Software Passports for Automated Performance Anomaly Detection of Cyber-Physical Systems

Abstract

Software performance anomaly detection is a major challenge in complex industrial cyber-physical systems. The automated comparison of runtime execution metrics to reference ones provides a potential solution. We introduce the concept of software passports, intended to act as a signature construct for runtime performance behaviour of reference executions. Our software passport design is based on Extra-Functional Behaviour (EFB) metrics. Amongst such metrics, our focus has been especially on CPU time, read and write communication event counts of different processes. The notion of phases for systems with repetitive tasks during their execution and its fundamental role in our software passports has also been elaborated. We employ regression modelling of our collected data for comparative purposes. The comparison reveals inconsistencies between the execution at hand and the software passport, if present. Such inconsistencies are strong indicators for presence of performance anomalies. Our design is capable of detecting synthetically introduced performance anomalies to the real execution tracing data from a semiconductor photolithography machine.