Locating object efficiently in a distributed computing system using ant colony optimisation

Li, J.B. and Fung, C.C. (2008) Locating object efficiently in a distributed computing system using ant colony optimisation. In: 2nd IEEE International Conference on Digital Ecosystems and Technologies, IEEE-DEST 2008, 26-29 Feb. 2008, Phitsanulok, Thailand.

Preview

PDF - Published Version Download (723kB) | Preview

Abstract

Digital Ecosystems reply on efficient computing and communication infrastructures. One way to improve computation efficiency is to utilise distributed computing systems. In an object-based distributed system, the use of location-independent naming scheme can improve the system's transparency, scalability and reliability. Names however need to be resolved prior to pass messages between the objects. This paper reports the use of a distributed Ant Colony Optimisation algorithms (ACO) to improve the efficiency of searching objects in a distributed computing system. The ACO algorithm is designed for an Adaptive RandoMised Structured search network termed ARMS. The approach provides name resolution by forwarding a query through neighbouring nodes. The performance of ARMS is compared to Chord, a well-known structured network. Simulation studies have shown ARMS is superior to Chord as ARMS requires a shorter path in query forwarding.