Freshness Based Cache Updating in Parallel Relay Networks

TL;DR

This paper analyzes information freshness in a parallel cache network with multiple caches receiving updates, deriving an analytical expression and proposing a near-optimal update policy with bounds on its performance gap.

Contribution

It introduces a novel analytical framework for freshness in multi-cache networks and proposes an approximate solution based on consolidating cache update rates.

Findings

Freshness increases with rate consolidation across caches.

The sub-optimal policy closely approximates the optimal policy.

An upper bound on the performance gap is provided.

Abstract

We consider a system consisting of a server, which receives updates for $N$ files according to independent Poisson processes. The goal of the server is to deliver the latest version of the files to the user through a parallel network of $K$ caches. We consider an update received by the user successful, if the user receives the same file version that is currently prevailing at the server. We derive an analytical expression for information freshness at the user. We observe that freshness for a file increases with increase in consolidation of rates across caches. To solve the multi-cache problem, we first solve the auxiliary problem of a single-cache system. We then rework this auxiliary solution to our parallel-cache network by consolidating rates to single routes as much as possible. This yields an approximate (sub-optimal) solution for the original problem. We provide an upper bound on the gap between the sub-optimal solution and the optimal solution. Numerical results show that the sub-optimal policy closely approximates the optimal policy.