Middle – Long Electric Power Load Forecasting Based on GM(1,1) and Support Vector Machine

Abstract:

Due to the variety and the randomicity of its influencing factors, the electricity demand forecasting is a difficult problem for a long time. In order to improve the forecast accuracy, the paper proposes a new load forecast model based on GM(1,1) and support vector machine. First, the GM(1,1) is used to forecast the load data in the model. And then according to factors and historical load vector, support vector machine load forecast model is established to forecast the residuals of GM(1,1) and modified the forecast results of GM(1,1). Case analysis shows that the forecast method is suitable and effective, improving prediction precision compared with GM(1,1) and support vector machine, and has better utility value in mid-log term load forecast.

• Periodical: Applied Mechanics and Materials (Volumes 44-47)
• Pages: 2983-2987
• DOI: https://doi.org/10.4028/www.scientific.net/AMM.44-47.2983
• Online since: December 2010
• Authors: Xi Miao Jia, Guo Ping Song, Ting Wang, Feng Kong
• Keywords: Error Correction, GM(1,1), Load Forecasting, Support Vector Machine (SVM)

References

[1] He-rui CUI, A long-term electrical power load forecasting model based on grey feed-back modification, Proc. of the Seventh International Conference on Machine Learning and Cybernetics, Kunming, July (2008).

DOI: 10.1109/icmlc.2008.4620770

[2] Park DC, El-Sharkawi MA, Marks II RJ, Atlas LE, Damborg MJ, Electric load forecasting using an artificial neural network, IEEE Trans Power System, 6, 442–9, (1991).

DOI: 10.1109/59.76685

[3] C.C. Hsu, C.Y. Chen, Regional load forecasting in Taiwan: applications of artificial neural networks, Energy Convers. Manage, vol. 44(2003), p.1941–(1949).

DOI: 10.1016/s0196-8904(02)00225-x

[4] Shao-mei Yang, Qian Zhu, Research on Comparison and Application of SVM and FNN Algorithm", Proc. of 4th International Conference on Wireless Communications, Networking and Mobile Computing, 2008. WiCOM , 08.

DOI: 10.1109/wicom.2008.1273

[5] ZHANG Xue-jun，CHEN Gang, ZHOU Jie, MA Ai-jun，etc . Medium and long-term load forecast based on PSO-RSVR, Power System Protection and Control, vol. 37(2008), pp.77-81.

[6] XIAO Zhi-gang, XU Hong, YANG Su-lin, etc. Support vector machine based on balance strategy applying in forecast mid—long term load of electrical power system, JOURNAL OF AGRICULTURAL UNIVERSITY OF HEBEI, vol. 29(2006), pp.123-126.

[7] Rui-ming Fang, Theory and Applied Analysis of Support Vector Machine, China Electric Power Press, Beijing, (2007).

[8] Jian Zhang, Power System Load Models and Identification, China Electric Power Press, Beijing, (2007).