Ivan Čilić, Ana Petra Jukić, Ivan Kralj - AIoTwin orchestration middleware
This hands-on session introduces participants to the practical deployment of Hierarchical Federated Learning (HFL) across the computing continuum. The session is divided into two parts. In the first part, participants will use the Flower framework to set up and execute standard Federated Learning (FL) tasks, gaining insights into FL without middleware orchestration. The second part focuses on the use of AIoTwin orchestration middleware, demonstrating how it enables scalable, distributed HFL workflows across heterogeneous edge, fog, and cloud environments. Participants will be guided through deploying their own custom FL tasks on a real distributed cluster, exploring the middleware’s capabilities for orchestration, resource management, and hierarchical coordination. This session is ideal for researchers and practitioners interested in edge-to-cloud AI pipelines and FL at scale.
Ivan Čilić is a Leading Researcher at the Department of Telecommunications, Faculty of Electrical Engineering and Computing, University of Zagreb. He received the MS degree in information and communication technology at the Faculty of Electrical Engineering and Computing, University of Zagreb, where he is currently pursuing his Ph.D. degree in computer science. During 2023, as part of the AIoTwin project, he participated in a study visit at the Distributed Systems Group at TU Wien, Vienna, Austria. His professional interests include Internet of Things (IoT), edge computing and container orchestration. The current focus of his research is on service orchestration and data-driven routing in the edge computing environment.
Ana Petra Jukić completed her master's degree in computer science from the Faculty of Electrical Engineering and Computing (FER) at the University of Zagreb. She is a PhD candidate and a teaching assistant at FER in the Department of Telecommunications. Her research focuses on federated learning for time series data, communication efficiency and deployment on edge devices.
Katarina Vuknić graduated in Computing from the Faculty of Electrical Engineering, Mechanical Engineering and Naval Architecture in Split. She is currently a PhD candidate and researcher at the University of Zagreb Faculty of Electrical Engineering and Computing in Zagreb. Her research focuses on the application of machine learning in distributed systems within the Internet of Things environment.
Anh Le Tuan - Building a Semantic Swarm of Edge Intelligence
This hands-on tutorial introduced participants to the Smartedge Toolchain, developed as part of the EU-funded Smartedge project. The toolchain enables the development of applications based on the collaboration of distributed Smartedge nodes that form a dynamic, swarm-like network. The system leverages semantic technologies to describe the capabilities and properties of Smartedge nodes, enabling automatic discovery of nodes suitable for executing specific tasks. Applications are modeled using the Recipe Model, which defines the desired workflow and required node functionalities.
During the tutorial, attendees gained practical experience using the toolchain, starting with describing smart node capabilities through Web of Things (WoT) Thing Descriptions to achieve semantic interoperability and dynamic discovery. They will then model applications using the Recipe Model and deploy them using SmarteRuntime, managing distributed execution across the edge network. The tutorial highlighted real-time device collaboration and is ideal for those interested in Edge AI, IoT, and semantic technologies.
Anh Le-Tuan is a postdoctoral researcher at the PICom Lab, Open Distributed Systems group,Technical University of Berlin. His research focuses on semantic technologies, knowledge graphs, the Internet of Things (IoT), and edge intelligence, aiming to enhance interoperability and intelligence in decentralized systems. He earned his M.Sc. and Ph.D. from the Insight Centre for Data Analytics at the National University of Ireland, Galway, where his research focused on processing linked data on mobile and edge devices. His academic journey began with a Bachelor's and Engineering degree from Volgograd State Technical University in Russia.
Presentation PDF file