US 12,373,322 B2
Machine learning for metric collection
Raja Kommula, Cupertino, CA (US); Ganesh Byagoti Matad Sunkada, Bengaluru (IN); Thayumanavan Sridhar, Sunnyvale, CA (US); Thiraviya Eswaran, Karur (IN); and Raj Yavatkar, Los Gatos, CA (US)
Assigned to Juniper Networks, Inc., Sunnyvale, CA (US)
Filed by Juniper Networks, Inc., Sunnyvale, CA (US)
Filed on Mar. 5, 2024, as Appl. No. 18/596,591.
Application 18/596,591 is a continuation of application No. 17/810,178, filed on Jun. 30, 2022, granted, now 12,099,427.
Claims priority of application No. 202241022566 (IN), filed on Apr. 16, 2022.
Prior Publication US 2024/0211368 A1, Jun. 27, 2024
This patent is subject to a terminal disclaimer.
Int. Cl. G06F 11/34 (2006.01); G06F 11/32 (2006.01); H04L 41/0604 (2022.01); H04L 41/0681 (2022.01); H04L 41/16 (2022.01); H04L 43/024 (2022.01); H04L 43/04 (2022.01); H04L 43/08 (2022.01)
CPC G06F 11/3409 (2013.01) [G06F 11/327 (2013.01); H04L 41/0604 (2013.01); H04L 41/0609 (2013.01); H04L 41/0681 (2013.01); H04L 41/16 (2013.01); H04L 43/024 (2013.01); H04L 43/04 (2013.01); H04L 43/08 (2013.01)] 20 Claims
OG exemplary drawing
 
1. A method comprising:
collecting, by a performance monitoring system, telemetry data comprising metrics related to a network of computing devices, wherein, for each metric, metric values associated with a corresponding metric name of the metric are collected at each of a plurality of times according to a first collection sampling interval;
storing, by the performance monitoring system, a query history comprising queries related to the metrics;
generating, by the performance monitoring system, a metric relevance attribute based on an access ratio determined from a portion of the query history corresponding to a first metric of the metrics;
determining, by the performance monitoring system, a predicted metric weight for the first metric based on the metric relevance attribute; and
collecting, by the performance monitoring system, additional telemetry data according to a second collection sampling interval for at least one of the metrics, wherein the second collection sampling interval is based on the predicted metric weight for the first metric.