A Hybrid Forecasting Model Based on Bivariate Division and a Backpropagation Artificial Neural Network Optimized by Chaos Particle Swarm Optimization for Day-Ahead Electricity Price

Abstract and Applied Analysis

Research Article

Jianzhou Wang¹  Jie Wu¹  Feng Liu¹  Zhilong Wang² 

[1] School of Mathematics and Statistics, Lanzhou University, Lanzhou 730000, China, lzu.edu.cn;Department of Basic Courses, Lanzhou Institute of Technology, Lanzhou 730050, China

Others  :  1319655
DOI  :  10.1155/2014/249208

 received in 2014-04-02, accepted in 2014-05-19,  发布年份 2014

【 摘 要 】

In the electricity market, the electricity price plays an inevitable role. Nevertheless, accurate price forecasting, a vital factor affecting both government regulatory agencies and public power companies, remains a huge challenge and a critical problem. Determining how to address the accurate forecasting problem becomes an even more significant task in an era in which electricity is increasingly important. Based on the chaos particle swarm optimization (CPSO), the backpropagation artificial neural network (BPANN), and the idea of bivariate division, this paper proposes a bivariate division BPANN (BD-BPANN) method and the CPSO-BD-BPANN method for forecasting electricity price. The former method creatively transforms the electricity demand and price to be a new variable, named DV, which is calculated using the division principle, to forecast the day-ahead electricity by multiplying the forecasted values of the DVs and forecasted values of the demand. Next, to improve the accuracy of BD-BPANN, chaos particle swarm optimization and BD-BPANN are synthesized to form a novel model, CPSO-BD-BPANN. In this study, CPSO is utilized to optimize the initial parameters of BD-BPANN to make its output more stable than the original model. Finally, two forecasting strategies are proposed regarding different situations.

【 授权许可】

CC BY   
Copyright © 2014 Zhilong Wang et al. 2014

【 图 表 】

Figure 1

Figure 2

Figure 3

Figure 4

Figure 5

Figure 6

Figure 7

Figure 8

Figure 9

Figure 10

Figure 11

Figure 12

Figure 13

【 参考文献 】

• [1]S. Anbazhagan, N. Kumarappan. (2012). Day-ahead deregulated electricity market price classification using neural network input featured by DCT. International Journal of Electrical Power and Energy Systems.37(1):103-109. DOI: 10.1016/j.ijepes.2011.12.011.
• [2]S. K. Aggarwal, L. M. Saini, A. Kumar. (2009). Electricity price forecasting in deregulated markets: a review and evaluation. International Journal of Electrical Power and Energy Systems.31(1):13-22. DOI: 10.1016/j.ijepes.2011.12.011.
• [3]H.-T. Pao. (2007). Forecasting electricity market pricing using artificial neural networks. Energy Conversion and Management.48(3):907-912. DOI: 10.1016/j.ijepes.2011.12.011.
• [4]X. R. Li, C. W. Yu, S. Y. Ren, C. H. Chiu. et al.(2013). Day-ahead electricity price forecasting based on panel cointegration and particle filter. Electric Power Systems Research.95:66-76. DOI: 10.1016/j.ijepes.2011.12.011.
• [5]J. Zhang, Z. Tan, S. Yang. (2012). Day-ahead electricity price forecasting by a new hybrid method. Computers and Industrial Engineering.63(3):695-701. DOI: 10.1016/j.ijepes.2011.12.011.
• [6]Z. Tan, J. Zhang, J. Wang, J. Xu. et al.(2010). Day-ahead electricity price forecasting using wavelet transform combined with ARIMA and GARCH models. Applied Energy.87(11):3606-3610. DOI: 10.1016/j.ijepes.2011.12.011.
• [7]N. Amjady, F. Keynia. (2009). Day-ahead price forecasting of electricity markets by a new feature selection algorithm and cascaded neural network technique. Energy Conversion and Management.50(12):2976-2982. DOI: 10.1016/j.ijepes.2011.12.011.
• [8]V. Vahidinasab, S. Jadid, A. Kazemi. (2008). Day-ahead price forecasting in restructured power systems using artificial neural networks. Electric Power Systems Research.78(8):1332-1342. DOI: 10.1016/j.ijepes.2011.12.011.
• [9]A. I. Arciniegas, I. E. Arciniegas Rueda. (2008). Forecasting short-term power prices in the Ontario Electricity Market (OEM) with a fuzzy logic based inference system. Utilities Policy.16(1):39-48. DOI: 10.1016/j.ijepes.2011.12.011.
• [10]S. Chakravarty, P. K. Dash. (2011). Dynamic filter weights neural network model integrated with differential evolution for day-ahead price forecasting in energy market. Expert Systems with Applications.38(9):10974-10982. DOI: 10.1016/j.ijepes.2011.12.011.
• [11]S. Bordignon, D. W. Bunn, F. Lisi, F. Nan. et al.(2013). Combining day-ahead forecasts for British electricity prices. Energy Economics.35:88-103. DOI: 10.1016/j.ijepes.2011.12.011.
• [12]H. Shayeghi, A. Ghasemi. (2013). Day-ahead electricity prices forecasting by a modified CGSA technique and hybrid WT in LSSVM based scheme. Energy Conversion and Management.74:482-491. DOI: 10.1016/j.ijepes.2011.12.011.
• [13]S. Anbazhagan, N. Kumarappan. (2014). Day-ahead deregulated electricity market price forecasting using neural network input featured by DCT. Energy Conversion and Management.78:711-719. DOI: 10.1016/j.ijepes.2011.12.011.
• [14]D. Niu, D. Liu, D. D. Wu. (2010). A soft computing system for day-ahead electricity price forecasting. Applied Soft Computing Journal.10(3):868-875. DOI: 10.1016/j.ijepes.2011.12.011.
• [15]W.-M. Lin, H.-J. Gow, M.-T. Tsai. (2010). An enhanced radial basis function network for short-term electricity price forecasting. Applied Energy.87(10):3226-3234. DOI: 10.1016/j.ijepes.2011.12.011.
• [16]X. Yan, N. A. Chowdhury. (2013). Mid-term electricity market clearing price forecasting: a hybrid LSSVM and ARMAX approach. International Journal of Electrical Power and Energy Systems.53(1):20-26. DOI: 10.1016/j.ijepes.2011.12.011.
• [17]X. Yan, N. A. Chowdhury. (2014). Mid-term electricity market clearing price forecasting: a multiple SVM approach. International Journal of Electrical Power and Energy Systems.58:206-214. DOI: 10.1016/j.ijepes.2011.12.011.
• [18]W.-M. Lin, H.-J. Gow, M.-T. Tsai. (2010). Electricity price forecasting using enhanced probability neural network. Energy Conversion and Management.51(12):2707-2714. DOI: 10.1016/j.ijepes.2011.12.011.
• [19]D. Singhal, K. S. Swarup. (2011). Electricity price forecasting using artificial neural networks. International Journal of Electrical Power and Energy Systems.33(3):550-555. DOI: 10.1016/j.ijepes.2011.12.011.
• [20]B. D. Rodrigues, M. J. Stevenson. (2013). Takeover prediction using forecast combinations. International Journal of Forecasting.29(4):628-641. DOI: 10.1016/j.ijepes.2011.12.011.
• [21]N. An, W. Zhao, J. Wang, D. Shang. et al.(2013). Using multi-output feedforward neural network with empirical mode decomposition based signal filtering for electricity demand forecasting. Energy.49(1):279-288. DOI: 10.1016/j.ijepes.2011.12.011.
• [22]X. W. Li, S. J. Cho, S. T. Kim. (2014). Combined use of BP neural network and computational integral imaging reconstruction for optical multiple-image security. Optics Communications.315:147-158. DOI: 10.1016/j.ijepes.2011.12.011.
• [23]R. Hecht-Nelson. Kolmogorov's mapping neural network existence theorem. :11-13. DOI: 10.1016/j.ijepes.2011.12.011.
• [24]Z.-H. Guo, J. Wu, H.-Y. Lu, J.-Z. Wang. et al.(2011). A case study on a hybrid wind speed forecasting method using BP neural network. Knowledge-Based Systems.24(7):1048-1056. DOI: 10.1016/j.ijepes.2011.12.011.
• [25]J. Wang, Z. Sheng, B. Zhou, S. Zhou. et al.(2014). Lightning potential forecast over Nanjing with denoised sounding-derived indices based on SSA and CS-BP neural network. Atmospheric Research.137:245-256. DOI: 10.1016/j.ijepes.2011.12.011.