24 hours fuzzy logic technique for load forecasting/ Mohd Daud Alang Hassan

Load forecasting is an important in energy management system. It can be used as an aid in operation and planning of distribution power system. In this thesis a knowledge-based expert system is proposed for the short term load forecasting in which fuzzyTECH software is employed to manipulate actual value of previous load forecast. To develop fuzzy logic system, three different load profiles from data collection are establish. The fuzzy logic based expert system utilizes the historical relationship between load and drybulb temperature and forecast load for 1-24 hour ahead. Experiments were carried out to develop the short term load forecasting (STLF) system. Based on these experiments a triangular membership function with five linguistic term and twenty five appropriate fuzzy rule base give accurate forecast and it used as a forecaster . Overall forecast give a percentage error less then
5 %.