What question did this study set out to answer?

This article aims to explore how deep reinforcement learning (DRL) can address decision-making challenges in mobile edge caching.

November 1, 2018

Deep Reinforcement Learning for Mobile Edge Caching: Review, New Features, and Open Issues

Key Points

This article aims to explore how deep reinforcement learning (DRL) can address decision-making challenges in mobile edge caching.
Reviewed recent literature on mobile edge caching and DRL applications.
Examined key issues and unique features of DRL in caching decisions.
Illustrated DRL-based caching with simulation results using trace data.
Identified gaps in current solutions that require further investigation.
Noted the potential of DRL to enhance caching performance and user experience.
Outlined several open research issues that need addressing.

Abstract

Mobile edge caching is a promising technique to reduce network traffic and improve the quality of experience of mobile users. However, mobile edge caching is a challenging decision making problem with unknown future content popularity and complex network characteristics. In this article, we advocate the use of DRL to solve mobile edge caching problems by presenting an overview of recent works on mobile edge caching and DRL. We first examine the key issues in mobile edge caching and review the existing learning- based solutions proposed in the literature. We also discuss the unique features in the application of DRL in mobile edge caching, and illustrate an example of DRL-based mobile edge caching with trace-data-driven simulation results. This article concludes with a discussion of several open issues that call for substantial future research efforts.

AI से पूछें

Bookmark