US 12,289,215 B2
Data center monitoring and management operation including model drift prediction for automated model retraining and deployment
Raja Neogi, Portland, OR (US)
Assigned to Dell Products L.P., Round Rock, TX (US)
Filed by Dell Products L.P., Round Rock, TX (US)
Filed on Jan. 26, 2023, as Appl. No. 18/101,716.
Prior Publication US 2024/0259273 A1, Aug. 1, 2024
This patent is subject to a terminal disclaimer.
Int. Cl. H04L 41/14 (2022.01); H04L 41/147 (2022.01)
CPC H04L 41/145 (2013.01) [H04L 41/147 (2013.01)] 20 Claims
OG exemplary drawing
 
1. A computer-implementable method for performing a data center management and monitoring operation, comprising:
establishing a communication channel between a data center asset and a connectivity management system of a data center monitoring and management console;
providing data center asset telemetry data from the data center asset to the connectivity management system of the data center monitoring and management console, the data center asset telemetry data including data center asset operational status information;
receiving operational status analysis (OSA) model data from a plurality of OSA models;
assigning the OSA model data to a vectorized input space;
reducing a dimension of the vectorized input space to a latent space, the latent space providing an OSA model dimension;
decoding the latent space to provide a vectorized decoded output space; and,
performing a model operational status forecasting operation using the vectorized decoded output space, the model operational status forecasting operation generating model operational status forecasting data; and
using the model operational status forecasting data to perform a model drift forecasting operation, the model drift forecasting operation forecasting drift in a parameter of an OSA model associated with an operational status of the data center asset to a point in time; and, wherein
the plurality of OSA models are trained using one of semi-supervised learning and unsupervised learning.