Register to attend this P4 Developer Days webinar, “AR/CG Network Traffic Classification in Programmable Dataplane”
Date: November 12, 2025
Time: 8:00am Pacific
Abstract
In this presentation, we explore the importance of classifying AR/CG traffic directly within the network device to enable low-latency, intelligent forwarding. We outline the end-to-end process of feature extraction and deployment within a programmable data plane, focusing on how key traffic features are computed and mirrored in P4-enabled switches. We also discuss the training of machine learning models tailored for the P4 data plane and their use in online pattern matching. Finally, we introduce our key contributions, including the extracted features, developed codebase, and publicly available repositories.
Speaker
Alireza Shirmarz received his B.Sc. in Computer Engineering from Shahed University in 2009 and his M.Sc. in Network Engineering from Amirkabir University of Technology (Tehran Polytechnic) in 2014. He earned his Ph.D. in Computer Engineering from IAU-Tehran North Branch in 2020. Since 2014, he has been actively teaching undergraduate courses in computer science and engineering and has been involved in graduate and Ph.D. supervision since 2020.
His research focuses on the intersection of networking and AI/ML, particularly in optimizing Quality of Experience (QoE) for real-time and interactive applications in future networks, including 6G. He specializes in intelligent data plane solutions, SDN architectures, and QoS/QoE management. Currently, he is a Postdoctoral Researcher at UFSCar, advancing AI/ML applications in networking.