The Joint Accelerator Conferences Website (JACoW) is an international collaboration that publishes the proceedings of accelerator conferences held around the world.
TY - CONF AU - Canzari, M. AU - Di Carlo, M. AU - Dolci, M. AU - Smareglia, R. ED - Schaa, Volker RW ED - Costa, Isidre ED - Fernández, David ED - Matilla, Ãscar TI - Using AI in the Fault Management Predictive Model of the SKA TM Services: A Preliminary Study J2 - Proc. of ICALEPCS2017, Barcelona, Spain, 8-13 October 2017 C1 - Barcelona, Spain T2 - International Conference on Accelerator and Large Experimental Control Systems T3 - 16 LA - english AB - SKA (Square Kilometer Array) is a project aimed to build a very large radio-telescope, composed by thousands of antennae and related support systems. The overall orchestration is performed by the Telescope Manager (TM), a suite of software applications. In order to ensure the proper and uninterrupted operation of TM, a local monitoring and control system is developed, called TM Services. Fault Management (FM) is one of these services, and is composed by processes and infrastructure associated with detecting, diagnosing and fixing faults, and finally returning to normal operations. The aim of the study, introducing artificial intelligence algorithms during the detection phase, is to build a predictive model, based on the history and statistics of the system, in order to perform trend analysis and failure prediction. Based on monitoring data and health status detected by the software system monitor and on log files gathered by the ELK (Elasticsearch, Logstash, and Kibana) server, the predictive model ensures that the system is operating within its normal operating parameters and takes corrective actions in case of failure. PB - JACoW CP - Geneva, Switzerland SP - 435 EP - 438 KW - ion KW - software KW - monitoring KW - ISOL KW - operation DA - 2018/01 PY - 2018 SN - 978-3-95450-193-9 DO - 10.18429/JACoW-ICALEPCS2017-TUPHA030 UR - http://jacow.org/icalepcs2017/papers/tupha030.pdf ER -