DocumentCode
2597868
Title
Study on the methodology of short-term load forecasting considering the accumulation effect of temperature
Author
Genyong, Chen ; Jingtian, Shi
Author_Institution
Sch. of Electr. Eng., Zhengzhou Univ., Zhengzhou, China
fYear
2009
fDate
6-7 April 2009
Firstpage
1
Lastpage
4
Abstract
The short-term load is nonlinear, and the change of it is influenced by various factors. Be one of them, the temperature is considered the main influencing factor. Not only the temperature of the day to be forecasted take a great influence on the load, but also the temperature of the previous days does. Especially in summer, the influence of the continuous high temperature on the load is different from the single high temperature. It can be seen as an embodiment of the accumulation effect of temperature. The historical load in summer and influencing factor of weather in Zhengzhou city are analyzed mainly in this paper, and then puts forward a short-term load forecasting methodology considering the accumulation effect of temperature in summer on this basis. Not only consider the day-type, precipitation, temperature, and other related factors, but also account into the effect of temperature of the other day in the case of continuous high temperatures. By virtue of the tool of ANN, we set up every single forecast model of total 48 points of daily load. It can be proved that this methodology can reflects the effect of continuous high temperature by the analysis of the actual load forecasting for Zhengzhou city in Central China, and get a approving forecast precision in the case of load fluctuating greatly in summer.
Keywords
load forecasting; meteorology; neural nets; power engineering computing; artificial neural network; historical load; load fluctuation; short term load forecasting; temperature effect; weather factor; Artificial neural networks; Cities and towns; Load forecasting; Meteorological factors; Meteorology; Neural networks; Power grids; Predictive models; Temperature; Weather forecasting; Accumulation effect; Neural networks; Power systems; Short-term load forecasting;
fLanguage
English
Publisher
ieee
Conference_Titel
Sustainable Power Generation and Supply, 2009. SUPERGEN '09. International Conference on
Conference_Location
Nanjing
Print_ISBN
978-1-4244-4934-7
Type
conf
DOI
10.1109/SUPERGEN.2009.5347944
Filename
5347944
Link To Document