Learning to Cache: Distributed Coded Caching in a Cellular Network With Correlated Demands

TL;DR

This paper introduces a distributed caching strategy for cellular networks that leverages correlated demands over time and across base stations, using theoretical guarantees and a federated learning heuristic to improve cache hit rates.

Contribution

It proposes a novel caching approach that accounts for demand correlations, provides performance guarantees, and develops a federated learning heuristic outperforming traditional methods.

Findings

The proposed caching strategy outperforms LRFU in simulations.

Theoretical guarantees are established for the caching performance.

Demand correlation significantly impacts caching effectiveness.

Abstract

Design of distributed caching mechanisms is considered as an active area of research due to its promising solution in reducing data load in the backhaul link of a cellular network. In this paper, the problem of distributed content caching in a small-cell Base Stations (sBSs) wireless network that maximizes the cache hit performance is considered. Most of the existing works focus on static demands, however, here, data at each sBS is considered to be correlated across time and sBSs. The caching strategy is assumed to be a weighted combination of past caching strategies. A high probability generalization guarantees on the performance of the proposed caching strategy is derived. The theoretical guarantee provides following insights on obtaining the caching strategy: (i) run regret minimization at each sBS to obtain a sequence of caching strategies across time, and (ii) maximize an estimate of the bound to obtain a set of weights for the caching strategy which depends on the discrepancy. Also, theoretical guarantee on the performance of the LRFU caching strategy is derived. Further, federated learning based heuristic caching algorithm is also proposed. Finally, it is shown through simulations using Movie Lens dataset that the proposed algorithm significantly outperforms LRFU algorithm.