Improving data quality monitoring via a partnership of technologies and resources between the CMS experiment at CERN and industry

¹ Massachusetts Institute of Technology (US)
² Carnegie-Mellon University (US)
³ CERN (CH)
⁴ University of Notre Dame (US)
⁵ Université Paris-Saclay (FR)
⁶ California Institute of Technology (US)

^* e-mail: virginia.azzolini@cern.ch

Published online: 17 September 2019

Abstract

The Compact Muon Solenoid (CMS) experiment dedicates significant effort to assess the quality of its data, online and offline. A real-time data quality monitoring system is in place to spot and diagnose problems as promptly as possible to avoid data loss. The a posteriori evaluation of processed data is designed to categorize it in terms of their usability for physics analysis. These activities produce data quality metadata. The data quality evaluation relies on a visual inspection of the monitoring features. This practice has a cost in term of human resources and is naturally subject to human arbitration. Potential limitations are linked to the ability to spot a problem within the overwhelming number of quantities to monitor, or to the lack of understanding of detector evolving conditions. In view of Run 3, CMS aims at integrating deep learning technique in the online workflow to promptly recognize and identify anomalies and improve data quality metadata precision. The CMS experiment engaged in a partnership with IBM with the objective to support, through automatization, the online operations and to generate benchmarking technological results. The research goals, agreed within the CERN Openlab framework, how they matured in a demonstration applic tion and how they are achieved, through a collaborative contribution of technologies and resources, are presented