Self-Chord: A Bio-inspired Algorithm for Structured P2P Systems

Abstract

This paper presents “Self-Chord”, a bio-inspired P2P algorithm that can be profitably adopted to build the information service of distributed systems, in particular Computational Grids and Clouds. Self-Chord inherits the ability of Chord-like structured systems for the construction and maintenance of an overlay of peers, but features enhanced functionalities deriving from the activity of ant-inspired mobile agents, such as autonomy behavior, self-organization and capacity to adapt to a changing environment. Self-Chord features three main benefits with respect to classical P2P structured systems: (i) it is possible to give a semantic meaning to keys, which enables the execution of "class" queries, often issued in Grids and Clouds; (ii) the keys are fairly distributed over the peers, thus improving the balancing of storage responsibilities; (iii) maintenance load is reduced because, as new peers join the ring, the mobile agents will spontaneously reorganize the keys in logarithmic time.