Short Term Load Forecasting Model Based on Kernel-Support Vector Regression with Social Spider Optimization Algorithm

  • Alireza Sina
  • Damanjeet KaurEmail author
Original Article


Short-term load forecasting in power system is an important factor planning and electricity marketing. Due to the uncertainty of the load demand, many studies have been devised for nonlinear prediction methods. In this paper, a hybrid approach consisting of support vector regression (SVR) and social spider optimization (SSO) is proposed for short term load forecasting. The SVR technique has proven to be useful in nonlinear forecasting problems. To improve accuracy of SVR parameters are tuned using SSO. The SSO algorithm is based on the simulation of cooperative behavior of social-spiders and helps in achieving good results.


Short term load forecasting Kernel Support vector regression Social spider optimization EUNITE and New England network 



  1. 1.
    Fan S, Chen L (2006) Short-term load forecasting based on an adaptive hybrid method. IEEE Trans Power Syst 21(1):392–401MathSciNetCrossRefGoogle Scholar
  2. 2.
    Bunn DW (2000) Forecasting loads and prices in competitive power markets. Proc IEEE 88(2):163–169CrossRefGoogle Scholar
  3. 3.
    Gonzalez-Romera E, Jaramillo-Moran MA, Carmona-Fernandez D (2006) Monthly electric energy demand forecasting based on trend extraction. IEEE Trans Power Syst 21(4):1946–1953CrossRefGoogle Scholar
  4. 4.
    Cortes C, Vapnik V (1995) Support-vector networks. Machine learning 20(3):273–297zbMATHGoogle Scholar
  5. 5.
    Bermolen P, Rossi D (2009) Support vector regression for link load prediction. Comput Netw 53(2):191–201CrossRefGoogle Scholar
  6. 6.
    Kavousi-Fard A, Samet H, Marzbani F (2014) A new hybrid modified firefly algorithm and support vector regression model for accurate short term load forecasting. Expert Syst Appl 41(13):6047–6056CrossRefGoogle Scholar
  7. 7.
    Selakov A, Cvijetinović D, Milović L, Mellon S, Bekut D (2014) Hybrid PSO–SVM method for short-term load forecasting during periods with significant temperature variations in city of Burbank. Applied Soft Computing 16:80–88CrossRefGoogle Scholar
  8. 8.
    Hu Z, Bao Y, Xiong T (2014) Comprehensive learning particle swarm optimization based memetic algorithm for model selection in short-term load forecasting using support vector regression. Applied Soft Computing 25:15–25CrossRefGoogle Scholar
  9. 9.
    Foelix R (1996) Biology of Spiders. Oxford Univ. Press, OxfordGoogle Scholar
  10. 10.
    Cuevas E, Cienfuegos M, Zaldívar D, Pérez-Cisneros M (2013) A swarm optimization algorithm inspired in the behavior of the social-spider. Expert Syst Appl 40(16):6374–6384CrossRefGoogle Scholar
  11. 11.
    Cuevas E, Cienfuegos M (2014) A new algorithm inspired in the behavior of the social-spider for constrained optimization. Expert Syst Appl 41(2):412–425CrossRefGoogle Scholar
  12. 12.
    Dorigo M, Bonabeau E, Theraulaz G (2000) Ant algorithms and stigmergy. Future Generation Computer Systems 16(8):851–871CrossRefGoogle Scholar
  13. 13.
    Abbaspour K, Schulin R, Van Genuchten MT (2001) Estimating unsaturated soil hydraulic parameters using ant colony optimization. Adv Water Resour 24(8):827–841CrossRefGoogle Scholar
  14. 14.
    Simpson A, Maier H, Foong W, Phang K, Seah H, Tan C (2001) Selection of parameters for ant colony optimization applied to the optimal design of water distribution systems. In: Proc. Int. Congress on Modeling and Simulation, Canberra, Australia, pp. 1931–1936Google Scholar
  15. 15.
    Fisher ML (1981) The Lagrangian relaxation method for solving integer programming problems. Manag Sci 27(1):1–18MathSciNetCrossRefzbMATHGoogle Scholar
  16. 16.
    Smola AJ, Schölkopf B (2004) A tutorial on support vector regression. Stat Comput 14(3):199–222MathSciNetCrossRefGoogle Scholar
  17. 17.
    Karush W (1939) Minima of functions of several variables with inequalities as side conditions, Master thesis, University of ChicagoGoogle Scholar
  18. 18.
    Kuhn H, Tucker A (1951) Nonlinear programming. Sid 481–492 i Proc. of the second Berkeley Symposium on mathematical statistics and probability.Univ. of California PressGoogle Scholar
  19. 19.
    Efendi R, Ismail Z, Deris MM (2015) A new linguistic out-sample approach of fuzzy time series for daily forecasting of Malaysian electricity load demand. Appl Soft Comput 28:422–430CrossRefGoogle Scholar
  20. 20.
    Vapnik V (2013) The nature of statistical learning theory. Springer science & business media, BerlinzbMATHGoogle Scholar
  21. 21.
    Gunn SR (1998) Support vector machines for classification and regression. ISIS technical report 14:85–86Google Scholar
  22. 22.
    Schölkopf B, Burges CJ, Smola AJ (1999) Advances in kernel methods: support vector learning. MIT press, CambridgezbMATHGoogle Scholar
  23. 23.
    Mirza M, Sommers J, Barford P, Zhu X (2007) A machine learning approach to TCP throughput prediction. ACM SIGMETRICS Perform Evaluat Rev 35(1):97–108 (ACM) CrossRefGoogle Scholar
  24. 24.
    Ruping S, Morik K (2003) Support vector machines and learning about time. In: Acoustics, Speech, and Signal processing, 2003. Proceedings.(ICASSP’03). 2003 IEEE international conference on, 2003, vol. 4, pp. IV-864: IEEEGoogle Scholar
  25. 25.
    James J, Li VO (2015) A social spider algorithm for global optimization. Applied Soft Comput 30:614–627CrossRefGoogle Scholar
  26. 26.
    Peters JF (2014) Topology of digital images: visual pattern discovery in proximity spaces. Springer, BerlinCrossRefzbMATHGoogle Scholar
  27. 27.
    Son H, Kim C (2015) Forecasting short-term electricity demand in residential sector based on support vector regression and fuzzy-rough feature selection with particle swarm optimization. Procedia Eng 118:1162–1168CrossRefGoogle Scholar
  28. 28.
    Nadtoka I, Balasim MA-Z (2015) Mathematical modelling and short-term forecasting of electricity consumption of the power system, with due account of air temperature and natural illumination, based on support vector machine and particle swarm. Procedia Eng 129:657–663CrossRefGoogle Scholar
  29. 29.
    Ceperic E, Ceperic V, Baric A (2013) A Strategy for Short-Term Load Forecasting by Support Vector Regression Machines. IEEE Trans Power Syst 28(4):4356–4364CrossRefGoogle Scholar
  30. 30.
    Laouafi A, Mordjaoui M, Laouafi F, Boukelia TE (2016) Daily Peak Electricity Demand Forecasting Based on an Adaptive Hybrid Two-Stage Methodology. Int J Electr Power Energy Syst 77:136–144CrossRefGoogle Scholar
  31. 31.
    Juan H, Tingting S, Jing C (2016) Comparison of random forest and SVM for electrical short-term load forecast with different data sources. In: 2016 7th IEEE International conference on software engineering and service science (ICSESS)Google Scholar

Copyright information

© The Korean Institute of Electrical Engineers 2019

Authors and Affiliations

  1. 1.Faculty member of ACECR and Research Scholar of Department of Electrical and Electronic EngineeringUIET, Panjab UniversityChandigarhIndia
  2. 2.Department of Electrical and Electronic EngineeringUIET, Panjab UniversityChandigarhIndia

Personalised recommendations