US 12,474,839 B2
System and method for calibrating heterogenous workloads in a machine learning model for storage objects
Shaul Dar, Petach Tikva (IL); Ramakanth Kanagovi, Bengaluru (IN); Guhesh Swaminathan, Tamil Nadu (IN); and Rajan Kumar, Nawada (IN)
Assigned to Dell Products L.P., Round Rock, TX (US)
Filed by Dell Products L.P., Round Rock, TX (US)
Filed on Sep. 5, 2023, as Appl. No. 18/460,960.
Prior Publication US 2025/0077081 A1, Mar. 6, 2025
Int. Cl. G06F 3/06 (2006.01)
CPC G06F 3/0613 (2013.01) [G06F 3/0629 (2013.01); G06F 3/0673 (2013.01)] 20 Claims
OG exemplary drawing
 
1. A computer-implemented method, executed on a computing device, comprising:
processing, via the computing device, a plurality of input/output (IO) requests associated with a storage object in a storage system;
generating, via the computing device, a plurality of IO features using the plurality of IO requests associated with the storage object;
identifying, via the computing device, a time dependent IO feature for the storage system from the plurality of IO features;
extracting, via the computing device, a coefficient for the time dependent IO feature for the storage system, wherein the coefficient is numerical representation of a value of the time dependent IO feature;
generating, via the computing device, a calibrated time dependent IO feature for the storage system by calibrating, via the computing device, the time dependent IO feature using the coefficient for the time dependent IO feature for the storage system relative to a corresponding time dependent IO feature from at least one other storage system, wherein calibrating the time dependent IO feature includes normalizing the coefficient for the time dependent IO feature for the storage system relative to the time dependent IO feature from at least one other storage system; and
processing, via the computing device, the calibrated time dependent IO feature for the storage system using a machine learning model trained using training data associated with the at least one other storage system.