IP Library Granted Patent US 12675708
Granted Patent B2
US 12675708 · App. 18/160,472 · Granted Jul 7, 2026

Storage and method for machine learning-based temperature forecasting for storage objects using storage sub-objects and temperature projection

Inventors: Shaul Dar (Petach Tikva, IL); Ramakanth Kanagovi (Bengaluru, IN); Guhesh Swaminathan (Tamil Nadu, IN); Rajan Kumar (Nawada, IN)
Assignee: Dell Products L.P.
G06N5/022
View Patent ↗
Loading inventors, assignments & file history…
Monitor This Case
Get email alerts when status or documents change.
Order Certified Copies
Most orders are placed with the USPTO same day — all within 24 business hours.
Order via The Patent Place →
Pre-filled with this patent's details
Quick Facts
Patent No.
US 12675708
App. No.
18/160,472
Granted
Jul 7, 2026
Kind
B2
Abstract

A method, computer program product, and computing system for forecasting a temperature of a storage object of a storage system using a first machine learning model and a plurality of input/output (IO) features. The storage object may be divided into a plurality of storage sub-objects. A temperature may be determined for each storage sub-object with a subset of the plurality of IO features using a second machine learning model. A portion of the temperature of the storage object may be projected onto the temperature of each of the plurality of storage sub-objects based upon, at least in part, the temperature determined for each storage sub-object and the temperature determined for each storage object.

Claims (70)

1 . A computer-implemented method, executed on a computing device, comprising:

forecasting a temperature of a storage object of a storage system using a first machine learning model and a plurality of input/output (IO) features;

dividing the storage object into a plurality of storage sub-objects;

determining a temperature for each storage sub-object with a subset of the plurality of IO features using a second machine learning model;

projecting a portion of the temperature of the storage object onto the temperature of each of the plurality of storage sub-objects based upon, at least in part, the temperature determined for each storage sub-object and the temperature determined for each storage object; and

tiering the plurality of storage sub-objects between a plurality of storage tiers of the storage system, based upon, at least in part, the temperature values defined for each storage sub-object.

2 . The computer-implemented method of claim 1 , wherein forecasting the temperature for each storage object includes:

processing a plurality of input/output (IO) requests associated with the storage object; and

generating the plurality of IO features using the plurality of IO requests.

3 . The computer-implemented method of claim 1 , wherein generating the plurality of IO features using the plurality of IO requests includes:

aggregating the plurality of IO requests periodically; and

generating the plurality of IO features using the aggregated plurality of IO requests.

4 . The computer-implemented method of claim 1 , wherein forecasting the temperature of the storage object includes processing the plurality of IO features using the first machine learning model.

5 . The computer-implemented method of claim 1 , wherein the limited subset of the plurality of IO features include one or more of the following:

a mean of a historical temperature variable;

a median of the historical temperature variable;

a standard deviation of the historical temperature variable;

a skewness of the historical temperature variable;

a kurtosis of the historical temperature variable;

a minimum of the historical temperature variable; and

a maximum of the historical temperature variable.

6 . The computer-implemented method of claim 1 , wherein dividing the storage object into a plurality of storage sub-objects includes adaptively dividing the storage object based upon, at least in part, performance of the storage system.

7 . The computer-implemented method of claim 1 , wherein projecting the portion of the temperature of the storage object includes determining a ratio of the temperature of each storage sub-object relative to other storage sub-objects of the storage object.

8 . A computer program product residing on a non-transitory computer readable medium having a plurality of instructions stored thereon which, when executed by a processor, cause the processor to perform operations comprising:

forecasting a temperature of a storage object of a storage system using a first machine learning model and a plurality of input/output (IO) features;

dividing the storage object into a plurality of storage sub-objects;

determining a temperature for each storage sub-object with a subset of the plurality of IO features using a second machine learning model;

projecting a portion of the temperature of the storage object onto the temperature of each of the plurality of storage sub-objects based upon, at least in part, the temperature determined for each storage sub-object and the temperature determined for each storage object; and

tiering the plurality of storage sub-objects between a plurality of storage tiers of the storage system, based upon, at least in part, the temperature values defined for each storage sub-object.

9 . The computer program product of claim 8 , wherein forecasting the temperature for each storage object includes:

processing a plurality of input/output (IO) requests associated with the storage object; and

generating the plurality of IO features using the plurality of IO requests.

10 . The computer program product of claim 8 , wherein generating the plurality of IO features using the plurality of IO requests includes:

aggregating the plurality of IO requests periodically; and

generating the plurality of IO features using the aggregated plurality of IO requests.

11 . The computer program product of claim 8 , wherein forecasting the temperature of the storage object includes processing the plurality of IO features using the first machine learning model.

12 . The computer program product of claim 8 , wherein the limited subset of the plurality of IO features include one or more of the following:

a mean of a historical temperature variable;

a median of the historical temperature variable;

a standard deviation of the historical temperature variable;

a skewness of the historical temperature variable;

a kurtosis of the historical temperature variable;

a minimum of the historical temperature variable; and

a maximum of the historical temperature variable.

13 . The computer program product of claim 8 , wherein dividing the storage object into a plurality of storage sub-objects includes adaptively dividing the storage object based upon, at least in part, performance of the storage system.

14 . The computer program product of claim 8 , wherein projecting the portion of the temperature of the storage object includes determining a ratio of the temperature of each storage sub-object relative to other storage sub-objects of the storage object.

15 . A computing system comprising:

a memory; and

a processor configured to:

forecast a temperature of a storage object of a storage system using a first machine learning model and a plurality of input/output (IO) features,

divide the storage object into a plurality of storage sub-objects,

determine a temperature for each storage sub-object with a subset of the plurality of IO features,

project a portion of the temperature of the storage object onto the temperature of each of the plurality of storage sub-objects based upon, at least in part, the temperature determined for each storage sub-object and the temperature determined for each storage object; and

tier the plurality of storage sub-objects between a plurality of storage tiers of the storage system, based upon, at least in part, the temperature values defined for each storage sub-object.

16 . The computing system of claim 15 , wherein forecasting the temperature for each storage object includes:

processing a plurality of input/output (IO) requests associated with the storage object; and

generating the plurality of IO features using the plurality of IO requests.

17 . The computing system of claim 15 , wherein generating the plurality of IO features using the plurality of IO requests includes:

aggregating the plurality of IO requests periodically; and

generating the plurality of IO features using the aggregated plurality of IO requests.

18 . The computing system of claim 15 , wherein forecasting the temperature of the storage object includes processing the plurality of IO features using the first machine learning model.

19 . The computing system of claim 15 , wherein the limited subset of the plurality of IO features include one or more of the following:

a mean of a historical temperature variable;

a median of the historical temperature variable;

a standard deviation of the historical temperature variable;

a skewness of the historical temperature variable;

a kurtosis of the historical temperature variable;

a minimum of the historical temperature variable; and

a maximum of the historical temperature variable.

20 . The computing system of claim 15 , wherein dividing the storage object into a plurality of storage sub-objects includes adaptively dividing the storage object based upon, at least in part, performance of the storage system.