كاربرد سيستم خبره فازي در پيش بيني بار كوتاه مدت شبكه سراسري ايران

Application of Fuzzy Expert System in Short Term Load Forecasting of Iran National Power

One of the most essential requirements for operation and planning activities of an electrical utility is the prediction of load for the next hours to several days out, known as short term load forecasting. The selected method is a combination of artificial neural networks and fuzzy expert systems. The forecasted load is obtained by passing through two stages. In the first stage, the artificial neural networks are trained with the load patterns and the provisional forecasted load is obtained. In the second stage, the fuzzy expert systems (FES) modify the provisional forecasted load considering the load variation due to changes in temperature and the load behaviour of holidays. This paper presents the Procedure of design of the above mentioned FES. The results show the efficiency and accuracy of this method.