POSMAC: Powering Up In-Network AR/CG Traffic Classification with Online Learning

TL;DR

POSMAC is a platform that enables real-time classification of AR and cloud gaming traffic using decision tree and random forest models on NVIDIA DPU hardware, optimizing throughput and model evaluation.

Contribution

It introduces a specialized platform for deploying machine learning models on DPU hardware for in-network AR and CG traffic classification.

Findings

Real-time classification with high throughput

Effective deployment of DT and RF models on DPU hardware

Enhanced model evaluation and generalization

Abstract

In this demonstration, we showcase POSMAC1, a platform designed to deploy Decision Tree (DT) and Random Forest (RF) models on the NVIDIA DOCA DPU, equipped with an ARM processor, for real-time network traffic classification. Developed specifically for Augmented Reality (AR) and Cloud Gaming (CG) traffic classification, POSMAC streamlines model evaluation, and generalization while optimizing throughput to closely match line rates.