History Data Driven Distributed Consensus in Networks

TL;DR

This paper introduces a novel history-data-driven approach for distributed consensus in networks, leveraging historical data to estimate trust levels between agents and improve consensus accuracy.

Contribution

It presents a new probabilistic method that uses historical data to determine trust levels, leading to a novel HDD consensus protocol.

Findings

Effective trust estimation from historical data.

Improved consensus accuracy through data-driven weights.

Robustness to trust estimation uncertainties.

Abstract

The association of weights in a distributed consensus protocol quantify the trust that an agent has on its neighbors in a network. An important problem in such networked systems is the uncertainty in the estimation of trust between neighboring agents, coupled with the losses arising from mistakenly associating wrong amounts of trust with different neighboring agents. We introduce a probabilistic approach which uses the historical data collected in the network, to determine the level of trust between each agent. Specifically, using the finite history of the shared data between neighbors, we obtain a configuration which represents the confidence estimate of every neighboring agent's trustworthiness. Finally, we propose a History-Data-Driven (HDD) distributed consensus protocol which translates the computed configuration data into weights to be used in the consensus update. The approach using the historical data in the context of a distributed consensus setting marks the novel contribution of our paper.