Distributed edge caching via reinforcement learning in fog radio access networks

  • Liuyang Lu
  • , Yanxiang Jiang
  • , Mehdi Bennis
  • , Zhiguo Ding
  • , Fu Chun Zheng
  • , Xiaohu You

Research output: Chapter in Book/Report/Conference proceedingConference contributionpeer-review

27 Scopus citations

Abstract

In this paper, the distributed edge caching problem in fog radio access networks (F-RANs) is investigated. By considering the unknown spatio-temporal content popularity and user preference, a user request model based on hidden Markov process is proposed to characterize the fluctuant spatio-temporal traffic demands in F-RANs. Then, the Q-learning method based on the reinforcement learning (RL) framework is put forth to seek the optimal caching policy in a distributed manner, which enables fog access points (F-APs) to learn and track the potential dynamic process without extra communications cost. Furthermore, we propose a more efficient Q-learning method with value function approximation (Q-VFA-learning) to reduce complexity and accelerate convergence. Simulation results show that the performance of our proposed method is superior to those of the traditional methods.

Original languageBritish English
Title of host publication2019 IEEE 89th Vehicular Technology Conference, VTC Spring 2019 - Proceedings
PublisherInstitute of Electrical and Electronics Engineers Inc.
ISBN (Electronic)9781728112176
DOIs
StatePublished - Apr 2019
Event89th IEEE Vehicular Technology Conference, VTC Spring 2019 - Kuala Lumpur, Malaysia
Duration: 28 Apr 20191 May 2019

Publication series

NameIEEE Vehicular Technology Conference
Volume2019-April
ISSN (Print)1550-2252

Conference

Conference89th IEEE Vehicular Technology Conference, VTC Spring 2019
Country/TerritoryMalaysia
CityKuala Lumpur
Period28/04/191/05/19

Keywords

  • Content popularity
  • Distributed edge caching
  • Fog radio access networks
  • Q-learning
  • User preference

Fingerprint

Dive into the research topics of 'Distributed edge caching via reinforcement learning in fog radio access networks'. Together they form a unique fingerprint.

Cite this