
EU-US 6G R&I Cooperation
6G Trans-Continental Edge Learning
This
About 6G-XCEL
6G-XCEL will bring together a large ecosystem of researchers from the EU and US to implement elements of the DMMAI framework in their testbeds and labs. DMMAI (Decentralized Multi-party, Multi-network AI) is a reference framework for AI in 6G that will pave the way towards global validation, adoption and standardization of AI approaches. This framework will enable the federation of AI-based network controls across network domains and physical layers, while promoting security and sustainable implementations. Research on the resulting decentralized multi-party, multi-network AI (DMMAI) framework will enable the development of reference use cases, data acquisition and generation methods, data and model repositories, curated training and evaluation data, as well as technologies and functionalities for its use as a benchmarking platform for future AI/ML solutions for 6G networks.
EU Testbeds
- OpenIreland Testbed
- Patras5G/P-NET Testbed
- SLICES RI
- City Lab, Smart Highway and 5GOpen, 5G-in-a-box portable and Time Sensitive Networks (TSN) Testbeds
US Testbeds
- CCI xG Testbed
- NSF Platforms for Advanced Wireless Research (PAWR) COSMOS
Use cases
- DMMAI for 6G spectrum management
- AI enhanced resource management
-
Live Demo at OFC Conference 2025 in San Francisco, California
6G-XCEL is at OFC 2025 this week! Visit us in the demo zone to check out our live Demonstration of the Cooperative Transport Interface (CTI). This demo showcases CTI running over an open source 7.2x split RAN and a virtualised Open PON network, illustrating how coordination between RAN and PON schedulers can reduce upstream latency and […]
-
AAAI Urban Planning Workshop 2025
Addressing Data Scarcity and Distribution Shifts in AI-Driven Networks! 5G & beyond demand high reliability, low latency, and massive throughput, making AI-powered network management essential. But there’s a challenge—ML models require vast labeled datasets, which are costly and time-consuming to collect. How do we solve this? Our team supported by 6G-XCEL project researched Pre-trained Transformers & Transfer Learning to address data scarcity and […]
-
AAU on International ITG Conference on Systems, Communications and Coding (SCC) 2025
Our academic team from Aalborg University presented at International ITG Conference on Systems, Communications and Coding (SCC) 2025 on TinyML Model Distribution for Energy-Efficient Data Retrieval using MQTT. Their work explores a Pull-based Communication Framework, achieving high energy efficiency while maintaining retrieval accuracy—a key step toward smarter, low-power AI-driven IoT solutions. This work acknowledges 6G-XCEL project’s contributions to low-power […]
-
CCI Joint Workshop at Virginia tech, Feb 25-26
6G-XCEL Commonwealth Cyber Initiative (CCI) Joint Workshop at Virginia Tech happened on Feb 25-26 2025, with lot of good discussions on Work Package Updates, Deliverables and Milestones review, 6G Architecture discussions around the components of DMMAI, use-cases features and requirements, Testbed updates and deployments as well as a wide range of Research Presentations (AI & 6G Research, Data Models, Intelligent […]
-
2024 At A Glance in our Newsletter Issue 1
Check out our newsletter issue 1 published in December 2024 to get insights around 6G-XCEL Project Goals, Dissemination and Communication activities as well as publications: https://www.6g-xcel.eu/wp-content/uploads/2024/12/6G-XCEL-Newsletter-Issue-1.pdf
-
IEEE Spectrum article from Aalborg University
Curious to get insights on how 6G-AI mashups are reshaping Telecom Industry impacting next-gen wireless networks? Shashi Raj Pandey, Assistant Professor at Connectivity Section (CNT) of Department of Electronic Systems in Aalborg University, published an interesting article in IEEE Spectrum related to 6G-XCEL Workshop in Rutgers. His insightful presentation was around the interplay between the value of […]
-
TIP FYUZ24 Panel on 6G & AI
6G-XCEL Team was around in TIP Fyuz2024 in Dublin Ireland on Nov 11-13, participating in two insightful panel discussions around “Future Networks: Are we ready for the AI Tsunami?” in partnership with CONNECT Centre.💡 “Panel 2 6G and AI” touched upon RAN Efficiency topics, and what AI for networking and Networking for AI means. Interested to learn more […]
-
TIP FYUZ24 Panel on GenAI and Network Transformation
6G-XCEL Team was around in TIP Fyuz2024 in Dublin Ireland on Nov 11-13, participating in two insightful panel discussions around “Future Networks: Are we ready for the AI Tsunami?” in partnership with CONNECT Centre.💡 “Panel 1 GenAI and Network Transformation: Challenges and Opportunities” discussed the main concepts of GenAI in networks, with people from Research, Academia and Industry […]
-
6G-XCEL Plenary Meeting
In 6G-XCEL Plenary meeting hosted on Sept 30-Oct 1 in WINLAB Rutgers University , team discussed on the Research Infrastructure and open testbeds: CCI xG, COSMOS at WINLAB, Patras5G, “Connected Antwerp: NextG Open, Smart Highway, and Citylab testbed” and OpenIreland. Teams highlighted the need for a future-proof resilient design of the Decentralized Multi-party Multi-network AI controller aka DMMAI using open interfaces, intent-based testbeds which are […]
-
Day 1 of 6G-XCEL ACCoRD Workshop
In Day 1 of 6G-XCEL ACCoRD joint Workshop, we heard an insightful roundtable discussion and panel on 6G-XCEL/ ACCoRD Cooperation Opportunities. Team discussed openly and exchanged ideas around Testbeds and Data usability, data availability to research communities and what are the challenges for AI in 6G Networks.
Objective
1
Investigate and design a framework for decentralized, multi-party, multi-network AI for the control of 6G networks.
2
Determine achievable time scales for DMMAI in real time, near-RT, and non-RT control loops.
3
Develop efficient and scalable advanced AI methods for large scale time series data in decentralized multi-party, multi-network control.
4
Investigate methods to address the security and privacy of multi-party, multi-network AI network control for DMMAI in 6G.
5
Determine energy efficiency of DMMAI for 6G and methods for its study.
6
Create a flexible DMMAI framework that can be used with different AI orchestration platforms in the EU and US.
7
Establish a community of excellence in research on Networks & AI spanning the EU and US to provide foundation for its use in 6G.