After more than a decade of development, real time communication (RTC) for video telephony has made significantly progress. However, emerging high-quality RTC applications with high definition and high frame rate requires sufficient bandwidth. The default congestion control mechanism specifically tuned for video telephony leaves plenty of room for optimization under high-rate scenarios. It is necessary to develop new rate control solutions to utilize bandwidth efficiently and to provide better experience for such services. A delay-based congestion control method called Cross is proposed, which regulates rate based on queue load with a multiplicative increase and multiplicative decrease fashion. A simulation module is developed to validate the effectiveness of these congestion control algorithms for RTC services. The module is released with the hope to provide convenience for RTC research community. Simulation results demonstrate that Cross can achieve low queuing delay and maintain high channel utilization under random loss environments. Online deployment shows that Cross can reduce the video freezing ratio by up to 58.45\% on average when compared with a benchmark algorithm.

翻译：经过十多年的发展，视频通话的实时通信技术已取得显著进步。然而，新兴的高清高帧率高质量实时通信应用需要充足的带宽。专为视频通话优化的默认拥塞控制机制在高码率场景下仍有较大的优化空间。有必要开发新的速率控制方案，以高效利用带宽并为这类服务提供更佳体验。本文提出了一种基于延迟的拥塞控制方法Cross，该方法通过乘性增加与乘性减少的方式，依据队列负载调节速率。我们开发了仿真模块以验证这些拥塞控制算法在实时通信服务中的有效性，并开源该模块以期便利实时通信研究社区。仿真结果表明，在随机丢包环境下，Cross能够实现低队列延迟并保持高信道利用率。实际部署数据显示，与基准算法相比，Cross平均可降低视频卡顿率高达58.45%。