The case for model-driven interpretability of delay-based congestion control protocols

TL;DR

This paper introduces a Model-Driven Interpretability framework to analyze complex delay-based congestion control protocols by simplifying their behavior into a Markov model, enabling better understanding in variable networks.

Contribution

It presents a novel MDI framework that models delay-based protocols with a Markov process, facilitating interpretability and analysis of protocol behavior.

Findings

Successfully approximates throughput and delay across network conditions

Provides insights into protocol convergence properties

Demonstrates effectiveness on Verus and Copa protocols

Abstract

Analyzing and interpreting the exact behavior of new delay-based congestion control protocols with complex non-linear control loops is exceptionally difficult in highly variable networks such as cellular networks. This paper proposes a Model-Driven Interpretability (MDI) congestion control framework, which derives a model version of a delay-based protocol by simplifying a congestion control protocol's response into a guided random walk over a two-dimensional Markov model. We demonstrate the case for the MDI framework by using MDI to analyze and interpret the behavior of two delay-based protocols over cellular channels: Verus and Copa. Our results show a successful approximation of throughput and delay characteristics of the protocols' model versions across variable network conditions. The learned model of a protocol provides key insights into an algorithm's convergence properties.