Key points are not available for this paper at this time.
This paper presents a Wide Area Control (WAC) design to enhance the transient stability of Doubly Fed Induction Generators (DFIG) integrated power grid. The proposed WAC design is based on a nonlinear optimal control algorithm using Reinforcement Learning (RL) and Neural Networks (NNs), which optimizes the closed-loop performance of the wind integrated power grid through Approximate Dynamic Programming (ADP). The aim of the WAC is to estimate the global energy function of the system, independent of the contingency, and derive supplementary damping control to augment the excitation system of synchronous generators and local active and reactive power control of DFIG. The controller objective is evolved from transient energy function terms developed for synchronous generators and wind farms within the framework of a coupled oscillatory system. The theoretical results are verified by conducting simulation studies on the modified IEEE 68-bus system with three aggregated wind farms modeled in electromagnetic transient simulator test-bed. It has been shown that the method improves transient stability of the test system and damps the interarea oscillations faster, including the active and reactive power support from DFIG during grid transient conditions.
Yousefian et al. (Wed,) studied this question.