ICALEPCS2017 - List of Authors (Gonzalez-Berges, M.)

Paper	Title	Page
TUCPA04	Model Learning Algorithms for Anomaly Detection in CERN Control Systems	265
	F.M. Tilaro, B. Bradu, M. Gonzalez-Berges, F. Varela CERN, Geneva, Switzerland M. Roshchin Siemens AG, Corporate Technology, München, Germany
	At CERN there are over 600 different industrial control systems with millions of deployed sensors and actuators and their monitoring represents a challenging and complex task. This paper describes three different mathematical approaches that have been designed and developed to detect anomalies in CERN control systems. Specifically, one of these algorithms is purely based on expert knowledge while the other two mine historical data to create a simple model of the system, which is then used to detect anomalies. The methods presented can be categorized as dynamic unsupervised anomaly detection; "dynamic" since the behaviour of the system is changing in time, "unsupervised" because they predict faults without reference to prior events. Consistent deviations from the historical evolution can be seen as warning signs of a possible future anomaly that system experts or operators need to check. The paper also presents some results, obtained from the analysis of the LHC Cryogenic system. Finally the paper briefly describes the deployment of Spark and Hadoop into the CERN environment to deal with huge datasets and to spread the computational load of the analysis across multiple nodes.
	Slides TUCPA04 [1.965 MB]
DOI •	reference for this paper ※ https://doi.org/10.18429/JACoW-ICALEPCS2017-TUCPA04
Export •	reference for this paper using ※ BibTeX, ※ LaTeX, ※ Text/Word, ※ RIS, ※ EndNote (xml)

TUPHA034	SCADA Statistics Monitoring Using the Elastic Stack (Elasticsearch, Logstash, Kibana)	451
	J.A.G. Hamilton, M. Gonzalez-Berges, B. Schofield, J-C. Tournier CERN, Geneva, Switzerland
	The Industrial Controls and Safety systems group at CERN, in collaboration with other groups, has developed and currently maintains around 200 controls applications that include domains such as LHC magnet protection, cryogenics and electrical network supervision systems. Millions of value changes and alarms from many devices are archived to a centralised Oracle database but it is not easy to obtain high-level statistics from such an archive. A system based on the Elastic Stack has been implemented in order to provide easy access to these statistics. This system provides aggregated statistics based on the number of value changes and alarms, classified according to several criteria such as time, application domain, system and device. The system can be used, for example, to detect abnormal situations and alarm misconfiguration. In addition to these statistics each application generates text-based log files which are parsed, collected and displayed using the Elastic Stack to provide centralised access to all the application logs. Further work will explore the possibilities of combining the statistics and logs to better understand the behaviour of CERN's controls applications.
	Poster TUPHA034 [5.094 MB]
DOI •	reference for this paper ※ https://doi.org/10.18429/JACoW-ICALEPCS2017-TUPHA034
Export •	reference for this paper using ※ BibTeX, ※ LaTeX, ※ Text/Word, ※ RIS, ※ EndNote (xml)

TUPHA035	Data Analytics Reporting Tool for CERN SCADA Systems	456
	P.J. Seweryn, M. Gonzalez-Berges, B. Schofield, F.M. Tilaro CERN, Geneva, Switzerland
	This paper describes the concept of a generic data analytics reporting tool for SCADA (Supervisory Control and Data Acquisition) systems at CERN. The tool is a response to a growing demand for smart solutions in the supervision and analysis of control systems data. Large scale data analytics is a rapidly advancing field, but simply performing the analysis is not enough; the results must be made available to the appropriate users (for example operators and process engineers). The tool can report data analytics for objects such as valves and PID controllers directly into the SCADA systems used for operations. More complex analyses involving process interconnections (such as correlation analysis based on machine learning) can also be displayed. A pilot project is being developed for the WinCC Open Architecture (WinCC OA) SCADA system using Hadoop for storage. The reporting tool obtains the metadata and analysis results from Hadoop using Impala, but can easily be switched to any database system that supports SQL standards.
	Poster TUPHA035 [1.016 MB]
DOI •	reference for this paper ※ https://doi.org/10.18429/JACoW-ICALEPCS2017-TUPHA035
Export •	reference for this paper using ※ BibTeX, ※ LaTeX, ※ Text/Word, ※ RIS, ※ EndNote (xml)

THPHA021	Large-Scale Upgrade Campaigns of SCADA Systems at CERN - Organisation, Tools and Lessons Learned	1384
	R. Kulaga, J.A.R. Arroyo Garcia, M. Boccioli, E. Genuardi, P. Golonka, M. Gonzalez-Berges, J-C. Tournier, F. Varela CERN, Geneva, Switzerland
	The paper describes planning and execution of large-scale maintenance campaigns of SCADA systems for CERN accelerator and technical infrastructure. These activities, required to keep up with the pace of development of the controlled systems and rapid evolution of software, are constrained by many factors, such as availability for operation and planned interventions on equipment. Experience gathered throughout the past ten years of maintenance campaigns for the SCADA Applications Service at CERN, covering over 230 systems distributed across almost 120 servers, is presented. Further improvements for the procedures and tools are proposed to adapt to the increasing number of applications in the service and reduce maintenance effort and required downtime.
	Poster THPHA021 [1.262 MB]
DOI •	reference for this paper ※ https://doi.org/10.18429/JACoW-ICALEPCS2017-THPHA021
Export •	reference for this paper using ※ BibTeX, ※ LaTeX, ※ Text/Word, ※ RIS, ※ EndNote (xml)

THPHA037	Future Archiver for CERN SCADA Systems	1442
	P. Golonka, M. Gonzalez-Berges, J. Guzik, R. Kulaga CERN, Geneva, Switzerland
	Funding: Presented work is conducted in collaboration with ETM/Siemens in the scope of the CERN openlab project The paper presents the concept of a modular and scalable archiver (historian) for SCADA systems at CERN. By separating concerns of archiving from specifics of data-storage systems at a high abstraction level, using a clean and open interface, it will be possible to integrate various data handling technologies without a big effort. The frontend part, responsible for business logic, will communicate with one or multiple backends, which in turn would implement data store and query functionality employing traditional relational databases as well as modern NOSQL and big data solutions, opening doors to advanced data analytics and matching the growing performance requirements for data storage.
	Poster THPHA037 [7.294 MB]
DOI •	reference for this paper ※ https://doi.org/10.18429/JACoW-ICALEPCS2017-THPHA037
Export •	reference for this paper using ※ BibTeX, ※ LaTeX, ※ Text/Word, ※ RIS, ※ EndNote (xml)

Paper

Title

Page

Model Learning Algorithms for Anomaly Detection in CERN Control Systems

265

F.M. Tilaro, B. Bradu, M. Gonzalez-Berges, F. Varela
CERN, Geneva, Switzerland
M. Roshchin
Siemens AG, Corporate Technology, München, Germany

At CERN there are over 600 different industrial control systems with millions of deployed sensors and actuators and their monitoring represents a challenging and complex task. This paper describes three different mathematical approaches that have been designed and developed to detect anomalies in CERN control systems. Specifically, one of these algorithms is purely based on expert knowledge while the other two mine historical data to create a simple model of the system, which is then used to detect anomalies. The methods presented can be categorized as dynamic unsupervised anomaly detection; "dynamic" since the behaviour of the system is changing in time, "unsupervised" because they predict faults without reference to prior events. Consistent deviations from the historical evolution can be seen as warning signs of a possible future anomaly that system experts or operators need to check. The paper also presents some results, obtained from the analysis of the LHC Cryogenic system. Finally the paper briefly describes the deployment of Spark and Hadoop into the CERN environment to deal with huge datasets and to spread the computational load of the analysis across multiple nodes.

Slides TUCPA04 [1.965 MB]

DOI •

reference for this paper ※ https://doi.org/10.18429/JACoW-ICALEPCS2017-TUCPA04

Export •

reference for this paper using ※ BibTeX, ※ LaTeX, ※ Text/Word, ※ RIS, ※ EndNote (xml)

TUPHA034

SCADA Statistics Monitoring Using the Elastic Stack (Elasticsearch, Logstash, Kibana)

451

J.A.G. Hamilton, M. Gonzalez-Berges, B. Schofield, J-C. Tournier
CERN, Geneva, Switzerland

The Industrial Controls and Safety systems group at CERN, in collaboration with other groups, has developed and currently maintains around 200 controls applications that include domains such as LHC magnet protection, cryogenics and electrical network supervision systems. Millions of value changes and alarms from many devices are archived to a centralised Oracle database but it is not easy to obtain high-level statistics from such an archive. A system based on the Elastic Stack has been implemented in order to provide easy access to these statistics. This system provides aggregated statistics based on the number of value changes and alarms, classified according to several criteria such as time, application domain, system and device. The system can be used, for example, to detect abnormal situations and alarm misconfiguration. In addition to these statistics each application generates text-based log files which are parsed, collected and displayed using the Elastic Stack to provide centralised access to all the application logs. Further work will explore the possibilities of combining the statistics and logs to better understand the behaviour of CERN's controls applications.

Poster TUPHA034 [5.094 MB]

DOI •

reference for this paper ※ https://doi.org/10.18429/JACoW-ICALEPCS2017-TUPHA034

Export •

reference for this paper using ※ BibTeX, ※ LaTeX, ※ Text/Word, ※ RIS, ※ EndNote (xml)

TUPHA035

Data Analytics Reporting Tool for CERN SCADA Systems

456

P.J. Seweryn, M. Gonzalez-Berges, B. Schofield, F.M. Tilaro
CERN, Geneva, Switzerland

This paper describes the concept of a generic data analytics reporting tool for SCADA (Supervisory Control and Data Acquisition) systems at CERN. The tool is a response to a growing demand for smart solutions in the supervision and analysis of control systems data. Large scale data analytics is a rapidly advancing field, but simply performing the analysis is not enough; the results must be made available to the appropriate users (for example operators and process engineers). The tool can report data analytics for objects such as valves and PID controllers directly into the SCADA systems used for operations. More complex analyses involving process interconnections (such as correlation analysis based on machine learning) can also be displayed. A pilot project is being developed for the WinCC Open Architecture (WinCC OA) SCADA system using Hadoop for storage. The reporting tool obtains the metadata and analysis results from Hadoop using Impala, but can easily be switched to any database system that supports SQL standards.

Poster TUPHA035 [1.016 MB]

DOI •

reference for this paper ※ https://doi.org/10.18429/JACoW-ICALEPCS2017-TUPHA035

Export •

reference for this paper using ※ BibTeX, ※ LaTeX, ※ Text/Word, ※ RIS, ※ EndNote (xml)

THPHA021

Large-Scale Upgrade Campaigns of SCADA Systems at CERN - Organisation, Tools and Lessons Learned

1384

R. Kulaga, J.A.R. Arroyo Garcia, M. Boccioli, E. Genuardi, P. Golonka, M. Gonzalez-Berges, J-C. Tournier, F. Varela
CERN, Geneva, Switzerland

The paper describes planning and execution of large-scale maintenance campaigns of SCADA systems for CERN accelerator and technical infrastructure. These activities, required to keep up with the pace of development of the controlled systems and rapid evolution of software, are constrained by many factors, such as availability for operation and planned interventions on equipment. Experience gathered throughout the past ten years of maintenance campaigns for the SCADA Applications Service at CERN, covering over 230 systems distributed across almost 120 servers, is presented. Further improvements for the procedures and tools are proposed to adapt to the increasing number of applications in the service and reduce maintenance effort and required downtime.

Poster THPHA021 [1.262 MB]

DOI •

reference for this paper ※ https://doi.org/10.18429/JACoW-ICALEPCS2017-THPHA021

Export •

reference for this paper using ※ BibTeX, ※ LaTeX, ※ Text/Word, ※ RIS, ※ EndNote (xml)

THPHA037

Future Archiver for CERN SCADA Systems

1442

P. Golonka, M. Gonzalez-Berges, J. Guzik, R. Kulaga
CERN, Geneva, Switzerland

Funding: Presented work is conducted in collaboration with ETM/Siemens in the scope of the CERN openlab project
The paper presents the concept of a modular and scalable archiver (historian) for SCADA systems at CERN. By separating concerns of archiving from specifics of data-storage systems at a high abstraction level, using a clean and open interface, it will be possible to integrate various data handling technologies without a big effort. The frontend part, responsible for business logic, will communicate with one or multiple backends, which in turn would implement data store and query functionality employing traditional relational databases as well as modern NOSQL and big data solutions, opening doors to advanced data analytics and matching the growing performance requirements for data storage.

Poster THPHA037 [7.294 MB]

DOI •

reference for this paper ※ https://doi.org/10.18429/JACoW-ICALEPCS2017-THPHA037

Export •

reference for this paper using ※ BibTeX, ※ LaTeX, ※ Text/Word, ※ RIS, ※ EndNote (xml)