Abstract
In this paper, a new dynamical evolutionary algorithm (DEA) is presented based on the theory of statistical mechanics. The novelty of this kind of dynamical evolutionary algorithm is that all individuals in a population (called particles in a dynamical system) are running and searching with their population evolving driven by a new selecting mechanism. This mechanism simulates the principle of molecular dynamics, which is easy to design and implement. A basic theoretical analysis for the dynamical evolutionary algorithm is given and as a consequence two stopping criteria of the algorithm are derived from the principle of energy minimization and the law of entropy increasing. In order to verify the effectiveness of the scheme, DEA is applied to solving some typical numerical function minimization problems which are poorly solved by traditional evolutionary algorithms. The experimental results show that DEA is fast and reliable.
This is a preview of subscription content, log in via an institution to check access.
Similar content being viewed by others
References
Mitchell M. An Introduction to Genetic Algorithms. MIT Press, Cambridge, Massachusetts, 1996.
Back T, Fogel D, Michalewicz Z. Handbook of Evolutionary Computation. Volume 1, Oxford University Press, Oxford, England, 1997.
Michalewicz Z. Genetic Algorithms+Data Structures =Evolution Programs. Springer-Verlag, Berlin 1996.
Banzhaf W, Nordin P, Keller R, Francone F. Genetic Programming: An Introduction. Morgan Kaufmann, San Francisco, California, 1998.
Lack D L. Darwin's Finches. Cambridge University Press, Cambridge, England, 1947.
Mitchell M, Forrest S, Holland J H. The royal road for genetic algorithms: Fitness landscapes and GA performance. InProc. the First European Conference on Artificial Life, Varela F J, Bourgine P (eds.), MIT Press, Cambridge, Massachusetts, 1992, pp.245–254.
Deb K, Goldberg D E. An investigation of niche and species formation in genetic function optimization. InProc. the Third International Conference on Genetic Algorithms, Schaffer J D (ed.), Morgan Kaufmann, San Mateo, California, 1989, pp.42–50.
Holland J H. Hidden Order: How Adaptation Builds Complexity. Addison-Wesley, Reading, Massachusetts, 1995.
Holland J H. Building blocks, cohort genetic algorithms, and hyperplane-defined functions.Evolutionary Computation, 2000, 8: 373–391.
Reichl L E. A Modern Course in Statistical Mechanics. University of Texas Press, Austin, Texas, 1980.
Eberhart R C, Kennedy J. A new optimizer using particle swarm theory. InProc. the Sixth International Symposium on Micro Machine and Human Science, Nagoya, Japan, 1995, pp.39–43.
Eberhart R C, Yuhui Shi. Particle swarm optimization: Development, applications and resources. InProc. the 2001 IEEE Congress on Evolutionary Computation, Seoul, Korea, 2001, pp.81–86.
Joseph J McCauley. Classical Mechanics: Transformations, Flows, Integrable and Chaotic Dynamics Cambridge University Press, Cambridge, England, 1997.
Demmel J W. Applied Numerical Linear Algebra, Society for Industrial and Applied Mathematics. Philadelphia, Pennsylvania, 1997.
Arts E H Let al. Simulated Annealing and Boltznann Machines. John Wiley & Sons, New York, 1988.
Eiben A E, Rudolph G. Theory of evolutionary algorithms: A bird's eye view.Theoretical Computer Science, 1999, 229: 3–9.
He J, Kang L S. On the convergence rate of genetic algorithms.Theoretical Computer Science, 1999, 229: 23–39.
Author information
Authors and Affiliations
Corresponding author
Additional information
This work was partly supported by the National Hi-Tech R&D 863 Program of China (Grant No.2002AA1z1490).
LI YuanXiang was born in 1962. He obtained the Ph.D. degree from Computer Science Department of Wuhan University in 1993. Now, he is a professor of computer science of Wuhan University, the vice-dean of college of computer. He serves as vice-director of the Professional Committee of Parallel Computing of China. He has devoted in parallel computing and evolutionary computation more than ten years especially in cellular automata modeling and parallel problem solying from nature (PPSN) for complex systems and problems. He published more than 50 papers. In 1994, as a collaborator of the project 1 “Asynchronous Parallel Algorithms and Domain Decompositions”, he was awarded the National Natural Science Prize of China. In 1999, he was awarded the Advanced Prize of Science and Technology of the National Educational Ministry for the project “Parallel Computational Models and Algorithms for Simulating Complex Systems'.
ZOU XiuFen was born in 1967. She is an associate professor of mathematics of Wuhan University. Her majors are parallel computing and evolutionary computation. She has published more than 30 papers. In 1999, as a collaborator of the project “Parallel Computational Models and Algorithms for Simulating Complex Systems”, she was awarded the Advanced Prize of Science and Technology of the National Educational Ministry.
KANG LiShan is a professor of computer science of Wuhan University. He has researched in parallel computing and evolutionary computation for decades. In 1994, he was awarded the National Natural Science Prize of China for the project “Asynchronous Parallel Algorithms and Domain Decompositions” and was awarded the Advanced Prize of Science and Technology of the National Educational Ministry tree times.
Zbigniew Michalewicz was born in 1952. He is a professor of computer science and the chairman of Computer Science Department of University of North Carolina at Charlotte in USA. He is one of the leading experts in evolutionary computation all over the world. Now he serves as the associate editor of IEEE Transactions on Evolutionary Computation.
Rights and permissions
About this article
Cite this article
Li, Y., Zou, X., Kang, L. et al. A new dynamical evolutionary algorithm based on statistical mechanics. J. Comput. Sci. & Technol. 18, 361–368 (2003). https://doi.org/10.1007/BF02948906
Received:
Revised:
Issue Date:
DOI: https://doi.org/10.1007/BF02948906