Multi-Objective Swarm Intelligent Systems

Recently, a new class of heuristic techniques, the swarm intelligence has emerged. In this context, more recently, biologists and computer scientists in the ?eld of“arti?cial life”have been turning to insects for ideas that can be used for heuristics. Many aspects of the collective activities of social insects, such as foraging of ants, birds ?ocking and ?sh schooling are self-organizing, meaning that complex group behavior emerges from the interactions of in- viduals who exhibit simple behaviors by themselves. Swarm intelligence is an innovative computational way to solving hard problems. This discipline is mostly inspired by the behavior of ant colonies, bird ?ocks and ?sh schools and other biological creatures. In general, this is done by mimicking the behavior of these swarms. Swarm intelligence is an emerging research area with similar population and evolution characteristics to those of genetic algorithms. However, it di?erentiates in emphasizing the cooperative behavior among group m- bers. Swarm intelligence is used to solve optimization and cooperative pr- lems among intelligent agents, mainly in arti?cial network training, co- erative and/or decentralized control, operational research, power systems, electro-magnetics device design, mobile robotics, and others. The most we- knownrepresentativesofswarmintelligenceinoptimizationproblemsare:the food-searching behavior of ants, particle swarm optimization, and bacterial colonies. Real-world engineering problems often require concurrent optimization of several design objectives, which are con?icting in most of the cases. Such an optimization is generally called multi-objective or multi-criterion optimi- tion.Inthis context,the developmentofimprovementsfor swarmintelligence methods to multi-objective problems is an emergent research area.