Saved in:
Bibliographic Details
Main Authors: Scomparin, Luca, Caselle, Michele, Garcia, Andrea Santamaria, Xu, Chenran, Blomley, Edmund, Dritschler, Timo, Mochihashi, Akira, Schuh, Marcel, Steinmann, Johannes L., Bründermann, Erik, Kopmann, Andreas, Becker, Jürgen, Müller, Anke-Susanne, Weber, Marc
Format: Preprint
Published: 2024
Subjects:
Online Access:https://arxiv.org/abs/2409.16177
Tags: Add Tag
No Tags, Be the first to tag this record!
_version_ 1866913515749507072
author Scomparin, Luca
Caselle, Michele
Garcia, Andrea Santamaria
Xu, Chenran
Blomley, Edmund
Dritschler, Timo
Mochihashi, Akira
Schuh, Marcel
Steinmann, Johannes L.
Bründermann, Erik
Kopmann, Andreas
Becker, Jürgen
Müller, Anke-Susanne
Weber, Marc
author_facet Scomparin, Luca
Caselle, Michele
Garcia, Andrea Santamaria
Xu, Chenran
Blomley, Edmund
Dritschler, Timo
Mochihashi, Akira
Schuh, Marcel
Steinmann, Johannes L.
Bründermann, Erik
Kopmann, Andreas
Becker, Jürgen
Müller, Anke-Susanne
Weber, Marc
contents The commissioning and operation of future large-scale scientific experiments will challenge current tuning and control methods. Reinforcement learning (RL) algorithms are a promising solution thanks to their capability of autonomously tackling a control problem based on a task parameterized by a reward function. The conventionally utilized machine learning (ML) libraries are not intended for microsecond latency applications, as they mostly optimize for throughput performance. On the other hand, most of the programmable logic implementations are meant for computation acceleration, not being intended to work in a real-time environment. To overcome these limitations of current implementations, RL needs to be deployed on-the-edge, i.e. on to the device gathering the training data. In this paper we present the design and deployment of an experience accumulator system in a particle accelerator. In this system deep-RL algorithms run using hardware acceleration and act within a few microseconds, enabling the use of RL for control of ultra-fast phenomena. The training is performed offline to reduce the number of operations carried out on the acceleration hardware. The proposed architecture was tested in real experimental conditions at the Karlsruhe research accelerator (KARA), serving also as a synchrotron light source, where the system was used to control induced horizontal betatron oscillations in real-time. The results showed a performance comparable to the commercial feedback system available at the accelerator, proving the viability and potential of this approach. Due to the self-learning and reconfiguration capability of this implementation, its seamless application to other control problems is possible. Applications range from particle accelerators to large-scale research and industrial facilities.
format Preprint
id arxiv_https___arxiv_org_abs_2409_16177
institution arXiv
publishDate 2024
record_format arxiv
spellingShingle Microsecond-Latency Feedback at a Particle Accelerator by Online Reinforcement Learning on Hardware
Scomparin, Luca
Caselle, Michele
Garcia, Andrea Santamaria
Xu, Chenran
Blomley, Edmund
Dritschler, Timo
Mochihashi, Akira
Schuh, Marcel
Steinmann, Johannes L.
Bründermann, Erik
Kopmann, Andreas
Becker, Jürgen
Müller, Anke-Susanne
Weber, Marc
Accelerator Physics
High Energy Physics - Experiment
Instrumentation and Detectors
The commissioning and operation of future large-scale scientific experiments will challenge current tuning and control methods. Reinforcement learning (RL) algorithms are a promising solution thanks to their capability of autonomously tackling a control problem based on a task parameterized by a reward function. The conventionally utilized machine learning (ML) libraries are not intended for microsecond latency applications, as they mostly optimize for throughput performance. On the other hand, most of the programmable logic implementations are meant for computation acceleration, not being intended to work in a real-time environment. To overcome these limitations of current implementations, RL needs to be deployed on-the-edge, i.e. on to the device gathering the training data. In this paper we present the design and deployment of an experience accumulator system in a particle accelerator. In this system deep-RL algorithms run using hardware acceleration and act within a few microseconds, enabling the use of RL for control of ultra-fast phenomena. The training is performed offline to reduce the number of operations carried out on the acceleration hardware. The proposed architecture was tested in real experimental conditions at the Karlsruhe research accelerator (KARA), serving also as a synchrotron light source, where the system was used to control induced horizontal betatron oscillations in real-time. The results showed a performance comparable to the commercial feedback system available at the accelerator, proving the viability and potential of this approach. Due to the self-learning and reconfiguration capability of this implementation, its seamless application to other control problems is possible. Applications range from particle accelerators to large-scale research and industrial facilities.
title Microsecond-Latency Feedback at a Particle Accelerator by Online Reinforcement Learning on Hardware
topic Accelerator Physics
High Energy Physics - Experiment
Instrumentation and Detectors
url https://arxiv.org/abs/2409.16177