Daily Load Forecasting Based on RBF-ARX Model

Abstract:

Short-term load forecasting plays a vital role for the power system’s safe operation and production arrangements. This paper regards electric load forecasting as a nonlinear time series prediction problem, and establishes the electric load autoregressive prediction model (ARX Model) based on historical load data, approaching ARX model parameters with RBF neural network, estimating model parameters with using a Structured Nonlinear Parameters Optimization Method (SNPOM), proposing cycle prediction method for short-term electric load forecasting. Experimental results show that the method has higher prediction accuracy for short-term electric load forecasting. Keywords: Short-term load forecasting; time series; RBF-ARX model; cycle forecasting; structured nonlinear parameter optimization method

• Periodical: Applied Mechanics and Materials (Volume 623)
• Pages: 48-56
• DOI: https://doi.org/10.4028/www.scientific.net/AMM.623.48
• Online since: August 2014
• Authors: Hai Liang Hou*, Jie Chen, Miao Ping Sun, Bin Jun Cai
• Keywords: Cycle Forecasting, RBF-ARX Model, Short-Term Load Forecasting, Structured Nonlinear Parameter Optimization Method, Time Series

References

[1] LIAO Ni-huan, HU Zhi-hong, etal. Review of the short-term load forecasting methods of electric power system [J]. Power System Protection and Control, 2011, 39(1): 147-152.

[2] KANG Chong-qing, ZHOU An-shi, etal. Impact Analysis of Hourly Weather Factors in Short-Term Load Forecasting and Its Processing Strategy [J]. Power System Technology, 2006(4): 5-10.

[3] NIU Dong-xiao, GU Zhi-hong, etal. Study on Forecasting Approach to Short-term Load of SVM Based on Data Mining [J]. Proceeding of CSEE, 2006, 9(18): 6-12.

[4] NIU Dongxiao, LIU Da, etal. Support Vector Machine Models Optimized by Genetic Algorithm for Hourly Load Rolling Forecasting [J]. Transaction of China Electrotechnical Society, 2007, 6(22): 148-153.

[5] YANG Jing-fei, CHENG Hao-zhong. Application of SVM to Power System Short-term Load Forecast [J]. Electric Power Automation Equipment, 2004, 2(2): 30-32.

[6] LI Canbing, LI Xiaohui, etal. A Novel Algorithm of Selecting Similar Days for Short-term Power Load Forecasting [J], Electric Power Automation Equipment, 2008, 5(9): 69-73.

[7] LIU Xu, LUO Dian-sheng, etal. Short-Term Load Forecasting Based on Load Decomposition and Hourly Weather Factors [J]. Power System Technology, 2009, 6(12): 94-100.

[8] WEI Zhiyuan, WANG Liming, etal. A ultra-short term forecasting method based on autogression[J]. Relay, 2007, 35(1): 77-81.

[9] ZHAO Yuan, ZHANG Xia-fei, XIE Kai-gui. Application of Nonparametric Auto-regression to Short-term Load Forecasting [J]. High Voltage Engineering, 2011, 2(37): 429-435.

[10] Hui Peng, Tohru Ozaki etcl. A Parameter Optimization Method for Radial Basis Function Type Models[J]. IEEE Transactions on Neural Networks, vol. 14, no. 2, pp.432-438, (2003).

DOI: 10.1109/tnn.2003.809395

[11] HOU Hai-liang, PENG Hui. Application of new ARX model to identification for magnetic levitation control system [J]. Computer Engineering and Applications, 2007, 43(29): 196-200, 213.

[12] M. B. Priestley. State dependent models: A general approach to nonlinear time series analysis[J]. J. Time Series Anal., 1980(1): 57–71.

DOI: 10.1111/j.1467-9892.1980.tb00300.x

[13] J. Vesin. An amplitude-dependent autoregressive signal model based on a radial basis function expansion [J]. in Proc. Int. Conf. Acoustics, Speech, Signal Processing, 1993, 3: 129–132.

DOI: 10.1109/icassp.1993.319452

[14] Hui Peng, Kazushi Nakano and Hideo Shioya. Nonlinear Predictive Control Using Neural Nets-Based Local Linearization ARX Model—Stability and Industrial Application [J]. IEEE Transaction on Control Systems Technology, 2007, 1(15): 130-143.

DOI: 10.1109/tcst.2006.883339

[15] D. Marquardt. An Algorithm for Least-squares Estimation of Nonlinear parameters [J]. SLAM J. Appl. Math., 1963(11): 431-441.

[16] Z. Shi, Y. Tamura, and T. Ozaki. Nonlinear Time Series Modeling With The Radial Basis Function-Based State-Dependent Autoregressive Model [J]. Int. J. Syst. Sci., vol. 30, p.717–727, (1999).

DOI: 10.1080/002077299292038

[17] S. McLoone, M. D. Brown, G. Irwin, and G. Lightbody. A hybrid linear/nonlinear training algorithm for feedforward neural networks [J], IEEE Trans. Neural Networks, 1998, 7(9): 669–684.

DOI: 10.1109/72.701180