Journal
2019 SEVENTH INTERNATIONAL CONFERENCE ON ADVANCED CLOUD AND BIG DATA (CBD)
Volume -, Issue -, Pages 363-368Publisher
IEEE
DOI: 10.1109/CBD.2019.00071
Keywords
TCP; Congestion control; NS3; BBR
Funding
- National Natural Science Foundation of China [61502250, 71801123, 61872191]
- NUPTSF [NY214188]
Ask authors/readers for more resources
With the increasing complexity of the network communication environment. Research on TCP congestion control algorithm is one of the effective ways to alleviate network congestion. Google published the bottleneck bandwidth and round-trip time (BBR) congestion control algorithm in 2016. Unlike many currently loss-based congestion control algorithms (like BIC), BBR uses an estimate of the available bottleneck link bandwidth and RTT to govern its pacing rate. BBR has a good performance on Google's internal network and gains widespread attention. In this paper, we use NS3 to establish different network communication models. By analyzing the simulation data, we find that BBR outperforms BIC on high-latency, high-bandwidth network; BBR could periodically reduce the pacing rate to alleviate the bufferfloat problem; and there is a fairness problem between BBR and other versions of TCP protocols. In addition, we confirm that BBR flows have RTT fairness problem: a BBR flow with longer RTT dominates a competing flow with shorter RTT. Finally, we analyze the adaptability between BBR and AQM algorithms.
Authors
I am an author on this paper
Click your name to claim this paper and add it to your profile.
Reviews
Recommended
No Data Available