Abstract
The success of local search techniques in the solution of combinatorial optimization problems has motivated their incorporation into multi-objective evolutionary algorithms, giving rise to the so-called multi-objective memetic algorithms (MOMAs). The main advantage for adopting this sort of hybridization is to speed up convergence to the Pareto front. However, the use of MOMAs introduces new issues, such as how to select the solutions to which the local search will be applied and for how long to run the local search engine (the use of such a local search engine has an extra computational cost). Here, we propose a new MOMA which switches between a hypervolume-based global optimizer and an IGD+-based local search engine. Our proposed local search engine adopts a novel clustering technique based on the IGD+ indicator for splitting the objective space into sub-regions. Since both computing the hypervolume and applying a local search engine are very costly procedures, we propose a GPU-based parallelization of our algorithm. Our preliminary results indicate that our MOMA is able to converge faster than SMS-EMOA to the true Pareto front of multi-objective problems having different degrees of difficulty.
E. Manoatl Lopez—Author acknowledges support from CONACyT and CINVESTAV-IPN to pursue graduate studies in Computer Science.
C.A. Coello Coello—Author gratefully acknowledges support from CONACyT project no. 221551 and from a Cátedra Marcos Moshinsky 2014 in Mathematics.
This is a preview of subscription content, log in via an institution to check access.
Access this chapter
Tax calculation will be finalised at checkout
Purchases are for personal use only
Notes
- 1.
SIMD (Single Instruction Multiple Data) is a computer architecture which can handle only one instruction but applies it to many data streams simultaneously [9].
- 2.
The GPU-based approach computes in a faster way the hypervolume contribution of a point.
- 3.
The GPU platform and API developed by Nvidia called CUDA [15] (Computer Unified Device Architecture), which is the one adopted in this work, is based on the CUDA-C language, which is an extension of C that allows the development of GPU routines called kernels. Each kernel defines instructions that are executed on the GPU by many threads at the same time.
References
Bader, J., Zitzler, E.: HypE: An Algorithm for Fast Hypervolume-Based Many-Objective Optimization. Evolutionary Computation, 19(1): 45–76, Spring, 2011
de Oliveira, F.B., Davendra, D., Guimarães, F.G.: Multi-objective differential evolution on the GPU with C-CUDA. In: Snášel, V., Abraham, A., Corchado, E.S. (eds.) SOCO 2012. AISC, vol. 188, pp. 123–132. Springer, Heidelberg (2013)
Beume, N., Naujoks, B., Emmerich, M.: SMS-EMOA: multiobjective selection based on dominated hypervolume. Eur. J. Oper. Res. 181(3), 1653–1669 (2007)
Coello Coello, C.A., Lamont, G.B., Van Veldhuizen, D.A.: Evolutionary Algorithms for Solving Multi-Objective Problems, 2nd edn. Springer, New York (2007). ISBN 978-0-387-33254-3
Das, I., Dennis, J.E.: Normal-boundary intersection: a new method for generating the pareto surface in nonlinear multicriteria optimization problems. SIAM J. Optim. 8(3), 631–657 (1998)
Deb, K., Pratap, A., Agarwal, S., Meyarivan, T.: A fast and elitist multiobjective genetic algorithm: NSGA-II. IEEE Trans. Evol. Comput. 6(2), 182–197 (2002)
Deb, K., Thiele, L., Laumanns, M., Zitzler, E.: Scalable test problems for evolutionary multiobjective optimization. In: Abraham, A., Jain, L., Goldberg, R. (eds.) Evolutionary Multiobjective Optimization. Theoretical Advances and Applications, pp. 105–145. Springer, New York (2005)
Emmerich, M.T.M., Deutz, A.H.: Test problems based on Lamé superspheres. In: Obayashi, S., Deb, K., Poloni, C., Hiroyasu, T., Murata, T. (eds.) EMO 2007. LNCS, vol. 4403, pp. 922–936. Springer, Heidelberg (2007)
Flynn, M.J.: Some computer organizations and their effectiveness. IEEE Trans. Comput. 21(9), 948–960 (1972)
Huband, S., Barone, L., While, L., Hingston, P.: A scalable multi-objective test problem toolkit. In: Coello Coello, C.A., Hernández Aguirre, A., Zitzler, E. (eds.) EMO 2005. LNCS, vol. 3410, pp. 280–295. Springer, Heidelberg (2005)
Huband, S., Hingston, P., Barone, L., While, L.: A review of multiobjective test problems and a scalable test problem toolkit. IEEE Trans. Evol. Comput. 10(5), 477–506 (2006)
Ishibuchi, H., Masuda, H., Nojima, Y.: A study on performance evaluation ability of a modified inverted generational distance indicator. In: 2015 Genetic and Evolutionary Computation Conference (GECCO 2015), 11–15 July 2015, Madrid, Spain, pp. 695–702. ACM Press (2015). ISBN 978-1-4503-3472-3
Ishibuchi, H., Masuda, H., Tanigaki, Y., Nojima, Y.: Modified distance calculation in generational distance and inverted generational distance. In: Gaspar-Cunha, A., Henggeler Antunes, C., Coello, C.C. (eds.) EMO 2015. LNCS, vol. 9019, pp. 110–125. Springer, Heidelberg (2015)
Lopez, E.M., Antonio, L.M., Coello Coello, C.A.: A GPU-based algorithm for a faster hypervolume contribution computation. In: Gaspar-Cunha, A., Henggeler Antunes, C., Coello, C.C. (eds.) EMO 2015. LNCS, vol. 9019, pp. 80–94. Springer, Heidelberg (2015)
NVIDIA Corporation. Cuda zone (2014)
Pilát, M., Neruda, R.: Hypervolume-based local search in multi-objective evolutionary optimization. In: 2014 Genetic and Evolutionary Computation Conference (GECCO 2014), 12–16 July 2014, Vancouver, Canada, pp. 637–644. ACM Press (2014). ISBN 978-1-4503-2662-9
Tan, Y.-Y., Jiao, Y.-C., Li, H., Wang, X.-K.: MOEA/D-SQA: a multi-objective memetic algorithm based on decomposition. Eng. Optim. 44(9), 1095–1115 (2012)
Wong, M.L., Cui, G.: Data mining using parallel multi-objective evolutionary algorithms on graphics processing units. In: Tsutsui, S., Collet, P. (eds.) Massively Parallel Evolutionary Computation on GPGPUs, pp. 287–307. Springer, Heidelberg (2013). ISBN 978-3-642-37958-1
Author information
Authors and Affiliations
Corresponding author
Editor information
Editors and Affiliations
Rights and permissions
Copyright information
© 2016 Springer International Publishing AG
About this paper
Cite this paper
Manoatl Lopez, E., Coello Coello, C.A. (2016). A Parallel Multi-objective Memetic Algorithm Based on the IGD+ Indicator. In: Handl, J., Hart, E., Lewis, P., López-Ibáñez, M., Ochoa, G., Paechter, B. (eds) Parallel Problem Solving from Nature – PPSN XIV. PPSN 2016. Lecture Notes in Computer Science(), vol 9921. Springer, Cham. https://doi.org/10.1007/978-3-319-45823-6_44
Download citation
DOI: https://doi.org/10.1007/978-3-319-45823-6_44
Published:
Publisher Name: Springer, Cham
Print ISBN: 978-3-319-45822-9
Online ISBN: 978-3-319-45823-6
eBook Packages: Computer ScienceComputer Science (R0)