Performance Evaluation of DQN-Based Congestion Control Algorithm for TCP 


Vol. 49,  No. 4, pp. 567-580, Apr.  2024
10.7840/kics.2024.49.4.567


PDF
  Abstract

The existing TCP congestion control suffers from the problem of slow congestion window (cwnd) increase, leading to underutilization of available bandwidth in environments where there is either a very large link bandwidth or frequent changes in channel characteristics. To address these issues, research on adaptive TCP congestion control using machine learning has been consistently progressing. In this paper, we propose DQN-based NewReno and DQN-based CUBIC, which enhance performance by applying a type of reinforcement learning, Deep-Q Network (DQN) to TCP congestion control algorithms. The implemented algorithms underwent performance evaluation using the Network Simulator 3 (NS3). Experimental results reveal that DQN-based CUBIC, in particular, demonstrates higher throughput compared to traditional congestion control. Additionally, fairness between different congestion control and round-trip time (RTT) fairness is also improved.

  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]

S. Seo and Y. Cho, "Performance Evaluation of DQN-Based Congestion Control Algorithm for TCP," The Journal of Korean Institute of Communications and Information Sciences, vol. 49, no. 4, pp. 567-580, 2024. DOI: 10.7840/kics.2024.49.4.567.

[ACM Style]

Sang-Jin Seo and You-Ze Cho. 2024. Performance Evaluation of DQN-Based Congestion Control Algorithm for TCP. The Journal of Korean Institute of Communications and Information Sciences, 49, 4, (2024), 567-580. DOI: 10.7840/kics.2024.49.4.567.

[KICS Style]

Sang-Jin Seo and You-Ze Cho, "Performance Evaluation of DQN-Based Congestion Control Algorithm for TCP," The Journal of Korean Institute of Communications and Information Sciences, vol. 49, no. 4, pp. 567-580, 4. 2024. (https://doi.org/10.7840/kics.2024.49.4.567)
Vol. 49, No. 4 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