Robustifying Measurement-Based Congestion Control Algorithms

TL;DR

This paper introduces PAD, a shim layer that enhances the robustness of measurement-based congestion control algorithms in fluctuating network environments without sacrificing their performance benefits.

Contribution

The paper proposes PAD, a novel approach that improves the robustness of measurement-based CCAs by mitigating the impact of measurement inaccuracies, applicable to any measurement-based CCA.

Findings

PAD outperforms most common CCAs in fluctuating environments.

PAD maintains high performance while improving robustness.

The shim layer effectively isolates CCAs from measurement inaccuracies.

Abstract

The design methodology of congestion control algorithms (CCAs) has shifted from control-based to measurement-based in recent years. However, we find that measurement-based CCAs, although having better performance, are not robust enough in fluctuating network environments, which are increasingly common nowadays. In this paper, we propose PAD to make measurement-based CCAs as robust as control-based CCAs in fluctuating environments while enjoying the performance benefits in general. PAD identifies that the root cause is that measurement-based CCAs blindly rely on measurement results, which unfortunately can be inaccurate, and will transiently mislead the CCAs to misbehave. The preliminary design of PAD works as a shim layer between the socket and CCAs so as to scale to any measurement-based CCAs, which turns out to outperform most commonly used CCAs in fluctuating environments.