Distributed Learning-based Cache Replacement in Collaborative Edge Networks

TY - JOUR

T1 - Distributed Learning-based Cache Replacement in Collaborative Edge Networks

AU - Sun, Zhenfeng

AU - Nakhai, Mohammad Reza

N1 - Publisher Copyright: © 1997-2012 IEEE. Copyright: Copyright 2021 Elsevier B.V., All rights reserved.

PY - 2021/8

Y1 - 2021/8

N2 - In this letter, distributed content caching is considered in a collaborative edge caching system where a central infostation broadcasts information about the content migration to all edge nodes. Each edge node is equipped with a small base station for fetching the requested contents from its neighbouring edge nodes and with a storage unit for caching the contents. To achieve efficient content caching and collaboration, an online decision-making problem of maximizing the cache-hit-ratio whilst ensuring the end users' quality-of-experience (QoE) is formulated. Furthermore, it is assumed that the content popularity knowledge is not available in advance and has to be leaned regularly over time in an online manner. To this end, we propose a distributed online content-popularity leaning algorithm based on Thompson sampling for updating the cache storage units in real-time. Simulation results demonstrate that the proposed algorithm outperforms the benchmarks in terms of the cache-hit-ratio and QoE in the long run.

AB - In this letter, distributed content caching is considered in a collaborative edge caching system where a central infostation broadcasts information about the content migration to all edge nodes. Each edge node is equipped with a small base station for fetching the requested contents from its neighbouring edge nodes and with a storage unit for caching the contents. To achieve efficient content caching and collaboration, an online decision-making problem of maximizing the cache-hit-ratio whilst ensuring the end users' quality-of-experience (QoE) is formulated. Furthermore, it is assumed that the content popularity knowledge is not available in advance and has to be leaned regularly over time in an online manner. To this end, we propose a distributed online content-popularity leaning algorithm based on Thompson sampling for updating the cache storage units in real-time. Simulation results demonstrate that the proposed algorithm outperforms the benchmarks in terms of the cache-hit-ratio and QoE in the long run.

KW - Base stations

KW - Cloud computing

KW - Collaboration

KW - Collaborative edge network

KW - distributed content caching

KW - Heuristic algorithms

KW - Libraries

KW - Optimization

KW - Quality of experience

KW - Thompson sampling

UR - http://www.scopus.com/inward/record.url?scp=85107204232&partnerID=8YFLogxK

U2 - 10.1109/LCOMM.2021.3081823

DO - 10.1109/LCOMM.2021.3081823

M3 - Article

AN - SCOPUS:85107204232

SN - 1089-7798

VL - 25

SP - 2669

EP - 2672

JO - IEEE COMMUNICATIONS LETTERS

JF - IEEE COMMUNICATIONS LETTERS

IS - 8

M1 - 9435369

ER -