US 11,722,359 B2
Drift detection for predictive network models
Enzo Fenoglio, Issy les Moulineaux (FR); David John Zacks, Vancouver (CA); Zizhen Gao, San Ramon, CA (US); Carlos M. Pignataro, Cary, NC (US); and Dmitry Goloubev, Waterloo (BE)
Assigned to CISCO TECHNOLOGY, INC., San Jose, CA (US)
Filed by Cisco Technology, Inc., San Jose, CA (US)
Filed on Sep. 20, 2021, as Appl. No. 17/479,297.
Prior Publication US 2023/0093130 A1, Mar. 23, 2023
Int. Cl. H04L 29/08 (2006.01); H04L 41/0631 (2022.01); H04L 43/04 (2022.01); H04L 41/16 (2022.01); G06F 18/214 (2023.01)
CPC H04L 41/064 (2013.01) [G06F 18/214 (2023.01); H04L 41/16 (2013.01); H04L 43/04 (2013.01)] 20 Claims
OG exemplary drawing
 
1. A computer-implemented method comprising:
obtaining a plurality of streams of time-series telemetry data, the time-series telemetry data generated by network devices of a data network;
analyzing the plurality of streams to identify a subset of streams, wherein each stream of the subset of streams includes telemetry data that substantially matches an empirical distribution function;
analyzing the subset of streams of time-series data to identify a change point by:
computing a matrix profile using the subset of streams of time-series data, and
identifying a plurality of windows based on a repeating pattern of the subset of streams of time-series data;
in response to identifying the change point, obtaining additional time-series data from one or more streams of the plurality of streams of time-series telemetry data; and
re-training a predictive model using the additional time-series data to update the predictive model and provide a trained predictive model.