# TCP Congestion Control on Lossy Network Scenario

Source: [TCP Congestion Control on Lossy Network Scenario](<https://www.sota2.com/research/sota/tcp-congestion-control-on-lossy-network-scenario>)

Collection index: [llms.txt](<https://www.sota2.com/research/llms.txt>)

Data updated: 2026-02-26T05:48:47.562Z

Evaluation of TCP Congestion Control performance within a lossy network environment, measuring throughput and round-trip time variations.

A research result applies to its stated dataset, split, metric and evaluation configuration. Compare like-for-like settings, preserve the metric's unit and direction, and distinguish paper-reported results from independent reproduction. The best result recorded here is not a claim of exhaustive, current global coverage.

| Scope | Recorded value |
| --- | --- |
| Task | TCP Congestion Control |
| Dataset (including any stated split) | Lossy Network Scenario |
| Metric | Lossy Throughput |
| Unit | SCALAR |
| Direction | Higher is better |
| Results loaded | 10 of 10 |
| Coverage | All results currently returned for this benchmark |

Evaluation settings may differ between results. The original papers and recorded configurations are needed to establish comparability. A shared metric name alone does not establish an identical protocol.

## Metrics

- [Lossy Throughput](<https://www.sota2.com/research/sota/tcp-congestion-control-on-lossy-network-scenario.md?metric=Lossy%20Throughput>): Higher is better; unit: SCALAR.

- [Total Throughput (Lossy)](<https://www.sota2.com/research/sota/tcp-congestion-control-on-lossy-network-scenario.md?metric=Total%20Throughput%20(Lossy)>): Higher is better; unit: SCALAR.

- [RTT Variation (Lossy)](<https://www.sota2.com/research/sota/tcp-congestion-control-on-lossy-network-scenario.md?metric=RTT%20Variation%20(Lossy)>): Lower is better; unit: TIME.

## Recorded results

| Method | Lossy Throughput | Result date | Report paper |
| --- | --- | --- | --- |
| SymbolicPCC | 28.55 | Not recorded | 68fa6dc31e209131cea3bee9 |
| SymbolicPCC | 28.4 | Not recorded | 68fa6dc31e209131cea3bee9 |
| Aurora | 27.55 | Not recorded | 68fa6dc31e209131cea3bee9 |
| Aurora | 27.03 | Not recorded | 68fa6dc31e209131cea3bee9 |
| Aurora | 26.42 | Not recorded | 68fa6dc31e209131cea3bee9 |
| Aurora | 25.97 | Not recorded | 68fa6dc31e209131cea3bee9 |
| BBR | 25.76 | Not recorded | 68fa6dc31e209131cea3bee9 |
| Aurora | 22.54 | Not recorded | 68fa6dc31e209131cea3bee9 |
| PCC Vivace | 8.72 | Not recorded | 68fa6dc31e209131cea3bee9 |
| TCP CUBIC | 1.27 | Not recorded | 68fa6dc31e209131cea3bee9 |

### SymbolicPCC

Lossy Throughput: 28.55. Result ID: 698fdaea3a6c314849fc5a93.

[Reporting paper](<https://www.sota2.com/research/paper/68fa6dc31e209131cea3bee9.md>)

[Method origin paper](<https://www.sota2.com/research/paper/68fa6dc31e209131cea3bee9.md>)

[Implementation](<https://github.com/VITA-Group/SymbolicPCC>)

Recorded evaluation configuration: {"Type":"Symbolic","Variant":"branched","FLOPs":63,"Runtime (us)":37}. This record does not assert independent reproduction.

### SymbolicPCC

Lossy Throughput: 28.4. Result ID: 698fdaea3a6c314849fc5a92.

[Reporting paper](<https://www.sota2.com/research/paper/68fa6dc31e209131cea3bee9.md>)

[Method origin paper](<https://www.sota2.com/research/paper/68fa6dc31e209131cea3bee9.md>)

[Implementation](<https://github.com/VITA-Group/SymbolicPCC>)

Recorded evaluation configuration: {"Type":"Symbolic","Variant":"baseline","FLOPs":48,"Runtime (us)":23}. This record does not assert independent reproduction.

### Aurora

Lossy Throughput: 27.55. Result ID: 698fdaea3a6c314849fc5a8d.

[Reporting paper](<https://www.sota2.com/research/paper/68fa6dc31e209131cea3bee9.md>)

Recorded evaluation configuration: {"Type":"RL-Based","Variant":"baseline","FLOPs":1488,"Runtime (us)":864}. This record does not assert independent reproduction.

### Aurora

Lossy Throughput: 27.03. Result ID: 698fdaea3a6c314849fc5a8e.

[Reporting paper](<https://www.sota2.com/research/paper/68fa6dc31e209131cea3bee9.md>)

Recorded evaluation configuration: {"Type":"RL-Based","Variant":"50% pruned","FLOPs":744,"Runtime (us)":781}. This record does not assert independent reproduction.

### Aurora

Lossy Throughput: 26.42. Result ID: 698fdaea3a6c314849fc5a8f.

[Reporting paper](<https://www.sota2.com/research/paper/68fa6dc31e209131cea3bee9.md>)

Recorded evaluation configuration: {"Type":"RL-Based","Variant":"80% pruned","FLOPs":298,"Runtime (us)":769}. This record does not assert independent reproduction.

### Aurora

Lossy Throughput: 25.97. Result ID: 698fdaea3a6c314849fc5a90.

[Reporting paper](<https://www.sota2.com/research/paper/68fa6dc31e209131cea3bee9.md>)

Recorded evaluation configuration: {"Type":"RL-Based","Variant":"95% pruned","FLOPs":74,"Runtime (us)":703}. This record does not assert independent reproduction.

### BBR

Lossy Throughput: 25.76. Result ID: 698fdaea3a6c314849fc5a8c.

[Reporting paper](<https://www.sota2.com/research/paper/68fa6dc31e209131cea3bee9.md>)

Recorded evaluation configuration: {"Type":"Conventional","FLOPs":"\< 10","Runtime (us)":"\< 10"}. This record does not assert independent reproduction.

### Aurora

Lossy Throughput: 22.54. Result ID: 698fdaea3a6c314849fc5a91.

[Reporting paper](<https://www.sota2.com/research/paper/68fa6dc31e209131cea3bee9.md>)

Recorded evaluation configuration: {"Type":"RL-Based","Variant":"quantized","FLOPs":835,"Runtime (us)":810}. This record does not assert independent reproduction.

### PCC Vivace

Lossy Throughput: 8.72. Result ID: 698fdaea3a6c314849fc5a8b.

[Reporting paper](<https://www.sota2.com/research/paper/68fa6dc31e209131cea3bee9.md>)

Recorded evaluation configuration: {"Type":"Conventional","FLOPs":"\< 10","Runtime (us)":"\< 10"}. This record does not assert independent reproduction.

### TCP CUBIC

Lossy Throughput: 1.27. Result ID: 698fdaea3a6c314849fc5a8a.

[Reporting paper](<https://www.sota2.com/research/paper/68fa6dc31e209131cea3bee9.md>)

Recorded evaluation configuration: {"Type":"Conventional","FLOPs":"\< 10","Runtime (us)":"\< 10"}. This record does not assert independent reproduction.

Page 1 of 1. This is an index page, not the full collection.
