Abstract
Several studies have applied particle swarm optimization (PSO) algorithms to train neural networks (NNs) for time series forecasting and the results indicated good performance. These studies, however, assumed static environments, making the PSO trained NNs unsuitable for forecasting many real-world time series which are generated by non-stationary processes. This study formulates training of a NN forecaster as a dynamic optimization problem, to investigate the application of a dynamic PSO algorithm to train NNs in forecasting time series in non-stationary environments. For this purpose, a set of experiments were conducted on three simulated and seven real-life time series forecasting problems under four different dynamic scenarios. Results obtained are compared to the results of NNs trained using a standard PSO and resilient backpropagation (Rprop). The results show that the NNs trained using dynamic PSO algorithms outperform the NNs trained using PSO and Rprop. These findings highlight the potential of using dynamic PSO in training NNs for real-world forecasting applications.
Similar content being viewed by others
References
Abdulkarim S, Garko A (2016) Effectiveness of firefly algorithm based neural network in time series forecasting. Bayero J Pure Appl Sci 9(1):6–10
Abdulkarim SA (2018) Time series forecasting using dynamic particle swarm optimizer trained neural networks. Phd thesis, University of Pretoria
Abdulkarim SA, Engelbrecht AP (2019) Time series forecasting using neural networks: Are recurrent connections necessary? Neural Process Lett 50:2763–2795
Adhikari R, Agrawal RK (2011) Effectiveness of PSO based neural network for seasonal time series forecasting. In: Proceedings of the fifth Indian international conference on artificial intelligence, pp 231–244
Ahmadi MH, Aghaj SSG, Nazeri A (2013) Prediction of power in solar stirling heat engine by using neural network based on hybrid genetic algorithm and particle swarm optimization. Neural Comput Appl 22(6):1141–1150
Blackwell T, Branke J (2006) Multiswarms, exclusion, and anti-convergence in dynamic environments. IEEE Trans Evol Comput 10(4):459–472
Blackwell T, Branke J, Li X (2008) Particle swarms for dynamic optimization problems. Swarm intelligence. Springer, Berlin pp 193–217
Blackwell TM, Bentley PJ (2002) Dynamic search with charged swarms. In: Proceedings of the genetic and evolutionary computation conference, pp 9–16
Box GEP, Jenkins GM, Reinsel GC, Ljung GM (2015) Time series analysis: forecasting and control. Wiley, New York
Brezak D, Bacek T, Majetic D, Kasac J, Novakovic B (2012) A comparison of feed-forward and recurrent neural networks in time series forecasting. In: Proceedings of IEEE conference on computational intelligence for financial engineering and economics, pp 1–6
Carlisle A, Dozier G (2000) Adapting particle swarm optimization to dynamic environments. Int Conf Artif Intell 1:429–434
Carlisle A, Dozler G (2002) Tracking changing extrema with adaptive particle swarm optimizer. In: Automation congress, 2002 proceedings of the 5th biannual world, vol 13. IEEE, pp 265–270
Chatfield C (2016) The analysis of time series: an introduction. CRC Press, Boca Raton
Deb C, Zhang F, Yang J, Lee SE, Shah KW (2017) A review on time series forecasting techniques for building energy consumption. Renew Sustain Energy Rev 74:902–924
Demšar J (2006) Statistical comparisons of classifiers over multiple data sets. J Mach Learn Res 7(Jan):1–30
Duhain JGOL (2011) Particle swarm optimization in dynamically changing environment an empirical study. MSc Thesis, University of Pretoria
Eberhart RC, Kennedy J (1995) Particles swarm optimization. In: Proceedings of IEEE international conference on neural networks, Perth, Australia, pp 1942–1948
Engelbrecht AP (2007) Computational intelligence: an introduction. Wiley, New York
Frank RJ, Davey N, Hunt SP (2001) Time series prediction and neural networks. J Intell Robot Syst 31(1–3):91–103
Galvan IM, Isasi P (2001) Multi-step learning rule for recurrent neural models: an application to time series forecasting. Neural Process Lett 13(2):115–133
Gordan B, Armaghani DJ, Hajihassani M, Monjezi M (2016) Prediction of seismic slope stability through combination of particle swarm optimization and neural network. Eng Comput 32(1):85–97
Grimaldi EA, Grimaccia F, Mussetta M, Zich RE (2004) PSO as an effective learning algorithm for neural network applications. In: 2004 3rd International Conference on proceedings of the computational electromagnetics and its applications, 2004 (ICCEA 2004). IEEE, pp 557–560
Hajihassani M, Armaghani DJ, Monjezi M, Mohamad ET, Marto A (2015) Blast-induced air and ground vibration prediction: a particle swarm optimization-based artificial neural network approach. Environ Earth Sci 74(4):2799–2817
Hamzacebi C (2008) Improving artificial neural networks performance in seasonal time series forecasting. Inf Sci 178(23):4550–4559
Harrison KR, Ombuki-berman BM, Engelbrecht AP (2016) A radius-free quantum particle swarm optimization technique for dynamic optimization problems. In: Proceedings of IEEE congress on evolutionary computation, pp 578–585
Hornik K, Stinchcombe M, White H (1989) Multilayer feedforward networks are universal approximators. Neural Netw 2(5):359–366
Iqbal S, Zang X, Zhu Y, Liu X (2014) Introducing undergraduate electrical engineering students to chaotic dynamics: computer simulations with logistic map and buck converter. In: IEEE modelling symposium, pp 47–52
Jha GK, Thulasiraman P, Thulasiram RK (2009) PSO based neural network for time series forecasting. In: Proceedings of IEEE international joint conference on neural networks, pp 1422–1427
Jordehi AR (2014) Particle swarm optimisation for dynamic optimisation problems: a review. Neural Comput Appl 25:1507–1516
Kedrowski R, Nelson J, Nair AS, Ranganathan P (2018) Short-term seasonal energy forecasting. In: 2018 IEEE international conference on electro/information technology (EIT). IEEE, pp 696–700
Kennedy J, Mendes R (2002) Population structure and particle swarm performance. Proc IEEE Congr Evol Comput 2:1671–1676
Laepes A, Farben R (1987) Nonlinear signal processing using neural networks: prediction and system modelling. In: Technical Report, Los Alamos National Laboratory, Los Alamos, NM
Lasheras FS, de Cos Juez FJ, Sánchez AS, Krzemień A, Fernández PR (2015) Forecasting the comex copper spot price by means of neural networks and arima models. Resour Policy 45:37–43
LeCun YA, Bottou L, Orr GB, Müller KR (2012) Efficient backprop. Neural networks: tricks of the trade. Springer, Berlin, pp 9–48
Li C, Sprott JC, Thio W (2015) Linearization of the Lorenz system. Phys Lett A 379(10):888–893
Li X, Dam KH (2003) Comparing particle swarms for tracking extrema in dynamic environments. IEEE Proc Evol Comput 3:1772–1779
Mann HB, Whitney DR (1947) On a test of whether one of two random variables is stochastically larger than the other. Ann Math Stat 18(1):50–60
Milano P, Elettrotecnica D (2004) PSO as an effective learning algorithm for neural network applications. In: Proceedings of the international conference on computational electronics and its applications, pp 557–560
Mohammad AA, Sohrab Z, Ali L, Ali E, Ioannis E (2013) Reservoir permeability prediction by neural networks combined with hybrid genetic algorithm and particle swarm optimization. Geophys Prospect 61(3):582–598
Momeni E, Armaghani DJ, Hajihassani M, Amin M (2015) Prediction of uniaxial compressive strength of rock samples using hybrid particle swarm optimization-based artificial neural networks. Measurement 60:50–63
Morrison RW (2003) Performance measurement in dynamic environments. In: Proceedings of the GECCO workshop on evolutionary algorithms for dynamic optimization problems, pp 5–8
Pampara G, Engelbrecht AP (2015) Towards a generic computational intelligence library: preventing insanity. In: Proceedings of the IEEE symposium series on computational intelligence, pp 1460–1467
Qi M, Zhang GP (2001) An investigation of model selection criteria for neural network time series forecasting. Eur J Oper Res 132(3):666–680
Rakitianskaia A (2011) Using particle swarm optimisation to train feedforward neural networks in dynamic environments. MSc. thesis, University of Pretoria
Rakitianskaia A, Engelbrecht AP (2008) Cooperative charged particle swarm optimiser. In: IEEE congress on evolutionary computation, pp 933–939
Rakitianskaia A, Engelbrecht AP (2009) Training neural networks with PSO in dynamic environments. In: IEEE congress on evolutionary computation, 2009 (CEC’09), pp 667–673
Rakitianskaia A, Engelbrecht AP (2015) Saturation in PSO neural network training: good or evil? IEEE Congr Evol Comput 2:125–132
Riedmiller M, Braun H (1993) A direct adaptive method for faster backpropagation learning: the RPROP algorithm. In: IEEE international conference on neural networks, pp 586–591
Röbel A (1994) The dynamic pattern selection algorithm: effective training and controlled generalization of backpropagation neural networks. In: Technical Report, Tech- nische Universität Berlin
Sitte R, Sitte J (2000) Analysis of the predictive ability of time delay neural networks applied to the S&P 500 time series. IEEE Trans Syst Man Cybern C Appl Rev 30(4):568–572
Soodi HA, Vural AM (2018) STATCOM estimation using back-propagation, PSO, shuffled frog leap algorithm, and genetic algorithm based neural networks. Comput Intell Neurosci 2018:6381610. https://doi.org/10.1155/2018/6381610
Suresh A, Harish K, Radhika N (2015) Particle swarm optimization over back propagation neural network for length of stay prediction. Procedia Comput Sci 46:268–275
Tang Z, Fishwick PA (1993) Feedforward neural nets as models for time series forecasting. ORSA J Comput 5(4):374–385
Unger NJ, Ombuki-Berman BM, Engelbrecht AP (2013) Cooperative particle swarm optimization in dynamic environments. In: Proceedings of IEEE symposium on swarm intelligence, pp 172–179
Van den Bergh F (2001) An analysis of particle swarm optimizers. Phd Thesis, University of Pretoria
Van den Bergh F, Engelbrecht AP (2001) Effects of swarm size on cooperative particle swarm optimisers. In: Proceedings of the genetic and evolutionary computation conference, pp 892–899
Van den Bergh F, Engelbrecht AP (2004) A cooperative approach to particle swarm optimization. IEEE Trans Evol Comput 8(3):225–239
Van Wyk AB, Engelbrecht AP (2010) Overfitting by PSO trained feedforward neural networks. In: IEEE congress on evolutionary computation, pp 1–8
Wessels LFA, Barnard E (1992) Avoiding false local minima by proper initialization of connections. IEEE Trans Neural Netw 3(6):899–905
Yalcin N, Tezel G, Karakuzu C (2015) Epilepsy diagnosis using artificial neural network learned by PSO. Turk J Electr Eng Comput Sci 23(2):421–432
Yeh W, Yeh Y, Chang P, Ke Y, Chung V (2014) Forecasting wind power in the Mai Liao wind farm based on the multi-layer perceptron artificial neural network model with improved simplified swarm optimization. Int J Electr Power Energy Syst 55:741–748
Zhang G, Patuwo BE, Hu MY (1998) Forecasting with artificial neural networks: the state of the art. Int J Forecast 14(1):35–62
Author information
Authors and Affiliations
Corresponding author
Ethics declarations
Conflict of interest
The authors declare that there is no conflict of interest.
Additional information
Publisher's Note
Springer Nature remains neutral with regard to jurisdictional claims in published maps and institutional affiliations.
Rights and permissions
About this article
Cite this article
Abdulkarim, S.A., Engelbrecht, A.P. Time series forecasting with feedforward neural networks trained using particle swarm optimizers for dynamic environments. Neural Comput & Applic 33, 2667–2683 (2021). https://doi.org/10.1007/s00521-020-05163-4
Received:
Accepted:
Published:
Issue Date:
DOI: https://doi.org/10.1007/s00521-020-05163-4