Artificial neural network enhanced by gap statistic algorithm applied for bad data detection of a power system

In this paper, a gap statistic algorithm (GSA) is applied for the bad data analysis. In the method, GSA is employed for the enhancement of neural networks. Because the number of cluster can be determined via GSA more effectively, this integrated approach is beneficial for the localization of the group of bad data. The proposed approach was validated through the data collected from the operation of a power system. Test results pointed to the feasibility of the method for the applications considered.