Short-term load forecasting based on support vector regression considering cooling load in summer

Abstract

With the rapid development of the economy and society, short-term load forecasting is becoming increasingly important in power system dispatch and demand response. Firstly, we analyze the daily load characteristics of Jinan in the summer of 2016. Then, a cooling maximum load prediction LS-SVM model is established based on meteorological factors considering accumulated temperature effect. Although the summer load is greatly influenced by meteorological factors, the daily load curves are still similar. Therefore, each point load is calculated by similarity of daily load curve and daily maximum and minimum load. The experimental results prove the effectiveness of the developed prediction algorithm.

Topics & Concepts