NFV VNF Allocation via Graph Partitioning
Find Innovative SolutionsGenerate Solutions
Solution Overview
Problem
In Network Function Virtualization (NFV) architecture, efficiently allocating Virtual Network Functions (VNFs) to physical computers is challenging due to the limitations of each computer running only a partial subset of VNFs, leading to suboptimal processing latency and network bandwidth usage.
Innovation Solution
A method and system that utilize graph representation to allocate VNFs to physical computers by applying an optimality criterion, such as minimizing latency or setting an upper bound on latency, by generating a graph where vertices represent VNFs and edges indicate joint allocation, and partitioning the graph to maximize weights and minimize processing delay.
Engineering Contradictions & Design Principles
Engineering Contradiction Analysis
1Loss of time
If VNFs are allocated to physical computers without using graph representation, then the allocation process is simpler, but the processing latency increases and system performance deteriorates
Solution Approach 1:
The patent replaces manual or simple allocation mechanisms with an automated graph-based optimization system. The graph representation model combined with optimization algorithms automatically determines optimal VNF-to-physical-computer mappings, minimizing processing latency through computational intelligence rather than straightforward assignment rules.
Solution Approach 2:
The patent transforms the allocation problem into a graph theory problem by changing the representation parameters. VNFs become vertices, packet types become edges, and allocation decisions become weight assignments. This parameter transformation enables sophisticated optimization to minimize latency while managing complexity through structured problem representation.
2Loss of energy
If each physical computer runs only a partial subset of VNFs, then the hardware constraints are satisfied, but the network bandwidth consumption increases
Solution Approach 1:
The patent segments the VNF allocation problem into discrete assignments based on packet type requirements. By representing packet types as edges connecting relevant VNFs (vertices), the system identifies optimal segments of VNFs that should be co-located on the same physical computer to minimize network bandwidth consumption while respecting hardware constraints.
Solution Approach 2:
The graph representation acts as an intermediary between the hardware constraints and the optimization goal. It mediates between the limited capacity of individual physical computers and the requirement to minimize network bandwidth by providing a structured framework for finding optimal allocation solutions.
3Productivity
If graph partitioning is applied to allocate VNFs, then the processing efficiency improves, but the computational complexity increases
Solution Approach 1:
The patent applies graph partitioning techniques that may not always produce perfectly optimal solutions but achieve sufficient improvement in processing efficiency. The optimization algorithms perform partial analysis of the graph structure to identify meaningful partitions, balancing computational effort with performance gains rather than exhaustively searching all possible allocations.
Data Source
AI summary
A method for designing a Network Function Virtualization (NFV) architecture includes accepting a definition of multiple Virtual Network Functions (VNFs), and of one or more packet types having respective occurrence probabilities, wherein each packet type is associated with a respective subset of the VNFs that are to be applied to packets of that packet type. Information on multiple available physical computers, each capable of running only a partial subset of the multiple VNFs, is further accepted. The VNFs are allocated to the physical computers by applying an optimality criterion to definition and the information.