Using a Combined Method to Forecasting Electricity Demand

Abstract:

In electric market, accurate electricity demand forecasting is often needed. Because electricity demand forecasting has become needful for creators and purchasers in the electric markets at present. But in electricity demand forecasting, noise signals, caused by various unstable factors, often corrupt demand series. In order to seek accurate demand forecasting methods, this article proposed a new combined electric load forecasting method (WSENN) which based on Wavelet Transform (WT), Seasonal Adjustment (SA) and Elman Neural Network (ENN) to forecast electricity demand. The effectiveness of WSENN is tested by applying the data from New South Wales (NSW) of Australia. Experimental results demonstrate that the WSENN model can offer more precise results than other methods that had mentioned in other literatures.

• Periodical: Applied Mechanics and Materials (Volume 678)
• Pages: 120-125
• DOI: https://doi.org/10.4028/www.scientific.net/AMM.678.120
• Online since: October 2014
• Authors: Xiang Quan Gui*, Li Li, Peng Shou Xie, Jie Cao
• Keywords: Electricity Demand Forecasting, Elman Neural Networks, Seasonal Adjustment, Wavelet Transform (WT)

References

[1] D.C. Li, C.J. Chang, C.C. Chen, W.C. Chen. Forecasting short-term electricity consumption using the adaptive grey-based approach—An Asian case [J]. Omega, 40(6), 767-773 (2012).

DOI: 10.1016/j.omega.2011.07.007

[2] L.C. Hsu. Using improved grey forecasting models to forecast the output of opto-electronics industry [J]. Expert Systems with Applications. 38(11), 13879-13885 (2011).

DOI: 10.1016/j.eswa.2011.04.192

[3] A. Kheirkhah, A. Azadeh, M. Saberi, A. Azaron, H. Shakouri. Improved estimation of electricity demand function by using of artificial neural network, principal component analysis and data envelopment analysis [J]. Computers & Industrial Engineering. 64(1), 425-441 (2013).

DOI: 10.1016/j.cie.2012.09.017

[4] P.C. Chang, C.Y. Fan, J.J. Lin. Monthly electricity demand forecasting based on aweighted evolving fuzzy neural network approach [J]. International Journal of Electrical Power & Energy Systems. 33(1), 17-27 (2011).

DOI: 10.1016/j.ijepes.2010.08.008

[5] I. Moghram, S. Rahman. Analysis and evaluation of five short-term load forecasting techniques [J]. IEEE Transactions on Power Systems. 4(4), 1484-1491 (1989).

DOI: 10.1109/59.41700

[6] Subrahmanya N, Shin YC. Constructive training of recurrent neural networks using hybrid optimization. Neurocomputing2010; 73: 2624–31.

DOI: 10.1016/j.neucom.2010.05.012

[7] Bashir ZA, El-Hawary ME. Applying wavelets to short-term load forecasting using PSO-based neural networks. IEEE Trans Power Syst 2009; 24(1): 20–7.

DOI: 10.1109/tpwrs.2008.2008606

[8] X. Tong, Z. Wang, H. Yu, A research using hybrid RBF/Elman neural networks for intrusion detection system secure model, Computer Physics Communications 180(10) (2009) 1795–1801.

DOI: 10.1016/j.cpc.2009.05.004

[9] S. -Y. Chen, F. -J. Lin, K. -K. Shyu, Direct decentralized neural control for nonlinear MIMO magnetic levitation system, Neurocomputing 72 (13 5) (2009) 3220–3230.

DOI: 10.1016/j.neucom.2009.02.009

[10] H. -W. Ge, F. Qian, Y. -C. Liang, W. -l. Du, L. Wang, Identification and control of nonlinear systems by a dissimilation particle swarm optimization-based Elman neural network, Nonlinear Analysis: Real World Applications 9 (4) (2008) 1345–1360.

DOI: 10.1016/j.nonrwa.2007.03.008