Prediction-Guided Control in Data Center Networks

2026-01-07

arXiv.org

AI Summary

This work addresses the degradation of tail latency in multi-tenant data center networks caused by minute-scale dynamic workloads. To this end, the authors propose Polyphony, the first system that integrates network-wide workload aggregation with approximate counterfactual prediction into a closed-loop control mechanism. Polyphony continuously monitors and predicts service-level quality metrics, dynamically adjusting network configurations to precisely meet operator-defined SLOs—without requiring modifications to existing congestion control or traffic engineering mechanisms. Experimental evaluation in CloudLab demonstrates that Polyphony converges to strict SLOs within 10 minutes and stabilizes within 15 minutes following large workload shifts, significantly outperforming state-of-the-art approaches.

Technology Category

• Planning, Routing, and Scheduling: Optimization of Spatio-temporal Systems
• Multiagent Systems: Mechanism Design
• Machine Learning: Online Learning & Bandits

Application Category

• Responsible Web: Human-perceived consequences of algorithmic deployment on the web
• Economics, Online Markets and Human Computation: Incentives in network design for Web infrastructures and ecosystems
• Systems and Infrastructure for Web, Mobile and WoT: Web performance, measurement, and characterization

Abstract

In this paper, we design, implement, and evaluate Polyphony, a system to give network operators a new way to control and reduce the frequency of poor tail latency events in multi-class data center networks, on the time scale of minutes. Polyphony is designed to be complementary to other adaptive mechanisms like congestion control and traffic engineering, but targets different aspects of network operation that have previously been considered static. By contrast to Polyphony, prior model-free optimization methods work best when there are only a few relevant degrees of freedom and where workloads and measurements are stable, assumptions not present in modern data center networks. Polyphony develops novel methods for measuring, predicting, and controlling network quality of service metrics for a dynamically changing workload. First, we monitor and aggregate workloads on a network-wide basis; we use the result as input to an approximate counterfactual prediction engine that estimates the effect of potential network configuration changes on network quality of service; we apply the best candidate and repeat in a closed-loop manner aimed at rapidly and stably converging to a configuration that meets operator goals. Using CloudLab on a simple topology, we observe that Polyphony converges to tight SLOs within ten minutes, and re-stabilizes after large workload shifts within fifteen minutes, while the prior state of the art fails to adapt.

Problem

• tail latency
• data center networks
• quality of service
• network control
• dynamic workloads

Innovation

• prediction-guided control
• counterfactual prediction
• closed-loop network optimization
• tail latency reduction
• multi-class data center networks