Study of Different Small-world Topology Generation Mechanisms for Genetic Algorithms
English
Dorronsoro, Bernabé[University of Luxembourg > Interdisciplinary Centre for Security, Reliability and Trust (SNT) > >]
Bouvry, Pascal[University of Luxembourg > Faculty of Science, Technology and Communication (FSTC) > Computer Science and Communications Research Unit (CSC) >]
2012
IEEE Congress on Evolutionary Computation
IEEE
1580 - 1587
Yes
No
International
978-1-4673-1508-1
Congress on Evolutionary Computation
from 10-06-2012 to 15-06-2012
Brisbane
Australia
[en] The use of small-world graphs as a topology structure for the population of Evolutionary Algorithms (EAs) has been recently proposed in the literature. The motivation is clear: the high clustering coefficient and low characteristic path length of such networks makes them suitable for fast local information dissemination, while at the same time preventing it from quickly spreading on the whole population, as it happens in panmictic populations. However, even though several papers addressed this issue so far, only a few of them are able to provide competitive results with other panmictic and/or decentralized population EAs with similar configurations. Therefore, we perform ax study in this work, both theoretically and empirically, on the most appropriate mechanisms to generate SW topologies for Genetic Algorithms (a family of EA). The algorithms are analyzed in terms of efficiency and efficacy, and the best studied variant is validated versus other GAs using well known centralized and decentralized population structures, outperforming them.
University of Luxembourg: High Performance Computing - ULHPC