This paper analises distributed evolutionary computation based on the Representational State Transfer (REST) protocol, which overlays a farming model on evolutionary computation. An approach to evolutionary distributed optimisation of multilayer perceptrons (MLP) using REST and language Perl has been done. In these experiments, a master-slave based evolutionary algorithm (EA) has been implemented, where slave processes evaluate the costly fitness function (training a MLP to solve a classification problem). Obtained results show that the parallel version of the developed programs obtains similar or better results using much less time than the sequential version, obtaining a good speedup.
@article{arxiv.1105.4971,
title = {Distributed Evolutionary Computation using REST},
author = {P. A. Castillo and M. G. Arenas and A. M. Mora and J. L. J. Laredo and G. Romero and V. M Rivas and J. J. Merelo},
journal= {arXiv preprint arXiv:1105.4971},
year = {2011}
}
Comments
Paper 3 for the First International Workshop of Distributed Evolutionary computation in Informal Environments