Parallelizing Evolutionary Algorithms for Clustering Data

  • Wojciech Kwedlo
Part of the Lecture Notes in Computer Science book series (LNCS, volume 3911)


In the paper the problem of using an evolutionary algorithm to partition a dataset into a known number of clusters is considered. A novel approach, based on data decomposition, for parallel computing of the fitness function is proposed. Both the learning set and the population of the evolutionary algorithm are distributed among processors. Processors form a pipeline using the ring topology. In a single step each processor computes the local fitness of its current subpopulation while sending the previous subpopulation to the successor and receiving next subpopulation from the predecessor. Thus it is possible to overlap communication and computation using non-blocking MPI routines. Our approach to parallel fitness computation was applied to differential evolution algorithm. The results of initial experiments show, that for large datasets the algorithm is capable of achieving very good scalability.


Evolutionary Algorithm Cluster Problem Trial Population Wide Area Network Trial Vector 


Unable to display preview. Download preview PDF.

Unable to display preview. Download preview PDF.


  1. 1.
    Alba, E., Tomassini, M.: Parallelism and evolutionary algorithms. IEEE Trans. Evolutionary Computation 6(5), 443–462 (2002)CrossRefGoogle Scholar
  2. 2.
    Duda, R.O., Hart, P.E., Stork, D.G.: Pattern Classification. John Wiley and Sons, Chichester (2001)MATHGoogle Scholar
  3. 3.
    Gersho, A., Gray, R.: Vector Quantization and Signal Compression. Kluwer Academic, Dordrecht (1992)CrossRefMATHGoogle Scholar
  4. 4.
    Grama, A., Gupta, A., Karypis, G., Kumar, V.: Introduction to Parallel Computing, 2nd edn. Addison-Wesley, Reading (2003)MATHGoogle Scholar
  5. 5.
    Gropp, W., Lusk, E., Doss, N., Skjellum, A.: A high-performance, portable implementation of the MPI message passing standard. Parallel Computing 22, 789–828 (1996)CrossRefMATHGoogle Scholar
  6. 6.
    Hall, L.O., Ozyurt, B., Bezdek, J.C.: Clustering with a genetically guided optimized approach. IEEE Trans. Evolutionary Computation 3(2), 103–112 (1999)CrossRefGoogle Scholar
  7. 7.
    Jain, A.K., Dubes, R.C.: Algorithms for Clustering Data. Prentice-Hall, Englewood Cliffs (1988)MATHGoogle Scholar
  8. 8.
    Kwedlo, W.: A parallel evolutionary algorithm for discovery of decision rules. In: Wyrzykowski, R., Dongarra, J., Paprzycki, M., Waśniewski, J. (eds.) PPAM 2004. LNCS, vol. 3019, Springer, Heidelberg (2004)CrossRefGoogle Scholar
  9. 9.
    Maulik, U., Bandyopadhyay, S.: Genetic algorithm-based clustering technique. Pattern Recognition 33, 1455–1465 (2000)CrossRefGoogle Scholar
  10. 10.
    Michalewicz, Z.: Genetic Algorithms + Data Structures = Evolution Programs. Springer, Heidelberg (1996)CrossRefMATHGoogle Scholar
  11. 11.
    Paterlini, S., Krink, T.: High performance clustering with differential evolution. In: Proceedings of the Sixth Congress on Evolutionary Computation (CEC-2004), pp. 2004–2011. IEEE Press, Los Alamitos (2004)Google Scholar
  12. 12.
    Price, K., Storn, R.: Minimizing the real functions of the ICEC 1996 optimization contest by differential evolution. In: IEEE International Conference on Evolutionary Computation ICEC 1996, pp. 842–844 (1996)Google Scholar
  13. 13.
    Snir, M., Otto, S., Huss-Lederman, S., Walker, D., Dongarra, J.: MPI: The Complete Reference. MIT Press, Cambridge (1996)Google Scholar
  14. 14.
    Storn, R., Price, K.: Differential evolution - a simple and efficient heuristic for global optimization over continuous spaces. Journal of Global Optimization 11, 341–359 (1997)MathSciNetCrossRefMATHGoogle Scholar
  15. 15.
    Wyrzykowski, R., Meyer, N., Stroiński, M.: CLUSTERIX: National cluster of Linux systems. In: Across GRIDS 2004, Nicosia, Cyprus (2004)Google Scholar

Copyright information

© Springer-Verlag Berlin Heidelberg 2006

Authors and Affiliations

  • Wojciech Kwedlo
    • 1
  1. 1.Faculty of Computer ScienceBiałystok Technical UniversityBiałystokPoland

Personalised recommendations