The Journal of Supercomputing

, Volume 74, Issue 8, pp 4019–4036 | Cite as

Optimization of resources in parallel systems using a multiobjective artificial bee colony algorithm

  • César Gómez-MartínEmail author
  • Miguel A. Vega-Rodríguez


Most of the approaches to achieve exascale computing heavily rely on designing power efficient hardware, but experts usually forget that the usage of efficient middlewares, like resource managers or job schedulers, can also play an important role in optimizing power and performance of supercomputing infrastructures. For the optimization of both, power and performance, we propose the implementation of a multiobjective version of artificial bee colony algorithm (MOABC). We have compared our algorithm with other deterministic (first-fit and MOHEFT) and stochastic (NSGA-II) resource selection approaches. The results of our simulations show that, in real computing environments, MOABC is more likely to obtain better optimizations of response times and power consumption.


Resource selection Parallel computing Performance evaluation Energy awareness Multiobjective optimization 



This work was partially Funded by the AEI (State Research Agency, Spain) and the ERDF (European Regional Development Fund, EU), under the contract TIN2016-76259-P (PROTEIN Project).


  1. 1.
    Bodas D, Song J, Rajappa M, Hoffman A (2014) Simple power-aware scheduler to limit power consumption by HPC system within a budget. In: Proceedings of the 2nd International Workshop on Energy Efficient Supercomputing, E2SC ’14. IEEE Press, Piscataway, NJ, USA, pp 21–30.
  2. 2.
    Chakraborty A, Kar AK (2017) Swarm intelligence: a review of algorithms. In: Patnaik S, Yang XS, Nakamatsu K (eds) Nature-inspired computing and optimization: theory and applications. Springer, Cham, pp 475–494. CrossRefGoogle Scholar
  3. 3.
    Chiesi M, Vanzolini L, Mucci C, Scarselli EF, Guerrieri R (2015) Power-aware job scheduling on heterogeneous multicore architectures. IEEE Trans Parallel Distrib Syst 26(3):868–877. CrossRefGoogle Scholar
  4. 4.
    Cicirello VA (2006) Non-wrapping order crossover: an order preserving crossover operator that respects absolute position. In: Proceedings of the 8th Annual Conference on Genetic and Evolutionary Computation. ACM, pp 1125–1132.
  5. 5.
    Coello CA, Dhaenens C, Jourdan L (2010) Advances in multi-objective nature inspired computing. Springer, Berlin. CrossRefzbMATHGoogle Scholar
  6. 6.
    Deb K, Pratap A, Agarwal S, Meyarivan T (2002) A fast and elitist multiobjective genetic algorithm: NSGA-II. IEEE Trans Evol Comput 6(2):182–197. CrossRefGoogle Scholar
  7. 7.
    Durillo JJ, Nae V, Prodan R (2014) Multi-objective energy-efficient workflow scheduling using list-based heuristics. Fut Gener Comput Syst 36:221–236. CrossRefGoogle Scholar
  8. 8.
    Etinski M, Corbalan J, Labarta J, Valero M (2012) Parallel job scheduling for power constrained HPC systems. Parallel Comput 38(12):615–630. MathSciNetCrossRefGoogle Scholar
  9. 9.
    Feitelson D (2001) Metrics for parallel job scheduling and their convergence. In: Job Scheduling Strategies for Parallel Processing, Lecture Notes in Computer Science, vol. 2221. Springer Berlin Heidelberg, pp 188–205.
  10. 10.
    Gómez-Martín C, Vega-Rodríguez MA, González-Sánchez JL (2015) Performance and energy aware scheduling simulator for HPC: evaluating different resource selection methods. Concurr Comput Pract Exp 27(17):5436–5459. CrossRefGoogle Scholar
  11. 11.
    Goldberg DE (1989) Genetic algorithm in search optimization and machine learning. Addison Wesley Publishing Company, ReadingzbMATHGoogle Scholar
  12. 12.
    Kaplan JM, Forrest W, Kindler N (2008) Revolutionizing data center energy efficiency. Technical Report, McKinsey & CompanyGoogle Scholar
  13. 13.
    Karaboga D, Basturk B (2007) A powerful and efficient algorithm for numerical function optimization: artificial bee colony (ABC) algorithm. J Glob Optim 39(3):459–471. MathSciNetCrossRefzbMATHGoogle Scholar
  14. 14.
    Karaboga D, Gorkemli B, Ozturk C, Karaboga N (2014) A comprehensive survey: artificial bee colony (ABC) algorithm and applications. Artif Intell Rev 42(1):21–57. CrossRefGoogle Scholar
  15. 15.
    Lee EK, Viswanathan H, Pompili D (2017) Proactive thermal-aware resource management in virtualized HPC cloud datacenters. IEEE Trans Cloud Comput 5(2):234–248. CrossRefGoogle Scholar
  16. 16.
    Lifka D (1995) The ANL/IBM SP scheduling system. In: Job Scheduling Strategies for Parallel Processing: IPPS ’95 Workshop, Lecture Notes in Computer Science, vol. 949. Springer Berlin Heidelberg, pp 295–303.
  17. 17.
    Mair J, Huang Z, Eyers D, Chen Y (2015) Quantifying the energy efficiency challenges of achieving exascale computing. In: 15th IEEE/ACM International Symposium on Cluster, Cloud and Grid Computing (CCGrid), pp 943–950.
  18. 18.
    Maqbool J, Oh S, Fox GC (2015) Evaluating ARM HPC clusters for scientific workloads. Concurr Comput Pract Exp 27(17):5390–5410. CrossRefGoogle Scholar
  19. 19.
    Messina P (2017) The exascale computing project. Comput Sci Eng 19(3):63–67. CrossRefGoogle Scholar
  20. 20.
    Mu’alem AW, Feitelson DG (2001) Utilization, predictability, workloads, and user runtime estimates in scheduling the IBM SP2 with backfilling. IEEE Trans Parallel Distrib Syst 12(6):529–543. CrossRefGoogle Scholar
  21. 21.
    Novotnỳ M (2009) Job scheduling with the SLURM resource manager. Bachelor Thesis, Masaryk University, Brno, Czech RepublicGoogle Scholar
  22. 22.
    Rajovic N, Vilanova L, Villavieja C, Puzovic N, Ramirez A (2013) The low power architecture approach towards exascale computing. J Comput Sci 4(6):439–443. CrossRefGoogle Scholar
  23. 23.
    Sofia A Sathya, GaneshKumar P (2018) Multi-objective task scheduling to minimize energy consumption and makespan of cloud computing using NSGA-II. J Netw Syst Manag 26(2):463–485. CrossRefGoogle Scholar
  24. 24.
    Spec power and performance benchmark methodology v2.1. Accessed: 2018-4-27
  25. 25.
    Specpower_ssj2008 results. Accessed: 2018-4-27
  26. 26.
    Staples G (2006) TORQUE resource manager. In: Proceedings of the 2006 ACM/IEEE Conference on Supercomputing, SC ’06. ACM, New York, NY, USA.
  27. 27.
    Tang K, Tiwari D, Gupta S, Vazhkudai SS, He X (2017) Effective running of end-to-end HPC workflows on emerging heterogeneous architectures. In: 2017 IEEE International Conference on Cluster Computing (CLUSTER), pp 344–348.
  28. 28.
    The Green500 list. Accessed: 2018-4-27
  29. 29.
    Wang B, Schmidl D, Terboven C, Müller MS (2017) Dynamic application-aware power capping. In: Proceedings of the 5th International Workshop on Energy Efficient Supercomputing, E2SC’17. ACM, New York, NY, USA, pp 1:1–1:8.
  30. 30.
    Yang X, Zhou Z, Wallace S, Lan Z, Tang W, Coghlan S, Papka ME (2013) Integrating dynamic pricing of electricity into energy aware scheduling for HPC systems. In: Proceedings of the International Conference on High Performance Computing, Networking, Storage and Analysis, SC ’13. ACM, New York, NY, USA, pp 60:1–60:11.
  31. 31.
    Yoo AB, Jette MA, Grondona M (2003) SLURM: simple linux utility for resource management. In: Job Scheduling Strategies for Parallel Processing. Springer, pp 44–60.
  32. 32.
    Zola E, Kassler AJ (2017) Optimising for energy or robustness? Trade-offs for VM consolidation in virtualized datacenters under uncertainty. Optim Lett 11(8):1571–1592. MathSciNetCrossRefzbMATHGoogle Scholar
  33. 33.
    Zotkin D, Keleher P (1999) Job-length estimation and performance in backfilling schedulers. In: Proceedings of the Eighth International Symposium on High Performance Distributed Computing, pp 236–243.

Copyright information

© Springer Science+Business Media, LLC, part of Springer Nature 2018

Authors and Affiliations

  1. 1.Escuela Politécnica de CáceresUniversity of ExtremaduraCáceresSpain

Personalised recommendations