A game theoretic approach to a network allocation problem

TL;DR

This paper models a peer-to-peer cloud storage network as a game, proposing a decentralized algorithm based on log-linear learning that converges to optimal data allocation, supported by theoretical proofs and simulations.

Contribution

It introduces a novel game-theoretic framework and a decentralized algorithm for network resource allocation in peer-to-peer storage systems.

Findings

Algorithm converges to optimal allocation

Decentralized approach is feasible and effective

Theoretical convergence proof supported by simulations

Abstract

In this paper, we consider a network allocation problem motivated by peer-to-peer cloud storage models. The setting is that of a network of units (e.g. computers) that collaborate and offer each other space for the back up of the data of each unit. We formulate the problem as an optimization problem, we cast it into a game theoretic setting and we then propose a decentralized allocation algorithm based on the log-linear learning rule. Our main technical result is to prove the convergence of the algorithm to the optimal allocation. We also present some simulations that show the feasibility of our solution and corroborate the theoretical results.