Adjustment of data collection rate based on anomaly detection

摘要

Systems and methods that vary multiple data sampling rates, to collect sets of data with different levels of granularity for an industrial system. The data for such industrial system includes sets of data from the "internal" data stream(s) ( e . g ., history data collected from an industrial unit) and sets of data from an "external" ( e . g ., traffic data on network services) data stream(s), based in part on the criticality/importance criteria assigned to each collection stage. Each set of data can be assigned its own unique data collection rate. For example, a higher sample rate can be employed when collecting data from the network during an operation stage that is deemed more critical ( e . g ., dynamic attribution of predetermined importance factors) than the rest of the operation.