Meteorological Factors Considered Load Decoupling Forecasting Techniques

Abstract:

In this paper, a similar historical meteorological data search technique was put forward. This method took the weather forecasting data as clustering center, found those days that had the similarity weather factors, and then decoupled these loads into secular trend load and meteorological load as sample data for load forecasting. This method can improve the similarity of the loads between forecast day and sample days. Simulation results showed that these methods are valid and can make the load forecast more precision.

• Periodical: Advanced Materials Research (Volumes 354-355)
• Pages: 922-926
• DOI: https://doi.org/10.4028/www.scientific.net/AMR.354-355.922
• Online since: October 2011
• Authors: Yi Xiong Jin
• Keywords: Linear Regression, Load Decoupling, Load Forecasting, Meteorological Factors, None-Linear Recession

References

[1] Taylor JamesW, Roberto Buizza. Neural network load forecasting with weather ensemble predictions [J]. IEEE Transaction on Power Systems, 2001, 17(3) : 626-632.

DOI: 10.1109/tpwrs.2002.800906

[2] HE Rong, ZENG Gang, YAO Jian-gang, et.al. Application of Weather Sensitivity Neural Network Model in Short-term Load Forecasting on Area [J]. Automation of Electric Power Systems, 2001,25(9): 32-35, 52. In Chinese

[3] Yang Zhengling, Tian Yong, Lin Kongyuan. Application of multi-step regression considering climate factors in method synthesizing double period s and chaotic components to short term load forecasting [J]. Power System Technology, 2004, 28(12) : 20-24. In Chinese

[4] KANG Chong-qing, ZHOU An-shi, WANG Peng, et al. Impact Analysis of Hourly Weather Factors in Short-term Load Forecasting and Its Processing Strategy [J]. Power System Technology, 2006, 30(7): 5-10. In Chinese

[5] Qin Haichao, Wang Wei, Zhou Hui. Short-term electric load forecast by inducting human body amenity [J]. Journal of Electric Power, 2006, 21(2): 143-145. In Chinese

[6] HE Jing, WEI Gang, XIONG Ling-ling. Fuzzy Improvement of Linear Regression Analysis for Load Forecasting [J]. East China Electric Power, 2003,( 11): 21-23. In Chinese

[7] Nima Amjady. Short-term hourly load forecasting using time-series modeling with peak load estimation capability [J]. IEEE Transaction on Power Systems, 2001, 16(3) : 498-505.

DOI: 10.1109/59.932287

[8] Zhang Lin, Liu Xianshan, Yin Hejun. Application of support vector machines based on time sequence in power system load forecasting [J]. Power System Technology, 2004, 28(19): 38-41. In Chinese

[9] Cao Guojian, Huang Chun, Long Hui et at. Load forecasting based on improved GM(1,1) Model [J]. Power System Technology, 2004, 28(13) : 50-53. In Chinese

[10] Yu Jianming, Yan Fei, Yang Wenyu et at. Gray variable weight combination model for middle and load term load forecasting [J]. Power System Technology, 2005, 29(17): 26-29. In Chinese

[11] Zhou Dianmin, Guan Xiaohong,Sun Jie, Huang Yong. A short-term load forecasting system based on BP artificial neural network [J]. Power System Technology, 2002, 26(2): 10-13, 18. In Chinese