Mobility-aware Content Preference Learning in Decentralized Caching Networks

TL;DR

This paper introduces a mobility-aware decentralized content preference learning model for caching networks, integrating mobility prediction with multi-task learning to improve cache hit ratios and content prediction accuracy.

Contribution

It develops a novel mobility-aware decentralized regularized multi-task learning framework that incorporates mobility patterns into content preference prediction for caching networks.

Findings

Mobility-aware DRMTL outperforms DRMTL in geography preference prediction.

The proposed algorithms converge with a rate of O(1/k).

Mobility-aware caching improves hit ratios over traditional schemes.

Abstract

Due to the drastic increase of mobile traffic, wireless caching is proposed to serve repeated requests for content download. To determine the caching scheme for decentralized caching networks, the content preference learning problem based on mobility prediction is studied. We first formulate preference prediction as a decentralized regularized multi-task learning (DRMTL) problem without considering the mobility of mobile terminals (MTs). The problem is solved by a hybrid Jacobian and Gauss-Seidel proximal multi-block alternating direction method (ADMM) based algorithm, which is proven to conditionally converge to the optimal solution with a rate $O(1/k)$. Then we use the tool of \textit{Markov renewal process} to predict the moving path and sojourn time for MTs, and integrate the mobility pattern with the DRMTL model by reweighting the training samples and introducing a transfer penalty in the objective. We solve the problem and prove that the developed algorithm has the same convergence property but with different conditions. Through simulation we show the convergence analysis on proposed algorithms. Our real trace driven experiments illustrate that the mobility-aware DRMTL model can provide a more accurate prediction on geography preference than DRMTL model. Besides, the hit ratio achieved by most popular proactive caching (MPC) policy with preference predicted by mobility-aware DRMTL outperforms the MPC with preference from DRMTL and random caching (RC) schemes.