Applied Intelligence

, Volume 39, Issue 2, pp 279–306 | Cite as

The sandpile mutation Genetic Algorithm: an investigation on the working mechanisms of a diversity-oriented and self-organized mutation operator for non-stationary functions

  • C. M. Fernandes
  • J. L. J. Laredo
  • A. C. Rosa
  • J. J. Merelo


This paper reports the investigation on the sandpile mutation, an unconventional mutation control scheme for binary Genetic Algorithms (GA) inspired by the Self-Organized Criticality (SOC) theory. The operator, which is based on a SOC system known as sandpile, is able to generate mutation rates that, unlike those given by other methods of parameter control, oscillate between low values and very intense mutations events. The distribution of the mutation rates suggests that the algorithm can be an efficient and yet simple and context-independent approach for the optimization of non-stationary fitness functions. This paper studies the mutation scheme of the algorithm and proposes a new strategy that optimizes is performance. The results also demonstrate the advantages of using the fitness distribution of the population for controlling the mutation. An extensive experimental setup compares the sandpile mutation GA (GGASM) with two state-of-the-art evolutionary approaches to non-stationary optimization and with the Hypermutation GA, a classical approach to dynamic problems. The results demonstrate that GGASM is able to improve the other algorithms in several dynamic environments. Furthermore, the proposed method does not increase the parameter set of traditional GAs. A study of the distribution of the mutation rates shows that the distribution depends on the type of problem and dynamics, meaning that the algorithm is able to self-regulate the mutation. The effects of the operator on the diversity of the population during the run are also investigated. Finally, a study on the effects of the topology of the sandpile mutation on its performance demonstrates that an alternative topology has minor effects on the performance.


Genetic Algorithms Non-stationary functions Self-Organized Criticality Parameter control 



The first author wishes to thank FCT, Ministério da Ciência e Tecnologia, his Research Fellowship SFRH/BPD/66876/2009, also partially supported by Fundação para a Ciência e a Tecnologia (ISR/IST plurianual funding) through the POS_Conhecimento Program that includes FEDER funds. This paper has been funded in part by the Spanish MICYT project TIN2008-06491-C04-01 and the Junta de Andalucía P06-TIC-02025 and P07-TIC-03044. The authors wish to thank Renato Tinós and Shengxiang Yang for providing the source code of SORIGA.


  1. 1.
    Arabas J, Michalewicz Z, Mulawka J (1994) GAVaPS—a genetic algorithm with varying population size. In: Proceedings of the 1st IEEE conference on evolutionary computation, vol 1. IEEE Press, New York, pp 73–78 Google Scholar
  2. 2.
    Angeline P (1997) Tracking extrema in dynamic environments. In: Angeline P et al (eds) Proceedings of the 6th international conference on evolutionary programming. Springer, London, pp 335–345 Google Scholar
  3. 3.
    Bäck T (1996) Evolutionary algorithms in theory and practice. Oxford University Press, London MATHGoogle Scholar
  4. 4.
    Bäck T, Eiben AE, van der Vart NAL (2000) An empirical study on GAs ‘Without parameters’. In: Schoenauer M et al (eds) Proceedings of the 6th international conference on parallel problem solving from nature (PPSN VI). Springer, London, pp 315–324 Google Scholar
  5. 5.
    Bak P, Tang C, Wiesenfeld K (1987) Self-organized criticality: an explanation of \(\frac{1}{f}\) noise. Phys Rev Lett 59:381–384 MathSciNetCrossRefGoogle Scholar
  6. 6.
    Bak P, Chen K, Tang C (1990) A forest-fire model and some thoughts on turbulence. Phys Lett A 147:197–300 CrossRefGoogle Scholar
  7. 7.
    Bak P, Sneppen K (1993) Punctuated equilibrium and criticality in a simple model of evolution. Phys Rev Lett 71(24):4083–4086 CrossRefGoogle Scholar
  8. 8.
    Boettcher S, Percus AG (2003) Optimization with extremal dynamics. Complexity 8(2):57–62 MathSciNetCrossRefGoogle Scholar
  9. 9.
    Branke J (1999) Memory enhanced evolutionary algorithms for changing optimization problems. In: Proceedings of the 1999 congress on evolutionary computation. IEEE Press, New York, pp 1875–1882 Google Scholar
  10. 10.
    Branke J, Kaußler T, Schmidt C, Schmeck H (2000) A multi-population approach to dynamic optimization problems. In: Parmee IC (ed) Proceedings of the adaptive computing in design and manufacturing (ACDM’2000). Springer, London, pp 299–308 Google Scholar
  11. 11.
    Branke J (2002) Evolutionary optimization in dynamic environments. Kluwer Academic, Norwell MATHCrossRefGoogle Scholar
  12. 12.
    Castillo PA, Arenas MG, Rico N, Mora AM, Gárcia-Sanchez P, Laredo JLJ, Merelo JJ (2012) Determining the significance and relative importance of parameters of a simulated quenching algorithm using statistical tools. Appl Intell 37(2):239–254 CrossRefGoogle Scholar
  13. 13.
    Caponio A, Cascella GL, Neri F, Salvatore N, Sumner M (2007) A fast adaptive memetic algorithm for off-line and on-line control design of PMSM drives. IEEE Trans Syst Man Cybern, Part B, Cybern 37(1):28–41 CrossRefGoogle Scholar
  14. 14.
    Cobb HG (1990) An investigation into the use of hypermutation as an adaptive operator in GAs having continuous, time-dependent nonstationary environments. Tech. report AIC-90-001, Naval Research Laboratory, Washington, USA Google Scholar
  15. 15.
    Deb K, Goldberg DE (1993) Analyzing deception in trap functions. In: Whitley LD (ed) Foundations of genetic algorithms 2. Morgan Kaufmann, San Francisco, pp 93–108 Google Scholar
  16. 16.
    Eiben AE, Hinterding R, Michalewicz Z (1999) Parameter control in evolutionary algorithms. IEEE Trans Evol Comput 3(2):124–141 CrossRefGoogle Scholar
  17. 17.
    Eiben AE, Marchiori E, Valkó VA (2004) Evolutionary algorithms with on-the-fly population size adjustment. In: Proceedings of the 8th conference on parallel problem solving from nature. LNCS. Springer, Birmingham, pp 315–324 Google Scholar
  18. 18.
    Eldredge N, Gould SJ (1985) Punctuated equilibria: an alternative to phyletic gradualism. In: Schopf TJM (ed) Models in paleobiology. Freeman Cooper, San Francisco, pp 82–115 Google Scholar
  19. 19.
    Fernandes CM, Merelo JJ, Ramos V, Rosa AC (2008) A self-organized criticality mutation operator for dynamic optimization problems. In: Proceedings of the 2008 genetic and evolutionary computation conference. ACM, New York, pp 937–944 CrossRefGoogle Scholar
  20. 20.
    Fernandes CM, Merelo JJ, Rosa AC (2008) Tracking extrema in dynamic fitness functions with dissortative mating genetic algorithms. In: Proceedings of the 8th international conference on hybrid intelligent system (HIS’2008). IEEE Comput Soc, Washington, pp 59–64 CrossRefGoogle Scholar
  21. 21.
    Fernandes CM, Laredo JLJ, Mora AC, Rosa Merelo JJ (2011) The sandpile mutation operator for genetic algorithms. In: Proceedings of the learning and intelligent optimization congress (LION 5) Google Scholar
  22. 22.
    Fernandes CM, Laredo JLJ, Mora A, Merelo JJ, Rosa AC (2011) A study on the mutation rates of a genetic algorithm interacting with a sandpile. In: Proceedings of the 2011 international conference on applications of evolutionary computation—part I, pp 32–42 Google Scholar
  23. 23.
    Fernandes CM, Merelo JJ, Rosa AC (2011) A comparative study on the performance of dissortative mating and immigrants’ strategies for evolutionary dynamic optimization. Inf Sci 181(20):4428–4459 CrossRefGoogle Scholar
  24. 24.
    Fernandes CM, Merelo JJ, Rosa AC (2012) Controlling the parameters of the particle swarm with a self-organized criticality model. In: Proceedings of parallel problem solving from nature PPSN XII. LNCS, vol 7492, pp 153–163 CrossRefGoogle Scholar
  25. 25.
    Goldberg DE, Smith RE (1987) Nonstationary function optimization using genetic algorithms with dominance and diploidy. In: Grefenstette J (ed) Proceedings of the 2nd international conference on genetic algorithms. Erlbaum, Hillsdale, pp 59–68 Google Scholar
  26. 26.
    Grefenstette JJ (1992) Genetic algorithms for changing environments. In: Proceedings of parallel problem solving from nature II. North-Holland, Amsterdam, pp 137–144 Google Scholar
  27. 27.
    Han M-F, Liao S-H, Chang J-Y, Lin C-T (2012) Dynamic group-based differential evolution using a self-adaptive strategy for global optimization problems. Appl Intell November:1–16. 2012 Google Scholar
  28. 28.
    Hansen N, Ostermeier A (2001) Completely derandomized self-adaptation in evolution strategies. Evol Comput 9(2):159–195 CrossRefGoogle Scholar
  29. 29.
    Kauffman SA (1993) The origins of order: self-organization and selection in evolution. Oxford University Press, New York Google Scholar
  30. 30.
    Kennedy J, Eberhart RC (2001) Swarm intelligence. Morgan Kaufmann, San Francisco Google Scholar
  31. 31.
    Krink T, Rickers P, René T (2000) Applying self-organized criticality to evolutionary algorithms. In: Proceedings of the 6th international conference on parallel problem solving from nature (PPSN-VI). LNCS, vol 1917. Springer, Berlin, pp 375–384 Google Scholar
  32. 32.
    Krink T, Thomsen R (2001) Self-organized criticality and mass extinction in evolutionary algorithms. In: Proceedings of the 2001 IEEE congress on evolutionary computation (CEC’2001), vol 2. IEEE Press, New York, pp 1155–1161 CrossRefGoogle Scholar
  33. 33.
    Lobo FG, Goldberg DE (2003) An overview of the parameter-less genetic algorithm. In: Proceedings of the 7th joint conference on information sciences, pp 20–23 Google Scholar
  34. 34.
    Løvbjerg M, Krink T (2002) Extending particle swarm optimizers with self-organized criticality. In: Proceedings of the 2002 IEEE congress on evolutionary computation, vol 2. IEEE Comput Soc, Los Alamitos, pp 1588–1593 Google Scholar
  35. 35.
    Mitchell M (1994) When will a genetic algorithm outperform hill climbing? In: Cowan J et al (eds) Advances in neural information processing systems 6. Morgan Kaufman, San Mateo, pp 51–58 Google Scholar
  36. 36.
    Morrison RW, De Jong KA (1999) A test problem generator for non-stationary environments. In: Proceedings of the 1999 IEEE congress on evolutionary computation, vol 3. IEEE Press, New York, pp 2047–2053 Google Scholar
  37. 37.
    Neri F, Toivanen J, Makinen R (2007) An adaptive evolutionary algorithm with intelligent mutation local searchers for designing multidrug therapies for HIV. Appl Intell 27(3):219–235 CrossRefGoogle Scholar
  38. 38.
    Neri F, Toivanen J, Cascella GL, Ong Y-S (2007) An adaptive multimeme algorithm for designing HIV multidrug therapies. IEEE/ACM Trans Comput Biol Bioinform 4(2):264–278 CrossRefGoogle Scholar
  39. 39.
    Park T, Choe RI, Ryu KR (2008) Dual-population genetic algorithm for nonstationary optimization. In: Proceedings of the 10th annual conference on genetic and evolutionary computation. ACM, New York, pp 1025–1032 Google Scholar
  40. 40.
    Park T, Ryu KR (2010) A dual population genetic algorithm for adaptive diversity control. IEEE Trans Evol Comput 14(6):865–884 CrossRefGoogle Scholar
  41. 41.
    Ramsey CL, Grefenstette JJ (1993) Case-based initialization of genetic algorithms. In: Forrest S (ed) Proceedings of the 5th international conference genetic algorithms (ICGA’1993). Morgan Kaufmann, San Francisco, pp 84–91 Google Scholar
  42. 42.
    Rudolph G (2001) Self-adaptive mutations may lead to premature convergence. IEEE Trans Evol Comput 5(4):410–414 CrossRefGoogle Scholar
  43. 43.
    Sastry K (2001) Evaluation-relaxation schemes for genetic and evolutionary algorithms. Masters thesis. University of Illinois at Urbana-Champaign, Urbana, IL, USA Google Scholar
  44. 44.
    Thierens D (1999) Scalability problems of simple genetic algorithms. Evol Comput 7(4):331–352 CrossRefGoogle Scholar
  45. 45.
    Tinós R, Yang S (2007) A self-organizing RIGA for dynamic optimization problems. Genet Program Evol Mach 8:255–286 CrossRefGoogle Scholar
  46. 46.
    Ursem RK (2000) Multinational GA optimization techniques in dynamic environments. In: Whitley D et al (eds) Proceedings of the 2000 genetic and evolutionary computation conference (GECCO’2000). Morgan Kaufmann, San Francisco, pp 19–26 Google Scholar
  47. 47.
    Uyar AS, Harmanci AE (2005) A new population based adaptive dominance change mechanism for diploid genetic algorithms in dynamic environments. J Soft Comput 9:803–815 MATHCrossRefGoogle Scholar
  48. 48.
    Winslow N (1997) Introduction to self-organized criticality and earthquakes. Discussion paper. Department of Geological Sciences, University of Michigan.
  49. 49.
    Yang S, Yao X (2005) Experimental study on PBIL algorithms for dynamic optimization problems. Soft Comput 9(11):815–834 MATHCrossRefGoogle Scholar
  50. 50.
    Yang S (2005) Memory-based immigrants for genetic algorithms in dynamic environments. In: Beyer H-G, O’Reilly U-M (eds) Proceedings of the 2005 genetic and evolutionary computation conference (GECCO’2005). ACM, New York, pp 1115–1122 CrossRefGoogle Scholar
  51. 51.
    Yang S (2007) Genetic algorithms with elitism-based immigrants for changing optimization problems. In: Giacobini M et al (eds) Proceedings of the 2007 EvoWorkshops. Lecture notes in computer science, vol 4448. Springer, Berlin, pp 627–636 Google Scholar
  52. 52.
    Yang S (2008) Genetic algorithms with memory- and elitism-based immigrants in dynamic environments. Evol Comput 16(3):385–416 CrossRefGoogle Scholar

Copyright information

© Springer Science+Business Media New York 2013

Authors and Affiliations

  • C. M. Fernandes
    • 1
  • J. L. J. Laredo
    • 2
  • A. C. Rosa
    • 3
  • J. J. Merelo
    • 1
  1. 1.University of GranadaGranadaSpain
  2. 2.University of LuxembourgLuxembourgLuxembourg
  3. 3.Technical University of LisbonLisbonPortugal

Personalised recommendations