New Method for Grid Computing Resource Discovery with Dynamic Structure of Peer-To-Peer Model Based on Learning Automata

The term "Grid" has become common parlance among parallel and distributed computer scientists to denote a middleware infrastructure for wide-area scientific and engineering computing. Information services are a vital part of any Grid software infrastructure, providing fundamental mechanisms for discovery and monitoring and thus for planning and adapting application behavior. Grid Information Service (GIS) stores information about the resources of a distributed computing environment and answer questions about it. So GIS has a key role in other grid computing services such as resource discovery service. Various kinds of solutions to organization of GIS have been suggested, in this paper we proposed dynamic structure of GIS based on peer-to-peer model using learning automata. Using learning automata is to increase efficiency of proposed model and generate dynamic structuring of peer-to-peer organization for GIS.