Combination Regression and Neural Network for Short Term Load Forecasting

Abstract:

The forecasting of gas demand has become one of the major research fields in gas engineering. Gas demand possesses dual property of increasement and seasonal fluctuation simultaneously, so it makes gas demand variation possess complex nonlinear combined character. Accurately forecast were essential part of an efficient gas system planning and operation. In this paper, a new forecasting model which named regression combined neural network is put forward. In this approach we used regression to model the trend and used neural network for calculating predicted values and errors. Taking the advantages of regression analysis and artificial neural network, the model improves the forecasting accuracy of power demand obviously. The results indicate that the model is effective and feasible for load forecasting.

• Periodical: Advanced Materials Research (Volumes 690-693)
• Pages: 2787-2795
• DOI: https://doi.org/10.4028/www.scientific.net/AMR.690-693.2787
• Online since: May 2013
• Authors: Qing Ming Chen, Xiao Zhong Xu, Nan Zeng
• Keywords: Detrended Data, Neural Network (NN), Regression, Short Term Load Forecast

References

[1] Magnano L, Boland JW. Generation of synthetic sequences of electricity demand: application in south Australia. Energy 2007;32:2230e43.

DOI: 10.1016/j.energy.2007.04.001

[2] Soares LJ, Souza LR. Forecasting electricity demand using generalized long memory. Int J Forecast 2006;22:17e28.

[3] Wang JZ, Chi DZ, Wu J, Lu HY. Chaotic time series method combined with particle swarm optimization and trend adjustment for electricity demand forecasting. Expert Syst Appl 2011;38(7):8419e29.

DOI: 10.1016/j.eswa.2011.01.037

[4] Ramanathan R, Engle R, Granger CWJ, Vahid-Araghi F, Brace C. Short-run forecasts of electricity loads and peaks. Int J Forecast 1997;13:161e74.

DOI: 10.1016/s0169-2070(97)00015-0

[5] Thatcher MJ. Modelling changes to electricity demand load duration curves as a consequence of predicted climate change for Australia. Energy 2007;32:1647e59.

DOI: 10.1016/j.energy.2006.12.005

[6] Bianco V, Manca O, Nardini S. Electricity consumption forecasting in Italy using linear regression models. Energy 2009;34(9):1413e21.

DOI: 10.1016/j.energy.2009.06.034

[7] Goia A, May C, Goia GF. Functional clustering and linear regression for peak load forecasting. Int J Forecast 2010;26(4):700e11.

DOI: 10.1016/j.ijforecast.2009.05.015

[8] Taylor J. Short-term electricity demand forecasting using double seasonal exponential smoothing. J Oper Res Soc 2003;54:799e805.

DOI: 10.1057/palgrave.jors.2601589

[9] Harvey A, Koopman SJ. Forecasting hourly electricity demand using timevarying splines. J Am Stat Assoc 1993;88:1228e36.

[10] Pao HT. Forecasting energy consumption in Taiwan using hybrid nonlinear models. Energy 2009;34(10):1438e46.

DOI: 10.1016/j.energy.2009.04.026

[11] Zhu S, Wang J, Zhao W, Wang J. A seasonal hybrid procedure for electricity demand forecasting in China. Appl Energy 2011;88:3807e15.

DOI: 10.1016/j.apenergy.2011.05.005

[12] Wang H, Zhu S, Zhao J, Li G. An improved combined model for the electricity demand forecasting. Int Conf Comput Inf Sci; 2010:108e11. IEEEXplore.

[13] Azadeh A, Ghaderi SF, Sohrabkhani S. A simulated-based neural network algorithm for forecasting electrical energy consumption in Iran. Energy Policy 2008;36(7):2637e44.

DOI: 10.1016/j.enpol.2008.02.035

[14] Chang PC, Fan CY, Lin JJ. Monthly electricity demand forecasting based on a weighted evolving fuzzy neural network approach. Int J Electr Power Energ Syst 2011;33(1):17e27. Goia A, May C, Goia GF. Functional clustering and linear regression for peak load forecasting. Int J Forecast 2010;26(4):700e11.

DOI: 10.1016/j.ijforecast.2009.05.015

[15] Metaxiotis K, Kagiannas A, Askounis D, Psarras J. Artificial intelligence in short term electrical load forecasting: a state-of-the-art survey for the researcher.Energy Convers Manage 2003;44:1525e34.

DOI: 10.1016/s0196-8904(02)00148-6

[16] Azadeh A, Ghaderi F, Tarvardiyan S. Integration of artificial neural network and genetic algorithm to predict electricity energy consumption. Appl Math Comput 2007;186(2):1731e41.

[17] Dash PK, Liew AC, Rahman S, Ramakrishna G. Building a fuzzy expert system for electric load forecasting using a hybrid neural network. Expert Syst Appl 1995;9(3):407e21.

DOI: 10.1016/0957-4174(95)00013-y

[18] Kucukali S, Baris K. Turkey's short-term gross annual electricity demand forecast by fuzzy logic approach. Energy Policy 2010;38(5):2438e45.

DOI: 10.1016/j.enpol.2009.12.037

[19] Lendasse A, Lee J, Wertz V, Verleysen M. Forecasting electricity consumption using nonlinear projection and self-organizing maps. Neuro computing 2002;48(1e4):299e311.

DOI: 10.1016/s0925-2312(01)00646-4

[20] Manera M, Marzullo A. Modelling the load curve of aggregate electricity consumption using principal components. Environ Model Software 2005;20:1389e400.

DOI: 10.1016/j.envsoft.2004.09.019

[21] Deng JL. Introduction to grey systems. J Grey Syst 1989;1:1e24.

[22] Zhou P, Ang BW, Poh KL. A trigonometric grey prediction approach to forecasting electricity demand. Energy 2006;31(14):2839e47.

DOI: 10.1016/j.energy.2005.12.002

[23] Nguyen HT, Nabney IT. Short-term electricity demand and gas price forecasts using wavelet transforms and adaptive models. Energy 2010;35(9):3674e85.

DOI: 10.1016/j.energy.2010.05.013

[24] Hong W-C. Electric load forecasting by seasonal recurrent SVR (support vector regression) with chaotic artificial bee colony algorithm. Energy 2011;36(9):5568e78.

DOI: 10.1016/j.energy.2011.07.015

[25] Qamber IS. Maximum annual load estimation and network strengthening for the kingdom of Bahrain. Arab Gulf J Sci Res 2010;28(4):214e23.

DOI: 10.51758/agjsr-04-2010-0009

[26] Taylor JW, Menezes LM, McSharry PE. A comparison of univariate methods for forecasting electricity demand up to a day ahead. Int J Forecast 2006;22(1):1e16.

DOI: 10.1016/j.ijforecast.2005.06.006

[27] Min Jin, Xiang Zhou, Zhi M. Zhang, Manos M.Tentzeris. Short-term power load forecasting using grey correlation contest modeling. Expert Systems with Applications 39(2012) 773-779.

DOI: 10.1016/j.eswa.2011.07.072