A MULTI-ATTRIBUTE RESOURCE DISCOVERY ALGORITHM FOR PEER-TO-PEER GRIDS
Javad Akbari Torkestani · Applied Artificial Intelligence · 2013
Centralized or hierarchical administration of the classical Grid resource discovery approaches is unable to efficiently manage the highly dynamic large‐scale Grid environments. In this study, a multi-attribute distributed learning automata-based resource discovery algorithm called MDLRD is proposed for large-scale peer-to-peer (P2P) Grids. Taking advantage of the learning automata theory, the proposed method routes the resource query through the path having the minimum expected hop count toward the Grid peers including the requested resources. Therefore, MDLRD significantly reduces the message overhead of the unstructured P2P resource discovery methods in which the resource queries are flooded within the network. Furthermore, MDLRD fully supports the multi-attribute range query that is impossible in structured P2P resource discovery approaches. A strong theorem is presented to show the convergence of the proposed distributed learning automata-based algorithm to the optimal solution. To investigate the performance of the proposed method, several simulation experiments are conducted. The obtained results confirm that MDLRD significantly outperforms the other methods in terms of the average hop count, average hit ratio, and control message overhead.