This paper presents an in-network machine learning (ML) approach for classifying Augmented Reality (AR) and Cloud Gaming (CG) traffic using programmable hardware. Random Forest (RF) models are deployed in a P411P4: Programming Protocol-independent Packet Processors data plane capable of processing Real-time Transport Protocol (RTP) traffic features like Frame Size (FS) and Inter-Frame Interval (IFI) for efficient classification. The classifier marks AR and CG traffic with Explicit Congestion Notification (ECN) codepoints to integrate with the Low Latency, Low Loss, Scalable Throughput (L4S) features of the programmable switch. The RF model prioritizes AR/CG traffic using Differentiated Services Code-Point (DSCP) assignments and modular ECN marking. The classification performance is evaluated using accuracy, precision, recall, and F1-score, while time overhead is assessed based on nodal processing time incurred during deployment by replaying AR/CG traffic. The P4 implementations for P4Pi22https://eng.ox.ac.uk/computing/projects/programmable-hardware/p4pi.(V1Model) and Tofino Native Architecture (TNA) are all publicly available.

Cloud Gaming (CG) research faces challenges due to the unpredictability of game engines and restricted access to commercial platforms and their logs. This creates major obstacles to conducting fair experimentation and evaluation. CGReplay captures and replays player commands and the corresponding video frames in an ordered and synchronized action-reaction loop, ensuring reproducibility. It enables Quality of Experience/Service (QoE/QoS) assessment under varying network conditions and serves as a foundation for broader CG research. The code is publicly available for further development11https://github.com/dcomp-leris/CGReplay.git.

Augmented Reality (AR) real-time interaction between users and digital overlays in the real world demands low latency to ensure seamless experiences. To address computational and battery constraints, AR devices often offload processing-intensive tasks to edge servers, enhancing performance and user experience. With the increasing adoption and complexity of AR applications, especially in remote rendering, accurately classifying AR network traffic becomes essential for effective resource allocation. This paper explores two methods based on Decision Tree (DT) and Random Forest (RF) to classify network traffic among AR, Cloud Gaming (CG), and other categories. We rigorously analyze specific features to precisely identify AR and CG traffic. Our models demonstrate robust performance, achieving accuracy rates ranging from 88.40% to 94.87% against pre-existing datasets. Moreover, we contribute with a novel dataset encompassing AR and CG traffic, curated specifically for this study and made publicly available to facilitate reproducible research in AR network traffic classification.