JACoW is a publisher in Geneva, Switzerland that publishes the proceedings of accelerator conferences held around the world by an international collaboration of editors.
TY - CONF AU - Vera Ramiréz, L. AU - Birke, T. AU - Hartmann, G. AU - Müller, R. AU - Ries, M. AU - Schnizer, P. AU - Schälicke, A. ED - Furukawa, Kazuro ED - Yan, Yingbing ED - Leng, Yongbin ED - Chen, Zhichu ED - Schaa, Volker R.W. TI - Machine Learning Tools Improve BESSY II Operation J2 - Proc. of ICALEPCS2021, Shanghai, China, 14-22 October 2021 CY - Shanghai, China T2 - International Conference on Accelerator and Large Experimental Physics Control Systems T3 - 18 LA - english AB - 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. PB - JACoW Publishing CP - Geneva, Switzerland SP - 784 EP - 790 KW - experiment KW - network KW - ISOL KW - simulation KW - controls DA - 2022/03 PY - 2022 SN - 2226-0358 SN - 978-3-95450-221-9 DO - doi:10.18429/JACoW-ICALEPCS2021-THAL01 UR - https://jacow.org/icalepcs2021/papers/thal01.pdf ER -