Towards Near-Real-Time Telemetry-Aware Routing with Neural Routing Algorithms

TL;DR

This paper introduces LOGGIA, a neural routing algorithm that effectively reacts to network traffic bursts in near-real-time by modeling delays and using reinforcement learning, outperforming traditional methods.

Contribution

The paper presents a delay-aware framework for training neural routing algorithms and proposes LOGGIA, a scalable graph neural network that predicts link weights using telemetry data.

Findings

LOGGIA outperforms shortest-path baselines on synthetic and real topologies.

Neural routing algorithms perform best when deployed locally at each router.

Realistic communication delays hinder the performance of existing neural approaches.

Abstract

Routing algorithms are crucial for efficient computer network operations, and in many settings they must be able to react to traffic bursts within milliseconds. Live telemetry data can provide informative signals to routing algorithms, and recent work has trained neural networks to exploit such signals for traffic-aware routing. Yet, aggregating network-wide information is subject to communication delays, and existing neural approaches either assume unrealistic delay-free global states, or restrict routers to purely local telemetry. This leaves their deployability in real-world environments unclear. We cast telemetry-aware routing as a delay-aware closed-loop control problem and introduce a framework that trains and evaluates neural routing algorithms, while explicitly modeling communication and inference delays. On top of this framework, we propose LOGGIA, a scalable graph neural routing algorithm that predicts log-space link weights from attributed topology-and-telemetry graphs. It utilizes a data-driven pre-training stage, followed by on-policy Reinforcement Learning. Across synthetic and real network topologies, and unseen mixed TCP/UDP traffic sequences, LOGGIA consistently outperforms shortest-path baselines, whereas neural baselines fail once realistic delays are enforced. Our experiments further suggest that neural routing algorithms like LOGGIA perform best when deployed fully locally, i.e., observing network states and inferring actions at every router individually, as opposed to centralized decision making.