Granted Patent B2

US 12,580,822 · App. 18/657,839 · Granted Mar 17, 2026

Inventors: Oleksandr Malakhovskyi (Berlin, DE); Kim Poh Wong (Singapore, SG); Ravinder Akula (Bengaluru, IN); Jeevabharathy Murugesan (Bangalore, IN); Clea Zolotow (Dublin, IE)

Assignee: Kyndryl, Inc.

H04L41/145H04L41/147

Abstract

Claims (70)

1 . A computer-implemented method comprising:

generating a mapping between entity utilization metrics and an application of a mainframe of a hybrid cloud system;

determining a correlation between the entity utilization metrics and information technology (IT) performance metrics;

defining a relationship between an entity utilization driver and the IT performance metrics using the mapping and the correlation, wherein the entity utilization driver comprises at least one of a number of products, a price of the products, personnel, or a number of stores, wherein a machine learning model is trained based on the entity utilization metrics, transaction rates, and central processing unit (CPU) times, wherein the relationship is validated;

generating, by the machine learning model, forecasted values using the relationship between the entity utilization driver and the IT performance metrics; and

generating a proposed infrastructure configuration based on the forecasted values, wherein the forecasted values are predictive values reflecting how the application behaves when migrated from the mainframe to the hybrid cloud system.

2 . The computer-implemented method of claim 1 , further comprising:

validating the relationship between the entity utilization driver and the IT performance metrics using values calculated using big O functions.

3 . The computer-implemented method of claim 1 , wherein defining the relationship between the entity utilization driver and the IT performance metrics using the mapping and the correlation further comprises:

using a regression curve to define the relationship between the entity utilization driver comprising the at least one of the number of the products, the price of the products, the personnel, or the number of the stores and the IT performance metrics.

4 . The computer-implemented method of claim 1 , further comprising:

receiving the IT performance metrics from different components of the hybrid cloud system.

5 . The computer-implemented method of claim 1 , further comprising:

identifying deviations of the forecasted values using a calculated correlation coefficient and a predetermined value.

6 . The computer-implemented method of claim 1 , further comprising:

receiving the entity utilization metrics from a file or access to a datastore of an entity.

7 . The computer-implemented method of claim 1 , further comprising:

generating a report comprising the proposed infrastructure configuration and a list of additional hardware components, a list of additional software components, or proposed cost savings.

8 . A system comprising:

a memory having computer readable instructions; and

one or more processors for executing the computer readable instructions, the computer readable instructions controlling the one or more processors to perform operations comprising:

generating a mapping between entity utilization metrics and an application of a mainframe of a hybrid cloud system;

determining a correlation between the entity utilization metrics and information technology (IT) performance metrics;

defining a relationship between an entity utilization driver and the IT performance metrics using the mapping and the correlation, wherein the entity utilization driver comprises at least one of a number of products, a price of the products, personnel, or a number of stores, wherein a machine learning model is trained based on the entity utilization metrics, transaction rates, and central processing unit (CPU) times, wherein the relationship is validated;

generating, by the machine learning model, forecasted values using the relationship between the entity utilization driver and the IT performance metrics; and

generating a proposed infrastructure configuration based on the forecasted values, wherein the forecasted values are predictive values reflecting how the application behaves when migrated from the mainframe to the hybrid cloud system.

9 . The system of claim 8 , wherein the one or more processors perform the operations further comprising:

validating the relationship between the entity utilization driver and the IT performance metrics using values calculated using big O functions.

10 . The system of claim 8 , wherein to define the relationship between the entity utilization driver and the IT performance metrics using the mapping and the correlation, the operations further comprise:

using a regression curve to define the relationship between the entity utilization driver and the IT performance metrics.

11 . The system of claim 8 , wherein the one or more processors perform the operations further comprising:

receiving the IT performance metrics from different components of the hybrid cloud system.

12 . The system of claim 8 , wherein the one or more processors perform the operations further comprising:

identifying deviations of the forecasted values using a calculated correlation coefficient and a predetermined value.

13 . The system of claim 8 , wherein the one or more processors perform the operations further comprising:

receiving the entity utilization metrics from a file or access to a datastore of an entity.

14 . The system of claim 8 , wherein the one or more processors perform the operations further comprising:

generating a report comprising the proposed infrastructure configuration and a list of additional hardware components, a list of additional software components, or proposed cost savings.

15 . A computer program product comprising a computer readable storage medium having program instructions embodied therewith, the program instructions executable by one or more processors to cause the one or more processors to perform operations comprising:

generating a mapping between entity utilization metrics and an application of a mainframe of a hybrid cloud system;

determining a correlation between the entity utilization metrics and information technology (IT) performance metrics;

defining a relationship between an entity utilization driver and the IT performance metrics using the mapping and the correlation, wherein the entity utilization driver comprises at least one of a number of products, a price of the products, personnel, or a number of stores, wherein a machine learning model is trained based on the entity utilization metrics, transaction rates, and central processing unit (CPU) times, wherein the relationship is validated;

generating, by the machine learning model, forecasted values using the relationship between the entity utilization driver and the IT performance metrics; and

generating a proposed infrastructure configuration based on the forecasted values, wherein the forecasted values are predictive values reflecting how the application behaves when migrated from the mainframe to the hybrid cloud system.

16 . The computer program product of claim 15 , wherein the operations further comprise:

validating the relationship between the entity utilization driver and the IT performance metrics using values calculated using big O functions.

17 . The computer program product of claim 15 , wherein to define the relationship between the entity utilization driver and the IT performance metrics using the mapping and the correlation, the operations further comprise:

using a regression curve to define the relationship between the entity utilization driver and the IT performance metrics.

18 . The computer program product of claim 15 , wherein the operations further comprise:

receiving the IT performance metrics from different components of the hybrid cloud system.

19 . The computer program product of claim 15 , wherein the operations further comprise:

identifying deviations of the forecasted values using a calculated correlation coefficient and a predetermined value.

20 . The computer program product of claim 15 , wherein the operations further comprise:

receiving the entity utilization metrics from a file or access to a datastore of an entity.

21 . The computer program product of claim 15 , wherein the operations further comprise:

generating a report comprising the proposed infrastructure configuration and a list of additional hardware components, a list of additional software components, or proposed cost savings.

22 . A computer-implemented method comprising:

receiving a request for a migration strategy for integration of a mainframe computer to a hybrid cloud system;

receiving performance metrics from different components of the hybrid cloud system;

receiving entity utilization metrics for an organization;

generating forecasted values using the performance metrics and the entity utilization metrics which comprises: generating a mapping between the entity utilization metrics and an application of the mainframe computer, determining a correlation between the entity utilization metrics and the performance metrics, defining a relationship between an entity utilization driver and the performance metrics using the mapping and the correlation, and generating by a machine learning model the forecasted values using the relationship between the entity utilization driver and the performance metrics, wherein the entity utilization driver comprises at least one of a number of products, a price of the products, personnel, or a number of stores, wherein the machine learning model is trained based on the entity utilization metrics, transaction rates, and central processing unit (CPU) times, wherein the relationship is validated; and

generating a proposed infrastructure configuration based on the forecasted values, wherein the forecasted values are predictive values reflecting how the application behaves when migrated from the mainframe to the hybrid cloud system.

23 . A system comprising:

a memory having computer readable instructions; and

one or more processors for executing the computer readable instructions, the computer readable instructions controlling the one or more processors to perform operations comprising:

receiving a request for a migration strategy for integration of a mainframe computer to a hybrid cloud system;

receiving performance metrics from different components of the hybrid cloud system;

receiving entity utilization metrics for an organization;

generating forecasted values using the performance metrics and the entity utilization metrics which comprises: generating a mapping between the entity utilization metrics and an application of the mainframe computer, determining a correlation between the entity utilization metrics and the performance metrics, defining a relationship between an entity utilization driver and the performance metrics using the mapping and the correlation, and generating by a machine learning model the forecasted values using the relationship between the entity utilization driver and the performance metrics, wherein the entity utilization driver comprises at least one of a number of products, a price of the products, personnel, or a number of stores, wherein the machine learning model is trained based on the entity utilization metrics, transaction rates, and central processing unit (CPU) times, wherein the relationship is validated; and

generating a proposed infrastructure configuration based on the forecasted values, wherein the forecasted values are predictive values reflecting how the application behaves when migrated from the mainframe to the hybrid cloud system.

Assignments (1)

Continuity (1)

References Cited (17)