# Towards Fault Propagation Modeling in the WLCG Using Graph Neural Networks

- Institution: CERN
- Speaker: Pavel Khudov Yakovlev
- Year: 2026
- Language: English
- Source: [CERN](https://videos.cern.ch/record/3026669)
- Licence: [CERN](https://copyright.web.cern)
- Who can watch: Teens profiles and older (sources give no ratings; placed by Invisible Network from the source's own words)

**Project Description**:

The Worldwide LHC Computing Grid (WLCG) is a large-scale distributed infrastructure supporting data processing and analysis for CERN experiments. Due to its complexity and the dependencies between its services, failures or degradation in individual components may affect other parts of the system. Understanding and predicting these effects could help improve its reliability and operational efficiency.

Graph Neural Networks are well suited to modelling interconnected systems. This project investigates whether the WLCG can be represented as a temporal graph and whether GNNs can use its topology to predict operational degradation. FTS monitoring data is used as an initial proxy, providing a first step towards data-driven modelling of the WLCG.

**Supervisor**: Maria Del Carmen Misa Moreira, Sofia Vallecorsa

00:00:00 Slide 1

00:00:12 Slide 2

00:00:44 Slide 3

00:01:32 Slide 4

00:02:06 Slide 5

00:02:39 Slide 6

00:03:07 Slide 7

00:03:23 Slide 8

00:04:05 Slide 9

00:04:29 Slide 10

00:04:58 Slide 11

00:05:51 Slide 12

00:06:11 Slide 13

00:06:32 Slide 14

## Lectures

1. [Towards Fault Propagation Modeling in the WLCG Using Graph Neural Networks](https://invisiblenetwork.ai/learn/cern/3026669/1f4884ccae8f), 8 min (CERN's player)