This document proposes adapting genetic programming to a peer-to-peer environment using an evolvable agent model. It discusses using a gossip-based newscast protocol for neighbor communication between agents to allow for a spatially structured evolutionary algorithm on a peer-to-peer network. Experimental results show that using this approach, genetic programming problems can be solved in parallel across the peer-to-peer network, improving times to solution.
1. A Peer-to-Peer Approach to Genetic Programming Juan Luis Jiménez Laredo, Daniel Lombraña González, Francisco Fernández de Vega, Maribel García Arenas, Juan Julián Merelo Guervós University of Granada (1,4,5) University of Extremadura (2,3) http://geneura.wordpress.com http://twitter.com/geneura
11. But here's the long answer Using the Evolvable Agent model: J.L.J. Laredo, P.A. Castillo, A.M. Mora, and J.J. Merelo. Exploring population structures for locally concurrent and massively parallel evolutionary algorithms . In IEEE Congress on Evolutionary Computation (CEC2008), WCCI2008 Proceedings, pages 2610–2617. IEEE Press, Hong Kong, June 2008. http://lugl.info/xiQP
15. Newscast: Gossip protocol Joining: connecting to an existing node. Leaving: stop communication Emergent small world graph structure Fault tolerance Graceful degradation