Cloud resource management using externally-sourced data

• US 11,159,446 B2
• Filed: 10/30/2018
• Issued: 10/26/2021
• Est. Priority Date: 10/30/2018
• Status: Active Grant

• Current Assignee: Red Hat, Inc. (International Business Machines Corporation)
• Original Assignee: Red Hat, Inc. (International Business Machines Corporation)
• Inventors: Nakfour, Juana
• Primary Examiner(s): Khan, Aftab N.
• Application Number:
  US16/174,332
• Publication Number:
  US 20200136987A1
• Time in Patent Office: 1,092 Days
• CPC Class Codes: G06N 20/00 Machine learning
• CPC Class Codes: H04L 41/16 using machine learning or artificial intelligence
• CPC Class Codes: H04L 41/5054 Automatic deployment of services triggered by the service manager, e.g. service implementation by automatic configuration of network components
• CPC Class Codes: H04L 41/5096 wherein the managed service relates to distributed or central networked applications
• CPC Class Codes: H04L 47/70 Admission control; Resource allocation
• CPC Class Codes: H04L 47/83 based on usage prediction
• CPC Class Codes: H04L 67/10 in which an application is distributed across nodes in the network software deployment G06F8/60; multiprogramming arrangements G06F9/46
• CPC Class Codes: H04L 67/1097 for distributed storage of data in networks, e.g. transport arrangements for network file system [NFS], storage area networks [SAN] or network attached storage [NAS]

Abstract

A processing device can make use of an Artificial Intelligence (AI) model to make projections about resource usage based on data from external sources. The processing device can then adjust cloud-based resources accordingly. The cluster resource allocation can be adjusted as examples, by increasing, decreasing, or maintaining a number of nodes allocated to a cluster, by increasing, decreasing, or maintaining the number of pods assigned to an application or a container running in a cluster, or by increasing, decreasing, or maintaining central processing unit (CPU) resource, memory, disk storage, or a replication factor assigned to a pod.

Claims

1. A system comprising:

a processing device; and

a memory device including instructions that are executable by the processing device for causing the processing device to perform operations comprising;

receiving a plurality of text data samples from a plurality of sources external to a cloud resource network running an application on at least one network cluster;

producing a sentiment score from the plurality of text data samples using a text analytics model that is an artificial intelligence model trained using service text samples;

generating at least one projection based on the sentiment score using the text analytics model;

determining prospective cluster resource usage for the application based on the at least one projection;

adjusting a cluster resource allocation for the application in accordance with the prospective cluster resource usage;

receiving training data samples from at least some of the plurality of sources external to the cloud resource network; and

retraining the text analytics model using the training data samples.

2. The system of claim 1 wherein the cluster resource allocation is adjusted by increasing, decreasing, or maintaining a number of nodes allocated to the at least one network cluster.

3. The system of claim 1 wherein cluster resource allocation is adjusted by increasing, decreasing, or maintaining a number of pods assigned to the application, wherein each of the pods comprises at least one container.

4. The system of claim 1 wherein the cluster resource allocation is adjusted by increasing, decreasing, or maintaining at least one of central processing unit (CPU) resource, memory, disk storage, or replication factor assigned to a pod.

5. The system of claim 1 wherein the plurality of text data samples comprises at least one of event user interest data, social media data, or weather data.

6. A method comprising:

receiving, by a processing device, a plurality of text data samples from a plurality of sources external to a cloud resource network running an application on at least one network cluster;

producing, by the processing device, a sentiment score from the plurality of text data samples using a text analytics model that is an artificial intelligence model trained using service text samples;

generating, by the processing device, at least one projection based on the sentiment score using the trained text analytics model;

determining, by the processing device, prospective cluster resource usage for the application based on the at least one projection;

adjusting a cluster resource allocation for the application in accordance with the prospective cluster resource usage;

receiving, by the processing device, training data samples from at least some of the plurality of sources external to the cloud resource network; and

retraining, by the processing device, the text analytics model using the training data samples.

7. The method of claim 6 wherein the cluster resource allocation is adjusted by increasing, decreasing, or maintaining a number of nodes allocated to the at least one network cluster.

8. The method of claim 6 wherein the cluster resource allocation is adjusted by increasing, decreasing, or maintaining a number of pods assigned to the application, wherein each of the pods comprises at least one container.

9. The method of claim 6 wherein the cluster resource allocation is adjusted by increasing, decreasing, or maintaining at least one of central processing unit (CPU) resource, memory, disk storage, or replication factor assigned to a pod.

10. The method of claim 6 wherein the plurality of text data samples comprises at least one of event user interest data, social media data, or weather data.

11. A non-transitory computer-readable medium comprising program code that is executable by a processing device for causing the processing device to:

receive a plurality of text data samples from a plurality of sources external to a cloud resource network running an application on at least one network cluster;

produce a sentiment score from the plurality of text data samples using a text analytics model that is an artificial intelligence model trained using service text samples;

generate at least one projection based on the sentiment score using the trained text analytics model;

determine prospective cluster resource usage for the application based on the at least one projection;

adjust a cluster resource allocation for the application in accordance with the prospective cluster resource usage;

receive training data samples from at least some of the plurality of sources external to the cloud resource network; and

retrain the text analytics model using the training data samples.

12. The non-transitory computer-readable medium of claim 11 wherein the cluster resource allocation is adjusted by increasing, decreasing, or maintaining a number of nodes allocated to the at least one network cluster.

13. The non-transitory computer-readable medium of claim 11 wherein the cluster resource allocation is adjusted by increasing, decreasing, or maintaining a number of pods assigned to the application, wherein each of the pods comprises at least one container.

14. The non-transitory computer-readable medium of claim 11 wherein the cluster resource allocation is adjusted by increasing, decreasing, or maintaining at least one of central processing unit (CPU) resource, memory, disk storage, or replication factor assigned to a pod.

15. The non-transitory computer-readable medium of claim 11 wherein the plurality of text data samples comprises at least one of event user interest data, social media data, or weather data.