Receive Window Limitation Results: BBR-n+ vs BBR-v3 and TCP Cubic Network Performance

Experimental results from 2026 evaluate the BBR-n+ (BBR Smart Exit) congestion control algorithm against BBR-v3 and TCP Cubic. The dataset, authored by Muhammad Ahsan and shared under CC-BY-4.0, contains performance metrics from tests in wired and wireless connectivity scenarios. It includes results for throughput, HTTP delay, and ping latency under different receiver window sizes and Active Queue Management (AQM) settings.

Use Cases

• Compare throughput gains of BBR-n+ over BBR-v3 based on the reported 15–20% median improvement in receive window limitation tests.
• Evaluate latency reduction for HTTP traffic based on the described 150 ms improvement over BBR-v3 and ~300 ms over Cubic.
• Analyze algorithm fairness in multi-flow scenarios based on the described limitations when competing against eight or more Cubic streams.
• Study the impact of modern AQMs like CAKE and FQ_CoDel on congestion control performance as mentioned in the experimental setup.

Strengths

• Includes specific, quantified performance gains such as a 15–20% median throughput improvement for BBR-n+.
• Compares algorithms across multiple metrics: throughput, HTTP delay, and ping latency, with concrete reductions reported (e.g., 150 ms, ~300 ms).
• Evaluates performance under varied conditions including different receiver window sizes and AQM types (CAKE, FQ_CoDel).

Limitations

• Row count and specific column definitions are unknown, requiring manual inspection after download to understand data structure.
• The dataset is very small (5.5 KB), indicating limited scope, likely containing summary results rather than raw packet-level traces.
• The description focuses on specific experimental conclusions; generalizability to other network conditions may be limited.

Provenance

Source

Muhammad Ahsan via figshare.

Collection Method

Likely contains empirically evaluated performance metrics from network experiments comparing congestion control algorithms.

Freshness

Last updated 2026-04-24 17:51:38.