Assessment on Fault-tolerance Performance Using Neural Network Model Based on Ant Colony Optimization Algorithm for Fault Diagnosis in Distribution Systems of Electric Power Systems

This paper presents a model based on neural network optimized by the ant colony optimization algorithm (ACOA) for fault section diagnosis in distribution systems of electric power systems, and the simulation results show that it can effectively improve the fault-tolerance ability of fault section diagnosis. It had better fault-tolerance ability in contrast with the BP-NN model and the DGA-NN model. It must be pointed out that the improvement degree is correlative with the space distribution of samples, and it isn ´t the essential improvement, but it is the potential mining of neural network.