Project goal

Our aim is to make control systems used for the LHC more efficient and “smarter”. We are working to enhance the functionality of WinCC OA (a SCADA tool used widely at CERN) and to apply data-analytics techniques to the recorded monitoring data, in order to detect anomalies and systematic issues that may impact upon system operation and maintenance.

R&D topic
R&D Topic 3: Machine learning and data analytics
Project coordinator(s)
Fernando Varela
Technical team members
Filippo Tilaro, Jakub Guzik, Rafal Kulaga, Piotr Golonka, Peter Sollander
Collaborator liaison(s)
Thomas Hahn, Juergen Kazmeier, Alexey Fishkin, Tatiana Mangels, Mikhail Kalinkin, Elisabeth Bakany, Ewald Sperrer

Collaborators

Project background

The HL-LHC programme aims to increase the integrated luminosity — and hence the rate of particle collisions — by a factor of ten beyond the LHC’s design value. Monitoring and control systems will therefore become increasingly complex, with unprecedented data throughputs. Consequently, it is vital to further improve the performance of these systems, and to make use of data-analytics algorithms to detect anomalies and anticipate future behaviour. Achieving this involves a number of related lines of work. This project focuses on the development of a modular and future-proof archiving system (NextGen Archiver) that supports different SQL and NOSQL technologies to enable data analytics. It is important that this can be scaled up to meet our requirements beyond 2020.

Recent progress

Significant progress was made on all components of the NextGen Archiver in 2018. The front end, the InfluxDB, and Oracle back ends now support almost all basic functionality planned for the initial release in 2019.

Reaching this level of functionality has made it possible to test the NextGen Archiver and deploy it in pilot systems at CERN. At the ProtoDUNE experiment, the InfluxDB back end is used to enable online access to archived data from Grafana, open platform for analytics and monitoring. At the ALICE experiment, members of the collaboration are developing a custom back end to stream control systems data to a new online-offline physics data readout system.

Several large-scale tests of the NextGen Archiver were performed at CERN in 2018 to stress-test the archiver and assess its scalability. These complemented the functional tests written at ETM, the Siemens-owned company behind the tool. The results of these tests have already influenced the query architecture of the archiver and helped us to improve its performance.

In 2018, tools for future benchmarking of Apache Kudu’s read- and write-performance were developed, with the help of a CERN openlab summer student.

Next steps

Work on all components of the NextGen Archiver — as well as testing efforts — will continue in 2019. This year also brings important deadlines and deliverables for the project, including the release of version 1.0 and the start of tests in the ALICE infrastructure in May (to be put in production in the final quarter of the year).