Selection of Hidden Layer Neurons and Best Training Method for FFNN in Application of Long Term Load Forecasting

Singh, Navneet; Singh, Asheesh; Tripathy, Manoj

doi:10.2478/v10187-012-0023-9

Abstract

For power industries electricity load forecast plays an important role for real-time control, security, optimal unit commitment, economic scheduling, maintenance, energy management, and plant structure planning etc. A new technique for long term load forecasting (LTLF) using optimized feed forward artificial neural network (FFNN) architecture is presented in this paper, which selects optimal number of neurons in the hidden layer as well as the best training method for the case study. The prediction performance of proposed technique is evaluated using mean absolute percentage error (MAPE) of Thailand private electricity consumption and forecasted data. The results obtained are compared with the results of classical auto-regressive (AR) and moving average (MA) methods. It is, in general, observed that the proposed method is prediction wise more accurate.

References

ALFARESM, H. K.—NAZEERUDDIN, M.: Electric Load Forecasting: Literature Survey and Classification of Methods, Int. Jour. of Systems Sc. 33 No. 1 (2002), 23-34.10.1080/00207720110067421
Search in Google Scholar
HINOJOSA, V. H.—HOESE, A.: Short-Term Load Forecasting Using Fuzzy Inductive Reasoning and Evolutionary Algorithms, IEEE Trans. on Power Systems 25 No. 1, 565-574, Feb. 2010.10.1109/TPWRS.2009.2036821
Search in Google Scholar
ALFARES, H. K.—NAZEERUDDIN, M.: Electric Load Forecasting: Literature Survey and Classification Of Methods, Int. Jour. of Systems Science 33 No. 1 (Jan. 2002), 23-34.
Search in Google Scholar
HINOJOSA, V. H.—HOESE, A.: Short-Term Load Forecasting Using Fuzzy Inductive Reasoning and Evolutionary Algorithms, IEEE Trans. on Power Systems 25 No. 1 (Feb 2010), 565-574.10.1109/TPWRS.2009.2036821
Search in Google Scholar
HAGAN, M. T.—BEHR, S. M.: The Time Series Approach to Short Term Load Forecasting, IEEE Trans. on Power Systems PWRS-2 No. 3 (Aug 1987), 785-791.10.1109/TPWRS.1987.4335210
Search in Google Scholar
WANG, B.—TAI, N. L.—ZHAI, H. Q.—YE, J.—ZHU, J. D.—QI, L. B: A New ARMAX Model based on Evolutionary Algorithm and Particle Swarm Optimization for Short-Term Load Forecasting, Electric Power Systems Research 78 No. 10 (Oct 2008), 1679-1685.10.1016/j.epsr.2008.02.009
Search in Google Scholar
AGUIRRE, L. A.—RODRIGUES, D. D.—LIMA, S. T.—MARTINEZ, C. B.: Dynamical Prediction and Pattern Mapping in Short-Term Load Forecasting, Int. Jour. of Electrical Power & Energy Systems, 30 No. 1 (Jan 2008), 73-82.10.1016/j.ijepes.2007.11.001
Search in Google Scholar
SRINIVASAN, D.: Energy Demand Prediction using GMDH Networks, Neurocomputing 72 No. 1-3 (Dec 2008), 625-629.10.1016/j.neucom.2008.08.006
Search in Google Scholar
AZADEH, A.—SABERI, M.—GHADERI, S. F.—GITIFOROUZ, A.—EBRAHIMIPOUR, V.: Improved Estimation of Electricity Demand Function by Integration of Fuzzy System and Data Mining Approach, Energy Conversion and Management 49 No. 8 (Aug 2008.), 2165-2177.10.1016/j.enconman.2008.02.021
Search in Google Scholar
HAHN, H.—MEYER-NIEBERG, S.—PICKL, S.: Electric Load Forecasting Methods: Tools for Decision making, European Journal of Operational Research 199 No. 3 (Dec 2009), 902-907.10.1016/j.ejor.2009.01.062
Search in Google Scholar
PAPPAS, S. S.—EKONOMOU, L.—KARAMPELAS, P.—KARAMOUSANTAS, D. C.—KATSIKAS, S. K.—CHATZARAKIS, G. E.—SKAFIDAS, P. D.: Electricity Demand Load Forecasting of the Hellenic Power System using an ARMA Model, Electric Power Systems Research 80 No. 3 (Mar 2010), 256-264.10.1016/j.epsr.2009.09.006
Search in Google Scholar
QI—WU: A Hybrid-Forecasting Model based on Gaussian Support Vector Machine and Chaotic Particle Swarm Optimization, Expert Systems with Applications: An Int. Jour. 37 No. 3 (Mar 2010), 2388-2394.10.1016/j.eswa.2009.07.057
Search in Google Scholar
DANESHI, H.—DANESHI, A.: Price Forecasting in Deregulated Electricity Markets - A Bibliographical Survey, Third Int. Conf. on Electric Utility Deregulation and Restructuring and Power Technologies, DRPT 2008, 6-9 Apr 2008, pp. 657-661.10.1109/DRPT.2008.4523487
Search in Google Scholar
AZADEH, A—GHADERI, S. F.—SOHRABKHANI, S.: Annual Electricity Consumption Forecasting by Neural Network in High Energy Consuming Industrial Sectors, Energy Conversion and Management 49 No. 8 (Aug 2008), 2272-2278.10.1016/j.enconman.2008.01.035
Search in Google Scholar
DANESHI, H.—SHAHIDEHPOUR, M.—CHOOBBARI, A. L.: Long-Term Load Forecasting in Electricity Market, IEEE Int. Conf. on Electro/Inf. Tech. 2008, 18-20 May 2008, pp. 395-400.
Search in Google Scholar
DANESHI, H.—DANESHI, A.: Real Time Load Forecast in Power System, Third Int. Conf. on Electric Utility Deregulation and Restructuring and Power Technologies, DRPT 2008, 6-9 Apr 2008, pp. 689-695.10.1109/DRPT.2008.4523494
Search in Google Scholar
PINDORIYA, N. M.—SINGH, S. N.—SINGH, S. K.: Forecasting the Day-Ahead Spinning Reserve Requirement in Competitive Electricity Market, Power and Energy Society General Meeting - Conversion and Delivery of Electrical Energy in the 21st Century, IEEE, USA, 20-24 July 2008, pp. 1-8.10.1109/PES.2008.4596099
Search in Google Scholar
HINOJOSA, V. H.—HOESE, A.: Short-Term Load Forecasting using Fuzzy Inductive Reasoning and Evolutionary Algorithms, IEEE Trans. Power Syst. 25 No. 1 (Feb 2010), 565-574.10.1109/TPWRS.2009.2036821
Search in Google Scholar
PARKPOOM, S. J.—HARRISON, G. P.: Analyzing the Impact of Climate Change on Future Electricity Demand in Thailand, IEEE Trans. Power Syst. 23 No. 3 (Aug 2008).10.1109/TPWRS.2008.922254
Search in Google Scholar
DREZGA, I.—RAHMAN, S.: Input Variable Selection for ANN-Based Short-Term Load Forecasting, IEEE Tran. on Power Sys. 13 No. 4 (Nov 1998).10.1109/59.736244
Search in Google Scholar
AZADEH, A.—FAIZ, Z. S.: A Meta-Heuristic Framework for Forecasting Household Electricity Consumption, Applied Soft Computing 11 No. 1 (Jan 2011), 614-620.10.1016/j.asoc.2009.12.021
Search in Google Scholar
TSEKOURAS, G. J.—DIALYNAS, E. N.—HATZIARGYRIOU, N. D.—KAVATZA, S.: A Non-Linear Multivariable Regression Model for Midterm Energy Forecasting of Power Systems, Electric Power Systems Research 77 No. 12 (Oct 2007), 1560-1568.10.1016/j.epsr.2006.11.003
Search in Google Scholar
SULLIVAN, W. G.—CLAYCOMBE, W. W.: Fundamentals of Forecasting, Reston Publishing Company, Inc., Restan Virginia, 1977.
Search in Google Scholar
McCULLOCH, W. S.—PITTS, W.: Bulletin of Mathematical Biophysics 5 (1943), 115-133.
Search in Google Scholar
HAYKIN, S.: Neural Network: A comprehensive foundation, Prentice Hall of India, New Delhi, 1999.
Search in Google Scholar
SHRIVASTAVA, V.—MISRA, R. B.: A Novel Approach of Input Variable Selection for ANN Based Load Forecasting, Joint Int. Conf. on Power System Technology and IEEE Power India Conf., POWERCON 2008, 12-15 Oct 2008, pp. 1-5.10.1109/ICPST.2008.4745348
Search in Google Scholar
METHAPRAYOON, K.—LEE, W. J.—RASMIDDATTA, S.— LIAO, J. R.—ROSS, R. J.: Multistage Artificial Neural Network Short Term Load Forecasting Engine with Front End Weather Forecasting, IEEE Trans. on Industry Applications 43 No. 6 (Nov/Dec 2007), 1410-1416.10.1109/TIA.2007.908190
Search in Google Scholar
CHARYTONIUK, W.—CHEN, M. S.: Neural Network Design for Short Term Load Forecasting, Int. Conf. on Electric Utility Deregulation and Restructuring and Power Technologies, Proceedings DRPT 2000, 2000, pp. 554-561.
Search in Google Scholar
BEALE, M. H.—HAGAN, M. T.—DEMUTH, H. B.: Neural Network ToolboxTM 7 Users Guide, The Math Works, Inc., Natick, MA, Sep 2010.
Search in Google Scholar
AMJADY, N.—DARAEEPOUR, A.: Mixed Price and Load Forecasting of Electricity Markets by a New Iterative Prediction Method, Electric Power Systems Research 79 No. 9 (Sep 2009), 1329-1336.10.1016/j.epsr.2009.04.006
Search in Google Scholar
http://www2.bot.or.th/statistics/ReportPage.aspx?reportID=108&language=eng
Search in Google Scholar
BOX, G. E. P.—JENKINS, G. M.: Time Series Analysis: Forecasting and Control, Holden-Day Inc., 500 Sansome street, San francisco, California, 1976.
Search in Google Scholar
KUNCORO, A. H.—ZUHAL, R. D.: Long-Term Load Forecasting on the Java-Madura-Bali Electricity System using Artificial Neural Network Method, Int. Conf. on Advances in Nuclear Science and Engineering in Conjunction with LKSTN, 2007, pp. 177-181.
Search in Google Scholar

Selection of Hidden Layer Neurons and Best Training Method for FFNN in Application of Long Term Load Forecasting

Abstract

Paradigm

My account