Research Article
Improving Scalability of Autonomic Systems: The Frequency-Aware Search Approach
@INPROCEEDINGS{10.4108/ICST.AUTONOMICS2008.4637, author={Pedro Fonseca and Hugo Miranda}, title={Improving Scalability of Autonomic Systems: The Frequency-Aware Search Approach}, proceedings={8th International ICST Workshop on Middleware for Network Eccentric and Mobile Applications}, publisher={ACM}, proceedings_a={MINEMA}, year={2010}, month={5}, keywords={peer-to-peer resource location unstructured overlays}, doi={10.4108/ICST.AUTONOMICS2008.4637} }- Pedro Fonseca
Hugo Miranda
Year: 2010
Improving Scalability of Autonomic Systems: The Frequency-Aware Search Approach
MINEMA
ICST
DOI: 10.4108/ICST.AUTONOMICS2008.4637
Abstract
Resource and data indexing in distributed, self-manageable systems can leverage on the experience gained from peer-to-peer networks, often built using distributed indexing. This paper presents FASE, a distributed indexing algorithm for unstructured overlays with flat topologies. FASE combines a replication policy and a search space division technique to achieve low hop counts using a small number of messages. The unexpected departure of nodes from the overlay, which may be observed in heterogeneous networks built over an unreliable medium, is mitigated by a distributed monitoring algorithm designed with FASE in mind. Simulation results validate FASE efficiency when compared to other search algorithms. The evaluation of the distributed monitoring algorithm shows that it maintains FASE performance when subjected to a constant arrival and departure of nodes.
