A Survey of Deep Reinforcement Learning-Based Edge Caching and Computing Techniques 


Vol. 47,  No. 1, pp. 28-38, Jan.  2022
10.7840/kics.2022.47.1.28


PDF
  Abstract

The distributed edge network has been getting spotlight nowadays for handling tens of exabytes of global data traffic on a daily basis and supporting increasingly exploding mobile devices. Especially, edge caching and edge computing technologies have been actively researched because they are appropriate for efficiently providing multimedia services in which a relatively small part of popular content is repeatedly requested and accounts for about 60-70% of the global wireless data traffic. As wireless edge services have become diversified and the number of mobile users sharply increases, edge caching and computing techniques optimized depending on time-varying channel, content popularity, and the current cache state require high complexity and execution latency. Accordingly, the deep reinforcement learning-based content caching and delivery, and data offloading techniques have been researched, and this paper surveys the state-of-the-art techniques. We first study the related work in a variety of edge network scenarios, and various kinds of reinforcement learning algorithms applied to edge networks are investigated. Also, the advanced edge caching and computing techniques jointly employed the deep reinforcement learning and other techniques are introduced and future research directions are lastly presented.

  Statistics
Cumulative Counts from November, 2022
Multiple requests among the same browser session are counted as one view. If you mouse over a chart, the values of data points will be shown.


  Cite this article

[IEEE Style]

M. Choi, "A Survey of Deep Reinforcement Learning-Based Edge Caching and Computing Techniques," The Journal of Korean Institute of Communications and Information Sciences, vol. 47, no. 1, pp. 28-38, 2022. DOI: 10.7840/kics.2022.47.1.28.

[ACM Style]

Minseok Choi. 2022. A Survey of Deep Reinforcement Learning-Based Edge Caching and Computing Techniques. The Journal of Korean Institute of Communications and Information Sciences, 47, 1, (2022), 28-38. DOI: 10.7840/kics.2022.47.1.28.

[KICS Style]

Minseok Choi, "A Survey of Deep Reinforcement Learning-Based Edge Caching and Computing Techniques," The Journal of Korean Institute of Communications and Information Sciences, vol. 47, no. 1, pp. 28-38, 1. 2022. (https://doi.org/10.7840/kics.2022.47.1.28)

Search
(IN TITLE, AUTHOR, ABSTRACT,KEYWORDS)

Advanced Search ▼

POPULAR KEYWORDS
(TOP 10 KEYWORDS)

Recent Publications
(LAST 3 YEARS)






pISSN : 1226 - 4717
eISSN : 2287 - 3880