Adaptive Offline and Online Similarity-Based Caching

TL;DR

This paper proposes a joint optimization framework for similarity-based caching that minimizes delay and dissimilarity costs, introducing algorithms for both offline and online scenarios, validated by numerical results.

Contribution

It introduces a novel joint caching and delivery optimization method with algorithms for offline and online settings, improving performance over standard solutions.

Findings

The proposed algorithms outperform standard per-cache solutions.

The offline algorithm converges reliably under known request rates.

The online extension adapts effectively to dynamic request patterns.

Abstract

With similarity-based content delivery, the request for a content can be satisfied by delivering a related content under a dissimilarity cost. This letter addresses the joint optimization of caching and similarity-based delivery decisions across a network so as to minimize the weighted sum of average delay and dissimilarity cost. A convergent alternate gradient descent ascent algorithm is first introduced for an offline scenario with prior knowledge of the request rates, and then extended to an online setting. Numerical results validate the advantages of the approach with respect to standard per-cache solutions.