Granted Patent B1

US 11,765,100 · App. 17/723,786 · Granted Sep 19, 2023

Inventors: Brandon Sloane (Indian Land, SC); James Thomas MacAulay (Erie, CO); Serge Alejandro Neri (Charlotte, NC); Lauren Jenae Alibey (Charlotte, NC); Sophie Morgan Danielpour (Durham, NC); Jinyoung Nathan Kim (Charlotte, NC)

Assignee: BANK OF AMERICA CORPORATION

H04L47/823G06N20/00

Abstract

Claims (86)

1. A system for intelligent capacity planning for resources with high load variance, the system comprising:

at least one non-transitory storage device; and

at least one processor coupled to the at least one non-transitory storage device, wherein the at least one processor is configured to:

receive, from a user input device, an input to process a request within a distributed computing environment at a first time;

retrieve, from the request, a resource requirement associated with processing the request;

determine, using a resource interception subsystem, network resources required to process the request based on at least the resource requirements;

determine, using a machine learning (ML) subsystem, a current capacity of the network resources at the first time;

retrieve, from an internal repository, a first predefined threshold associated with the network resources, wherein the first predefined threshold is associated with the current capacity;

determine that the resource requirement is greater than the first predefined threshold;

predict, using the ML subsystem, a future capacity of the network resources at a second time;

determine a second predefined threshold associated with the network resources, wherein the second predefined threshold is associated with the future capacity;

determine that the resource requirement is lesser than the second predefined threshold at the second time; and

in response, generate, using a reporting subsystem, a dashboard report, wherein the dashboard report indicates that the network resources are at a peak load capacity at the first time and that the network resources are available to process the request at the second time; and

transmit control signals configured to cause the user input device to display the dashboard report.

2. The system of claim 1 , wherein the at least one processor is further configured to:

receive, from a network administrator device, a registration request for the network resources;

retrieve resource attributes associated with the network resources; and

register the network resources and the resource attributes associated with the network resources.

3. The system of claim 2 , wherein the resource attributes comprise at least component configurations of the network resources, processing times associated with processing past requests, dependencies associated with the network resources, type of requests previously processed, tolerance of the network resources, and/or average number of requests processed at any particular time instant.

4. The system of claim 3 , wherein the at least one processor is further configured to:

determine the current capacity of the network resources based on at least the resource attributes.

5. The system of claim 1 , wherein predicting the future capacity further comprises:

training, using the ML subsystem, a machine learning (ML) model using the resource attributes associated with the network resources, one or more time periods of operation, and past load capacities of the network resources at the one or more time periods of operation; and

generate the trained ML model based on at least the training.

6. The system of claim 5 , wherein the at least one processor is further configured to:

predict, using the trained ML model, the future capacity of the network resources.

7. The system of claim 1 , wherein the at least one processor is further configured to:

capture information associated with the request at the first time; and

store, in a request repository, the information associated with the request.

8. The system of claim 7 , wherein the at least one processor is further configured to:

at the second time, retrieve, from the request repository, the information associated with the request;

in response, transmit control signals configured to cause the user input device to display a prompt indicating that the network resources are available to process the request;

receive, from the user input device, a user acknowledgement to process the request at the second time; and

process the request at the second time based on at least the user acknowledgement.

9. The system of claim 1 , wherein the at least one processor is further configured to:

determine a processing time associated with processing the request during peak load capacity; and

generate, using the reporting subsystem, the dashboard report, wherein the dashboard report indicates the processing time.

10. A computer program product for intelligent capacity planning for resources with high load variance, the computer program product comprising a non-transitory computer-readable medium comprising code causing a first apparatus to:

receive, from a user input device, an input to process a request within a distributed computing environment at a first time;

retrieve, from the request, a resource requirement associated with processing the request;

determine, using a resource interception subsystem, network resources required to process the request based on at least the resource requirements;

determine, using a machine learning (ML) subsystem, a current capacity of the network resources at the first time;

retrieve, from an internal repository, a first predefined threshold associated with the network resources, wherein the first predefined threshold is associated with the current capacity;

determine that the resource requirement is greater than the first predefined threshold;

predict, using the ML subsystem, a future capacity of the network resources at a second time;

determine a second predefined threshold associated with the network resources, wherein the second predefined threshold is associated with the future capacity;

determine that the resource requirement is lesser than the second predefined threshold at the second time; and

in response, generate, using a reporting subsystem, a dashboard report, wherein the dashboard report indicates that the network resources are at a peak load capacity at the first time and that the network resources are available to process the request at the second time; and

transmit control signals configured to cause the user input device to display the dashboard report.

11. The computer program product of claim 10 , wherein the code causes the first apparatus to:

receive, from a network administrator device, a registration request for the network resources;

retrieve resource attributes associated with the network resources; and

register the network resources and the resource attributes associated with the network resources.

12. The computer program product of claim 11 , wherein the resource attributes comprise at least component configurations of the network resources, processing times associated with processing past requests, dependencies associated with the network resources, type of requests previously processed, tolerance of the network resources, and/or average number of requests processed at any particular time instant.

13. The computer program product of claim 12 , wherein the code causes the first apparatus to:

determine the current capacity of the network resources based on at least the resource attributes.

14. The computer program product of claim 10 , wherein the code causes the first apparatus to:

training, using the ML subsystem, a machine learning (ML) model using the resource attributes associated with the network resources, one or more time periods of operation, and past load capacities of the network resources at the one or more time periods of operation; and

generate the trained ML model based on at least the training.

15. The computer program product of claim 14 , wherein the code causes the first apparatus to:

predict, using the trained ML model, the future capacity of the network resources.

16. The computer program product of claim 10 , wherein the code causes the first apparatus to:

capture information associated with the request at the first time; and

store, in a request repository, the information associated with the request.

17. The computer program product of claim 16 , wherein the code causes the first apparatus to:

at the second time, retrieve, from the request repository, the information associated with the request;

in response, transmit control signals configured to cause the user input device to display a prompt indicating that the network resources are available to process the request;

receive, from the user input device, a user acknowledgement to process the request at the second time;

process the request at the second time based on at least the user acknowledgement.

18. A method for intelligent capacity planning for resources with high load variance, the method comprising:

receiving, from a user input device, an input to process a request within a distributed computing environment at a first time;

retrieving, from the request, a resource requirement associated with processing the request;

determining, using a resource interception subsystem, network resources required to process the request based on at least the resource requirements;

determining, using a machine learning (ML) subsystem, a current capacity of the network resources at the first time;

retrieving, from an internal repository, a first predefined threshold associated with the network resources, wherein the first predefined threshold is associated with the current capacity;

determining that the resource requirement is greater than the first predefined thresholds;

predicting, using the ML subsystem, a future capacity of the network resources at a second time;

determining a second predefined threshold associated with the network resources, wherein the second predefined threshold is associated with the future capacity;

determining that the resource requirement is lesser than the second predefined threshold at the second time;

in response, generating, using a reporting subsystem, a dashboard report, wherein the dashboard report indicates that the network resources are at a peak load capacity at the first time and that the network resources are available to process the request at the second time; and

transmitting control signals configured to cause the user input device to display the dashboard report.

19. The method of claim 18 , wherein the method further comprises:

receiving, from a network administrator device, a registration request for the network resources;

retrieving resource attributes associated with the network resources; and

registering the network resources and the resource attributes associated with the network resources.

20. The method of claim 19 , wherein the resource attributes comprise at least component configurations of the network resources, processing times associated with processing past requests, dependencies associated with the network resources, type of requests previously processed, tolerance of the network resources, and/or average number of requests processed at any particular time instant.

Assignments (1)

Cited By (9)

US 12,210,858 US 12,210,949 US 12,505,352 US 12,596,738 US 12,602,418 US 12,602,624 US 12,681,830 US 12,694,343 US 12,748,827