Investigation on the short-term variations of electricity demand due to the climate changes via a hybrid TSK-FR model

Electricity demand forecasts in the short-terms have a vital application in electricity markets. Knowing that energy is a product of power in time, in this study, a fuzzy based relation between the climate change and the average electricity consumption duration is investigated. This paper introduces a type III TSK fuzzy inference machine combined with a set of linear and nonlinear fuzzy regressors in the consequent part to model effects of the climate change on the electricity demand. However, a simplified version of the model is applied to daily data of the average temperature in Tehran, 2004. First, based on an initially fitted nonlinear curve, an optimization model is employed to cluster data into three groups of cold, temperate and hot. The fuzzy data have been expanded to reduce the temperature volatile property. Then the relation is estimated by the fuzzy regressions (REG) in company with the TSK model. Numerical results show high efficiency of the proposed combined fuzzy model.