System and method for managing resources in cloud environment

• US 10,700,992 B1
• Filed: 03/26/2019
• Issued: 06/30/2020
• Est. Priority Date: 02/12/2019
• Status: Active Grant

• Current Assignee: Wipro Limited
• Original Assignee: Wipro Limited
• Inventors: Das, Rishav, Yagnik, Maulik
• Primary Examiner(s): Dennison, Jerry B
• Application Number:
  US16/364,208
• Time in Patent Office: 462 Days
• CPC Class Codes: G06F 16/1805 Append-only file systems, e.g. using logs or journals to store data
• CPC Class Codes: G06N 3/044 Recurrent networks, e.g. Hopfield networks
• CPC Class Codes: G06N 3/08 Learning methods
• CPC Class Codes: H04L 41/147 for predicting network behaviour
• CPC Class Codes: H04L 41/149 for prediction of maintenance
• CPC Class Codes: H04L 41/16 using machine learning or artificial intelligence
• CPC Class Codes: H04L 41/5019 Ensuring fulfilment of SLA
• 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

Abstract

A method of managing resources in a cloud environment is disclosed. The method includes receiving a plurality of parameters associated with an event. The method further includes comparing a value of each of the plurality of parameters with a predefined threshold range. The method includes converting the value of each of the plurality of parameters into a vector, when the value of each of the plurality of parameters is within the predefined threshold range. The method further includes training a neural network based on the vector of the value of each of the plurality of parameters, wherein the neural network is trained to manage the event. The method includes storing an output of the trained neural network in a database in response to the training. The output corresponds to management of the event and the database further comprises a mapping of the event to the trained neural network.

Claims

1. A method of managing resources in a cloud environment, the method comprising:

receiving from at least one layer in the cloud environment, by a resource managing device, a plurality of parameters associated with an event;

predicting, by the resource managing device, a value of each of the plurality of parameters based on a plurality of information associated with the plurality of parameters;

comparing, by the resource managing device, the value of each of the plurality of parameters with a predefined threshold range;

converting, by the resource managing device, the value of each of the plurality of parameters into a vector, when the value of each of the plurality of parameters is within the predefined threshold range;

training, by the resource managing device, a neural network based on the vector of the value of each of the plurality of parameters, wherein the neural network is trained to manage the event; and

storing, by the resource managing device, an output of the trained neural network in a database in response to the training, wherein the output corresponds to management of the event, and wherein the database further comprises a mapping of the event to the trained neural network.

2. The method of claim 1, wherein the at least one layer comprises at least one of a management layer, a security layer, a network layer, a database layer, a data storage layer, or an application layer.

3. The method of claim 2, wherein the plurality of parameters are retrieved from a log database associated with each of the at least one layer, and wherein the log database comprises a plurality of logs associated with the event.

4. The method of claim 1, further comprising:

determining at least one attribute associated with the event; and

updating the predefined threshold range based on the at least one attribute.

5. The method of claim 1, further comprising discarding the plurality of parameters, when the value of at least one of the plurality of parameters is below the predefined threshold range.

6. The method of claim 1, further comprising matching the event with a list of events in the database, when the value of each of the plurality of parameters is above the predefined threshold range, wherein the database comprises mapping of each of the list of events with an associated trained neural network.

7. The method of claim 1, further comprising:

detecting occurrence of the event in the cloud environment; and

deploying the trained neural network to manage the event, based on the mapping in the database.

8. A resource managing device in a cloud environment, the resource managing device comprising:

a processor; and

a memory communicatively coupled to the processor, wherein the memory stores processor instructions, which, on execution, causes the processor to;

receive from at least one layer in the cloud environment, a plurality of parameters associated with an event;

predict a value of each of the plurality of parameters based on a plurality of information associated with the plurality of parameters;

compare the value of each of the plurality of parameters with a predefined threshold range;

convert the value of each of the plurality of parameters into a vector, when the value of each of the plurality of parameters is within the predefined threshold range;

train a neural network based on the vector of the value of each of the plurality of parameters, wherein the neural network is trained to manage the event; and

store an output of the trained neural network in a database in response to the training, wherein the output corresponds to management of the event, and wherein the database further comprises a mapping of the event to the trained neural network.

9. The resource managing device of claim 8, wherein the at least one layer comprises at least one of a management layer, a security layer, a database layer, a data storage layer, a network layer, or an application layer.

10. The resource managing device of claim 9, wherein the plurality of parameters are retrieved from a log database associated with each of the at least one layer, and wherein the log database comprises a plurality of logs associated with the event.

11. The resource managing device of claim 8, wherein the processor instructions further cause the processor to:

determine at least one attribute associated with the event; and

update the predefined threshold range based on the at least one attribute.

12. The resource managing device of claim 8, wherein the processor instructions further cause the processor to discard the plurality of parameters, when the value of at least one of the plurality of parameters is below the predefined threshold range.

13. The resource managing device of claim 8, wherein the processor instructions further cause the processor to match the event with a list of events in the database, when the value of each of the plurality of parameters is above the predefined threshold range, wherein the database comprises mapping of each of the list of events with an associated trained neural network.

14. The resource managing device of claim 8, wherein the processor instructions further cause the processor to:

detect occurrence of the event in the cloud environment; and

deploy the trained neural network to manage the event, based on the mapping in the database.

15. A non-transitory computer-readable storage medium having stored thereon, a set of computer-executable instructions causing a computer comprising one or more processors to perform steps comprising:

receiving from at least one layer in a cloud environment, a plurality of parameters associated with an event;

predicting a value of each of the plurality of parameters based on a plurality of information associated with the plurality of parameters;

comparing the value of each of the plurality of parameters with a predefined threshold range;

converting the value of each of the plurality of parameters into a vector, when the value of each of the plurality of parameters is within the predefined threshold range;

training a neural network based on the vector of the value of each of the plurality of parameters, wherein the neural network is trained to manage the event; and

storing an output of the trained neural network in a database in response to the training, wherein the output corresponds to management of the event, and wherein the database further comprises a mapping of the event to the trained neural network.