Distributed Overlay Anycast Table using Space filling curves

TL;DR

This paper introduces the Distributed Overlay Anycast Table (DOAT), a structured overlay network that uses space filling curves and delay coordinates to enable efficient, locality-aware group discovery for real-time peer-to-peer applications.

Contribution

The paper presents a novel overlay structure combining space filling curves, delay coordinates, and Bloom filters to improve locality-aware routing and group discovery efficiency.

Findings

High accuracy in group member discovery

Low query times demonstrated in simulations

Effective locality-aware routing achieved

Abstract

In this paper we present the \emph{Distributed Overlay Anycast Table}, a structured overlay that implements application-layer anycast, allowing the discovery of the closest host that is a member of a given group. One application is in locality-aware peer-to-peer networks, where peers need to discover low-latency peers participating in the distribution of a particular file or stream. The DOAT makes use of network delay coordinates and a space filling curve to achieve locality-aware routing across the overlay, and Bloom filters to aggregate group identifiers. The solution is designed to optimise both accuracy and query time, which are essential for real-time applications. We simulated DOAT using both random and realistic node distributions. The results show that accuracy is high and query time is low.