A flexible long-term load forecasting approach based on new dynamic simulation theory - GSIM

Load forecasting is a difficult task because of the complex relations exist ing in the load and the load-affecting factors. This paper presents a flexi ble long-term load forecasting method based on a new dynamic theory - Gener al Simulation (GSIM) theory that can treat two kinds of logical and intuiti ve information simultaneously and integrally. We divide the relations of fa ctors affecting load demand into functional relations and impact relations. Owing to describing the functional relations by functional formula and imp act relations by impact matrix, we can consider both of the relations as a whole simultaneously in our load model. The successful load forecasting res ults prove the possibility of improving the forecasting accuracy of convent ional approaches. (C) 2001 Elsevier Science Ltd. All rights reserved.