AI approach to optimal VAr control with fuzzy reactive loads

This paper presents an artificial intelligence (AI) approach to the optimal reactive power (VAr) control problem. The method incorporates the reactive load uncertainty in optimizing the overall system performance. The artificial neural network (ANN) enhanced by fuzzy sets is used to determine the memberships of control variables corresponding to the given load values. A power flow solution determines the corresponding state of the system. Since the resulting system state may not be feasible in real-time, a heuristic method based on the application of sensitivities in an expert system is employed to refine the solution with minimum adjustments of control variables. Test cases and numerical results demonstrate the applicability of the proposed approach. Simplicity, processing speed and ability to model load uncertainties make this approach a viable option for online VAr control.<
>