Data mining approach for short term load forecasting by combining wavelet transform and group method of data handling (WGMDH)
Published in IEEE 2017 3rd International Conference on Science in Information Technology (ICSITech), 2017
Forecasting is one of the essential activities at the electrical power company. Inaccurate forecasting will lead to wastage of operating costs. Data mining has been widely used to solve the problem of forecasting. In this study, we propose a method using data mining technique for doing electrical load forecasting, which is a combination of wavelet transform and group method of data handling (WGMDH). The proposed algorithm is used to predict the short-term power load which aims to improve the accuracy of forecasting. The results show that by using proposed algorithm better accuracy is achieved compared with the coefficient method which is used by Indonesian Power Company in Sumatera to forecast the electrical load. The method can improve the forecasting of electricity on average above 50% per year, both for the type of similar day and daily electricity load characteristic pattern.