Federated Learning Assisted Edge Caching Scheme Based on Lightweight Architecture DDPM

TL;DR

This paper introduces a federated learning-based edge caching scheme utilizing a lightweight denoising diffusion probabilistic model, significantly improving cache hit rates while preserving user privacy.

Contribution

It presents a novel FL-assisted caching scheme based on LDPM, enhancing cache efficiency without compromising privacy.

Findings

Higher cache hit percentage compared to existing FL methods

Effective privacy preservation in edge caching

Demonstrated improvements through simulation results

Abstract

Edge caching is an emerging technology that empowers caching units at edge nodes, allowing users to fetch contents of interest that have been pre-cached at the edge nodes. The key to pre-caching is to maximize the cache hit percentage for cached content without compromising users' privacy. In this letter, we propose a federated learning (FL) assisted edge caching scheme based on lightweight architecture denoising diffusion probabilistic model (LDPM). Our simulation results verify that our proposed scheme achieves a higher cache hit percentage compared to existing FL-based methods and baseline methods.