Optimal Modeling and Forecasting of Equipment Failure Rate for the Electricity Distribution Network

In order to gain a deep understanding of planned maintenance, check the weaknesses of distribution network and detect unusual events, the network outage should be traced and monitored. On the other hand, the most important task of electric power distribution companies is to supply reliable and stable electricity with the minimum outage and standard voltage. This research intends to use time series and artificial neural network and propose some models to forecast the failure rate of equipment in the two regions controlled by Tehran Power Distribution Company. The data have been extracted weekly from the ENOX software from March 2012 to March 2016. To this end, after data pre-processing, the appropriate models have been provided using Minitab and MATLAB software. Moreover, the average air temperature, the average rainfall and the average wind speed were selected as inputs to the neural network. The mean square error (MSE) was used as a criterion to evaluate the error corresponding to the proposed models. The results revealed that time series models perform better than MLP neural network in forecasting equipment failure rates and thus they can be used for future periods.