Systems and methods for proactive infrastructure resource management for multiple application clusters

Patent metadata

Field	Value
Publication number	US-11625659-B2
Application number	US-202117486783-A
Country	US
Kind code	B2
Filing date	Sep 27, 2021
Priority date	Nov 19, 2018
Publication date	Apr 11, 2023
Grant date	Apr 11, 2023

Abstract

A system including: a processor; and a memory storing computer program code that controls the processor to: collect real-time business process metrics; collect real-time cluster metrics for a plurality of application clusters indicative of a required allotment of infrastructure resources for a given business process level; estimate a predicted future business process level; based on the estimated predicted future business process level and the real-time cluster metrics, predict a future infrastructure resource requirement of each of the plurality of application clusters; compare the predicted future infrastructure resource requirement of each of the plurality of application clusters to a current dedication of each of the plurality of application clusters; automatically adjust, in real-time and based on the comparison, respective allotments of infrastructure resources for each of the plurality of application clusters; receive an actual business process; and process the business process across the plurality of application clusters.

First claim

What is claimed is:

1. A system for predictive real-time scaling of a plurality of connected application clusters, the system comprising:
one or more processors;
a memory having stored thereon instructions that, when executed by the one or more processors, causes the system to:
perform, with the plurality of connected application clusters, one or more business processes, wherein the one or more business processes are associated with loan applications;
collect real-time business process metrics from the plurality of connected application clusters, wherein the real-time business process metrics comprise a volume of loan applications processed by the plurality of connected application clusters;
retrieve, from a time series database, real-time cluster metrics for the plurality of connected application clusters based on the volume of loan applications processed by the plurality of connected application clusters;
correlate the real-time cluster metrics with the volume of loan applications processed by the plurality of connected application clusters;
analyze the business process metrics to estimate a predicted future business process level using one or more machine learning algorithms by estimating a future volume of loan applications to be processed by the plurality of connected application clusters;
predict a future requirement of each of the plurality of connected application clusters based on the future business process level and the correlated real-time cluster metrics;
compare the future requirement of each of the plurality of connected application clusters to a current usage of each of the plurality of connected application clusters to identify a first application cluster for which the current usage is below the future requirement; and
automatically adjust, in real-time and based on the comparison, a first allotment of infrastructure resources assigned to the first application cluster.

2. The system of claim 1 , wherein the one or more machine learning algorithms are configured to perform ridge regression using cross validation on the time series database.

3. The system of claim 1 , wherein the memory stores instructions, that when executed by the one or more processors, are configured to cause the system to:
calculate a time delay between adjusting the first allotment and adjusting a second allotment of infrastructure resources assigned to a second application cluster;
predict a new future business process level based on the calculated time delay; and

compare the new future business process level of the second application cluster to a current dedication of the second application cluster.

4. The system of claim 1 , wherein the predicted future requirement of each of the plurality of connected application clusters is further based on historic cluster requirements for a given business process level.

5. The system of claim 3 , wherein automatically adjusting a first allotment of infrastructure resources assigned to the first application cluster and automatically adjusting a second allotment of infrastructure resources assigned to the second application cluster further comprises executing an API call to a respective application cluster to adjust an allotment of infrastructure resources.

6. The system of claim 1 , wherein each of the plurality of connected application clusters is associated with different types of loan applications.

7. The system of claim 6 , wherein each of the different types of loan applications comprise a loan type selected from a mortgage loan, a car loan, a personal loan, a business loan, a prime loan, a subprime loan, or a refinance loan.

8. The system of claim 1 , wherein
the business process level corresponds to an expected number of financial services applications, and
each of the plurality of connected application clusters comprise respective sets of mutually exclusive applications for processing financial services applications.

9. The system of claim 1 , wherein analyzing the business process metrics to estimate the predicted future business process level is based on at least one from among a time of day, a day of the week, and a time of year.

10. A method of predictive real-time scaling of a plurality of connected application clusters, the method comprising:
performing, with the plurality of connected application clusters, one or more business processes, wherein the one or more business processes are associated with loan applications;
collecting real-time business process metrics from the plurality of connected application clusters, wherein the real-time business process metrics comprise a volume of loan applications processed by the plurality of connected application clusters;
collecting real-time cluster metrics of the plurality of connected application clusters based on the volume of loan applications processed by the plurality of connected application clusters;
correlating the real-time cluster metrics with the volume of loan applications processed by the plurality of connected application clusters;
analyzing the collected real-time business process metrics to estimate a predicted future volume of loan applications to be processed by the plurality of connected application clusters;
predicting a future requirement of each of the plurality of connected application clusters based on the predicted future volume of loan applications and the correlated real-time cluster metrics;
comparing the predicted future requirement of each of the plurality of connected application clusters to a current usage of each of the plurality of connected application clusters; and
automatically adjusting, in real-time and based on the comparison, a first allotment of infrastructure resources allocated to a first application cluster.

11. The method of claim 10 , wherein the analyzing comprises one or more machine learning algorithms configured to perform ridge regression using cross validation.

12. The method of claim 10 , wherein the predicted future requirement of each of the plurality of connected application clusters is further based on historic cluster requirements for a given volume of loan applications.

13. The method of claim 10 , further comprising automatically adjusting a second allotment to a second application cluster based on the comparison and the first allotment, wherein automatically adjusting the first allotment and the second allotment is performed independently for each of the plurality of connected application clusters.

14. The method of claim 10 , further comprising comparing the predicted future requirement of each of the plurality of connected application clusters to an actual volume of loan applications processed by the plurality of connected application clusters to tune one or more machine learning algorithms.

15. The method of claim 13 , wherein automatically adjusting a first allotment of infrastructure resources assigned to the first application cluster and automatically adjusting a second allotment of infrastructure resources assigned to the second application cluster further comprises executing, by a scaling server, an API call to a respective application cluster to adjust an allotment of infrastructure resources.

16. The method of claim 10 , wherein each of the plurality of connected application clusters is associated with different types of loan application.

17. The method of claim 16 , wherein each of the different types of loan applications comprise a loan type selected from a mortgage loan, a car loan, a personal loan, a business loan, a prime loan, a subprime loan, or a refinance loan.

18. The

Assignees

• Capital One Services Llc

Inventors

• Pandey Amit
• Awasthi Ateet Kumar
• Hoenig Aaron L
• Anand Kumar

Classifications

• G06Q10/06

  Resources, workflows, human or project management; Enterprise or organisation planning; Enterprise or organisation modelling · CPC title

• G06Q10/00

  Administration; Management · CPC title

• G06F9/46

  Multiprogramming arrangements · CPC title

• G06F9/50

  Allocation of resources, e.g. of the central processing unit [CPU] · CPC title

• G06Q10/067 Primary

  Enterprise or organisation modelling · CPC title