MSWiM 2026

Title: Modelling and Simulating the Computing Continuum with ENIGMA

Jesus Carretero, Universidad Carlos III de Madrid, Spain
Elías del Pozo, Universidad Politécnica de Madrid, Spain

Abstract: The explosive growth of the Internet of Things (IoT) paradigm has driven the emergence of highly complex, multi-layered network architectures encompassing Cloud, Edge, and Fog Computing. This Computing Continuum reduces latency and distributes computational load efficiently across the network. However, before physically deploying these costly infrastructures, researchers and engineers require robust simulation platforms to model dynamic environments and analyze key behavioral metrics (e.g., power consumption, CPU usage, and network bandwidth). The scope of this tutorial focuses on addressing the critical challenge of scalable simulation within the Computing Continuum, specifically highlighting environments that integrate mobile devices

Bio: Jesús Carretero is a Full Professor of Computer Architecture and Technology at Universidad Carlos III de Madrid (UC3M) in Spain, where he is responsible for that knowledge area since 2000 and is the leader of the Computer Architecture Research Group (ARCOS). My major research lines are High-Performance Computing, Large-scale distributed systems, Data-intensive computing and storage, and IoT and real-time systems. His research activity is centered on high-performance computing systems, large-scale distributed systems, data-intensive computing, IoT and real-time systems. He has been coordinator of the EuroHPC project ADMIRE and the Action Chair of the IC1305 COST Action "Network for Sustainable Ultrascale Computing Systems (NESUS)", and he was also the coordinator of the ADMIRE EuroHPC project. He is the director of the UC3M Scientific Computing Center (C3).
Bio: Elias Del Pozo Puñal is a post-doctoral researcher in High Performance Computing (HPC) at the Universidad Politécnica de Madrid (UPM). He is a member of the Computer Architecture Research Group (ARCOS) at Universidad Carlos III de Madrid, where he completed his PhD in 2025 with the highest distinction (cum laude). His research activity focuses mainly on High Performance Computing, computing continuum, distributed systems, file systems, Internet of Things (IoT), and simulation of edge and fog environments. This has allowed him to participate in multiple national research projects and collaborate with leading institutions in the field. As a result of his research, he has authored and co-authored more than 10 journal and conference articles, with expertise in scalable data management, distributed systems, and edge computing platforms. His work has been published in journals such as Future Generations Computer Systems and IEEE Access.

Title: Edge-Cloud Collaborative Computing on Distributed Intelligence and Model Optimization

Jing Liu, Duke Kunshan University, China; The University of British Columbia, Canada
Azzedine Boukerche, University of Ottawa, Canada
Peng Sun, Duke Kunshan University, China; University of Ottawa, Canada

Abstract: The rapid proliferation of artificial intelligence (AI)-enabled applications and Internet of Things (IoT) devices is driving a fundamental shift from centralized cloud computing toward edge-cloud collaborative computing (ECCC). By considering the heterogeneous nature of the IoT environment, e.g., various communication and storage requirements, computing capacity across end devices, edge infrastructure, and cloud platforms, ECCC provides a promising foundation for supporting emerging intelligent applications with stringent requirements on latency, efficiency, scalability, and privacy. While, as the development of modern AI techniques, the increasing complexity of deep neural networks and large AI models introduces significant challenges in deploying and optimizing distributed intelligence over heterogeneous and resource-constrained edge-cloud environments.

Accordingly, in this tutorial, we will provide a comprehensive introduction to the foundations, enabling technologies, and emerging research directions of edge-cloud collaborative computing for supporting distributed intelligence and model optimization. We will first introduce the fundamental architectures of ECCC and discuss how task, data, and model parallelism can be exploited to distribute AI workloads across the edge-cloud continuum. We will then examine key model optimization techniques, including model compression, model adaptation, and resource-aware model optimization, with particular emphasis on the trade-offs among model accuracy, computational complexity, communication overhead, and resource constraints. We will further explore AI-driven resource management, including intelligent task offloading, dynamic computation and communication resource allocation, and energy-efficient optimization. We will discuss how AI techniques, particularly reinforcement learning, can enable adaptive decision-making under dynamic network conditions, heterogeneous computing capabilities, and varying workloads. Meanwhile, we will also discuss the privacy and security issues associated with distributed intelligence. We will introduce some representative approaches for privacy-preserving learning, model protection, and secure communications.

In addition, to bridge theoretical methodologies with real-world systems, we will further discuss representative ECCC applications, including autonomous driving, smart healthcare, industrial automation, etc., and examine performance evaluation methodologies and practical design considerations. Finally, we will highlight open challenges and emerging opportunities, including the deployment of large language models (LLMs) and AI agents across the edge-cloud continuum, embodied AI, 6G-integrated computing and networking, neuromorphic computing, and quantum edge computing.

Through this tutorial, attendees will gain a systematic understanding of how AI models, computing resources, and communication networks can be jointly designed and optimized to enable scalable, efficient, and intelligent edge-cloud systems, as well as insights into promising directions for future research in distributed intelligence.

Bio: Jing Liu (Member, IEEE) received his B.S. and M.S. from the University of Shanghai for Science and Technology (2014, 2017) and his Ph.D. from Fudan University (2023). Currently a Postdoctoral Fellow at The University of British Columbia, his research focuses on edge-cloud collaboration, multimodal learning, anomaly detection, and distributed signal processing. Dr. Liu has published in leading venues and reviews for premier journals (e.g., IEEE TII, TMC) and conferences (e.g., CVPR, NeurIPS). His academic service includes Session Organizer for ICASSP/ICME’26, Publicity Chair for CloudCom’25, and Lead Guest Editor for IEEE TCSS.

Bio: Azzedine Boukerche (F’IEEE, F’EiC, F’CAE, F’AAAS) is a Distinguished University Professor and holds a Canada Research Chair Tier-1 position with the University of Ottawa. He is founding director of the PARADISE Research Laboratory and the DIVA Strategic Research Center, and NSERC-CREATE TRANSIT at University of Ottawa. He has received the C. Gotlieb Computer Medal Award, Ontario Distinguished Researcher Award, Premier of Ontario Research Excellence Award, G. S. Glinski Award for Excellence in Research, IEEE Computer Society Golden Core Award, IEEE CS-Meritorious Award, IEEE TCPP Leaderships Award, IEEE ComSoc ComSoft and IEEE ComSoc ASHN Leaderships and Contribution Award, and University of Ottawa Award for Excellence in Research.

Bio: Peng Sun (SM’IEEE; SM’CIC) is a tenure-track Assistant Professor of Data Science at Duke Kunshan University and an adjunct professor at the University of Ottawa. His current research interests include Intelligent Transportation Systems, Internet-of-Vehicles, cross-layer optimization and design, etc. Currently, he serves as an Associate Editor for ACM CSUR and Elsevier COMCOM, and a guest editor for ACM TOMM, and Springer/Nature J. Supercomputing. He also served as Technical Program Committee Co-chair/member in many well-known conferences, e.g., PIMRC’23, ICDCS’22, MSWiM’17∼26, ICC’20∼26, etc. He is the recipient of IEEE ICDCS’26 Distinguished Paper Award, IEEE MMSP’26 Best Paper Award, MSWiM’25 Best Short Paper Award, and the IEEE GLOBECOM’19 Best Paper Award, etc.