Simulating Network Paths with Recurrent Buffering Units

TL;DR

This paper introduces RBU, a novel recurrent neural network model that simulates network path delays by capturing the dynamic, load-dependent behavior of physical networks, combining interpretability with neural network flexibility.

Contribution

The paper presents a new grey-box RNN model called RBU that effectively simulates network delays, integrating physical network semantics with neural modeling for improved accuracy and interpretability.

Findings

RBU outperforms traditional models on synthetic network traces.

RBU achieves promising results on real-world network data.

The model offers a balance of interpretability and predictive power.

Abstract

Simulating physical network paths (e.g., Internet) is a cornerstone research problem in the emerging sub-field of AI-for-networking. We seek a model that generates end-to-end packet delay values in response to the time-varying load offered by a sender, which is typically a function of the previously output delays. The problem setting is unique, and renders the state-of-the-art text and time-series generative models inapplicable or ineffective. We formulate an ML problem at the intersection of dynamical systems, sequential decision making, and time-series modeling. We propose a novel grey-box approach to network simulation that embeds the semantics of physical network path in a new RNN-style model called RBU, providing the interpretability of standard network simulator tools, the power of neural models, the efficiency of SGD-based techniques for learning, and yielding promising results on synthetic and real-world network traces.