In the next ROC seminar, PhD student Moussa GUEMDANI and postdoctoral researcher Hugo De Oliveira will present their current work on Tuesday, March 24, 2026, from 14h00 to 17h00.
Seminar Location: Room 33.1.27C, Access 31 – Level 1, 2 rue Conté, 75003 Paris, France
Speaker: Moussa GUEMDANI
Title: Experimental Performance Evaluation of Open-Source O-RAN Software Stacks
Abstract: Open-source software is increasingly enabling flexible and cost-effective experimentation with 5G Radio Access Networks (RANs). However, only a limited number of studies provide a systematic comparative evaluation of experimental testbeds that combine different open-source RAN software stacks across multiple deployment scenarios. Moreover, system performance under high traffic loads remains insufficiently explored. In this work in progress, we present the design of an experimental 5G standalone (SA) testbed, detailing its architectural components, hardware infrastructure, software protocol stack, and key configuration parameters. We implement four testbed configurations and conduct a comparative performance analysis. The study focuses on monolithic and 3GPP functional split Option 2 architectures, using open-source RAN implementations. The evaluation considers a set of key performance indicators (KPIs) that characterize end-to-end (E2E) performance, system-level behavior, and radio conditions
Bio: Moussa GUEMDANI holds a Master’s degree in Computer Networks and IoT Systems from CNAM Paris. His paper, “Comparative E2E Performance Analysis of O-RAN Designs in a 5G Standalone Testbed,” was presented at HPSR 2025 in Osaka, Japan. This work is currently being extended and will be submitted to the IEEE Transactions on Network and Service Management (TNSM). His research interests include Open RAN, machine learning for wireless communications, and energy-efficient edge AI-based wireless network design for Beyond 5G systems.
Speaker: De Oliveira Hugo
Title: Multimodal Federated Learning-based Jamming detection for future 6G network
Abstract: The evolution toward 6G systems promises ultra-reliable and low-latency communication, in particular in 6G Cellular Vehicle-to-Everything networks. These highly connected and dynamic networks face increasing threats from sophisticated jamming attacks that exploit large coverage and complex radio environments. Traditional centralized machine learning approaches are limited by high communication overhead, data privacy issues, and poor adaptation facing different jamming models. In this work, we leverage Federated Learning combined with multimodal learning to enable efficient, privacy-preserving jamming detection. By integrating heterogeneous data modalities, such as radio signal features and spectrum observations, multimodal FL can achieve robust detection of diverse jamming patterns with improved convergence rate and signaling. Preliminary results demonstrate high detection accuracy compared to other distributed learning baselines or unimodal model.
Bio: De Oliveira Hugo is a postdoctoral researcher at CNAM. He received the bachelor’s and master’s degrees in computer science from Paris-Saclay University, France, in 2020 and 2022, respectively. He received the Ph.D. degree in 2025 under a joint international program (cotutelle) between Paris-Saclay University, France, and the Graduate University for Advanced Studies (SOKENDAI), Japan. His research interests include wireless communications, IoT networks, machine learning methods for wireless systems, and optimization problems.
