AI/ML Models for Virtual Network Function Vendor Selection
Find Innovative SolutionsGenerate Solutions
Solution Overview
Problem
Service providers face challenges in designing and selecting Virtual Network Functions (VNFs) and vendors, as traditional methodologies require knowledge of vendor-specific qualities and lead to lengthy design cycles due to the need for iterations and delays in finding compliant VNFs, with designers often unaware of available VNFs or their quality.
Innovation Solution
The use of AI/ML models, specifically trained quality and similarity scoring models, to identify and assess VNFs and vendors independently of the supply chain, allowing for the selection of VNFs that meet specific network function requirements, optimizing service design and implementation by decoupling it from specific vendors.
Engineering Contradictions & Design Principles
Engineering Contradiction Analysis
1Reliability
If traditional vendor-specific methodologies are used to select VNFs, then designers can leverage known vendor qualities, but the design cycle becomes lengthy due to iterations and delays
Solution Approach 1:
The system performs preliminary actions by pre-training ML models with vendor quality data and VNF characteristics before the actual service design process. This allows the system to have vendor quality assessments ready in advance, eliminating the need for time-consuming iterative evaluations during the design cycle.
Solution Approach 2:
The patent replaces the manual, iterative mechanical process of vendor evaluation and VNF selection with an automated ML-based system. The ML models automatically assess vendor qualities and match VNFs to service requirements, substituting the traditional time-consuming human-driven selection process with efficient algorithmic decision-making.
2Manufacturing precision
If designers manually evaluate VNFs from multiple vendors, then they can find compliant VNFs, but the process requires extensive iterations and delays
Solution Approach 1:
The system replaces manual VNF evaluation and compliance checking with automated ML models that can simultaneously assess multiple VNFs from multiple vendors. This substitution maintains high compliance accuracy through sophisticated algorithms while dramatically increasing design throughput by processing numerous options in parallel rather than through sequential manual review.
Solution Approach 2:
The ML-based VNF selection system acts as an intermediary between service requirements and vendor VNF offerings. This intermediary automatically matches VNFs to requirements based on compliance criteria, eliminating the need for designers to manually iterate through vendor catalogs and compliance checks, thereby maintaining precision while boosting productivity.
3Reliability
If service design is coupled with specific vendors, then vendor-specific qualities can be leveraged, but flexibility for dynamic vendor insertion is reduced
Solution Approach 1:
The system implements universality by creating vendor-agnostic service designs that can work with multiple vendors through standardized interfaces and ML-based selection criteria. The ML models evaluate VNFs based on functional requirements and quality metrics rather than vendor-specific characteristics, enabling the same service design to be implemented with different vendors as needed, thus maintaining both quality assurance and flexibility.
4Measurement precision
If comprehensive vendor evaluation is performed, then high-quality VNFs can be identified, but the complexity of the selection process increases
Solution Approach 1:
The system extracts the complex vendor evaluation and VNF assessment tasks from the manual design process and encapsulates them within pre-trained ML models. These models have already processed comprehensive vendor data during training, so during actual service design, they provide streamlined, accurate recommendations without requiring designers to navigate complex evaluation procedures manually.
Data Source
AI summary
The disclosed systems and methods are directed to a computer-implemented method for use in designing a service. In at least one embodiment, a method includes designing a service with one or more generic virtual network functions (VNFs), where the generic VNFs are defined independent of vendor sourcing information. One or more trained machine learning (ML) models are used to identify VNFs available from VNF vendors that may source one or more VNFs similar to the generic VNFs. The service is implemented using VNFs provided by one or more VNF vendors, where the VNFs provided by the one or more VNF vendors have network functionality generating similar to the one or generic VNFs.