Artificial Intelligence Based Approach for Short Term Load Forecasting for Selected Feeders at Madina, Saudi Arabia

Abstract

Short term load forecasting is one of the most important tools for smart energy management particularly in the planning and operation of large buildings. It assists in minimizing the energy losses as well as in maintenance scheduling for critical times. One of the widespread methods for load predicting is implemented by artificial intelligence techniques. In this research, fuzzy logic and artificial neural networks are utilized for short term load forecasting of selected feeders in one of the biggest buildings, Madina, Saudi Arabia. A high-quality measured data is collected from the selected locations and used here in training, testing and validation purposes. The performance of the models is evaluated on the basis of statistical indices such as an absolute relative error. Obtained results are compared with the high-quality measured data and it is found that the performance of the fuzzy logic model is found better as compared to artificial neural network model for the selected feeders.