Abstract
Nowadays, the application of Evolutionary Multi-Objective Optimization (EMO) algorithms in real-time systems receives considerable interest. In this context, the energy efficiency of computational systems is of paramount relevance. Recently, the use of embedded systems based on heterogeneous (CPU + GPU) platforms is consistently increasing. For example, NVIDIA Jetson cards are low-power computers designed for development of embedded applications. They incorporate Tegra processors which feature a CUDA-capable GPU. This way, Jetson cards can be considered as a prototype of low-power computer of High-Performance Computing. In this work, our interest is focused on the NSGA-II algorithm, a well-known representative of EMO algorithms. The strength of NSGA-II lies in its Non-Dominated Sorting (NDS) procedure of a population of individuals. Our purpose on the low-power computers is twofold: to define and evaluate the parallel NSGA-II versions with major focus on NDS procedure on the Jetson platforms and to determinate the size of NSGA-II problems which can be solved. The results show that the parallel version which achieves the best performance depends on the objectives functions and the frequencies of the clocks of the cores and memory of the GPU. The analysis of the results shows the capability of the Jetson as a low-consumption platform which allows to accelerate the execution of instances of the state-of-the-art EMO algorithm—NSGA-II.
Similar content being viewed by others
References
Brodtkorb AR, Hagen TR, Sætra ML (2013) Graphics processing unit (GPU) programming strategies and trends in GPU computing. J Parallel Distrib Comput 73(1):4–13
Chang X, Dong M, Yang D (2013) Multi-objective real-time dispatching for integrated delivery in a fab using ga based simulation optimization. J Manuf Syst 32(4):741–751
Coll P, Factorovich P, Loiseau I, Gómez R (2013) A linear programming approach for adaptive synchronization of traffic signals. Int Trans Oper Res 20(5):667–679
Corne D, Jerram N, Knowles J, Oates M (2001) PESA-II: region-based selection in evolutionary multiobjective optimization. In: GECCO, pp 283–290
Cortés C, Sáez D, Milla F, Nuez A, Riquelme M (2010) Hybrid predictive control for real-time optimization of public transport systems’ operations based on evolutionary multi-objective optimization. Transp Res Part C Emerg Technol 18(5):757–769
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
Deb K, Sundar J, Udaya Bhaskara Rao N, Chaudhuri S (2006) Reference point based multi-objective optimization using evolutionary algorithms. Int J Comput Intell Res 2(3):273–286
Deb K, Thiele L, Laumanns M, Zitzler E (2002) Scalable multi-objective optimization test problems. In: WCCI, pp 825–830
Dehuri S, Ghosh A, Mall R (2007) Parallel multi-objective genetic algorithm for classification rule mining. IETE J Res 53(5):475–483
Dendaluce M, Valera JJ, Gómez-Garay V, Irigoyen E, Larzabal E (2014) Microcontroller implementation of a multi objective genetic algorithm for real-time intelligent control. In: International Joint Conference SOCO13-CISIS13-ICEUTE13, pp 71–80. Springer
Domínguez J, Montiel O, Sepúlveda R, Medina N (2013) High performance architecture for NSGA-II. In: Recent Advances on Hybrid Intelligent Systems, pp 451–461. Springer
Dujardin Y, Vanderpooten D, Boillot F (2015) A multi-objective interactive system for adaptive traffic control. Eur J Oper Res 244(2):601–610
Durillo JJ, Nebro AJ, Luna F, Alba E (2008) A study of master-slave approaches to parallelize NSGA-II. In: IPDPS, pp 1–8. IEEE
Fang H, Wang Q, Tu YC, Horstemeyer MF (2008) An efficient non-dominated sorting method for evolutionary algorithms. Evol Comput 16(3):355–384
Filatovas E, Kurasova O, Sindhya K (2015) Reference point based multi-objective optimization using evolutionary algorithms. Informatica 26(1):33–50
Gupta S, Tan G (2015) A scalable parallel implementation of evolutionary algorithms for multi-objective optimization on GPUs. In: CEC, pp 1567–1574. IEEE
Harris M (2014) Maxwell: the most advanced CUDA GPU ever made. https://devblogs.nvidia.com/parallelforall/maxwell-most-advanced-cuda-gpu-ever-made/
Huband S, Hingston P, Barone L, While L (2006) A review of multiobjective test problems and a scalable test problem toolkit. IEEE Trans Evol Comput 10(5):477–506
Jensen MT (2003) Reducing the run-time complexity of multiobjective EAs: the NSGA-II and other algorithms. IEEE Trans Evol Comput 7(5):503–515
Khamis MA, Gomaa W (2014) Adaptive multi-objective reinforcement learning with hybrid exploration for traffic signal control based on cooperative multi-agent framework. Eng Appl Artif Intell 29:134–151
Knowles J, Corne D (2000) Approximating the non-dominated front using the Pareto archived evolution strategy. Evol Comput 8(2):149–172
Lančinskas A, Žilinskas J (2012) Approaches to parallelize pareto ranking in NSGA-II algorithm. In: PPAM, pp 371–380. Springer
Lančinskas A, Żilinskas J (2013) Solution of multi-objective competitive facility location problems using parallel NSGA-II on large scale computing systems. In: PARA, pp 422–433. Springer
Li Y, Canepa E, Claudel C (2014) Optimal traffic control in highway transportation networks using linear programming. In: ECC, pp 2880–2887. IEEE
Lokuciejewski P, Marwedel P (2011) Multi-objective optimizations. Springer, Netherlands, Dordrecht, pp 197–227. doi:10.1007/978-90-481-9929-7_7
Mamdoohi G, Abas AF, Samsudin K, Ibrahim NH, Hidayat A, Mahdi MA (2012) Implementation of genetic algorithm in an embedded microcontroller-based polarization control system. Eng Appl Artif Intell 25(4):869–873
McClymont K, Keedwell E (2012) Deductive sort and climbing sort: new methods for non-dominated sorting. Evol Comput 20(1):1–26
Miettinen K (1999) Nonlinear multiobjective optimization. Kluwer Academic Publishers, Boston
NVIDIA: NVIDIA’s next generation CUDA compute architecture: Kepler GK110 (2012). https://www.nvidia.com/content/PDF/kepler/NVIDIA-Kepler-GK110-Architecture-Whitepaper.pdf
NVIDIA: Tegra K1 technical reference manual (2014). https://developer.nvidia.com/gameworksdownload#?search=Tegra%20K1%20Technical
NVIDIA: CUDA C programming guide. version 7.0 (2015). http://docs.nvidia.com/cuda/cuda-c-programming-guide/
Odan FK, Ribeiro Reis LF, Kapelan Z (2015) Real-time multiobjective optimization of operation of water supply systems. J Water Resour Plan Manag 141(9):04015,011
de Oliveira FB, Davendra D, Guimarães FG (2013) Multi-objective differential evolution on the GPU with C-CUDA. In: Soft Computing Models in Industrial and Environmental Applications, pp 123–132. Springer
Shi C, Chen M, Shi Z (2005) A fast nondominated sorting algorithm. In: ICNN, vol 3, pp 1605–1610. IEEE
Smutnicki C, Rudy J, Żelazny D (2014) Very fast non-dominated sorting. Decis Mak Manuf Serv 8(1–2):13–23
Wang, Z, Ju G (2009) A parallel genetic algorithm in multi-objective optimization. In: Control and Decision Conference, 2009. CCDC’09. Chinese, pp 3497–3501. IEEE
Wong ML (2009) Parallel multi-objective evolutionary algorithms on graphics processing units. In: GECCO, pp 2515–2522. ACM
Yu Q, Chen C, Pan Z (2005) Parallel genetic algorithms on programmable graphics hardware. In: Advances in Natural Computation, pp 1051–1059. Springer
Zhang Q, Li H (2007) Moea/d: a multiobjective evolutionary algorithm based on decomposition. IEEE Trans Evol Comput 11(6):712–731
Zhang X, Ye T, Cheng R, Jin Y (2012) An efficient approach to non-dominated sorting for evolutionary multi-objective optimization. IEEE Trans Evol Comput 19(2):201–213
Zitzler E, Künzli S (2004) Indicator-based selection in multiobjective search. In: Parallel Problem Solving from Nature-PPSN VIII, pp 832–842. Springer
Zitzler E, Laumanns M, Thiele L (2001) SPEA2: improving the strength Pareto evolutionary algorithm. Tech. Rep. 103, Computer Engineering and Networks Laboratory (TIK), ETH Zurich, Zurich, Switzerland
Author information
Authors and Affiliations
Corresponding author
Additional information
This work has been partially supported by the Spanish Ministry of Science throughout projects TIN2015-66680 and CAPAP-H5 network TIN2014-53522, by J. Andalucía through projects P12-TIC-301 and P11-TIC7176, and by the European Regional Development Fund (ERDF). Ernestas Filatovas has been partially granted by the European COST Action IC1305: Network for sustainable Ultrascale computing (NESUS).
Rights and permissions
About this article
Cite this article
Moreno, J.J., Ortega, G., Filatovas, E. et al. Using low-power platforms for Evolutionary Multi-Objective Optimization algorithms. J Supercomput 73, 302–315 (2017). https://doi.org/10.1007/s11227-016-1862-0
Published:
Issue Date:
DOI: https://doi.org/10.1007/s11227-016-1862-0