September 22 (Mon), 2025, 09:00-10:30 (T1) and 10:45-12:15 (T2), Track I
Chair: Takayuki Kuroda (NEC Corporation, Japan)
Subject: AI-Driven MPQUIC Scheduling: Model Design, Simulation, and Real-World Deployment
Summary: Multipath QUIC (MPQUIC) is a cutting-edge transport protocol that empowers mobile devices to leverage multiple wireless networks simultaneously, significantly improving throughput and reliability. As we enter the 5G era and beyond, MPQUIC has become indispensable across various applications. Its performance hinges on an efficient scheduler that dynamically selects the best transmission paths. However, traditional scheduling approaches struggle to adapt to the ever-changing nature of wireless networks, driving the rise of learning-based solutions that offer promising improvements. While research on learning-based MPQUIC scheduling has gained traction, much of it remains narrowly focused on protocol design, lacking a holistic perspective that encompasses simulation, real-world deployment, and thorough performance evaluation. This tutorial seeks to fill this gap by providing a comprehensive, step-by-step guide to learning-based MPQUIC scheduling. Attendees will explore the entire pipeline, from conceptualizing solutions and utilizing simulation frameworks to setting up real-world experiments and employing advanced tools for performance monitoring and analysis. By the end of this session, participants will gain an in-depth and practical understanding of AI-driven MPQUIC scheduling, equipping them with the knowledge to implement and optimize these solutions effectively.
Kien Nguyen is an expert in Communication Networks with over 20 years of experience spanning both industry and academia. He received his B.E. degree in Electronics and Telecommunications from Hanoi University of Science and Technology (HUST), Vietnam, in 2004, and his Ph.D. in Informatics from the Graduate University for Advanced Studies, Japan, in 2012. From 2014 to 2018, he worked as a researcher at the National Institute of Information and Communication Technology (NICT), Japan, where he contributed to cutting-edge networking and communication technologies, focusing on next-generation networks, multipath transport protocols, and IoT connectivity. Since 2018, he has been with Chiba University, where he is currently an Associate Professor, conducting research on communication networks, distributed systems, and AI-driven network optimizations. Dr. Nguyen has published over 160 peer-reviewed papers in top-tier IEEE/ACM journals and conferences, such as IEEE JSAC, IEEE IoTJ, IEEE TVT, IEEE TNSM, IEEE Commag, IEEE TII, IEEE TGCN, and ACM Transactions on Sensor Networks. His research has led to three patents, several IETF Internet drafts, and multiple collaborative projects in wireless communication, multipath transport, and intelligent networking. As an active member of the networking community, he is a Senior Member of IEEE and a member of IEICE and IPSJ. Besides, he is a technical editor of the Computer Communications (COMCOM) journal.
Phi Le Nguyen is an expert in Artificial Intelligence (AI) for Communication Networks, with extensive experience in network architectures, intelligent transport protocols, and resource optimization. She received her B.E. and M.S. degrees from the University of Tokyo in 2007 and 2010, respectively, and her Ph.D. in Informatics from the Graduate University for Advanced Studies (SOKENDAI), National Institute of Informatics, Tokyo, Japan, in 2019. She is currently an Associate Professor at the School of Information and Communication Technology, Hanoi University of Science and Technology (HUST), Vietnam. Her research focuses on AI-driven network optimization, including reinforcement learning-based multipath scheduling, federated learning for communication networks, and AI-assisted wireless resource allocation. She has been the principal investigator (PI) or key member in multiple national and international research projects, applying AI to autonomous networking, IoT systems, and next-generation wireless networks. Her work has been recognized through numerous best paper awards, and she has received prestigious fellowships, including the 2023 APEC-Australia Women in Research Fellowship. She has authored and co-authored dozens of high-impact journal and conference papers, contributing to IEEE TNSM, Computer Communications, and Engineering Applications of AI.
Minh Hai Vu received his B.E. from School of Information and Communication Technology, Hanoi University of Science and Technology in 2024. His research interests include reinforcement learning, applied AI in networking, and wireless communication. He has extensive experience with MPQUIC, multipath scheduling strategies, and network emulation tools such as Mininet-WiFi. His expertise also covers network shaping and mobility models for evaluating transport protocols in dynamic environments. His work on assessing and optimizing multipath schedulers for mobile networks has been published in flagship conferences (e.g., IEEE CCNC, IEEE VTC-Fall) and leading journals in the field (e.g., Computer Communications).
Thanh Trung Nguyen received his B.E. and M.S. degrees from Hanoi University of Science and Technology (HUST), Vietnam, in 2016 and 2019, respectively. He is currently a Ph.D. student at the School of Information and Communication Technology, HUST, specializing in multipath transport protocols, network architecture, optimization, and reinforcement learning. He has extensive experimental experience in MPQUIC scheduling, including the design, implementation, and real-world evaluation of AI-driven schedulers for heterogeneous wireless networks. He is the first author of multiple peer-reviewed papers on MPQUIC's scheduler optimization published in IEEE CCNC, IEEE WF-IoT, and Computer Communication. His work has contributed to both simulated network environments and real-world deployments, demonstrating the feasibility of AI-driven MPQUIC optimization. His research plays a crucial role in enhancing next-generation multipath transport by integrating machine learning and reinforcement learning techniques into practical implementations.
September 23 (Tue), 2025, 13:10-14:50, Track I
Chair: Shao-Yu Lien (National Yang Ming Chiao Tung University, Taiwan)
Subject: MIMO-OFDM ISAC Systems: Fundamentals, Recent Advances, and Opportunities
Summary: To enable emerging applications in the new era, integrated sensing and communication (ISAC) has been recognized as one of the key enabling technologies. Meanwhile, orthogonal frequency division multiplexing (OFDM), as the dominant waveform in modern wireless communication systems, together with multi-input multi-output (MIMO) technology, is expected to continue playing a critical role in future 6G networks. In this context, this tutorial will first introduce the fundamentals of MIMO-OFDM ISAC systems and the underlying signal processing techniques. Then, several advanced precoding design approaches for MIMO-OFDM ISAC will be presented. Finally, the tutorial will highlight some key challenges and discuss promising research opportunities for MIMO-OFDM ISAC.
Ming-Chun Lee received the B.S. and M.S. degrees in Electrical and Computer Engineering from National Chiao Tung University, Hsinchu, Taiwan, in 2012 and 2014, respectively, and the PhD from the Ming Hsieh Department of Electrical Engineering at University of Southern California in 2020. From 2014 to 2016, he was a research assistant in Wireless Communications Lab in the Research Center for Information Technology Innovation, Academia Sinica, Taiwan. He is now the Associate Professor of Institute of Communications Engineering at National Yang Ming Chiao Tung University. He received USC Annenberg Fellowship from 2016 to 2020. He was awarded the exemplary reviewer of IEEE Transactions on Communications in 2019. He is an Editor of IEEE Transactions on Wireless Communications. His research interest includes signal processing, design, modeling, and analysis in wireless systems and networks. He is especially working on topics relevant to caching, computing, and communication in wireless networks and integrated sensing and communication systems in recent years.
September 23 (Tue), 2025, 15:00-16:40, Track I
Chair: Shao-Yu Lien (National Yang Ming Chiao Tung University, Taiwan)
Subject: Autonomic Closed-Loop Service Management Conducted by Interworking Three AI Models Dedicated for Self-Monitoring, Self-Configuration and Self-Optimization
Summary: Constant monitoring and agile management of cloud-native network functions (CNFs) are the essential to prevent serious degradation of quality of services (QoS) in network service infrastructure. To monitor and agilely manage services against dynamically changing situations in complicated cloud-native (CN) network infrastructure, automation of closed-loop service management should be discussed. In this talk, we introduce a unified interface of interworking multiple functions including different AI models to establish autonomic closed-loop service management that adapts not only to the past failure events, but also to the future ones according to the failure prediction. We also demonstrate the prototype of automatic closed-loop service management for CN infrastructure that automatically constructs network services and maintains QoS of the existing services based on the interworking three AI models dedicated for self-monitoring, self-configuration, and self-optimization.
Takahiro Hirayama received a M.S. Degree and Ph.D. Degree from Osaka University in 2010, 2013, respectively. In April 2013, he joined National Institute of Information and Communications Technology (NICT) and is currently a senior researcher at Network Research Institute in NICT. His research interests are in software defined networking (SDN), network function virtualization (NFV) and ML-based network management. He is a member of IEEE and IEICE.
Takuya Miyasaka received his M.S. in Information Science and Technology from the University of Tokyo in 2011 and joined KDDI Corporation, spending seven years advancing the development of KDDI’s nation-wide backbone network. In 2018 he was seconded to KDDI Research, Inc., where he led research on communication infrastructure for connected vehicles and contributed to related standards work until 2021. He now heads R&D and standardization initiatives in network operations at KDDI Research, focusing on autonomous operation, intent-based networking, and AI-driven management frameworks. His professional interests span network architecture, large-scale automation, and the application of AI/ML to carrier-grade infrastructures. He is an active member of IEICE, TM Forum, and several IETF working groups, and currently serves as Chair of JANOG (Japan Network Operators’ Group).
Takayuki Kuroda received his Ph.D. in Information Science from Tohoku University. He joined NEC Corporation in 2009, where he has been engaged in research of automation technologies for system construction and operation. In 2013, he served as a Visiting Researcher at Vanderbilt University in the United States. Currently, he holds dual positions as a Senior Professional in NEC's Common Themes SI Services Division and a Senior Principal Researcher at the Secure System Platform Research Laboratories. ICM Research Award of IEICE in 2023 and 2024.