Seasonal Support Vector Regression with Chaotic Genetic Algorithm in Electric Load Forecasting

Application of support vector regression (SVR) with evolutionary algorithms could significantly improve forecasting accuracy and effectively avoid converging prematurely. However, the tendency of electric load sometimes reveals cyclic changes due to seasonal economic activities or climate seasonal nature. the applications of SVR model to deal with cyclic electric load forecasting have not been widely explored. This investigation presents a SVR-based electric load forecasting model with a novel hybrid algorithm, namely chaotic genetic algorithm (CGA), to improve the forecasting performance. the proposed CGA, based on the chaotic optimization algorithm and GA, employs internal randomness of chaos iterations to overcome premature local optimum of GA in determining parameters of a SVR model. a numerical example from an existed reference is used to elucidate the forecasting performance of the proposed model, namely SSVRCGA model. the forecasting results indicate that the proposed model yields more accurate forecasting results than ARIMA and TF-Îμ-SVR-SA models in existed papers.