Distributed artificial intelligence: Difference between revisions

Revision as of 12:45, 17 November 2014

Revision as of 21:21, 25 December 2014

Line 12:

* A [[Distributed_computing|distributed system]] with robust and elastic computation on unreliable and failing resources that are loosely coupled

* Coordination of the actions and communication of the nodes

* Subsamples of large data sets and [[Online_machine_learning|online machine learning]]

There are many reasons for wanting to distribute intelligence or cope with multi-agent systems. Mainstreams in DAI research include the following:

Line 32:

task decomposition and synthesis of the knowledge and solutions.

DAI can apply a bottom-up approach to AI, similar to the [[Subsumption_architecture|subsumption architecture]] as well as the traditional top-down

approach of AI. In addition, DAI can also be a vehicle for [[Emergence|emergence]].

==Applications==

Line 40:

* Networks, e.g. in [[Telecommunication|telecommunications]] the DAI system controls the cooperative resources in a WLAN network http://dair.uncc.edu/projects/past-projects/wlan-resource

* [[Scheduling_(production_processes)|Routing]], e.g. model veichle flow in transport networks

* [[Scheduling_(production_processes)|Scheduling]], e.g. [[Flow_shop_scheduling|flow shop scheduling]] where the resource management entity ensures local optimization and cooperation for global and local consistency

* Multi-Agent systems, e.g. [[Artificial_life|Artificial Life]], the study of simulated life