An approach for identifying faulty protection devices in a distribution system using ANFIS

Power utilities are seeking for alternative methods to improve the system condition and reduce the customer average interruption duration index. One way to do this is to monitor effectively the operating states of installed protective devices and provide immediate system restoration. This paper presents an intelligent technique for accurate identification of faulty protection devices using operating status of main and back up protection devices. The proposed technique is based on parallel Adaptive Neuro-Fuzzy Inference System (ANFIS) for representing each device in the network. First, fault point data are obtained from a developed fault location system. Then, it is used to provide information about the operating status of protective devices. This technique produces satisfactory result with average maximum errors of 0.053 and 0.182 for the respective status of main and back up protection devices. The result was validated by simulating the operation of the protection devices in the IEEE 34 node test distribution system.