Soft Computing

, Volume 21, Issue 19, pp 5557–5572 | Cite as

Optimizing a parameterized message-passing metaheuristic scheme on a heterogeneous cluster

Focus

Abstract

This paper studies the development of message-passing parameterized schemes of metaheuristics and the use of auto-tuning techniques to optimize their execution time. Previous parameterized schemes on shared-memory are extended with new metaheuristic-parallelism parameters representing the migration frequency, the size of the migration and the number of processes. An optimization Problem of Electricity Consumption in Exploitation of Wells is used as test case. Experimental results in heterogeneous systems are reported for this problem, and the influence of the parallelism parameters is studied. The message-passing scheme proves to be preferable to the shared-memory scheme in terms of execution time, giving similar results for the goodness of the solutions. In the executions in a heterogeneous cluster, the best experimental results are obtained in terms of speed-up and quality of the solution by mapping a number of processes close to the value of the population size, and considering the relative speeds of the components of the heterogeneous system. Furthermore, optimized execution times can be achieved with auto-tuning techniques based on theoretical–empirical models of the execution time.

Keywords

Parameterized metaheuristic schemes Parallel metaheuristics Message-passing metaheuristic schemes Heterogeneous computing Auto-tuning 

References

  1. Alba E (2005) Parallel metaheuristics: a new class of algorithms. Wiley-Interscience, New YorkCrossRefMATHGoogle Scholar
  2. Almeida F, Giménez D, López-Espín J-J (2011) A parameterized shared-memory scheme for parameterized metaheuristics. J Supercomput 58(3):292–301CrossRefGoogle Scholar
  3. Almeida F, Giménez D, López-Espín J-J, Pérez-Pérez M (2013) Parameterised schemes of metaheuristics: basic ideas and applications with genetic algorithms, scatter search and GRASP. IEEE Trans Syst Man Cybern A Syst Hum 43(3):570–586CrossRefGoogle Scholar
  4. Azadeh A, Faiz Z (2011) A meta-heuristic framework for forecasting household electricity consumption. Appl Soft Comput 11(1):614–620CrossRefGoogle Scholar
  5. Azadeh A, Ghaderi SF, Tarverdian S, Saberi M (2007) Integration of artificial neural networks and genetic algorithm to predict electrical energy consumption. Appl Math Comput 186(2):1731–1741MathSciNetMATHGoogle Scholar
  6. Birattari M (2009) Tuning metaheuristics: a machine learning perspective, 2nd edn. Springer Publishing Company, BerlinCrossRefMATHGoogle Scholar
  7. Cantú-Paz E (1998) A survey of parallel genetic algorithms. Calculateurs Paralleles, Reseaux et Systems Repartis 10Google Scholar
  8. Cantú-Paz E, Goldberg DE (1999) On the scalability of parallel genetic algorithms. Evol Comput 7(4):429–449CrossRefGoogle Scholar
  9. Cutillas-Lozano J-M, Giménez D (2013) Determination of the kinetic constants of a chemical reaction in heterogeneous phase using parameterized metaheuristics. In: Proceedings of the international conference on computational science, pp 787–796Google Scholar
  10. Cutillas-Lozano J-M, Giménez D (2014) Optimizing shared-memory hyperheuristics on top of parameterized metaheuristics. In Proceedings of the international conference on computational science, pp 20–29Google Scholar
  11. Cutillas-Lozano L-G, Giménez D, Giménez D (2012) Modeling shared-memory metaheuristic schemes for electricity consumption. In: 9th International conference on distributed computing and artificial intelligence, pp 33–40Google Scholar
  12. Cutillas-Lozano J-M, Giménez D, Almeida F (2015) Hyperheuristics based on parametrized metaheuristic schemes. In: Proceedings of the genetic and evolutionary computation conference, pp 361–368Google Scholar
  13. Frigo M, Johnson SG (1998) FFTW: an adaptive software architecture for the FFT. IEEE Int Conf Acoust Speech Signal Process 3:1381–1384Google Scholar
  14. Harik GR, Cantú-Paz E, Goldberg DE, Miller BL (1999) The gambler’s ruin problem, genetic algorithms, and the sizing of populations. Evol Comput 7(3):231–253CrossRefGoogle Scholar
  15. Imbernón B, Cecilia JM, Giménez D (2016) Enhancing metaheuristic-based virtual screening methods on massively parallel and heterogeneous systems. In: Proceedings of the 7th international workshop on programming models and applications for multicores and manycores, pp 50–58Google Scholar
  16. Kalinov A, Lastovetsky A (2001) Heterogeneous distribution of computations while solving linear algebra problems on network of heterogeneous computers. J Parallel Distrib Comput 61(44):520–535CrossRefMATHGoogle Scholar
  17. Karafotias G, Hoogendoorn M, Eiben ÁE (2015) Parameter control in evolutionary algorithms: trends and challenges. IEEE Trans Evol Comput 19(2):167–187CrossRefGoogle Scholar
  18. Katagiri T, Kise K, Honda H (2004) Effect of auto-tuning with user’s knowledge for numerical software. In: Vassiliadis JLGS, Piuri V (eds) Proceedings of the first conference on computing frontiers, pp 12–25Google Scholar
  19. Lässig J, Sudholt D (2011a) Adaptive population models for offspring populations and parallel evolutionary algorithms. In: Foundations of genetic algorithms, 11th international workshop, pp 181–192Google Scholar
  20. Lässig J, Sudholt D (2011b) Analysis of speedups in parallel evolutionary algorithms for combinatorial optimization—(extended abstract). In: Algorithms and computation—22nd international symposium, pp 405–414Google Scholar
  21. Mezmaz M-S, Kessaci Y, Lee YC, Melab N, Talbi E-G, Zomaya AY, Tuyttens D (2010) A parallel island-based hybrid genetic algorithm for precedence-constrained applications to minimize energy consumption and makespan. In: GRID, pp 274–281Google Scholar
  22. Raidl GR (2006) A unified view on hybrid metaheuristics. Hybrid metaheuristics, third international workshop, LNCS 4030:1–12Google Scholar
  23. Talbi E (2015) Parallel evolutionary combinatorial optimization. In: Springer handbook of, computational intelligence, pp 1107–1125Google Scholar
  24. Whaley RC, Petitet A, Dongarra J (2001) Automated empirical optimizations of software and the ATLAS project. Parallel Comput 27(1–2):3–35CrossRefMATHGoogle Scholar
  25. Yu T, Sastry K, Goldberg DE (2005) Online population size adjusting using noise and substructural measurements. In: Proceedings of the IEEE congress on evolutionary computation, pp 2491–2498Google Scholar

Copyright information

© Springer-Verlag Berlin Heidelberg 2016

Authors and Affiliations

  1. 1.Departamento de Informática y SistemasUniversity of MurciaMurciaSpain

Personalised recommendations