FORECASTING LONG-TERM ELECTRIC POWER DEMAND BY LINEAR SEMIPARAMETRIC REGRESSION
Shengying Zhao, Linfeng Zhao
This is an open access article distributed under the Creative Commons Attribution License CC BY 4.0, which permits unrestricted use, distribution, and reproduction in any medium, provided the original work is properly cited
Market economic system put forward high request for electric power demand’s forecast. The advantage and disadvantage of ancient forecast models in the world were simply summarized which had been employed in electric demand’s forecast, and then semi-parametric model to forecast electric demand was brought forward to enhance the result precision and method rifeness. The semi-parametric model was constructed by the part of linear parameter and non-linear parameter. The portion orderliness knowable was reflected by the part of linear parameter. Instabilization rule was reflected by the part of non-linear parameter. So as to estimate semi-parametric model, the method of PARTIAL RESIDUAL was used. Forecast result was gained from two processes. The first, the part of linear parameter was estimated, then the part of non-linear parameter estimated too. By computing a demonstration, the forecast error of semi-parametric model is not only less but also lower than the outcome of linear regression. Computing result shows that Semi-parametric model to forecast electric power is the arithmetic of high precision, widely utilizable and computed easily.
Forecasting, Semi-Parametric, Regression, Core Function, Band