UPDATE ......Confluence has now been updated to version 9.2.6. Please see following page for details and feedback about changes:
Updates
9th and 10th October 2025
SIG-NGN is the Special Interest Group on Next Generation Networks.
SIG-AI explores the potential applications of Artificial Intelligence (AI) within the context of Research and Education Networks (NRENs).
The 16th The 15th SIG-NGN, in collaboration with SIG-AI, will take place on the 9th and 10th October 2025, co-located with the LHCOPN and LHCONE meeting at KIT in Karlsruhe, Germany. This will be an in-person meeting over two half-days with possibility for remote participation.
Theme: Networking for AI and AI for Networking.
One half-day will be spent exploring how we build networks for new upcoming demands, such as ‘AI,’ and we hope to include presentations on Ultra Ethernet, beyond 1T (or even 10T) networking, and “ultra large networks.”
The The second half day will be spent looking at how AI (or machine learning) can help us build and operate the networks. In this we hope to have a couple of (suitably prepared) vendor presentations, plus community presentations on how the technology might enable troubleshooting and workflow management.
Feel free to contact the NGN Steering Committee if you have suggestions for the programme.
More information on logistics (e.g. hotels, travel, shuttle bus to venue) can be found on the LHCONE/LHCOPN meeting page.
Meeting location: SCC Building 449 / Room 140, Karlsruhe Institute of Technology, Karlsruhe, DE.
| View file | ||||
|---|---|---|---|---|
|
ZOOM LINK for remote participants
RECORDING |
|---|
Socialising
Quick Links
All Presentations (currently past meeting presentations.)
Checkout the discussion on NREN.slack.com (sign up here)
Subscribe to the NGN mailing list or View the Archive
Contact the NGN Steering Committee
Registration is open
Agenda - (all times are in
CETCEST - UTC+2)
MondayThursday, 9
September 2024October 2025
| Time | What's happening | |||
|---|---|---|---|---|
| 0912:2045 - 0913:3000 | Get a coffee - Testing audio & video | |||
| 0913:30 00 - 0913:50 20 ('20) | Welcome and Introduction | |||
| 1st session | ||||
0913:50 20 - 1013:10 40 ('20) |
| Why do we need to talk about networking for AI? Requirements and solutions. Kamran Naqvi, Broadcom | ||
13:40 - 14:00 10:10 - 10:30 ('20) | ||||
10:30- 10:50 ('20) | Discussions | |||
AI at Scale: HPC Primitives in the Cloud-Native Era Ricardo Rocha | ||||
14:00- 14:30 ('30) | Building Networks for AI Eli Dart, ESnet | |||
| 14:30 - 15:00 10:50 - 11:20 ('30) | Coffee Break | |||
| 2nd session | ||||
| 1115:20 00 -1115:40 30 ('20)30) | UltraEthernet Andreas Roeder, Nokia | |||
| 15:30 - 1611:40 - 12:00 ('2030) | AI/ML data center fabric advanced load balancing Michal Styszynski, Juniper | |||
| 1612:00 - 1216:20 30 ('20) |
| 12:20 - 13:20 ('60) | Lunch Break30) | AI for Network Management and the IETF Network Management Research Group Jefferson Nobre |
| 16:30 - 17:00 ('30) | Discussions | |||
End of the day |
Friday, 10 October 2025
| Time | What's happening |
|---|---|
| 8:45 - 9:00 | Get a coffee - Testing audio & video |
| 3rd session |
9: |
|---|
00 - |
|---|
9: |
|---|
10 ('10) | Scene setting: AI for network management |
|---|---|
9:10 - 9:20 ('10) |
An overview of SIG-AI |
9:20 - 9:40 ('20) |
|---|
GN5-2 Survey on AI for Network Management Pavle Vuletic | |
9:40 - 10:10 ('30) | AI for Workflow Orchestrator Peter Boers |
|---|---|
10:10 - 10:30 |
('20) |
|---|
| LogLLM |
| 10: |
|---|
| 30 - |
|---|
| 11: |
|---|
| 00 ('30) | Coffee Break |
|---|---|
| 4th session |
| 11:00 -11:20 ('20) | Classification and Identification of network traffic using AI models Maarten Meijer |
|---|---|
| 11:20 - 11:40 (' |
| 20) | Tour into Practical AI for Network Traffic Analysis Jaroslav Pesek, CESNET We present recent R&D results within an end-to-end monitoring and analysis pipeline. We show how to detect network anomalies and convert them into events for SOC team, introduce libraries and datasets for reproducible modelling, and demonstrate that a simple k-NN on packet-sequence metadata can perform on-par with complex models. We conclude with visualisations that aid traffic interpretation. |
|---|---|
| 11:40 - 12:10 ('30) |
Discussions |
| 12:10 - |
|---|
| 12:30 ('20) |
|---|
16:30 - 16:40 ('10)
Discussions
Wrap up
Wrap-Up | |
End of the meeting |