Comparison Of Particle Swarm And Differential Evolution Optimization Algorithms Considering Various Benchmark Functions

Year 2017, Volume: 20 Issue: 4, 899 - 905, 20.12.2017

Hasan Özcan

https://doi.org/10.2339/politeknik.369076

Cited By: 1

Abstract

This study aims to compare Particle Swarm
Optimization (PSO) and Differential Evolution (DE) methods for various input
parameters. Both optimization methods show high performance in optimization of
any physical system including simple and complex constraints and objectives.
Average and standard values of both methods were evaluated by utilizing 8
benchmark functions and a graphical representation and comparison of
corresponding methods was presented for 50x50 and
100x100 population sizes and dimensionalities. It is concluded that DE and PSO
show the best fitness value for Sum of Different Powers benchmark function for
both number of populations. Approach to the optimum is found to be
faster through the PSO method. Both methods are flexible to be used for simple
and complex engineering problems with high performances with ease of
programming.

Keywords

Particle swarm, differential evolution, optimization, benchmark function

References

• 1) Das S., Abraham A. and Konar A., “Particle swarm optimization and differential evolution algorithms: technical analysis, applications and hybridization perspectives”, Studies in Computational Intelligence, 116: 1-38, (2008). 2) Holland J.H., “Adaptation in natural and artificial systems”, University of Michigan Press, Ann Arbor, (1975). 3) Kennedy J.and Elbehart R, “Particle swarm optimization” in proceedings of IEEE International Conference on Neural Networks, 1942-1948, (1995). 4) Storn R.,and Price K., “Differential evolution – a simple and efficient heuristic for global optimization over continuous spaces”, Journal of Global Optimization, 11(4): 341-359, (1997). 5) Ozcan H., Ozdemir K. and Ciloglu H., “Optimum cost of an air cooling system by using differential evolution and particle swarm algorithms”,.Energy and Buildings, 65:93-100, (2013). 6) Zhang F., Deb C., Lee S.E., Yang J. and Shah K.W., “Time series forecasting for building energy consumption using weighted Support Vector Regression with differential evolution optimization technique”, Energy and Buildings, 126: 94-103, (2016). 7) Dezelak K., Bracinik P., Höger M. and Otcenasova A., “Comparison between the particle swarm optimisation and differential evolution approaches for the optimal proportional–integral controllers design during photovoltaic power plants modelling”, IET Renewable Power Generation,10(4): 522-530, (2016). 8) MATLAB Version 7.5.0, The Mathworks Inc., 2007. 9) Price K., Storn R.M. and Lampinen J.A., “Differential evolution: a practical approach to global optimization”. Springer, London, (2005). 10) Talbi E.G., “Metaheuristics: from design to implementation”, John Wiley & Sons, Newyork, (2009). 11) Kennedy J., Elbehart R., “Swarm intelligence”, Morgan Kaufmann, San Francisco, (2001). 12) Internet Source: http://www.cs.cmu.edu/afs/cs/project /jair/pub/ volume 24/ ortiz boyer 05a-html/node6.html, accessed on May 2016.