Abstract
This paper describes a thermodynamic particle swarm optimizer (TDPSO) based on the simple evolutionary equations. Inspired by the minimum free energy principle of the thermodynamic theoretics, a rating-based entropy (RE) and a component thermodynamic replacement (CTR) rule are implemented in the novel algorithm TDPSO. The concept of RE is utilized to systemically measure the fitness dispersal of the swarm with low computational cost. And the fitness range of all particles is divided into several ranks. Furthermore, the rule CTR is applied to control the optimal process with steeply fast convergence speed. It has the potential to maintain population diversity. Compared with the other improved PSO techniques, experimental results on some typical minimization problems show that the proposed technique outperforms other algorithms in terms of convergence speed and stability.
Keywords
Access this chapter
Tax calculation will be finalised at checkout
Purchases are for personal use only
Preview
Unable to display preview. Download preview PDF.
References
Kennedy, J., Eberhart, R.: Particle swarm optimization. In: IEEE International Conference on Neural Network, pp. 1942–1948. IEEE Press, Perth (1995)
Shi, Y.H., Eberhart, R.: A modified particle swarm optimizer. In: IEEE International Conference on Evolutionary Computation, pp. 69–73. IEEE Press, Anchorage (1998)
Clerc, M., Kennedy, J.: A The particle swarm explosion, stability, and convergence in a multidimensional complex space. IEEE Transactions on Evolutionary Computation 6, 58–73 (2002)
J. Riget and J. S. Vesterstrφm: A diversity-guided particle swarm optimizer Cthe arPSO. Dep. of Computer Science, University of Aarhus (2002)
Kennedy, J.: SmallWorlds and Mega-Minds: Effects of Neighborhood Topology on Particle Swarm Performance. In: The Congress of Evolutionary Computation, vol. 3, pp. 1931–1938. IEEE Press, Los Alamitos (1999)
Eberhart, R., Shi, Y.H.: Comparing Inertia Weights and Constriction Factors in Particle Swarm Optimization. In: IEEE International Conference on Evolutionary Computation, pp. 84–88. IEEE Press, Piscataway (2000)
Lφvbjerg, M., Rasmussen, T.K., Krink, T.: Hybrid Particle Swarm Optimiser with Breeding and Subpopulations. In: 3rd Genetic and Evolutionary Computation Conference. ACM Press, New York (2001)
Shi, Y.H., Eberhart, R.: Empirical study of particle swarm optimization. In: IEEE International Conference on Evolutionary Computation, pp. 101–106. IEEE Press, Los Alamitos (1999)
Kennedy, J.: The particle swarm: social adaptation of knowledge. In: IEEE International Conference on Evolutionary Computation, pp. 303–308. IEEE Press, Piscataway (1997)
Shang, G., Jingyu, Y.: Particle Swarm Optimization based on the Ideal of Simulated Annealing Algorithm. Computer Applications and Software 1, 104–110 (2005)
Wang, H., Zhishu, L.: A Simpler and More Effective Particle Swarm Optimization Algorithm. Journal of Software 18(4), 861–868 (2007)
Eberhart, R., Shi, Y.H.: Comparison between genetic algorithms and particle swarm optimization. In: Annual Conference on Evolutionary Programming. IEEE Press, San Diego (1998)
Mori, N., Yoshida, J., Tamaki, H.: A thermodynamical selection rule for the genetic algorithm. In: IEEE International Conference on Evolutionary Computation, pp. 188–192. IEEE Press, Piscataway (1995)
Weiqin, Y., Yuanxiang, L.: A thermodynamical selection rule for the genetic algorithm. In: Shi, Y., van Albada, G.D., Dongarra, J., Sloot, P.M.A. (eds.) ICCS 2007. LNCS, vol. 4490, pp. 997–1004. Springer, Heidelberg (2007)
Author information
Authors and Affiliations
Editor information
Editors and Affiliations
Rights and permissions
Copyright information
© 2008 Springer-Verlag Berlin Heidelberg
About this paper
Cite this paper
Wu, Y., Li, Y., Xu, X., Peng, S. (2008). Hybrid Particle Swarm Optimization Based on Thermodynamic Mechanism. In: Li, X., et al. Simulated Evolution and Learning. SEAL 2008. Lecture Notes in Computer Science, vol 5361. Springer, Berlin, Heidelberg. https://doi.org/10.1007/978-3-540-89694-4_29
Download citation
DOI: https://doi.org/10.1007/978-3-540-89694-4_29
Publisher Name: Springer, Berlin, Heidelberg
Print ISBN: 978-3-540-89693-7
Online ISBN: 978-3-540-89694-4
eBook Packages: Computer ScienceComputer Science (R0)