Research on combined model based on multi-objective optimization and application in time series forecast

  • Shenghui Zhang
  • Jiyang WangEmail author
  • Zhenhai Guo
Methodologies and Application


Combined model theory has been widely used to forecast the time series problems that are often nonlinear, nonstationary and irregular. Current forecasting models based on combined models theory could adapt to some time series data and overcome some disadvantages of the single models. However, in previous studies, most forecasting models have just focused on improving the accuracy or stability. Nevertheless, for an effective forecasting model, considering only one criterion or rule (stability or accuracy) is insufficient. In this paper, a novel forecasting system, called non-dominated sorting genetic algorithm III combined system with three objective functions, was proposed and successfully employed to solve the predicament of electricity load forecasting which demands to obtain both high accuracy and strong stability as an example. Both stability and accuracy of our proposed combined system are superior to the model compared which showed in the experiment results.


Combined model Multi-objective optimization Time series forecast Non-dominated sorting genetic algorithm III 



This work is supported by National Natural Science Foundation of China, Grant No. 41475013.

Compliance with ethical standards

Conflict of interest

The authors declare that they have no conflict of interest.


  1. Abdel-Aal RE, Al-Garni AZ, Al-Nassar YN (1997) Modelling and forecasting monthly electric energy consumption in eastern Saudi Arabia using abductive networks. Energy 22:911–921Google Scholar
  2. Ai-Hamadi HM, Soliman SA (2005) Long-term/mid-term electric load forecasting based on short-term correlation and annual growth. Electr Power Syst Res 74(3):353–361Google Scholar
  3. Al-Janabi S (2017) Pragmatic miner to risk analysis for intrusion detection (PMRA-ID). Soft Comput Data Sci 788:263–277Google Scholar
  4. Al-Janabi S (2018) Smart system to create an optimal higher education environment using IDA and IOTs. Int J Comput Appl 1–16.
  5. Al-Janabi S, Alwan E (2017) Soft mathematical system to solve black box problem through development the FARB based on hyperbolic and polynomial functions. In: 2017 10th international conference on Developments in eSystems Engineering (DeSE). IEEE, Paris, 2017, pp 37–42Google Scholar
  6. Al-Janabi S, Rawat S, Patel A, Al-Shourbaji I (2015) Design and evaluation of a hybrid system for detection and prediction of faults in electrical transformers. Int J Electr Power Energy Syst 67:324–335Google Scholar
  7. Al-Janabi S, Al-Shourbaji I, Salman MA (2018) Assessing the suitability of soft computing approaches for forest fires prediction. Appl Comput Inf 14(2):214–224Google Scholar
  8. Amral N, Ozveren CS, King D (2007) Short term load forecasting using multiple linear regression. In: Universities power engineering conference, 2007. UPEC 2007. International. IEEE, pp 1192–1198Google Scholar
  9. Bates JM, Granger CWJ (1969) The combination of forecasts. Oper Res Soc 20(4):451–468Google Scholar
  10. Bunnoon P, Chalermyanont K, Limsakul C (2013) Multi-substation control central load area forecasting by using HP-filter and double neural networks (HP-DNNs). Electr Power Energy Syst 44:561–570Google Scholar
  11. Bureerat S, Sriworamas K (2013) Simultaneous topology and sizing optimization of a water distribution network using a hybrid multi-objective evolutionary algorithm. Appl Soft Comput 13(8):3693–3702Google Scholar
  12. Chen HY, Hou DP (2002) Research on superior combination forecasting models based on forecasting effective measures. J Univ Sci Technol China 2(2):172–180MathSciNetzbMATHGoogle Scholar
  13. Chen JF, Wang WM, Huang CM (1995) Analysis of an adaptive time-series autoregressive moving-average (ARMA) model for short-term load forecasting. Electr Power Syst Res 34:187–196Google Scholar
  14. Chen BJ, Chang MW, Lin CJ (2004) Load forecasting using support vector machines: a study on EUNITE competition 2001. IEEE Trans Power Syst 19:1821–1830Google Scholar
  15. Ciro GC, Dugardin F, Yalaoui F, Kelly R, Elattar EE, Goulermas J, Wu QH (2012) Generalized locally weighted GMDH for short term load forecasting. IEEE Trans Syst Man Cybern 42(3):345–356Google Scholar
  16. Ciro GC, Dugardin F, Yalaoui F, Kelly R (2016) A NSGA-II and NSGA-III comparison for solving an open shop scheduling problem with resource constraints. IFAC Papersonline 49(12):1272–1277Google Scholar
  17. Coello CAC, Pulido GT, Lechuga MS (2004) Handling multiple objectives with particle swarm optimization. IEEE Trans Evol Comput 8(3):256–279Google Scholar
  18. Das I, Dennis J (1998) Normal-boundary intersection: a new method for generating the Pareto surface in nonlinear multicriteria optimization problems. SIAM J Optim 8(3):631–657MathSciNetzbMATHGoogle Scholar
  19. Deb K, Jain H (2014) An evolutionary many-objective optimization algorithm using reference-point based nondominated sorting approach, part I: solving problems with box constraints. IEEE Trans Evol Comput 18(4):577–601Google Scholar
  20. Deb K, Pratap A, Agarwal S, Meyarivan T (2002) A fast and elitist multi-objective genetic algorithm: NSGA-II. IEEE Trans Evol Comput 6(2):182–197Google Scholar
  21. Diebold FX, Mariano R (1995) Comparing predictive accuracy. J Bus Econ Stat 20(1):134–144MathSciNetGoogle Scholar
  22. Diebold FX, Pauly P (1987) Structural change and the combination of forecasts. J Forecast 6:21–40Google Scholar
  23. Geweke J, Amisano G (2011) Optimal prediction pools. J Econ 164(1):130–141MathSciNetzbMATHGoogle Scholar
  24. Goia A, May C, Fusai G (2010) Functional clustering and linear regression for peak load forecasting. Int J Forecast 26:700–711Google Scholar
  25. Hippert HS, Pedreira CE, Souza RC (2001) Neural networks for short-term load forecasting: a review and evaluation. IEEE Trans Power Syst 16:44–55Google Scholar
  26. Hobbs BF, Jitprapaikulsarn S, Konda S, Chankong V, Loparo KA, Maratukulam DJ (1999) Analysis of the value for unit commitment of improved load forecasts. IEEE Trans Power Syst 14(4):1342–1348Google Scholar
  27. Hong WC (2009) Electric load forecasting by support vector model. Appl Math Model 33:2444–2454zbMATHGoogle Scholar
  28. Islam SM, Al-Alawi SM, Ellithy KA (1995) Forecasting monthly electric load and energy for a fast growing utility using an artificial neural network. Electr Power Syst Res 34:1–9Google Scholar
  29. Jain H, Deb K (2014) An evolutionary many-objective optimization algorithm using reference-point based nondominated sorting approach, part II: handling constraints and extending to an adaptive approach. IEEE Trans Evol Comput 18(4):602–622Google Scholar
  30. Kong W, Chai T, Yang S, Ding J (2013) A hybrid evolutionary multi-objective optimization strategy for the dynamic power supply problem in magnesia grain manufacturing. Appl Soft Comput 13(5):2960–2969Google Scholar
  31. Kouhi S, Keynia F (2013) A new cascade NN based method to short-term load forecast in deregulated electricity market. Energy Convers Manage 71:76–83Google Scholar
  32. Lam LC, Tang HL, Li DHW (2008) Seasonal variations in residential and commercial sector electricity consumption in Hong Kong. Energy 33:513–523Google Scholar
  33. Laumanns M, Thiele L, Zitzler E (2006) An efficient, adaptive parameter variation scheme for metaheuristics based on the epsilon-constraint method. Eur J Oper Res 169(3):932–942MathSciNetzbMATHGoogle Scholar
  34. Lauret P, Fock E, Randrianarivony RN, Manicom-Ramsamy JF (2008) Bayesian neural network approach to short time load forecasting. Energy Convers Manage 49:1156–1166Google Scholar
  35. Lee HH, Shin GW, Hong ST, Choi JW, Chun MG (2016) Post-chlorination process control based on flow prediction by time series neural network in water treatment plant. Int J Fuzzy Log Intell Syst 16(3):197–207Google Scholar
  36. Li J, Burke EK, Curtois T, Petrovic S, Qu R (2012) The falling tide algorithm: a new multi-objective approach for complex workforce scheduling. Omega 40:283–293Google Scholar
  37. Lin RC, Sir MY, Pasupathy KS (2013) Multi-objective simulation optimization using data envelopment analysis and genetic algorithm: specific application to determining optimal resource levels in surgical services. Omega 41:881–892Google Scholar
  38. Liu N, Tang QF, Zhang JH, Fan W, Liu J (2014) A hybrid forecasting model with parameter optimization for short-term load forecasting of micro-grids. Appl Energy 129:336–345Google Scholar
  39. Liu D, Wang J, Wang H (2015) Short-term wind speed forecasting based on spectral clustering and optimised echo state networks. Renew Energy 78:599–608Google Scholar
  40. Lu J, Ireland D, Lewis A (2009) Multi-objective optimization in high frequency electromagnetics—an effective technique for smart mobile terminal antenna (SMTA) design. IEEE Trans Magn 45(3):1072–1075Google Scholar
  41. Mamlook R, Badran O, Abdulhadi E (2009) A fuzzy inference model for short-term load forecasting. Energy Policy 37(4):1239–1248Google Scholar
  42. Masa-Bote D, Castillo-Cagigal M, Matallanas E et al (2014) Improving photovoltaics grid integration through short time forecasting and self-consumption. Appl Energy 125(15):103–113Google Scholar
  43. Niu D, Wang Y, Wu DD (2010) Power load forecasting using support vector machine and ant colony optimization. Expert Syst Appl 37:2531–2539Google Scholar
  44. Novák V (2018) Detection of structural breaks in time series using fuzzy techniques. Int J Fuzzy Logic Intell Syst 18(1):1–12Google Scholar
  45. Ohtsuka Y, Oga T, Kakamu K (2010) Forecasting electricity demand in Japan: a Bayesian spatial autoregressive ARMA approach. Comput Stat Data Anal 54(11):2721–2735MathSciNetzbMATHGoogle Scholar
  46. Önkal D, Sayım KZ, Lawrence M (2012) Wisdom of group forecasts: does role-playing play a role? Omega 40(6):693–702Google Scholar
  47. Pao HT (2006) Comparing linear and nonlinear forecasts for Taiwan’s electricity consumption. Energy 31:2129–2141Google Scholar
  48. Pappas SS, Ekonomou L, Karamousantas DC, Chatzarakis GE, Katsikas SK, Liatsis P (2008) Electricity demand loads modeling using auto regressive moving average (ARMA) models. Energy 33:1353–1360Google Scholar
  49. Pesaran M, Timmermann A (2007) Selection of estimation window in the presence of breaks. J Econ 137:134–161MathSciNetzbMATHGoogle Scholar
  50. Rahman S, Hazim O (1996) Load forecasting for multiple sites: development of an expert system-based technique. Electr Power Syst Res 39:161–169Google Scholar
  51. Savic DA, Walters GA (1997) Genetic algorithms for the least-cost design of water distribution networks. J Water Res Plan Manag 123(2):67–77Google Scholar
  52. Schaffer JD (1985) Multiple objective optimization with vector evaluated genetic algorithms. In: International conference on genetic algorithms, vol 2, pp 93–100Google Scholar
  53. Sorjamaa A, Hao J, Reyhani N, Ji Y, Lendasse A (2007) Methodology for long-term prediction of time series. Neurocomputing 70(16):2861–2869Google Scholar
  54. Specht D (1991) A general regression neural network. IEEE Trans Neural 2(6):568–576Google Scholar
  55. Stock JH, Watson MW (2004) Combination forecasts of output growth in a seven-country data set. J Forecast 23(6):405–430Google Scholar
  56. Wang JZ, Zhu SL, Zhang WY, Lu HY (2010) Combined modeling for electric load forecasting with adaptive particle swarm optimization. Energy 35:1671–1678Google Scholar
  57. Wang JZ, Chi D, Wu J, Lu H (2011) Chaotic time series method combined with particle swarm optimization and trend adjustment for electricity demand forecasting. Expert Syst Appl 38(7):8419–8429Google Scholar
  58. Wei L, Zhang Z (2009) Based on time sequence of ARIMA model in the application of short-term electricity load forecasting. In: International conference on research challenges in computer science. IEEE, pp 11–14Google Scholar
  59. Wu H, Chang X (2006) Power load forecasting with least squares support vector machines and chaos theory. In: 6th World congress on intelligent control and automation, 2006. WCICA 2006. IEEE, pp 1020–1024Google Scholar
  60. Xiao L, Wang J, Hou R, Wu J (2015a) A combined model based on data pre-analysis and weight coefficients optimization for electrical load forecasting. Energy 82:524–549Google Scholar
  61. Xiao L, Wang J, Yang X, Xiao L (2015b) A hybrid model based on data preprocessing for electrical power forecasting. Electr Power Energy Syst 64:311–327Google Scholar
  62. Xiao LY, Shao W, Liang TL, Wang C (2016) A combined model based on multiple seasonal patterns and modified firefly algorithm for electrical load forecasting. Appl Energy 167:135–153Google Scholar
  63. Yalcinoz T, Eminoglu U (2015) Short term and medium term power distribution load forecasting by neural networks. Energy Convers Manag 46:1393–1405Google Scholar
  64. Yang Y, Chen YH, Wang YC, Li CH, Li L (2016) Modelling a combined method based on ANFIS and neural network improved by DE algorithm: a case study for short-term electricity demand forecasting. Appl Soft Comput 49:663–675Google Scholar
  65. Yu JW, Kim SS (2016) Locally-weighted polynomial neural network for daily short-term peak load forecasting. Int J Fuzzy Log Intell Syst 16(3):163–172MathSciNetGoogle Scholar
  66. Zhang X, Yan W (2011) Short-term load forecasting of power systems by combination of wavelet transform and AMPSO based neural network. Energy Procedia 13:6006–6016Google Scholar
  67. Zhang M, Bao H, Yan L, Cao J, Du J (2003) Research on processing of short term historical data of daily load based on Kalman filter. Power Syst Technol 27(10):39–42Google Scholar
  68. Zhou QP, Jiang HY, Wang JZ, Zhou JL (2014) A hybrid model for PM2. 5 forecasting based on ensemble empirical mode decomposition and a general regression neural network. Sci Total Environ 496:264–274Google Scholar
  69. Zitzler E, Laumanns M, Thiele L (2001) SPEA2: improving the strength Pareto evolutionary algorithm for multiobjective optimization. In: Proceedings of the evolutionary methods for design, optimization and control with applications to industrial problems, Eurogen’2001, Athens, GreeceGoogle Scholar

Copyright information

© Springer-Verlag GmbH Germany, part of Springer Nature 2018

Authors and Affiliations

  1. 1.School of Mathematics and StatisticsLanzhou UniversityLanzhouPeople’s Republic of China
  2. 2.Faculty of Information TechnologyMacau University of Science and TechnologyMacauPeople’s Republic of China
  3. 3.State Key Laboratory of Numerical Modeling for Atmospheric Sciences and Geophysical Fluid Dynamics, Institute of Atmospheric PhysicsChinese Academy of SciencesBeijingPeople’s Republic of China

Personalised recommendations