PulseTrendingJournal ClubResearchersJournalsExplore
Instagram
HomeTrendingJournal ClubExplore
Synapse
⌘+K
Synapse
January 14, 2026InformationOpen Access

A Machine Learning-Based AQM to Synergize Heterogeneous Congestion Control Algorithms

View Full Paper
Ask AI
Bookmark
Share

Authors

YGYa GaoYLYunji LiCDChunjuan Diao

Discussion

Loading...

Member takes

Overview

Implementation of Warbler shows a 0.99 Jain's fairness index and reduces latency by 60% with high scalability.

Key Points

  • The research aims to improve network performance and fairness by using a machine learning-based active queue management framework.
  • Developed a machine learning-driven framework called Warbler
  • Classified network flows based on traffic characteristics
  • Implemented and evaluated the Warbler prototype on a programmable switch
  • Achieved a Jain's fairness index of 0.99
  • Reduced latency to 60% of the baseline
  • Halved jitter
  • Saved 43% of buffer usage
  • Supported 10,000 concurrent long flows with latency below 0.7 s

Cite This Study

Gao et al. (2026) studied this question.

synapsesocial.com/papers/6966f33b13bf7a6f02c0124bhttps://doi.org/10.3390/info17010068
View Full Paper
Ask AI
Bookmark
Share