A low-latency feedback system for the control of horizontal betatron oscillations
Caselle, Michele 1; Weber, Marc; Kopmann, Andreas
1; Santamaria Garcia, Andrea
2; Steinmann, Johannes
3; Scomparin, Luca
1; Mueller, Anke-Susanne
; Bründermann, Erik
3; Blomley, Edmund
3; Assmann, Ralph [Hrsg.]; McIntosh, Peter [Hrsg.]; Fabris, Alessandro [Hrsg.]; Bisoffi, Giovanni [Hrsg.]; Andrian, Ivan [Hrsg.]; Vinicola, Giulia [Hrsg.]
1 Institut für Prozessdatenverarbeitung und Elektronik (IPE), Karlsruher Institut für Technologie (KIT)
2 Laboratorium für Applikationen der Synchrotronstrahlung (LAS), Karlsruher Institut für Technologie (KIT)
3 Institut für Beschleunigerphysik und Technologie (IBPT), Karlsruher Institut für Technologie (KIT)
1; Santamaria Garcia, Andrea
2; Steinmann, Johannes
3; Scomparin, Luca
1; Mueller, Anke-Susanne
; Bründermann, Erik
3; Blomley, Edmund
3; Assmann, Ralph [Hrsg.]; McIntosh, Peter [Hrsg.]; Fabris, Alessandro [Hrsg.]; Bisoffi, Giovanni [Hrsg.]; Andrian, Ivan [Hrsg.]; Vinicola, Giulia [Hrsg.]1 Institut für Prozessdatenverarbeitung und Elektronik (IPE), Karlsruher Institut für Technologie (KIT)
2 Laboratorium für Applikationen der Synchrotronstrahlung (LAS), Karlsruher Institut für Technologie (KIT)
3 Institut für Beschleunigerphysik und Technologie (IBPT), Karlsruher Institut für Technologie (KIT)
Abstract:
Reinforcement learning (RL) algorithms are investigated at KIT as an option to control the beam dynamics at storage rings.
These methods require specialized hardware to satisfy throughput and latency constraints dictated by the timescale of the relevant phenomena.
The KINGFISHER platform, based on the novel Xilinx Versal Adaptive Compute and Acceleration Platform, is an ideal candidate to deploy RL-on-a-chip thanks to its ability to execute computationally intensive and low latency feedback loops in the order of tens of microseconds.
In this publication, we will present the integration of the KINGFISHER system at the Karlsruhe Research Accelerator (KARA), as a proof-of-principle turn-by-turn control feedback loop, to control induced transversal oscillations of an electron beam.
These methods require specialized hardware to satisfy throughput and latency constraints dictated by the timescale of the relevant phenomena.
The KINGFISHER platform, based on the novel Xilinx Versal Adaptive Compute and Acceleration Platform, is an ideal candidate to deploy RL-on-a-chip thanks to its ability to execute computationally intensive and low latency feedback loops in the order of tens of microseconds.
In this publication, we will present the integration of the KINGFISHER system at the Karlsruhe Research Accelerator (KARA), as a proof-of-principle turn-by-turn control feedback loop, to control induced transversal oscillations of an electron beam.
| Zugehörige Institution(en) am KIT | Institut für Beschleunigerphysik und Technologie (IBPT) Institut für Prozessdatenverarbeitung und Elektronik (IPE) Laboratorium für Applikationen der Synchrotronstrahlung (LAS) |
| Publikationstyp | Proceedingsbeitrag |
| Publikationsdatum | 26.09.2023 |
| Sprache | Englisch |
| Identifikator | ISBN: 978-3-95450-231-8 ISSN: 2673-5490 KITopen-ID: 1000163620 |
| HGF-Programm | 54.11.11 (POF IV, LK 01) Accelerator Operation, Research and Development |
| Weitere HGF-Programme | 54.12.03 (POF IV, LK 01) Science Systems |
| Erschienen in | 14th International Particle Accelerator Conference, Vernedig, 7th-12th May 2023 |
| Veranstaltung | 14th International Particle Accelerator Conference (IPAC 2023), Venedig, Italien, 07.05.2023 – 12.05.2023 |
| Verlag | JACoW Publishing |
| Seiten | 4479-4482 |
| Schlagwörter | Accelerator Physics, mc6-beam-instrumentation-controls-feedback-and-operational-aspects - MC6: Beam Instrumentation, Controls, Feedback and Operational Aspects, mc6-a27-machine-learning-and-digital-twin-modelling - MC6.A27: Machine Learning and Digital Twin Modelling |