Welcome!
This is the homepage of the Mathematical and Computational Foundations for Digital Twins of Wireless Ad Hoc Networks (MAITRE) project.
About MAITRE
The MAITRE project explores the convergence of Artificial Intelligence (AI) and Digital Twin (DT) technologies to optimize the operation of wireless ad hoc networks, including satellite, UAV, sensor, and massive IoT systems. These networks underpin modern communications but remain highly dynamic and unstable due to fluctuating traffic, topology, and resource availability, making real-time control and testing costly and complex.
MAITRE envisions AI-driven Digital Twins as dynamic, real-time digital counterparts of physical networks (Physical Twins, PTs), enabling two-way interaction for prediction, optimization, and control. Unlike traditional simulators, MAITRE’s DTs will continuously adapt to evolving network conditions through learning-based models, offering proactive and intelligent network management.
The project will establish reference DT architectures and Key Performance Indicators (KPIs), optimize data collection and placement between cloud and edge environments, and design AI modules based on Reinforcement Learning, Continual Learning, and Transfer Learning for decentralized and adaptive decision-making. Generative AI will address data scarcity and enhance model generalization.
Overall, by providing the mathematical, algorithmic, and methodological foundations for next-generation DT frameworks, MAITRE will create a validated proof-of-concept that demonstrates efficient, autonomous, and intelligent management of wireless ad hoc networks—advancing the path toward future 6G and machine-to-machine systems.
Fact sheet
| Duration | 10/2025 - 10/2029 |
|---|---|
| Principal Investigator | Stavros Toumpis |
| Collaborators |
Iordanis Koutsopoulos Stratis Ioannidis Christian Bettstetter Yannis Thomas Merkourios Karaliopoulos Spyridon Chadoulos Thomas Tsouparopoulos Dimitrios Kafetzis Ioannis Papageorgiou Triantafyllos Papadopoulos |
Dissemination
Publications in journals, conferences and workshops
- T. Tsouparopoulos and I. Koutsopoulos, “Learning to Fine-tune Foundation Models under Resource Limitations,” in Proc. 2025 IEEE International Conference on Machine Learning for Communication and Networking (ICMLCN), 2026.
Deliverables
- To be updated
Testbed
A testbed is designed and implemented in the context of LEMONADE project in order to make real-life transmission rate measurements in ad hoc wireless networks. The testbed currently consists of 30 wireless nodes, materialized through Rasbperry Pi devices, that are placed inside three different floors of an office building of the Athens University of Economics and Business. The testbed supports the estimation of performance in sophisticated transmission mode schemes, thus introducing the first scientific tool for studying the Capacity Region of wireless ad hoc networks without resorting to modeling tools.Datasets
- To be updated
Software
- To be updated
Contact
Project Leader
Stavros ToumpisPatission 76,
Athens 104 34, Greece
Office Location: Troias/Spetson/Kimolou building, office 406.
Tel: (+30) 210 8203650
Fax: (+30) 210 8226105
Homepage Mobile Multimedia Laboratory
Office Locations: Room 209, Trias 2
Athens 104 34, Greece
Tel: (+30) 210 8203551
Fax: (+30) 210 8203686
This work has received funding from the Hellenic Foundation for Research and Innovation (H.F.R.I.), Greece under the ‘‘3rd Call for H.F.R.I.’s Research Projects to Support Faculty Members & Researchers’’ (ProjectNumber: 23767, Project Title: Towards advancing the Mathematical and Computational Foundations for Digital Twins of Wireless Ad Hoc Networks).
