Application of reinforcement learning in the LHC tune feedback
The Beam-Based Feedback System (BBFS) was primarily responsible for correcting the beam energy, orbit and tune in the CERN Large Hadron Collider (LHC). A major code renovation of the BBFS was planned and carried out during the LHC Long Shutdown 2 (LS2). This work consists of an explorative study to...
| Main Authors: | , , , |
|---|---|
| Format: | Article |
| Language: | English |
| Published: |
Frontiers Media S.A.
2022-09-01
|
| Series: | Frontiers in Physics |
| Subjects: | |
| Online Access: | https://www.frontiersin.org/articles/10.3389/fphy.2022.929064/full |
| _version_ | 1798037431801348096 |
|---|---|
| author | Leander Grech Gianluca Valentino Diogo Alves Simon Hirlaender |
| author_facet | Leander Grech Gianluca Valentino Diogo Alves Simon Hirlaender |
| author_sort | Leander Grech |
| collection | DOAJ |
| description | The Beam-Based Feedback System (BBFS) was primarily responsible for correcting the beam energy, orbit and tune in the CERN Large Hadron Collider (LHC). A major code renovation of the BBFS was planned and carried out during the LHC Long Shutdown 2 (LS2). This work consists of an explorative study to solve a beam-based control problem, the tune feedback (QFB), utilising state-of-the-art Reinforcement Learning (RL). A simulation environment was created to mimic the operation of the QFB. A series of RL agents were trained, and the best-performing agents were then subjected to a set of well-designed tests. The original feedback controller used in the QFB was reimplemented to compare the performance of the classical approach to the performance of selected RL agents in the test scenarios. Results from the simulated environment show that the RL agent performance can exceed the controller-based paradigm. |
| first_indexed | 2024-04-11T21:26:27Z |
| format | Article |
| id | doaj.art-0f2a97323cb44dd68fca328c01ac213f |
| institution | Directory Open Access Journal |
| issn | 2296-424X |
| language | English |
| last_indexed | 2024-04-11T21:26:27Z |
| publishDate | 2022-09-01 |
| publisher | Frontiers Media S.A. |
| record_format | Article |
| series | Frontiers in Physics |
| spelling | doaj.art-0f2a97323cb44dd68fca328c01ac213f2022-12-22T04:02:23ZengFrontiers Media S.A.Frontiers in Physics2296-424X2022-09-011010.3389/fphy.2022.929064929064Application of reinforcement learning in the LHC tune feedbackLeander Grech0Gianluca Valentino1Diogo Alves2Simon Hirlaender3Department of Communication and Computer Engineering, University of Malta, Msida, MaltaDepartment of Communication and Computer Engineering, University of Malta, Msida, MaltaCERN, Geneva, SwitzerlandDepartment of Artificial Intelligence and Human Interfaces, University of Salzburg, Salzburg, AustriaThe Beam-Based Feedback System (BBFS) was primarily responsible for correcting the beam energy, orbit and tune in the CERN Large Hadron Collider (LHC). A major code renovation of the BBFS was planned and carried out during the LHC Long Shutdown 2 (LS2). This work consists of an explorative study to solve a beam-based control problem, the tune feedback (QFB), utilising state-of-the-art Reinforcement Learning (RL). A simulation environment was created to mimic the operation of the QFB. A series of RL agents were trained, and the best-performing agents were then subjected to a set of well-designed tests. The original feedback controller used in the QFB was reimplemented to compare the performance of the classical approach to the performance of selected RL agents in the test scenarios. Results from the simulated environment show that the RL agent performance can exceed the controller-based paradigm.https://www.frontiersin.org/articles/10.3389/fphy.2022.929064/fullLHCbeam-based controllertune feedbackreinforcement learningcern |
| spellingShingle | Leander Grech Gianluca Valentino Diogo Alves Simon Hirlaender Application of reinforcement learning in the LHC tune feedback Frontiers in Physics LHC beam-based controller tune feedback reinforcement learning cern |
| title | Application of reinforcement learning in the LHC tune feedback |
| title_full | Application of reinforcement learning in the LHC tune feedback |
| title_fullStr | Application of reinforcement learning in the LHC tune feedback |
| title_full_unstemmed | Application of reinforcement learning in the LHC tune feedback |
| title_short | Application of reinforcement learning in the LHC tune feedback |
| title_sort | application of reinforcement learning in the lhc tune feedback |
| topic | LHC beam-based controller tune feedback reinforcement learning cern |
| url | https://www.frontiersin.org/articles/10.3389/fphy.2022.929064/full |
| work_keys_str_mv | AT leandergrech applicationofreinforcementlearninginthelhctunefeedback AT gianlucavalentino applicationofreinforcementlearninginthelhctunefeedback AT diogoalves applicationofreinforcementlearninginthelhctunefeedback AT simonhirlaender applicationofreinforcementlearninginthelhctunefeedback |