基于Relief相关性特征提取和微分进化支持向量机的短期电价预测

Abstract
Figure/Table
References
Related Citation (15)

Download: PDF (883 KB) HTML (1 KB)
Export: BibTeX | EndNote (RIS)

Abstract To avoid the unreasonable inputs selection for electricity price forecasting, based on the improvements of traditional Relief algorithm, a novel feature selection method is proposed in this paper. Moreover, correlation analysis is used to eliminate redundant features. Based on the selected features, the price forecasting model is established by using support vector machine(SVM), and differential evolution algorithm is employed to determine the best parameters of SVM. Simulation results based on the real electricity price data obtained from PJM electric power market demonstrate the proposed feature selection method can extract features that reflect the short-run and periodical characters of electricity price, and furthermore, the SVM optimized by differential evolution algorithm can achieve better forecasting results than BP neural network and common SVM.

Key words： electricity price forecasting relief algorithm correlation analysis differential evolution algorithm support vector machine

Received: 10 May 2011 Published: 27 November 2013

PACS:

TM734

	Service

	E-mail this article
	Add to my bookshelf
	Add to citation manager
	E-mail Alert
	RSS
	Articles by authors
	Peng Chunhua
	Liu Gang
	Xiang Longyang

Cite this article:

Peng Chunhua,Liu Gang,Xiang Longyang. Short-Term Electricity Price Forecasting Using Relief-Correlation Analysis Based on Feature Selection and Differential Evolution Support Vector Machine[J]. Transactions of China Electrotechnical Society, 2013, 28(1): 277-284.

URL:

http://dgjsxb.ces-transaction.com/EN/ OR http://dgjsxb.ces-transaction.com/EN/Y2013/V28/I1/277

[1] Shahidehpour M, Yamin H, Li Z. Market operations in electric power systems[M]. John Wiley & Sons, Inc., 2002.
[2] 周明, 严正, 倪以信, 等. 含误差预测校正的ARIMA电价预测新方法[J]. 中国电机工程学报, 2004, 24(12): 63-68.
Zhou Ming, Yan Zheng, Ni Yixin, et al. A novel ARIMA approach on electricity price forecasting with the improvement of predicted error[J]. Proceedings of the CSEE, 2004, 24(12): 63-68
[3] Francisco J N, Javier C, Antonio J C. Forecasting next-day electricity prices by time series models[J]. IEEE Transactions on Power Systems, 2002, 17(2): 342-348.
[4] Contreras J, Espinola R, Nogales F J, et al. ARIMA models to predict next-day electricity prices[J]. IEEE Transactions on Power Systems, 2003, 18(3): 1014- 1020.
[5] Raquel G, Luis M R, Antonia G. Forecasting of electricity prices with neural networks[J]. Energy Conversion and Management, 2006, 47(13-14), 1770-1778.
[6] Raúl P, José P, Alberto G, et al. Forecasting next-day price of electricity in the Spanish energy market using artificial neural networks[J]. Engineering Applications of Artificial Intelligence, 2008, 21(1): 53-62.
[7] Hong Y Y, Lee C F. A neuro-fuzzy price forecasting approach in deregulated electricity markets[J]. Electric Power Systems Research, 2005, 73(2): 151-157.
[8] Lin W M, Gow H J, Tsai M T. Electricity price forecasting using enhanced probability neural network[J]. Energy Conversion and Management, 2010, 51(12): 2707-2714.
[9] Gao C W, Bompard E, Napoli R. Price forecast in the competitive electricity market by support vector machine[J]. Physica A: Statistical Mechanics and its Applications, 2007, 382(1): 98-113.
[10] Amjady N, Daraeepour A. Design of input vector for day-ahead price forecasting of electricity markets[J]. Expert Systems with Applications, 2009, 36(10): 12281-12294.
[11] Rocha Reis AJ, Alves da Silva AP. Feature extraction via multi-resolution analysis for short-term load forecasting[J]. IEEE Transactions on Power Systems, 2005, 20(1): 189-198.
[12] Sun Y J. Iterative Relief for feature weighting: algorithms, theories and applications[J]. IEEE Transactions on Pattern Analysis and Machine Intelligence, 2007, 29(6): 1035-4051.
[13] Pao H T. Forecasting electricity market pricing using artiﬁcial neural networks[J]. Energy Conversion Management, 2007, 48(3): 907-912.
[14] Corts C, Vapnik V. Support vector networks[J]. Machine Learning, 1995, 20(3): 273-297.
[15] 牛东晓, 刘达, 陈广娟. 基于遗传优化的支持向量机小时负荷滚动预测[J]. 电工技术学报, 2007, 22(6): 149-153.
Liu X D, Liu D, Chen G J. Support vector machine models optimized by genetic algorithm for hourly load rolling forecasting[J]. Transactions of China Electrotechnical Society, 2007, 22(6): 143-153.
[16] Yang G Y, Dong Z Y, Wong K P. A modified differential evolution algorithm with fitness sharing for power system planning[J]. IEEE Transactions on Power Systems, 2008, 23(2): 514-522.
[17] 唐贤伦, 庄陵, 胡向东. 铁水硅含量的混沌粒子群支持向量机预报方法[J]. 控制理论与应用, 2009, 26(8): 838-842.
Tang X L, Zhuang L, Hu X D. The support vector regression based on the chaos particle swarm optimization algorithm for the prediction of silicon content in hot metal[J]. Control Theory & Applications, 2009, 26(8): 838-842.