Integrating heuristic time series with modified grey forecasting for renewable energy in Taiwan

Abstract

Abstract Incomplete or less data render traditional forecasting algorithms, such as regression analysis or time series analysis, unsuitable. Forecast based on less data is prone to errors because it fails to simulate data accurately. Therefore, this study integrates heuristic fuzzy time series with modified grey forecasting model, namely HFEGM(1,1), to improve the accuracy of the traditional GM(1,1) model for small datasets. Adopting the annual renewable energy in Taiwan, experimental results show that the HFEGM(1,1) model can effectively reduce forecasting errors of the HFGM(1,1) model and also enhance the forecasting accuracy of the GM(1,1) model. Particularly, the forecasting accuracy of the HFEGM(1,1) model for renewable energy is more than 90%, which can be used as a reference for formulating energy policy by managers.