Medium-term load forecasting using neural network approach

Load forecasting is very paramount to the operation transmission and distribution electricity utilities. It enhances the reliable planning, construction and management of the power systems. This paper presents a neural network approach for midterm load forecasting based on historical monthly load data, temperature, humidity and wind speed. The proposed approach is applied to Al-Dakhiliya franchise area of Mazoon Electricity Distribution (MZEC) Company, Oman. The results obtained by the neural networks were compared with the classical multiple linear regression models results and found more reasonable and satisfactory.