Performance Improvement of Reinforcement Learning Based Slotted ALOHA 


Vol. 45,  No. 11, pp. 1886-1892, Nov.  2020
10.7840/kics.2020.45.11.1886


PDF Full-Text
  Abstract

In the existing ALOHA-Q, which applies reinforcement learning to frame based slotted ALOHA, each node intelligently selects a slot and sends packets without collision. A channel consists of several frames, and a frame consists of several slots. In ALOHA-Q protocol, because each node selects only one slot per frame, network performance is greatly reduced if the frame size and the number of nodes are different. So, in this paper, we apply the objective function to the existing ALOHA-Q to control the number of slots that each node uses within the frame to increase network performance. The simulation results show that the throughput of the proposed algorithm is not sensitive to the number of nodes, and that high performance is produced compared to ALOHA-Q.

  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]

C. Lee and S. Rhee, "Performance Improvement of Reinforcement Learning Based Slotted ALOHA," The Journal of Korean Institute of Communications and Information Sciences, vol. 45, no. 11, pp. 1886-1892, 2020. DOI: 10.7840/kics.2020.45.11.1886.

[ACM Style]

Chang-Kyu Lee and Seung-Hyong Rhee. 2020. Performance Improvement of Reinforcement Learning Based Slotted ALOHA. The Journal of Korean Institute of Communications and Information Sciences, 45, 11, (2020), 1886-1892. DOI: 10.7840/kics.2020.45.11.1886.

[KICS Style]

Chang-Kyu Lee and Seung-Hyong Rhee, "Performance Improvement of Reinforcement Learning Based Slotted ALOHA," The Journal of Korean Institute of Communications and Information Sciences, vol. 45, no. 11, pp. 1886-1892, 11. 2020. (https://doi.org/10.7840/kics.2020.45.11.1886)

Search
(IN TITLE, AUTHOR, ABSTRACT,KEYWORDS)

Advanced Search ▼

POPULAR KEYWORDS
(TOP 10 KEYWORDS)

Recent Publications
(LAST 3 YEARS)






pISSN : 1226 - 4717
eISSN : 2287 - 3880