A Transmission Rate Control Method for Active Congestion Reduction Based on Network Node Bandwidth Allocation
-
Published:2023-11-29
Issue:12
Volume:15
Page:385
-
ISSN:1999-5903
-
Container-title:Future Internet
-
language:en
-
Short-container-title:Future Internet
Author:
Liu Hongyu12ORCID, Ni Hong12, Han Rui12
Affiliation:
1. National Network New Media Engineering Research Center, Institute of Acoustics, Chinese Academy of Sciences, No. 21, North Fourth Ring Road, Haidian District, Beijing 100190, China 2. School of Electronic, Electrical and Communication Engineering, University of Chinese Academy of Sciences, No. 19(A), Yuquan Road, Shijingshan District, Beijing 100049, China
Abstract
The control of transmission rates is currently a major topic in network research, as it plays a significant role in determining network performance. Traditional network design principles suggest that network nodes should only be responsible for forwarding data, while the sending node should manage control. However, sending nodes often lack information about network resources and must use slow-start algorithms to increase the transmission rate, potentially leading to wasted bandwidth and network congestion. Furthermore, incorrect judgments about network congestion by sending nodes may further reduce network throughput. The emergence of new Internet architectures, such as information-centric networks (ICNn), has empowered network nodes with more capabilities, including computation and caching. This paper proposes a method for transmission rate control that actively avoids congestion through network node bandwidth allocation. The sending, network, and receiving nodes each calculate the available transmission rate, and the sending node negotiates with the other nodes through a rate negotiation message to obtain the maximum transmission rate possible given the current state of the network. The network nodes notify the sending node to adjust the transmission rate to adapt to changes in the network through a rate adjustment message. Simulation experiments show that the proposed method is better than traditional methods in reducing network congestion, providing a stable transmission rate, increasing the network throughput capacity, and improving performance in high-latency and high-bandwidth networks. Additionally, the proposed transmission rate control method is fairer than traditional methods.
Funder
Strategic Priority Research Program of Chinese Academy of Sciences
Subject
Computer Networks and Communications
Reference25 articles.
1. Allman, M., Paxson, V., and Blanton, E. (2023, November 01). TCP Congestion Control. No. rfc5681. Available online: https://www.rfc-editor.org/rfc/rfc5681. 2. Floyd, S., Henderson, T., and Gurtov, A. (2023, November 01). The NewReno Modification to TCP’s Fast Recovery Algorithm. No. rfc3782. Available online: https://www.rfc-editor.org/rfc/rfc6582.html. 3. CUBIC: A new TCP-friendly high-speed TCP variant;Ha;ACM SIGOPS Oper. Syst. Rev.,2008 4. Brakmo, L.S., O’Malley, S.W., and Peterson, L.L. (September, January 31). TCP Vegas: New techniques for congestion detection and avoidance. Proceedings of the Conference on Communications Architectures, Protocols and Applications, London, UK. 5. Tan, K., Song, J., Zhang, Q., and Sridharan, M. (2006, January 23–29). A compound TCP approach for high-speed and long distance networks. Proceedings of the IEEE INFOCOM, Catalunya, Spain.
|
|