Historical load curve correction for short-term load forecasting

Author

Yang, Jingfei ; Stenzel, Jürgen

Author_Institution

Dept. of Electr. Eng. & Inf. Technol., Darmstadt Univ. of Technol.

fYear

2005

fDate

Nov. 29 2005-Dec. 2 2005

Firstpage

1

Lastpage

40

Abstract

Short-term load forecasting (STLF) is a significant task for power system operation. The existence of bad data in historical load curve affects the precision of load forecasting result. This paper presents the second order difference method to detect the bad data, eliminate them and evaluate the real data. To decrease the effect of impulse load on the prediction result, weighted least square quadratic fitting is proposed to filter the curve. K-means clustering and support vector machine method are employed to forecast the future load. The proposed method is successfully applied to an actual power system

Keywords

curve fitting; difference equations; least squares approximations; load forecasting; support vector machines; K-means clustering; bad data detection; bad data elimination; historical load curve correction; power system operation; second order difference method; short-term load forecasting; support vector machine method; weighted least square quadratic fitting; Curve fitting; Filtering; Filters; Information technology; Least squares methods; Load forecasting; Metals industry; Power systems; Steel; Support vector machines; impulsive load; load forecasting; second order difference bad data detection; support vector machine; virtual prediction; weighted least square quadratic fitting;

fLanguage

English

Publisher

ieee

Conference_Titel

Power Engineering Conference, 2005. IPEC 2005. The 7th International

Conference_Location

Singapore

Print_ISBN

981-05-5702-7

Type

conf

DOI

10.1109/IPEC.2005.206875

Filename

1627164