Alireza Shirmarz

Dep. of Computer Science

LERIS Lab

Room 4108, Building FINEP 4

Federal University of Sorocaba (UFSCar)

I have been a researcher and teacher in the university which my research and teaching interests have been focused on the # Software Defined Networking (SDN), # Distributed Systems, and # Machine Learning (ML) for making the network more intelligent and automated for the future. Currently, I am a Postdoc/Visiting Researcher at UFSCar and I am working in LERIS (Laboratory of Studies in Networks, Innovation, and, Software) Lab and I am also a part of SMART NEtworks and ServiceS for 2030 (SMARTNESS) Engineering Research Center (ERC) where I contribute as a researcher within Cognetive Closed Control Loops Architecture for Edge IoV Services (C3LA) and In Edge Network Industrial Automation (NEWTON)

My research interests encompass, but are not limited to, Machine Learning (ML) and its application in Dataplane to enhance network automation and intelligence. I focus particularly on Augmented Reality (AR) and Cloud Gaming (CG) applications, aiming to improve their Quality of Experience (QoE). Additionally, I have a strong interest in Queue Management and automation strategies. I am also open to exploring new and challenging topics related to advancing network automation and intelligence.

selected publications

CGSynth: Cloud Gaming Synthesizer

Alireza Shirmarz, Goes Castro Ariel, Victor Hugo Schneider Lopes, and 3 more authors

In Proceedings of the ACM SIGCOMM 2025 Posters and Demos, Coimbra, Portugal, 2025

Abs DOI

Cloud gaming’s unique network traffic is challenging to reproduce for research. This demo introduces Cloud Gaming Synthesizer (CGSynth), a platform that generates realistic, configurable synthetic cloud gaming (CG) traffic. CGSynth captures real CG patterns and allows their synthetic reproduction with user-defined flow/packet parameters and deterministic protocol headers. It employs a GRU for accurate, order-preserving timestamp generation and AI-based video interpolation for realistic payloads. Crucially, CGSynth integrates a QoE evaluation module using objective (e.g., SSIM) and subjective metrics (e.g., MOS) to validate synthetic traffic’s video quality and responsiveness against real streams
In-Network AR/CG Traffic Classification Entirely Deployed in the Programmable Data Plane: Unlocking RTP Features and L4S Integration

Alireza Shirmarz, Mateus N. Bragatto, Fábio Luciano Verdi, and 4 more authors

In 2025 IEEE 11th International Conference on Network Softwarization (NetSoft), 2025

DOI
CGReplay: Capture and Replay of Cloud Gaming Traffic for QoE/QoS Assessment

Alireza Shirmarz, Ariel G. Castro, Fabio L. Verdi, and 1 more author

In 2025 IEEE 11th International Conference on Network Softwarization (NetSoft), 2025

DOI
DCTPQ: Dynamic Cloud Gaming Traffic Prioritization Using Machine Learning and Multi-Queueing for QoE Enhancement

Alireza Shirmarz, Carlos Henrique França Marques, Fábio Luciano Verdi, and 3 more authors

In Anais do XLIII Simpósio Brasileiro de Redes de Computadores e Sistemas Distribuídos, Natal/RN, 2025

DOI
From Pixels to Packets: Traffic Classification of Augmented Reality and Cloud Gaming

Alireza Shirmarz, Fábio Luciano Verdi, Suneet Kumar Singh, and 1 more author

In 2024 IEEE 10th International Conference on Network Softwarization (NetSoft), 2024

DOI
MATADOR: ML-based Cloud Gaming Traffic Detection entirely in Programmable Hardware

Suneet Kumar Singh, Christian Esteve Rothenberg, Alireza Shirmarz, and 4 more authors

In 2024 IEEE Conference on Network Function Virtualization and Software Defined Networks (NFV-SDN), 2024

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

Alireza Shirmarz, Fábio Luciano Verdi, Suneet Kumar Singh, and 1 more author

In 2024 IEEE Conference on Network Function Virtualization and Software Defined Networks (NFV-SDN), 2024

DOI