Granted Patent B2

US 11,663,524 · App. 16/941,623 · Granted May 30, 2023

Inventors: Sathish Kumar Bikumala (Round Rock, TX); Vasile Radoaca (Burlington, MA); Deepak NagarajeGowda (Cary, NC)

Assignee: EMC IP Holding Company LLC

G06N20/00H04L41/145H04L41/16

Abstract

Claims (67)

1. A computer-implemented method for use in designing a service, the method comprising:

designing a service with one or more generic virtual network functions (VNFs), wherein each of the generic VNFs is defined to provide a generic network functionality independent of vendor sourcing information;

using one or more trained machine learning (ML) models to identify available VNFs from VNF vendors that source one or more VNFs to implement the generic network functionality;

determining a similarity score for each implementation of the generic network functionality by a respective one of the available VNFs;

using the similarity score for each implementation of the generic network functionality to select one of the available VNFs to implement the generic network functionality; and

implementing the service using the selected one of the available VNFs to implement the generic network functionality.

2. The computer-implemented method of claim 1 , wherein

the one or more trained ML models include an ML quality model configured to assess a quality of VNFs provided by vendors.

3. The computer-implemented method of claim 2 , wherein the method further comprises:

executing an unsupervised learning operation using raw data relating to past performance of vendors providing VNFs;

clustering and classifying data provided from the unsupervised learning operation to generate a set of training data; and

using the set of training data to train the ML quality model.

4. The computer-implemented method of claim 1 , wherein

the one or more trained ML models include an ML similarity scoring model configured to

identify a degree of similarity between one or more of the generic VNFs and one or more VNFs available from the vendors.

5. The computer-implemented method of claim 4 , wherein

the ML similarity scoring model is trained using data derived from VNF images, VNF descriptions, and taxonomy data available from the vendors; and

wherein training the ML similarity scoring model further includes feature selection and engineering of features derived from the VNF images, VNF descriptions, and taxonomy data.

6. The computer-implement method of claim 5 , wherein

the data derived from feature selection and feature engineering are subject to localities sensitive hashing to train the ML similarity scoring model.

7. The computer-implemented method of claim 1 , wherein

the one or more trained machine learning (ML) models provide VNF and vendor information including one or more VNF vendors, the VNFs available from VNF vendors that source VNFs similar to the generic VNFs, VNF vendor quality metrics, similarity scores comparing vendors sourced VNFs with generic VNFs, and/or taxonomy data for VNFs provided by vendors, and wherein the VNF and vendor information is stored in a smart VNF catalog.

8. A computer system comprising:

one or more information handling systems, wherein the one or more information handling systems include:

a processor;

a data bus coupled to the processor; and

a non-transitory, computer-readable storage medium embodying computer program code, the non-transitory, computer-readable storage medium being coupled to the data bus;

wherein the computer program code included in one or more of the information handling systems is executable by the processor of the information handling system so that the information handling system, alone or in combination with other information handling systems, executes operations comprising:

designing a service with one or more generic virtual network functions (VNFs), wherein each of the generic VNFs is defined to provide a generic network functionality independent of vendor sourcing information;

using one or more trained machine learning (ML) models to identify available VNFs from VNF vendors that source one or more VNFs to implement the generic network functionality;

determining a similarity score for each implementation of the generic network functionality by a respective one of the available VNFs;

using the similarity score for each implementation of the generic network functionality to select one of the available VNFs to implement the generic network functionality; and

implementing the service using the selected one of the available VNFs to implement the generic network functionality.

9. The system of claim 8 , wherein

the one or more trained ML models include an ML quality model configured to assess a quality of VNFs provided by vendors.

10. The system of claim 9 , wherein the operations further comprise:

executing an unsupervised learning operation using raw data relating to past performance of vendors providing VNFs;

clustering and classifying data provided from the unsupervised learning operation to generate a set of training data; and

using the set of training data to train the ML quality model.

11. The system of claim 8 , wherein

the one or more trained ML models include an ML similarity scoring model configured to identify a degree of similarity between one or more of the generic VNFs and one or more VNFs available from the vendors.

12. The system of claim 11 , wherein

the ML similarity scoring model is trained using data derived from VNF images, VNF descriptions, and taxonomy data available from the vendors; and

wherein training the ML similarity scoring model further includes feature selection and engineering of features derived from the VNF images, VNF descriptions, and taxonomy data.

13. The system of claim 12 , wherein

the data derived from feature selection and feature engineering are subject to localities sensitive hashing to train the ML similarity scoring model.

14. The system of claim 8 , wherein

the one or more trained machine learning (ML) models provide VNF and vendor information including one or more VNF vendors, the VNFs available from VNF vendors that source VNFs similar to the generic VNFs, VNF vendor quality metrics, similarity scores comparing vendors sourced VNFs with generic VNFs, and/or taxonomy data for VNFs provided by vendors, and wherein the VNF and vendor information is stored in a smart VNF catalog.

15. A non-transitory, computer-readable storage medium embodying computer program code, the computer program code comprising computer-executable instructions configured for:

designing a service with one or more generic virtual network functions (VNFs), wherein each of the generic VNFs is defined to provide a generic network functionality independent of vendor sourcing information;

using one or more trained machine learning (ML) models to identify available VNFs from VNF vendors that source one or more VNFs to implement the generic network functionality;

determining a similarity score for each implementation of the generic network functionality by a respective one of the available VNFs;

using the similarity score for each implementation of the generic network functionality to select one of the available VNFs to implement the generic network functionality; and

implementing the service using the selected one of the available VNFs to implement the generic network functionality.

16. The non-transitory, computer-readable storage medium of claim 15 , wherein

the one or more trained ML models include an ML quality model configured to assess a quality of VNFs provided by vendors.

17. The non-transitory, computer-readable storage medium of claim 16 , wherein the instructions are further configured for:

executing an unsupervised learning operation using raw data relating to past performance of vendors providing VNFs;

clustering and classifying data provided from the unsupervised learning operation to generate a set of training data; and

using the set of training data to train the ML quality model.

18. The non-transitory, computer-readable storage medium of claim 15 , wherein

the one or more trained ML models include an ML similarity scoring model configured to identify a degree of similarity between one or more of the generic VNFs and one or more VNFs available from the vendors.

19. The non-transitory, computer-readable storage medium of claim 18 , wherein

the ML similarity scoring model is trained using data derived from VNF images, VNF descriptions, and taxonomy data available from the vendors; and

wherein training the ML similarity scoring model further includes feature selection and engineering of features derived from the VNF images, VNF descriptions, and taxonomy data.

20. The non-transitory, computer-readable storage medium of claim 15 , wherein

the one or more trained machine learning (ML) models provide VNF and vendor information including one or more VNF vendors, the VNFs available from VNF vendors that source VNFs similar to the generic VNFs, VNF vendor quality metrics, similarity scores comparing vendors sourced VNFs with generic VNFs, and/or taxonomy data for VNFs provided by vendors, and wherein the VNF and vendor information is stored in a smart VNF catalog.

Assignments (9)

Continuity (1)

Cited By (1)

US 12,481,946