A NOVEL NEURO-FUZZY BASED SELF-CORRECTING ONLINE ELECTRIC-LOAD FORECASTING-MODEL

The paper presents a neuro-fuzzy short-term load forecasting (STLF) mo del. The proposed ANN function approximator models the relationships b etween the system hourly peak load and system variables affecting it, namely, weather and temperature variations, type and time of day, the inherent parameters of historical load patterns such as trend, cyclic oscillations, regular seasonal and irregular 'special' events. The loa d predictor forecasting input vector was extended to account for most of the input dominant variables affecting the short-term forecast load . The model utilizes a preprocessor for input vector generation and pr iority classifications using historical load and system data. A postpr ocessor fuzzy logic block provides error correction and data filtering and online tuning and adjustment of electric load forecast data.