Techniques for policy-controlled analytic data collection in large-scale systems

Abstract

Exemplary techniques for policy-controlled analytic data collection in large-scale systems are described. A policy engine receives predicate / action pairs and an alerts policy, each predicate identifying an operating condition at a reporting module that can be evaluated as true or false, and a corresponding action identifying what the reporting module is to do upon the corresponding predicate beingevaluated as true. The policy engine provides the predicate / action pairs to reporting modules to be installed as rules, which generate analytic data vectors and apply those vectors against the rules.The actions may cause the reporting modules to send the analytic data vectors as analytic report data to an analytics engine, which has been configured with the alerts policy received by the policy engine. The analytics engine applies received analytic report data against the alerts policy to determine whether to send alert event data to the policy engine or to perform a responsive action.

Description

technical field [0001] Embodiments of the invention relate to the field of computing systems, and more particularly, to techniques for analytical data collection for policy control in large-scale systems. Background technique [0002] With the advent of machine intelligence at scale, the ability to almost completely automate the management of cloud and / or network services based on data analysis has entered conceivable territory. However, for this capability to become a reality, data from these services must be analyzed in real time, which is known as "streaming analytics." However, scaling streaming analytics for services provided to end users is particularly problematic because a particular service may have millions of end users, making it very difficult to achieve real-time, scalable, and cost-effective performance for streaming analytics with such large amounts of data. Furthermore, there are areas other than end-user services where the collection and real-time analysis ...

AI Technical Summary

Problems solved by technology

However, scaling streaming analytics for services delivered to end users is particularly problematic because a particular service may have millions of end users, making it very difficult to achieve real-time, scalable, and cost-effective performance for streaming analytics with such large amounts of data

Furthermore, there are areas other than end-user services where the collection and real-time analysis of streaming data is difficult, for example in machine-to-machine communication involving a large number of vehicles or in very specific cases where data volume issues are not as responding to the need for high-speed network devices that are so large

Images