energy Conversion Systems

Abstract

<em>In this paper an adaptive PID controller for Wind Energy Conversion Systems (WECS) has been developed. The<br />adaptation technique applied to this controller is based on Reinforcement Learning (RL) theory. Nonlinear<br />characteristics of wind variations as plant input, wind turbine structure and generator operational behavior<br />demand for high quality adaptive controller to ensure both robust stability and safe performance. Thus, a<br />reinforcement learning algorithm is used for online tuning of PID coefficients in order to enhance closed loop<br />system performance. In this study, at start the proposed controller is applied to two pure mathematical plants,<br />and then the closed loop WECS behavior is discussed in the presence of a major disturbance.<br /></em>