Elevator: Self-* and Persistent Hub Sampling Service in Unstructured Peer-to-Peer Networks
Abstract
We present Elevator, a novel algorithm for hub sampling
in peer-to-peer networks, enabling the construction of overlays with a
topology between a random graph and a star network, and networks
that have both hubs and are resilient to failures. Our approach emerges
from principles of preferential attachment, forming hubs spontaneously,
offering an innovative solution for decentralized networks that can benefit
use cases requiring a network with both low diameter and resilience to
failures.
Origin | Files produced by the author(s) |
---|