System and method for determining resources utilization in a virtual network

1. A method for determining optimized resources utilization in a virtual network, comprising:

collecting at least one computing resource parameter, wherein the at least one computing resource parameter comprises a measurement of computing resources performance in the virtual network;

collecting at least one key performance indicator, where the at least one key performance indicator includes measurement of network traffic performance;

determining, based on the at least one computing resource parameter and the at least one key performance indicator, at least one optimized resource parameter over a period of predetermined time interval, wherein the optimized resource parameter indicates a usage rule for a computing resource component;

generating a data model using machine learning techniques, based on the at least one computing resource parameter and the at least one key performance indicator, wherein the data model describes a connection between the virtual network's performance and the collected measurements of the at least one computing resource parameter and the at least one key performance indicator; and

configuring the computing resource component with the determined usage rule.

2. The method of claim 1 , wherein the at least one computing resource parameter includes at least one of: current and historical central processing unit usage, memory usage, and disk space usage of the computer resources components.

3. The method of claim 1 , wherein the at least one key performance indicator includes at least one of: percentage of network packets lost over a network connection, percentage of network procedures that have not been successfully completed over a network connection, and time taken for the completion of a network task over a network connection.

4. The method of claim 1 , wherein the at least one computing resource parameter and the at least one key performance indicator are repeatedly collected at predetermined time intervals.

5. The method of claim 1 , wherein the data model is further configured to determine which of the computing resource parameters and key performance indicators are most indicative of future network performance.

6. The method of claim 1 , further comprising:

predicting future values of the at least one key performance indicator for determining the usage rule.

7. The method of claim 1 , wherein the at least one optimized resource parameter is determined by a dimensionality reduction process.

8. A non-transitory computer readable medium having stored thereon instructions for causing a processing circuitry to perform a method for determining optimized resources utilization in a virtual network, the method comprising:

collecting at least one computing resource parameter, wherein the at least one computing resource parameter comprises a measurement of computing resources performance in the virtual network;

accessing at least one key performance indicator, where the at least one key performance indicator includes measurement of network traffic performance;

determining, based on the at least one computing resource parameter and the at least one key performance indicator, at least one optimized resource parameter over a period of predetermined time interval, wherein the optimized resource parameter indicates a usage rule for a computing resource component;

generating a data model using machine learning techniques, based on the at least one computing resource parameter and the at least one key performance indicator, wherein the data model describes a connection between the virtual network's performance and the collected measurements of the at least one computing resource parameter and the at least one key performance indicator; and

configuring the computing resource component with the determined usage rule.

9. A system for determining optimized resources utilization in a virtual network, comprising:

a processing circuitry; and

a memory, the memory containing instructions that, when executed by the processing circuitry, configure the system to:

collect at least one computing resource parameter, wherein the at least one computing resource parameter comprises a measurement of computing resources performance in the virtual network;

access at least one key performance indicator, where the at least one key performance indicator includes measurement of network traffic performance;

determine, based on the at least one computing resource parameter and the at least one key performance indicator, at least one optimized resource parameter over a period of predetermined time interval, wherein the optimized resource parameter indicates a usage rule for a computing resource component;

generate a data model using machine learning techniques, based on the at least one computing resource parameter and the at least one key performance indicator, wherein the data model describes a connection between the virtual network's performance and the collected measurements of the at least one computing resource parameter and the at least one key performance indicator; and

configure the computing resource component with the determined usage rule.

10. The system of claim 9 , wherein the at least one computing resource parameter includes at least one of: current and historical central processing unit usage, memory usage, and disk space usage of the computer resources components.

11. The system of claim 9 , wherein the at least one key performance indicator includes at least one of: percentage of network packets lost over a network connection, percentage of network procedures that have not been successfully completed over a network connection, and time taken for the completion of a network task over a network connection.

12. The system of claim 9 , wherein the at least one computing resource parameter and the at least one key performance indicator are repeatedly collected at predetermined time intervals.

13. The system of claim 9 , wherein the data model is further configured to determine which of the computing resource parameters and key performance indicators are most indicative of future network performance.

14. The system of claim 9 , wherein the system is further configured to:

predict future values of the at least one key performance indicator for determining the usage rule.

15. The system of claim 9 , wherein the at least one optimized resource parameter is determined by a dimensionality reduction process.