A comparative study of medium-weather-dependent load forecasting using enhanced artificial/fuzzy neural network and statistical techniques

Monthly peak load demand of Jeddah area for the past nine years is used for investigation throughout this work. The first seven years data is used for training while the prediction is carried out for the following two years. First, Minitab statistical software package is used for peak load prediction using autoregressive integrated moving average (ARIMA) technique, and an average error value of 11.7% is achieved. Next, an artificial neural network (ANN) is utilised and several suggestions are implemented to build an adaptive form of ANN. Direct ANN implementation shows poor performance. Also, fuzzy neural network (FNN) is also examined but showed comparatively poor performance. The modelling of the trend of peak load demand is incorporated by introducing “time index feature” and that clearly enhanced the performance of both ANN (6.8% error) and FNN (4.7% error). A comparative study is provided below to show the accuracy of distinction among these techniques.