Automatic Segmentation of Resource Utilization Data

Industrial systems seek advancements to achieve required level of quality of service and efficient performance management. It is essential though to have better understanding of resource utilization behaviour of applications in execution. Even the expert engineers desire to envision dependencies and impact of one computer resource on the other. For such reasons it is advantageous to have fine illustration of resource utilization behaviour with reduced complexity. Simplified complexity is useful for the management of shared resources such that an application with higher cache demand should not be scheduled together with other cache hungry application at the same time and same core. However, the performance monitoring data coming from hardware and software is huge but grouping of this data based on similar behaviour can display distinguishable execution phases. For benefits like these we opt to choose change point analysis method. By using this method our study determines an optimal threshold which can identify more or less same segments for other executions of same application and same event. Furthermore the study demonstrates a synopsis of resource utilization behaviour with local and compact statistical model.