Skip to main content

Advertisement

Log in

Time series prediction using PSO-optimized neural network and hybrid feature selection algorithm for IEEE load data

  • Original Article
  • Published:
Neural Computing and Applications Aims and scope Submit manuscript

An Erratum to this article was published on 04 July 2012

Abstract

Artificial neural networks have been widely used in time series prediction. In this paper, multi-layer feedforward neural networks with optimized structures, using particle swarm optimization (PSO) algorithm, are used for hourly load prediction based on load time series of IEEE Reliability Test System. To have a small and appropriate feature subset, a hybrid method is used for feature selection in this paper. This hybrid method uses the combination of genetic algorithm (GA) and ant colony optimization (ACO) algorithm. The season, day of the week, time of the day and history load are considered as load influencing factors in this study based on the mentioned standard load dataset. The optimized number of neurons in the hidden layers of multi-layer perceptron (MLP) is determined using PSO algorithm. Experimental results show that the proposed hybrid model offers superior performance, in terms of mean absolute percentage error (MAPE), in time series prediction as compared to some recent researches in this field.

This is a preview of subscription content, log in via an institution to check access.

Access this article

Price excludes VAT (USA)
Tax calculation will be finalised during checkout.

Instant access to the full article PDF.

Institutional subscriptions

Fig. 1

Similar content being viewed by others

References

  1. Granger CWJ, Anderson AP (1978) An introduction to bilinear time series models. Vandenhoeck & Ruprecht, Göttingen

    MATH  Google Scholar 

  2. Tong H, Lim KS (1980) Threshold autoregressive, limit cycles and cyclic data. Journal of Royal Statistical Society, Series B 42:245–292

    MATH  Google Scholar 

  3. Engle RF (1982) Autoregressive conditional heteroscedasticity with estimates of the variance of UK inflation. Econometrica 50:987–1008

    Article  MathSciNet  MATH  Google Scholar 

  4. Bollerslev T (1986) Generalized autoregressive conditional heteroscedasticity. Journal of Econometrics 31:307–327

    Article  MathSciNet  MATH  Google Scholar 

  5. Lauret P, David M, Calogine D (2012) Nonlinear models for short-time load forecasting. Energy Procedia 14:1404–1409

    Article  Google Scholar 

  6. Chakraborty K, Merotra K, Mohan CK, Ranka S (1992) Forecasting the behavior of multivariate time-series using neural networks. Neural Networks 5:461–470

    Article  Google Scholar 

  7. Yao J, Li Y, Tan CL (2000) Option price forecasting using neural networks. Omega 28:455–466

    Article  Google Scholar 

  8. Zemouri R, Racoceanu D, Zerhouni N (2003) Recurrent radial basis function network for time series prediction. Eng Appl Artif Intell 16:453–463

    Article  Google Scholar 

  9. Katijani Y, Hipel WK, McLeod AI (2005) Forecasting nonlinear time series with feedforward neural networks: a case study of Canadian lynx data. Journal of Forecasting 24:105–117

    Article  MathSciNet  Google Scholar 

  10. Chen Y, Yang B, Dong J, Abraham A (2005) Time-series forecasting using flexible neural tree model. Inf Sci 174:219–235

    Article  MathSciNet  Google Scholar 

  11. Harpham V, Dawson CW (2006) The effect of different basis function on radial basis function network for time series prediction: a comparative study. Neurocomputing 69:2161–2170

    Article  Google Scholar 

  12. Giordano F, La Rocca M, Perna C (2007) Forecasting nonlinear time series with neural network sieve bootstrap. Comput Stat Data Anal 51:3871–3884

    Article  MATH  Google Scholar 

  13. Jain A, Kumar AM (2007) Hybrid neural network models for hydrologic time series forecasting. Applied Soft Computing 7:585–592

    Article  Google Scholar 

  14. Lee CM, Ko CN (2009) Time series prediction using RBF neural networks with a nonlinear time-varying evolution PSO algorithm. Neurocomputing 73:449–460

    Article  Google Scholar 

  15. Gheyas IA, Smith LS (2011) A novel neural network ensemble architecture for time series forecasting. Neurocomputing 74:3855–3864

    Article  Google Scholar 

  16. Crone SF, Hibon M, Nikolopoulos K (2011) Advances in forecasting with neural networks? Empirical evidence from the NN3 competition on time series prediction. Int J Forecast 27:635–660

    Article  Google Scholar 

  17. Hornik K, Stinchcombe M, White H (1989) Multilayer feedforward networks are universal approximators. Neural Networks 2:359–366

    Article  Google Scholar 

  18. Bates JM, Granger CWJ (1969) The combination of forecasts. Operation Research 20:451–468

    Google Scholar 

  19. Clemen R (1989) Combining forecasts: a review and annotated bibliography with discussion. Int J Forecast 5:559–608

    Article  Google Scholar 

  20. Pai PF, Lin CS (2005) A hybrid ARIMA and support vector machines model in stock price forecasting. Omega 33:497–505

    Article  Google Scholar 

  21. Chen KY, Wang CH (2007) A hybrid ARIMA and support vector machines in forecasting the production values of the machinery industry in Taiwan. Expert Syst Appl 32:254–264

    Article  Google Scholar 

  22. Nie H, Liu G, Liu X, Wang Y (2012) Hybrid of ARIMA and SVMs for short-term load forecasting. Energy Procedia 14:1455–1460

    Article  Google Scholar 

  23. Zhou ZJ, Hu CH (2008) An effective hybrid approach based on Grey and ARMA for forecasting gyro drift. Chaos, Solitons Fractals 35:525–529

    Article  Google Scholar 

  24. Tseng FM, Tzeng GH, Yu HC, Yuan BJC (2001) Fuzzy ARIMA model for forecasting the foreign exchange market. Fuzzy Sets Syst 118:9–19

    Article  MathSciNet  Google Scholar 

  25. Wang J, Li L, Niu D, Tan Z (2012) An annual load forecasting model based on support vector regression with differential evolution algorithm. Appl Energy 94:65–70

    Article  Google Scholar 

  26. Tian L, Noore A (2005) On-line prediction of software reliability using an evolutionary connectionist model. Journal of Systems and Softwares 77:173–180

    Article  Google Scholar 

  27. Armano G, Marchesi M, Murru A (2005) A hybrid genetic-neural architecture for stock indexes forecasting. Inf Sci 170:3–33

    Article  MathSciNet  Google Scholar 

  28. Kim H, Shin K (2007) A hybrid approach based on neural networks and genetic algorithms for detecting temporal patterns in stock markets. Applied Soft Computing 7:569–575

    Article  Google Scholar 

  29. Shen W, Guo X, Wu C, Wu D (2011) Forecasting stock indices using radial basis function neural networks optimized by artificial swarm algorithm. Knowl-Based Syst 24:378–385

    Article  Google Scholar 

  30. Yu L, Wang S, Lai KK (2005) A novel nonlinear ensemble forecasting model incorporating GLAR and ANN for foreign exchange rates. Comput Oper Res 32:2523–2541

    Article  MATH  Google Scholar 

  31. Tsaih R, Hsu Y, Lai CC (1998) Forecasting S&P 500 stock index futures with a hybrid AI system. Decis Support Syst 23:161–174

    Article  Google Scholar 

  32. Santana ÁL, Conde GB, Rego LP, Rocha CA, Cardoso DL, Costa JCW, Bezerra UH, Francês CRL (2012) PREDICT-Decision support system for load forecasting and inference: a new undertaking for Brazilian power suppliers. Int J Electr Power Energy Syst 38:33–45

    Article  Google Scholar 

  33. Bunnoon P, Chalermyanont K, Limsakul C (2012) Mid-term load forecasting: level suitably of wavelet and neural network based on factor selection. Energy Procedia 14:438–444

    Article  Google Scholar 

  34. Wedding DK, Cios KJ (1996) Time series forecasting by combining RBF networks, certainty factors, and Box-Jenkins model. Neurocomputing 10:149–168

    Article  MATH  Google Scholar 

  35. Zhang GP (2003) Time series forecasting using a hybrid ARIMA and neural network model. Neurocomputing 50:159–175

    Article  MATH  Google Scholar 

  36. Tseng FM, Yu HC, Tzeng GH (2002) Combining neural network model with seasonal time series ARIMA model. Technol Forecast Soc Chang 69:71–78

    Article  Google Scholar 

  37. Ginzburg I, Horn D (1994) Combined neural networks for time series analysis. Advanced Neural Information Processing Systems 6:224–231

    Google Scholar 

  38. Chang P, Liu C, Wang Y (2006) A hybrid model by clustering and evolving fuzzy rules for sales decision supports in printed circuit board industry. Decis Support Syst 42:1254–1269

    Article  Google Scholar 

  39. Huarng K, Yu THK (2006) The application of neural networks to forecast fuzzy time series. Phys A 336:481–491

    Article  Google Scholar 

  40. Khashei M, Bijari M, Raissi Ardali GA (2009) Improvement of auto-regressive integrated moving average models using fuzzy logic and artificial neural networks (ANNs). Neurocomputing 72:956–967

    Article  Google Scholar 

  41. Akdemir B, Çetinkaya N (2012) Long-term load forecasting based on adaptive neural fuzzy inference system using real energy data. Energy Procedia 14:794–799

    Article  Google Scholar 

  42. Potter C, Venayagamoorthy GK, Kosbar K (2008) MIMO beam-forming with NN channel prediction trained by a novel PSO-EA-DEPSO algorithm. In: The proceedings of the international joint conference on neural networks, pp 3338–3344

  43. Gross G, Galiana F (1987) Short term load forecasting. Proc IEEE 75:1558–1573

    Article  Google Scholar 

  44. Sadownik R, Barbosa E (1999) Short-term forecasting of industrial electricity consumption in Brazil. Int J Forecast 18:215–224

    Article  Google Scholar 

  45. Lee CM, Ko CN (2011) Short-term load forecasting using lifting scheme and ARIMA models. Expert Syst Appl 38:5902–5911

    Article  Google Scholar 

  46. Jin M, Zhou X, Zhang ZM, Tentzeris MM (2012) Short-term power load forecasting using grey correlation contest modeling. Expert Syst Appl 39:773–779

    Article  Google Scholar 

  47. Javed F, Arshad N, Wallin F, Vassileva I, Dahlquist E (2012) Forecasting for demand response in smart grids: an analysis on use of anthropologic and structural data and short term multiple loads forecasting. Appl Ener (article in press, available online 29 Mar. 2012, doi:10.1016/j.apenergy.2012.02.027)

  48. Marvuglia A, Messineo A (2012) Using recurrent artificial neural networks to forecast household electricity consumption. Energy Procedia 14:45–55

    Article  Google Scholar 

  49. Huang SJ, Shih KR (2003) Short-term load forecasting via ARMA model identification including non-Gaussian process considerations. IEEE Trans Power Syst 18:673–679

    Article  Google Scholar 

  50. Al-Hamadi HM, Soliman SA (2004) Short-term electric load forecasting based on Kalman filtering algorithm with moving window weather and load model. Electric Power Systems Research 68:47–59

    Article  Google Scholar 

  51. Vilar JM, Cao R, Aneiros G (2012) Forecasting next-day electricity demand and price using nonparametric functional methods. Int J Electr Power Energy Syst 39:48–55

    Article  Google Scholar 

  52. Kodogiannis VS, Anagnostakis EM (2002) Soft computing based techniques for short-term load forecasting. Fuzzy Sets Syst 128:413–426

    Article  MathSciNet  MATH  Google Scholar 

  53. Al-Kandari AM, Soliman SA, El-Hawary ME (2004) Fuzzy short-term electric load forecasting. Int J Electr Power Energy Syst 26:111–122

    Article  Google Scholar 

  54. Badri A, Ameli Z, Motie Birjandi A (2012) Application of artificial neural networks and fuzzy logic methods for short term load forecasting. Energy Procedia 14:1883–1888

    Article  Google Scholar 

  55. He W (2008) Forecasting electricity load with optimized local learning models. Int J Electr Power Energy Syst 30:603–608

    Article  Google Scholar 

  56. Xiao Z, Ye S-J, Zhang B, Sun C-X (2009) BP neural network with rough set for short term load forecasting. Expert Syst Appl 36:273–279

    Article  Google Scholar 

  57. Niu D, Wang Y, Dash Wu D (2010) Power load forecasting using support vector machine and ant colony optimization. Expert Syst Appl 37:2531–2539

    Article  Google Scholar 

  58. Wang Y, Niu D, Ji L (2012) Short-term power load forecasting based on IVL-BP neural network technology. Systems Engineering Procedia 4:168–174

    Article  Google Scholar 

  59. Sousa JC, Neves LP, Jorge HM (2012) Assessing the relevance of load profiling information in electrical load forecasting based on neural network models. Int J Elect Power Energy Syst (article in press, available online 13 Mar. 2012, doi:10.1016/j.ijepes.2012.02.008)

  60. Goldberg DE (1989) Genetic algorithms in search, optimization, and machine learning. Addison Wesley, Reading

    MATH  Google Scholar 

  61. Maniezzo V, Colomi A (1999) The ant system applied to the quadratic assignment problem. Knowledge Data Engineering 11:769–778

    Article  Google Scholar 

  62. Sheikhan M, Mohammadi N (2011) Neural-based electricity load forecasting using hybrid of GA and ACO for feature selection. Neural Comput Appl (article in press, available online 1 May 2011, doi:10.1007/s00521-011-0599-1)

  63. The University of Washington Power System Test Case Archive (http://www.ee.washington.edu/research/pstca/rts/pg_tcarts.htm)

  64. Kennedy J, Eberhart R (1995) Particle swarm optimization. In: The proceedings of the IEEE international conference on neural networks, vol 4, pp 1942–1948

  65. Cai Y, Wang JZ, Tang Y, Yang YC (2011) An efficient approach for electric load forecasting using distributed ART (adaptive resonance theory) & HS-ARTMAP (Hyper-spherical ARTMAP network) neural network. Energy 36:1340–1350

    Article  Google Scholar 

  66. Deihimi A, Showkati H (2012) Application of echo state networks in short-term electric load forecasting. Energy 39:327–340

    Article  Google Scholar 

  67. Kim KH, Park JK, Hwang KJ, Kim SH (1995) Implementation of hybrid short-term load forecasting system using artificial neural networks and fuzzy expert-systems. IEEE Trans Power Syst 10:1534–1539

    Article  Google Scholar 

  68. Liao GC, Tsao TP (2004) Application of fuzzy neural networks and artificial intelligence for load forecasting. Electric Power Systems Research 70:237–244

    Article  Google Scholar 

  69. Yao SJ, Song YH, Zhang LZ, Cheng XY (2000) Wavelet transform and neural networks for short-term electrical load forecasting. Energy Convers Manage 41:1975–1988

    Article  Google Scholar 

  70. Zhang BL, Dong ZY (2001) An adaptive neural-wavelet model for short-term load forecasting. Electric Power Systems Research 59:121–129

    Article  Google Scholar 

  71. Chang PC, Fan CY, Lin JJ (2011) Monthly electricity demand forecasting based on a weighted evolving fuzzy neural network approach. Int J Electr Power Energy Syst 33:17–27

    Article  Google Scholar 

  72. Che J, Wang J, Wang G (2012) An adaptive fuzzy combination model based on self-organizing map and support vector regression for electric load forecasting. Energy 37:657–664

    Article  Google Scholar 

  73. Nagi J, Siah Yap K, Nagi F, Tiong SK, Ahmed SK (2011) A computational intelligence scheme for the prediction of the daily peak load. Applied Soft Computing 11:4773–4788

    Article  Google Scholar 

  74. Yadav V, Srinivasan D (2011) A SOM-based hybrid linear-neural model for short-term load forecasting. Neurocomputing 74:2874–2885

    Article  Google Scholar 

  75. Hong WC (2011) Electric load forecasting by seasonal recurrent SVR (support vector regression) with chaotic artificial bee colony algorithm. Energy 36:5568–5578

    Article  Google Scholar 

  76. Pian Z, Li S, Zhang H, Zhang N (2012) The application of the PSO based BP network in short-term load forecasting. Physics Procedia 24:626–632

    Article  Google Scholar 

  77. Leung SYS, Tang Y, Wong WK (2012) A hybrid particle swarm optimization and its application in neural networks. Expert Syst Appl 39:395–405

    Article  Google Scholar 

  78. Zhang JR, Zhang J, Lok TM, Lyu MR (2007) A hybrid particle swarm optimization-back propagation algorithm for feedforward neural network training. Appl Math Comput 185:1026–1037

    Article  MATH  Google Scholar 

  79. Li J, Liu X (2011) Melt index prediction by RBF neural network optimized with an MPSO-SA hybrid algorithm. Neurocomputing 74:735–740

    Article  Google Scholar 

  80. Yu J, Wang S, Xi L (2008) Evolving artificial neural networks using an improved PSO and DPSO. Neurocomputing 71:1054–1060

    Article  Google Scholar 

  81. Luitel B, Venayagamoorthy GK (2010) Quantum inspired PSO for the optimization of simultaneous recurrent neural networks as MIMO learning systems. Neural Networks 23:583–586

    Article  Google Scholar 

  82. Khayat O, Ebadzadeh MM, Shahdoosti HR, Rajaei R, Khajehnasiri I (2009) A novel hybrid algorithm for creating self-organizing fuzzy neural networks. Neurocomputing 73:517–524

    Article  Google Scholar 

  83. Tang Y, Wang Z, Fang JA (2011) Controller design for synchronization of an array of delayed neural networks using a controllable probabilistic PSO. Inf Sci 181:4715–4732

    Article  Google Scholar 

  84. Nabavi-Kerizi SH, Abadi M, Kabir E (2010) A PSO-based weighting method for linear combination of neural networks. Comput Electr Eng 36:886–894

    Article  MATH  Google Scholar 

  85. Gheyas IA, Smith LS (2010) Feature subset selection in large dimensionality domains. Pattern Recogn 43:5–13

    Article  MATH  Google Scholar 

  86. Kabir MM, Shahjahan M, Murase K (2011) A new local search based hybrid genetic algorithm for feature selection. Neurocomputing 74:2914–2928

    Article  Google Scholar 

  87. Bae C, Yeh WC, Chung YY, Liu SL (2010) Feature selection with intelligent dynamic swarm and rough set. Expert Syst Appl 37:7026–7032

    Article  Google Scholar 

  88. Niu D, Gu Z, Zhang Y (2009) An AFSA-TSGM based wavelet neural network for power load forecasting. Lect Notes Comput Sci 5553:1034–1043

    Article  Google Scholar 

  89. Wang X, Yang J, Teng X, Xia W, Jensen R (2007) Feature selection based on rough sets and particle swarm optimization. Pattern Recogn Lett 28:459–471

    Article  Google Scholar 

  90. Huang CL (2009) ACO-based hybrid classification system with feature subset selection and model parameters optimization. Neurocomputing 73:438–448

    Article  Google Scholar 

  91. Chen Y, Miao D, Wang R (2010) A rough set approach to feature selection based on ant colony optimization. Pattern Recogn Lett 31:226–233

    Article  Google Scholar 

  92. Nemati S, Basiri ME, Ghasem-Aghaee N, Hosseinzadeh Aghdam M (2009) A novel ACO-GA hybrid algorithm for feature selection in protein function prediction. Expert Syst Appl 36:12086–12094

    Article  Google Scholar 

  93. Shi Y, Eberhart R (1998) Parameter selection in particle swarm optimization. In: The proceedings of the international conference on evolutionary programming, pp 591–601

  94. Moré JJ (1978) The Levenberg-Marquardt algorithm: implementation and theory. Lecture Notes in Mathematics 630:105–116

    Article  Google Scholar 

  95. Kelo SM, Dudul SV (2011) Short-term Maharashtra state electrical power load prediction with special emphasis on seasonal changes using a novel focused time lagged recurrent neural network based on time delay neural network model. Expert Syst Appl 38:1554–1564

    Article  Google Scholar 

  96. Hippert HS, Taylor JW (2010) An evaluation of Bayesian techniques for controlling model complexity and selecting inputs in a neural network for short-term load forecasting. Neural Networks 23:386–395

    Article  Google Scholar 

  97. Amjady N, Keynia F (2009) Short-term load forecasting of power systems by combination of wavelet transform and neuro-evolutionary algorithm. Energy 34:46–57

    Article  Google Scholar 

  98. Mishra S, Patra SK (2008) Short term load forecasting using a neural network trained by a hybrid artificial immune system. In: The proceedings of the IEEE third international conference on industrial and information systems, pp 1–5. doi:10.1109/ICIINFS.2008.4798349

    Google Scholar 

Download references

Author information

Authors and Affiliations

Authors

Corresponding author

Correspondence to Mansour Sheikhan.

Rights and permissions

Reprints and permissions

About this article

Cite this article

Sheikhan, M., Mohammadi, N. Time series prediction using PSO-optimized neural network and hybrid feature selection algorithm for IEEE load data. Neural Comput & Applic 23, 1185–1194 (2013). https://doi.org/10.1007/s00521-012-0980-8

Download citation

  • Received:

  • Accepted:

  • Published:

  • Issue Date:

  • DOI: https://doi.org/10.1007/s00521-012-0980-8

Keywords

Navigation