Self-Healing Smart Grid System Based on Artificial Neural Network

Abstract

In this paper, a novel logic decomposing method in selfhealing smart grid system based on neural networks is presented and the theoretical fundamentals of the design are expounded. The proposed automatic smart grid topology search algorithm, which is based on artificial neural network (ANN), realizes the adaptive function of analyzing and updating the self-healing system logic in the grid automatically. Furthermore, the configuration design in a neural network mode makes the system have the parallel processing mechanism and the ability of learning and fault decision-making. The outlet of protection is transferred from the neural networks by adjusting the connecting weights. Therefore, the system can classify and recognize arbitrarily complex connecting mode and acting logic.