iccrg G. Zhao Internet-Draft G. Chen Intended status: Informational China Mobile Expires: 19 February 2027 18 August 2026 Competitive Mode Enhancement for Delay-Based Congestion Control Algorithms draft-zhao-iccrg-competitive-mode-01 Abstract This document proposes introducing a "Competitive Mode" into delay- based congestion control algorithms to improve their competitiveness and fairness during coexistence scenarios. Status of This Memo This Internet-Draft is submitted in full conformance with the provisions of BCP 78 and BCP 79. Internet-Drafts are working documents of the Internet Engineering Task Force (IETF). Note that other groups may also distribute working documents as Internet-Drafts. The list of current Internet- Drafts is at https://datatracker.ietf.org/drafts/current/. Internet-Drafts are draft documents valid for a maximum of six months and may be updated, replaced, or obsoleted by other documents at any time. It is inappropriate to use Internet-Drafts as reference material or to cite them other than as "work in progress." This Internet-Draft will expire on 19 February 2027. Copyright Notice Copyright (c) 2026 IETF Trust and the persons identified as the document authors. All rights reserved. This document is subject to BCP 78 and the IETF Trust's Legal Provisions Relating to IETF Documents (https://trustee.ietf.org/ license-info) in effect on the date of publication of this document. Please review these documents carefully, as they describe your rights and restrictions with respect to this document. Code Components extracted from this document must include Revised BSD License text as described in Section 4.e of the Trust Legal Provisions and are provided without warranty as described in the Revised BSD License. Zhao & Chen Expires 19 February 2027 [Page 1] Internet-Draft CMPM August 2026 Table of Contents 1. Introduction . . . . . . . . . . . . . . . . . . . . . . . . 2 2. Introducing Competitive Mode into Delay-Based Congestion Control Algorithms . . . . . . . . . . . . . . . . . . . 2 2.1. Method for Determining Competitive Mode . . . . . . . . . 2 2.2. Congestion Window Compensation in Competition Mode . . . 3 3. Examples . . . . . . . . . . . . . . . . . . . . . . . . . . 3 3.1. Copa with Competitive Mode . . . . . . . . . . . . . . . 3 3.2. Vegas with Competitive Mode . . . . . . . . . . . . . . . 3 4. IANA Considerations . . . . . . . . . . . . . . . . . . . . . 3 5. Security Considerations . . . . . . . . . . . . . . . . . . . 4 6. Contributors . . . . . . . . . . . . . . . . . . . . . . . . 4 7. Acknowledgements . . . . . . . . . . . . . . . . . . . . . . 4 8. References . . . . . . . . . . . . . . . . . . . . . . . . . 4 8.1. Normative References . . . . . . . . . . . . . . . . . . 4 8.2. Informative References . . . . . . . . . . . . . . . . . 4 Authors' Addresses . . . . . . . . . . . . . . . . . . . . . . . 5 1. Introduction Congestion control algorithms can be categorized into loss-based and delay-based algorithms based on their congestion detection mechanisms. Loss-based congestion control algorithms typically fill the link buffer until packet loss occurs, then reduce the sending rate. In contrast, delay-based congestion control algorithms proactively reduce the sending rate when queuing delay increases. Representative delay-based congestion control algorithms (e.g., Vegas[Vegas], FAST[FAST], Copa[Copa]) measure RTT or queuing delay, calculate the expected throughput based on delay variations, determine congestion, and adjust the congestion window size. While delay-based algorithms generally exhibit lower packet loss rates and smaller queuing delays than loss-based algorithms, they fail to fairly share link bandwidth with loss-based algorithms (e.g., Cubic) when both types of traffic coexist. 2. Introducing Competitive Mode into Delay-Based Congestion Control Algorithms 2.1. Method for Determining Competitive Mode Determine whether the current flow is in a coexistence/competition phase with Cubic traffic based on the magnitude of queuing delay variation. The COPA provides a method to determine whether it is in competitive mode. Zhao & Chen Expires 19 February 2027 [Page 2] Internet-Draft CMPM August 2026 Specifically, upon receiving an ACK, the algorithm calculates the RTT for each flow and maintains a historical minimum RTT value(min_rtt). Based on RTT samples, it records the maximum(max_delay) and minimum(min_delay) RTT values over a 4-RTT window. Competitive Mode is triggered based on the following inequality. min_delay < min_rtt + 0.1(max_delay - min_rtt) Formula 1 Here, max_delay and min_delay represent the maximum and minimum RTT values within the last 4 RTT intervals, and min_rtt is the historical minimum RTT. The difference between min_delay and min_rtt represents the minimum queuing delay at the bottleneck link during this period, while the difference between max_delay and min_rtt represents the maximum queuing delay. If the inequality is not satisfied, it indicates that the bottleneck link's queue has not emptied during this period, suggesting likely competition from Cubic-like flows. Consequently, the algorithm enters Competitive Mode. If the inequality holds, the algorithm operates in Default Mode. 2.2. Congestion Window Compensation in Competition Mode When the algorithm determines it is in Competition Mode, it introduces an additional congestion window gain factor to moderately increase the congestion window size. Cubic persistently fills the switch buffer, and a larger window size leads to more severe delay inflation. Accordingly, the congestion window can be adjusted based on delay variations to match Cubic's window size. Since the delay gradient effectively characterizes the rise and fall of delay, the congestion control algorithm computes this gradient every round trip time(RTT) and adjusts the window size accordingly. TBD. 3. Examples 3.1. Copa with Competitive Mode TBD. 3.2. Vegas with Competitive Mode TBD. 4. IANA Considerations TBD. Zhao & Chen Expires 19 February 2027 [Page 3] Internet-Draft CMPM August 2026 5. Security Considerations TBD. 6. Contributors The following people have substantially contributed to this document: Zhiqiang Li lizhiqiangyjy@chinamobile.com Hongwei Yang yanghongwei@chinamoblie.com 7. Acknowledgements TBD. 8. References 8.1. Normative References [RFC2119] Bradner, S., "Key words for use in RFCs to Indicate Requirement Levels", BCP 14, RFC 2119, DOI 10.17487/RFC2119, March 1997, . [RFC8174] Leiba, B., "Ambiguity of Uppercase vs Lowercase in RFC 2119 Key Words", BCP 14, RFC 8174, DOI 10.17487/RFC8174, May 2017, . 8.2. Informative References [Vegas] Brakmo, L., O'Malley, S., and L. Peterson, "TCP Vegas: New Techniques for Congestion Detection and Avoidance", ACM SIGCOMM Computer Communication Review 24.4(1994) , August 1994. [FAST] Wei, D., Jin, C., and S. Low, "FAST TCP : motivation, architecture, algorithms, performance", IEEE/ACM Transactions on Networking 14(2006) , December 2006. [Copa] Arun, V. and H. Hari, "Practical delay-based congestion control for the internet", the Applied Networking Research Workshop 2018. , April 2018. Zhao & Chen Expires 19 February 2027 [Page 4] Internet-Draft CMPM August 2026 [I-D.ietf-ccwg-bbr] Cardwell, N., Swett, I., and J. Beshay, "BBR Congestion Control", Work in Progress, Internet-Draft, draft-ietf- ccwg-bbr-06, 6 July 2026, . Authors' Addresses Guangyu Zhao China Mobile No.32 XuanWuMen West Street Beijing 100053 China Email: zhaoguangyu@chinamobile.com Guowei Chen China Mobile No.2 Qianfu Road, Xishan District Kunming 650228 China Email: chenguowei@yn.chinamobile.com Zhao & Chen Expires 19 February 2027 [Page 5]