CSMA/CA Protocol Based on Multi Agent Deep Reinforcement 


Vol. 48,  No. 3, pp. 359-361, Mar.  2023
10.7840/kics.2023.48.3.359


PDF
  Abstract

In this letter, the performances are compared and analyzed by applying Multi Agent Deep Reinforcement Learning to the CSMA/CA protocol. In the case of the existing CSMA/CA protocol, a terminal with a backoff value of 0 using the random backoff method transmits a packet, so the higher the number of terminals connected to the channel, the higher the number of packet collisions, which degrades the performance. We propose that each terminal connected to a channel is regarded as one agent, and all agents belonging to the channel observe the channel state, and then determine the Contention Window (CW) with a high transmission success rate according to the channel state to improve performance.

  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.


  Related Articles
  Cite this article

[IEEE Style]

Yeong-jeJo and Gyung-HoHwang, "CSMA/CA Protocol Based on Multi Agent Deep Reinforcement," The Journal of Korean Institute of Communications and Information Sciences, vol. 48, no. 3, pp. 359-361, 2023. DOI: 10.7840/kics.2023.48.3.359.

[ACM Style]

Yeong-jeJo and Gyung-HoHwang. 2023. CSMA/CA Protocol Based on Multi Agent Deep Reinforcement. The Journal of Korean Institute of Communications and Information Sciences, 48, 3, (2023), 359-361. DOI: 10.7840/kics.2023.48.3.359.

[KICS Style]

Yeong-jeJo and Gyung-HoHwang, "CSMA/CA Protocol Based on Multi Agent Deep Reinforcement," The Journal of Korean Institute of Communications and Information Sciences, vol. 48, no. 3, pp. 359-361, 3. 2023. (https://doi.org/10.7840/kics.2023.48.3.359)
Vol. 48, No. 3 Index

Search
(IN TITLE, AUTHOR, ABSTRACT,KEYWORDS)

Advanced Search ▼

POPULAR KEYWORDS
(TOP 10 KEYWORDS)

Recent Publications
(LAST 3 YEARS)






pISSN : 1226 - 4717
eISSN : 2287 - 3880