| CPC G06F 11/3414 (2013.01) [G06F 8/77 (2013.01); G06F 11/3428 (2013.01)] | 12 Claims |
|
1. A system associated with a cloud computing environment, comprising:
a historical managed software system data store containing electronic records associated with controllers and deployed workloads, each electronic record including time series data representing performance metrics extracted via an autoencoder that performs dimensionality reduction;
an entropy calculation system, coupled to the historical managed software system data store, to calculate historical multiscale entropy values, based on information in the historical managed software system data store, associated with (i) Central Processing Unit (“CPU”) utilization, (ii) memory usage, and (iii) request latency; and
a detection engine, coupled to monitored microservices packaged as processes or containers that are currently executing a deployed workload in the cloud computing environment, including:
a computer processor, and
a computer memory coupled to the computer processor and storing instructions that, when executed by the computer processor, cause the detection engine to:
(i) collect time series data representing current performance metrics associated with the monitored microservices,
(ii) calculate current monitored entropy values, based on the collected time series data, representing current performance metrics associated with (i) CPU utilization, (ii) memory usage, and (iii) request latency,
(iii) compare the current monitored entropy values with threshold values associated with runtime entropy predictions, the threshold values being based on the historical multiscale entropy values, and
(iv) based on the comparison, trigger a blue green deployment corrective action for the monitored microservices.
|