Enhancing Power Quality in Microgrids With a New Online Control Strategy for DSTATCOM Using Reinforcement Learning Algorithm

Abstract

To mitigate the power quality issue in microgrids, a new online reference control strategy for distribution static compensator using the reinforcement learning algorithm is presented. The new controller is supposed to compensate the reactive power, harmonics, and unbalanced load current in a microgrid utilizing voltage and current parameters. Voltage controller is used to adjust the set point of the reactive power reference, whereas the current based controller tries to compensate the unbalanced load current in distributed resource network through the quadrature axis (q-axis) and zero axis (0-axis). The proposed control strategy is applied to an autonomous microgrid with a weak ac-supply (non-stiff source) distribution system under different loads as well as three-phase fault conditions. Different scenarios are studied and simulation results for various conditions are discussed. The performance of the proposed online secondary control strategy is also discussed in detail.