A search for routing strategies in a peer-to-peer
network using genetic programming
M. Iles, and D. Deugo. Proceedings 21st IEEE Symposium on Reliable
Distributed Systems, page 341--346. (13-16 October 2002)
Abstract
Results taken from a simulated peer-to-peer network
are described, in which genetic programming is used to
evolve routing strategies that optimise resource
location in various traffic flow scenarios. In all
cases the evolved strategies result in more numerous
resource locations than a pure, non-adaptive
peer-to-peer protocol such as the Gnutella protocol.
The resulting evolved strategies are described, and
empirical validation of the Gnutella protocol is given
via both its creation through machine-learning
techniques, and through the analysis of real-world
constants used in the protocol.
%0 Conference Paper
%1 iles:2002:RDS
%A Iles, Michael
%A Deugo, Dwight
%B Proceedings 21st IEEE Symposium on Reliable
Distributed Systems
%D 2002
%K (artificial Gnutella algorithms, computer discrete event flow genetic intelligence), learning location machine network network, networks, optimization, peer-to-peer programming, protocol, protocols, resource routing routing, scenarios simulated simulation, strategies, techniques, telecommunication traffic
%P 341--346
%T A search for routing strategies in a peer-to-peer
network using genetic programming
%X Results taken from a simulated peer-to-peer network
are described, in which genetic programming is used to
evolve routing strategies that optimise resource
location in various traffic flow scenarios. In all
cases the evolved strategies result in more numerous
resource locations than a pure, non-adaptive
peer-to-peer protocol such as the Gnutella protocol.
The resulting evolved strategies are described, and
empirical validation of the Gnutella protocol is given
via both its creation through machine-learning
techniques, and through the analysis of real-world
constants used in the protocol.
@inproceedings{iles:2002:RDS,
abstract = {Results taken from a simulated peer-to-peer network
are described, in which genetic programming is used to
evolve routing strategies that optimise resource
location in various traffic flow scenarios. In all
cases the evolved strategies result in more numerous
resource locations than a pure, non-adaptive
peer-to-peer protocol such as the Gnutella protocol.
The resulting evolved strategies are described, and
empirical validation of the Gnutella protocol is given
via both its creation through machine-learning
techniques, and through the analysis of real-world
constants used in the protocol.},
added-at = {2008-06-19T17:35:00.000+0200},
author = {Iles, Michael and Deugo, Dwight},
biburl = {https://www.bibsonomy.org/bibtex/2893c5c7e81dc0de7d929947dae271427/brazovayeye},
booktitle = {Proceedings 21st IEEE Symposium on Reliable
Distributed Systems},
interhash = {6f5ef6e6ba51f548b666afed853f84ae},
intrahash = {893c5c7e81dc0de7d929947dae271427},
issn = {1060-9857},
keywords = {(artificial Gnutella algorithms, computer discrete event flow genetic intelligence), learning location machine network network, networks, optimization, peer-to-peer programming, protocol, protocols, resource routing routing, scenarios simulated simulation, strategies, techniques, telecommunication traffic},
month = {13-16 October},
notes = {Inspec Accession Number: 7516795.
Carleton Univ., Ottawa, Ont., Canada},
pages = {341--346},
timestamp = {2008-06-19T17:42:08.000+0200},
title = {A search for routing strategies in a peer-to-peer
network using genetic programming},
year = 2002
}