Feb 5 – 7, 2024
Universität Salzburg (Paris-Lodron-Universität)
Europe/Berlin timezone
Registration and call for abstracts extended to 5 January

Optimising non-linear Injection using Reinforcement Learning

Feb 7, 2024, 9:00 AM
20m
Blue lecture hall (Universität Salzburg (Paris-Lodron-Universität))

Blue lecture hall

Universität Salzburg (Paris-Lodron-Universität)

Hellbrunnerstrasse 34 5020 Salzburg
Student Talk Student Session

Speaker

Alexander Schütt (Helmholtz-Zentrum Berlin)

Description

Synchrotron light source storage rings aim to maintain a continuous beam current without observable beam motion during injection. One element that paves the way to this target is the non-linear kicker (NLK). The field distribution it generates poses challenges for optimising the topping-up operation.

Within this study, a reinforcement learning agent was developed and trained to optimise the NLK operation parameters. We present the models employed, the optimisation process, and the achieved results.

Possible contributed talk Yes
Are you a student? Yes

Primary author

Alexander Schütt (Helmholtz-Zentrum Berlin)

Co-authors

Pierre Schnizer (pierre.schnizer@helmholtz-berlin.de) Prof. Christoph Knochenhauer (TU Munich)

Presentation materials