A distributed intelligent agent platform for genetic optimization in CEM: Applications in a quasi-point matching method

Lymperopoulos, DG; Tsitsas, NL; Kaklamani, DI

dc.contributor.author	Lymperopoulos, DG	en
dc.contributor.author	Tsitsas, NL	en
dc.contributor.author	Kaklamani, DI	en
dc.date.accessioned	2014-03-01T01:25:40Z
dc.date.available	2014-03-01T01:25:40Z
dc.date.issued	2007	en
dc.identifier.issn	0018-926X	en
dc.identifier.uri	https://dspace.lib.ntua.gr/xmlui/handle/123456789/17717
dc.subject	Cooperative systems	en
dc.subject	Distributed genetic algorithms (DGAs)	en
dc.subject	Fictitious sources (FSs)	en
dc.subject	Genetic search agents (GSA)	en
dc.subject	Least squares methods	en
dc.subject	Point matching methods	en
dc.subject.classification	Engineering, Electrical & Electronic	en
dc.subject.classification	Telecommunications	en
dc.subject.other	Computational methods	en
dc.subject.other	Distributed computer systems	en
dc.subject.other	Genetic algorithms	en
dc.subject.other	Intelligent agents	en
dc.subject.other	Least squares approximations	en
dc.subject.other	Optimization	en
dc.subject.other	Cooperative systems	en
dc.subject.other	Distributed genetic algorithms	en
dc.subject.other	Fictitious sources	en
dc.subject.other	Genetic search agents	en
dc.subject.other	Point matching methods	en
dc.subject.other	Electromagnetic fields	en
dc.title	A distributed intelligent agent platform for genetic optimization in CEM: Applications in a quasi-point matching method	en
heal.type	journalArticle	en
heal.identifier.primary	10.1109/TAP.2007.891560	en
heal.identifier.secondary	http://dx.doi.org/10.1109/TAP.2007.891560	en
heal.language	English	en
heal.publicationDate	2007	en
heal.abstract	The use of genetic algorithms in computational electromagnetics (CEM) has proved a fruitful, but resource demanding optimization method with numerous practical applications. This paper introduces a parallel distributed computing framework based on the intelligent agent technology that is capable of handling the genetic optimization for diverse CEM problems. The platform core component is the genetic search agent (GSA), a collaborative computational entity that communicates with its peers in order to carry out a genetic optimization scheme. The platform can interface with foreign codes transparently due to its flexible code loading mechanisms, specially designed for CEM applications. The framework is applied to the optimization of a quasi-point matching method with fictitious sources (QPM-FS). The analysis comprises two case studies, involving electromagnetic scattering by: i) a two-layered cylinder; and ii) a cylinder buried in a two-layered earth medium, a problem of practical use in subsurface imaging. The performance results indicate that the sophisticated distribution mechanisms achieve high speed-up, while physically intuitive conclusions are obtained from the genetic optimization of the developed QPM-FS method. © 2007 IEEE.	en
heal.publisher	IEEE-INST ELECTRICAL ELECTRONICS ENGINEERS INC	en
heal.journalName	IEEE Transactions on Antennas and Propagation	en
dc.identifier.doi	10.1109/TAP.2007.891560	en
dc.identifier.isi	ISI:000244969900012	en
dc.identifier.volume	55	en
dc.identifier.issue	3 I	en
dc.identifier.spage	619	en
dc.identifier.epage	628	en