PolicyCache-SDN: Hierarchical Intra-Path Learning for Adaptive SDN Traffic Control

TL;DR

PolicyCache-SDN introduces a hierarchical, online adaptive SDN traffic control framework that improves network utilization and reduces latency and violations through local decision-making within a centralized policy envelope.

Contribution

It proposes a novel hierarchical control framework with policy envelopes enabling local online adaptation and auditability, addressing fragility of offline-trained schemes.

Findings

35.5% improvement in core link utilization over Static ECMP

34.3% reduction in elephant flow P99 FCT compared to end host congestion control

Reduced SLA violations from 18.2% to 6.8%

Abstract

Software defined networks offer global visibility, yet centralized control loops are too slow for transient congestion and bursty traffic dynamics. Existing learned traffic control schemes often rely on offline training, making them fragile under distribution shifts. We present PolicyCache-SDN, a hierarchical SDN traffic control framework that enables local online adaptation under centralized policy control. Its key abstraction is a policy envelope: the controller compiles network wide intent into bounded per path action spaces, while edge agents learn and execute metering, queueing, and rerouting decisions only within those bounds. Policy envelopes also make local actions auditable and reversible when they affect shared bottlenecks. Evaluation on a 1,024 host software SDN testbed shows that PolicyCache-SDN improves average core link utilization by 35.5% over Static ECMP and 18.3% over Centralized TE. It reduces elephant flow P99 FCT by 34.3% over end host congestion control, lowers SLA violations from 18.2% to 6.8%, and uses less than 2% CPU and 12 MB memory per edge agent. The source code is available in an anonymized repository at https://anonymous.4open.science/r/JCC2026-PolicyCache-SDN/.