JACoW is a publisher in Geneva, Switzerland that publishes the proceedings of accelerator conferences held around the world by an international collaboration of editors.
@inproceedings{veraramirez:icalepcs2021-thal01,
author = {L. Vera Ramiréz and T. Birke and G. Hartmann and R. Müller and M. Ries and P. Schnizer and A. Schälicke},
% author = {L. Vera Ramiréz and T. Birke and G. Hartmann and R. Müller and M. Ries and P. Schnizer and others},
% author = {L. Vera Ramiréz and others},
title = {{Machine Learning Tools Improve BESSY II Operation}},
booktitle = {Proc. ICALEPCS'21},
pages = {784--790},
eid = {THAL01},
language = {english},
keywords = {experiment, network, ISOL, simulation, controls},
venue = {Shanghai, China},
series = {International Conference on Accelerator and Large Experimental Physics Control Systems},
number = {18},
publisher = {JACoW Publishing, Geneva, Switzerland},
month = {03},
year = {2022},
issn = {2226-0358},
isbn = {978-3-95450-221-9},
doi = {10.18429/JACoW-ICALEPCS2021-THAL01},
url = {https://jacow.org/icalepcs2021/papers/thal01.pdf},
abstract = {{At the HZB user facility BESSY II Machine Learning (ML) technologies aim at advanced analysis, automation, explainability and performance improvements for accelerator and beamline operation. The development of these tools is intertwined with improvements of the prediction part of the digital twin instances at BESSY II [*] and the integration into the Bluesky Suite [**,***]. On the accelerator side, several use cases have recently been identified, pipelines designed and models tested. Previous studies applied Deep Reinforcement Learning (RL) to booster current and injection efficiency. RL now tackles a more demanding scenario: the mitigation of harmonic orbit perturbations induced by external civil noise sources. This paper presents methodology, design and simulation phases as well as challenges and first results. Further ML use cases under study are, among others, anomaly detection prototypes with anomaly scores for individual features.}},
}