Short-term Load Forecasting of Power System Based on WTVS Model
HE Huaqin
HE Houyu
Abstract：Short term load forecasting plays an important role in the daily operation and scheduling of power systems. Season and temperature are the most important factors affecting load change,but random factors will change demand consumption in a giv?en time,which will lead to sudden change of load. In order to improve the prediction accuracy,a weighted time-varying sliding fuzzy time series model(WTVS)for short-term load forecasting is proposed. The WTVS model is divided into three parts:data pre?processing,trend training and load forecasting. In the data preprocessing stage,smoothing historical data will weaken the influence of random factors. In the trend training and load forecasting stage,seasonal factors and weighted historical data are introduced into the time-varying sliding fuzzy time series model(TVS)for short-term load forecasting. The WTVS model is tested by the load data of Shaanxi power company of national network. The results show that compared with the TVS model,the proposed WTVS model has a significant improvement in the precision of load forecasting.
Keywords：load forecastingfuzzy time seriesweighted historical datasliding windows
Publication Date：2019-01-01
Online Publishing Date：2025-08-15(First online date of this platform, not the publication date of the document)
Pages：5( 1571-1575 )