DocumentCode :
3256688
Title :
GP-based temperature forecasting for electric load forecasting
Author :
Mori, Hiroyuki ; Kanaoka, Daisuke
Author_Institution :
Dept. of Electron. & Bioinf., Meiji Univ., Kawasaki, Japan
fYear :
2009
fDate :
23-26 Jan. 2009
Firstpage :
1
Lastpage :
5
Abstract :
This paper proposes a new probabilistic method for maximum temperature forecasting in short-term electrical load forecasting. The proposed method makes use of Gaussian process (GP)of the kernel machine to evaluate the predicted temperature. In recent years, electric power markets become more deregulated and competitive. The power system players are concerned with maximizing a profit while minimizing a risk in the power markets. To improve the accuracy of load forecasting model, it is a key to predict the weather conditions of input variables precisely. In other words, it is meaningful to consider the uncertainty of the predicted temperature in short-term load forecasting. The proposed method aims at extending temperature forecasting for the average point into that for the posterior distribution to handle the uncertainty of temperature forecasting. The proposed method is successfully applied to real data of temperature in Tokyo. A comparison is made between the proposed and the conventional methods such as MLP (multi-layered perceptron), RBFN (radial basis function network) and SVR (support vector regression).
Keywords :
Gaussian processes; load forecasting; power markets; power system economics; Gaussian process; electric load forecasting; electric power markets; multilayered perceptron; power system; radial basis function network; support vector regression; temperature forecasting; Economic forecasting; Gaussian processes; Kernel; Load forecasting; Load modeling; Power markets; Power system modeling; Temperature distribution; Uncertainty; Weather forecasting; Artificial Neural Networks; Gaussian Process; Kernel machines; Load forecasting; Temperature forecasting; Time series analysis;
fLanguage :
English
Publisher :
ieee
Conference_Titel :
TENCON 2009 - 2009 IEEE Region 10 Conference
Conference_Location :
Singapore
Print_ISBN :
978-1-4244-4546-2
Electronic_ISBN :
978-1-4244-4547-9
Type :
conf
DOI :
10.1109/TENCON.2009.5396073
Filename :
5396073
Link To Document :
بازگشت