A Transfer Learning Approach for Cache-Enabled Wireless Networks

TL;DR

This paper introduces a transfer learning-based caching method for 5G wireless networks that leverages contextual data from device interactions to improve content placement, addressing data sparsity and cold-start issues.

Contribution

It proposes a novel transfer learning approach for edge caching in small cell networks, utilizing social and interaction data to enhance caching decisions.

Findings

Achieves up to 22% improvement in user QoE.

Effectively mitigates data sparsity and cold-start problems.

Enhances backhaul offloading in small cell networks.

Abstract

Locally caching contents at the network edge constitutes one of the most disruptive approaches in $5$G wireless networks. Reaping the benefits of edge caching hinges on solving a myriad of challenges such as how, what and when to strategically cache contents subject to storage constraints, traffic load, unknown spatio-temporal traffic demands and data sparsity. Motivated by this, we propose a novel transfer learning-based caching procedure carried out at each small cell base station. This is done by exploiting the rich contextual information (i.e., users' content viewing history, social ties, etc.) extracted from device-to-device (D2D) interactions, referred to as source domain. This prior information is incorporated in the so-called target domain where the goal is to optimally cache strategic contents at the small cells as a function of storage, estimated content popularity, traffic load and backhaul capacity. It is shown that the proposed approach overcomes the notorious data sparsity and cold-start problems, yielding significant gains in terms of users' quality-of-experience (QoE) and backhaul offloading, with gains reaching up to $22\%$ in a setting consisting of four small cell base stations.