Simulation of Dissemination Strategies on Temporal Networks

TL;DR

This paper simulates various dissemination strategies on temporal networks to evaluate their efficiency, coverage, and anonymity guarantees in distributed systems like peer-to-peer networks and cryptocurrencies.

Contribution

It introduces a simulation framework for analyzing dissemination protocols on temporal networks and compares their performance in terms of coverage, traffic, and anonymity.

Findings

Gossip protocols can reduce message count or enhance anonymity.

Trade-offs exist between coverage, message overhead, and anonymity.

Temporal network dynamics significantly affect dissemination performance.

Abstract

In distributed environments, such as distributed ledgers technologies and other peer-to-peer architectures, communication represents a crucial topic. The ability to efficiently disseminate contents is strongly influenced by the type of system architecture, the protocol used to spread such contents over the network and the actual dynamicity of the communication links (i.e. static vs. temporal nets). In particular, the dissemination strategies either focus on achieving an optimal coverage, minimizing the network traffic or providing assurances on anonymity (that is a fundamental requirement of many cryptocurrencies). In this work, the behaviour of multiple dissemination protocols is discussed and studied through simulation. The performance evaluation has been carried out on temporal networks with the help of LUNES-temporal, a discrete event simulator that allows to test algorithms running on a distributed environment. The experiments show that some gossip protocols allow to either save a considerable number of messages or to provide better anonymity guarantees, at the cost of a little lower coverage achieved and/or a little increase of the delivery time.