Randomized Parameter Settings for Heterogeneous Workers in a Pool-Based Evolutionary Algorithm
详细信息 查看全文
- 作者：Mario Garc铆a-Valdez (19)
Leonardo Trujillo (19)
Juan Juli谩n Merelo-Gu茅rvos (20)
Francisco Fern谩ndez-de-Vega (21) - 关键词：Pool ; based Evolutionary Algorithms ; Distributed Evolutionary Algorithms ; Algorithm Parametrization
- 刊名：Lecture Notes in Computer Science
- 出版年：2014
- 出版时间：2014
- 年：2014
- 卷：8672
- 期：1
- 页码：702-710
- 全文大小：366 KB
- 参考文献：1. Alba, E.: Parallel Metaheuristics: A New Class of Algorithms. John Wiley & Sons (2005)
2. Cant煤-Paz, E.: Parameter setting in parallel genetic algorithms. In: Lobo, F.G., Lima, C.F., Michalewicz, Z. (eds.) Parameter Setting in Evolutionary Algorithms. SCI, vol.聽54, pp. 259鈥?76. Springer, Heidelberg (2007) CrossRef
3. De Jong, K.A., Potter, M.A., Spears, W.M.: Using problem generators to explore the effects of epistasis. In: B盲ck, T. (ed.) ICGA, pp. 338鈥?45. Morgan Kaufmann (1997)
4. De Jong, K.A., Spears, W.M.: An analysis of the interacting roles of population size and crossover in genetic algorithms. In: Schwefel, H.-P., M盲nner, R. (eds.) PPSN 1990. LNCS, vol.聽496, pp. 38鈥?7. Springer, Heidelberg (1991) CrossRef
5. Di Martino, S., Ferrucci, F., Maggio, V., Sarro, F.: Towards migrating genetic algorithms for test data generation to the cloud. In: Software Testing in the Cloud: Perspectives on an Emerging Discipline, pp. 113鈥?35. IGI Global (2013)
6. Eiben, A.E., Smith, J.E.: Introduction to Evolutionary Computing. Springer (2003)
7. Fazenda, P., McDermott, J., O鈥橰eilly, U.-M.: A library to run evolutionary algorithms in the cloud using mapReduce. In: Di Chio, C., et al. (eds.) EvoApplications 2012. LNCS, vol.聽7248, pp. 416鈥?25. Springer, Heidelberg (2012) CrossRef
8. Fern谩ndez De Vega, F., Olague, G., Trujillo, L., Lombra帽a Gonz谩lez, D.: Customizable execution environments for evolutionary computation using boinc + virtualization. Natural Computing聽12(2), 163鈥?77 (2013) CrossRef
9. Garcia-Valdez, M., Mancilla, A., Trujillo, L., Merelo, J.-J., Fernandez-de Vega, F.: Is there a free lunch for cloud-based evolutionary algorithms? In: 2013 IEEE Congress on Evolutionary Computation (CEC), pp. 1255鈥?262 (2013)
10. Garc铆a-Valdez, M., Trujillo, L., de Vega, F.F., Merelo Guerv贸s, J.J., Olague, G.: Evospace-interactive: A framework to develop distributed collaborative-interactive evolutionary algorithms for artistic design. In: Machado, P., McDermott, J., Carballal, A. (eds.) EvoMUSART 2013. LNCS, vol.聽7834, pp. 121鈥?32. Springer, Heidelberg (2013) CrossRef
11. Garc铆a-Valdez, M., Trujillo, L., Fern谩ndez de Vega, F., Merelo Guerv贸s, J.J., Olague, G.: EvoSpace: A Distributed Evolutionary Platform Based on the Tuple Space Model. In: Esparcia-Alc谩zar, A.I. (ed.) EvoApplications 2013. LNCS, vol.聽7835, pp. 499鈥?08. Springer, Heidelberg (2013) CrossRef
12. Gong, Y., Fukunaga, A.: Distributed island-model genetic algorithms using heterogeneous parameter settings. In: IEEE Congress on Evolutionary Computation, pp. 820鈥?27. IEEE (2011)
13. Holland, J.H.: Adaptation in Natural and Artificial Systems. MIT Press, Cambridge (1992)
14. Kennedy, J., Spears, W.: Matching algorithms to problems: an experimental test of the particle swarm and some genetic algorithms on the multimodal problem generator. In: The 1998 IEEE International Conference on Evolutionary Computation Proceedings, IEEE World Congress on Computational Intelligence 1998, pp. 78鈥?3 (May 1998)
15. Kramer, O.: Self-Adaptive Heuristics for Evolutionary Computation. SCI, vol.聽147. Springer, Heidelberg (2008)
16. Lobo, F.G., Lima, C.F., Michalewicz, Z.: Parameter Setting in Evolutionary Algorithms. Springer Publishing Company, Incorporated (2007)
17. Merelo-Guervos, J., Castillo, P., Laredo, J.L.J., Mora Garcia, A., Prieto, A.: Asynchronous distributed genetic algorithms with Javascript and JSON. In: 2008 IEEE Congress on Evolutionary Computation (CEC), pp. 1372鈥?379 (June 2008)
18. Sherry, D., Veeramachaneni, K., McDermott, J., O鈥橰eilly, U.-M.: Flex-GP: Genetic programming on the cloud. In: Di Chio, C., et al. (eds.) EvoApplications 2012. LNCS, vol.聽7248, pp. 477鈥?86. Springer, Heidelberg (2012) CrossRef
19. Smaoui Feki, M., Nguyen, H.V., Garbey, M.: Parallel genetic algorithm implementation for boinc. In: PARCO, pp. 212鈥?19 (2009)
20. Tanabe, R., Fukunaga, A.: Evaluation of a randomized parameter setting strategy for island-model evolutionary algorithms. In: IEEE Congress on Evolutionary Computation, pp. 1263鈥?270. IEEE (2013)
21. Trujillo, L., Valdez, M.G., de Vega, F.F., Guerv贸s, J.J.M.: Fireworks: Evolutionary art project based on evospace-interactive. In: IEEE Congress on Evolutionary Computation, pp. 2871鈥?878. IEEE (2013) - 作者单位：Mario Garc铆a-Valdez (19)
Leonardo Trujillo (19)
Juan Juli谩n Merelo-Gu茅rvos (20)
Francisco Fern谩ndez-de-Vega (21)
19. Instituto Tecnol贸gico de Tijuana, Tijuana, B.C., M茅xico
20. Universidad de Granada, Granada, Spain
21. Grupo de Evoluci贸n Artificial, Universidad de Extremadura, M茅rida, Spain - ISSN：1611-3349
文摘
Recently, several Pool-based Evolutionary Algorithms (PEAs) have been proposed, that asynchronously distribute an evolutionary search among heterogeneous devices, using controlled nodes and nodes outside the local network, through web browsers or cloud services. In PEAs, the population is stored in a shared pool, while distributed processes called workers execute the actual evolutionary search. This approach allows researchers to use low cost computational power that might not be available otherwise. On the other hand, it introduces the challenge of leveraging the computing power of heterogeneous and unreliable resources. The heterogeneity of the system suggests that using a heterogeneous parametrization might be a better option, so the goal of this work is to test such a scheme. In particular, this paper evaluates the strategy proposed by Gong and Fukunaga for the Island-Model, which assigns random control parameter values to each worker. Experiments were conducted to assess the viability of this strategy on pool-based EAs using benchmark problems and the EvoSpace framework. The results suggest that the approach can yield results which are competitive with other parametrization approaches, without requiring any form of experimental tuning.