VNF Placement Optimization for Network Affinity Index
Find Innovative SolutionsGenerate Solutions
Solution Overview
Problem
Network Functions Virtualization (NFV) systems face inefficiencies due to architectural limitations that introduce latency and errors through packet rerouting between memory zones, leading to suboptimal high-speed packet processing.
Innovation Solution
A controller optimizes the placement of Virtualized Network Functions (VNFs) within the NFV system by calculating a memory zone efficiency index to minimize packet copying between memory zones, thereby reducing processing latency and increasing efficiency.
Engineering Contradictions & Design Principles
Engineering Contradiction Analysis
1Adaptability or versatility
If VNFs are deployed in NFV systems to replace physical network hardware, then resource efficiency and service deployment flexibility are improved, but packet processing latency increases due to architectural limitations requiring packet rerouting between memory zones
Solution Approach 1:
The patent applies local quality by optimizing the placement of VNFs on specific cores within the server. The system calculates a memory zone efficiency index for each core based on packet processing characteristics and places VNFs on cores with the highest efficiency indices. This ensures that packet processing operations are performed locally on the most suitable hardware resources, minimizing the need for packet rerouting between memory zones and reducing latency while maintaining service deployment flexibility.
2Reliability
If packet rerouting is performed between memory zones to handle VNF processing, then network service functionality is maintained, but processing latency and errors increase
Solution Approach 1:
The patent applies preliminary action by calculating and determining the optimal placement of VNFs on specific cores before packet processing begins. The system computes a memory zone efficiency index for each core in advance and uses this information to pre-position VNFs on the most suitable cores. This preliminary optimization ensures that when packets arrive, they can be processed with minimal rerouting, reducing latency while maintaining reliable network service functionality.
3Productivity
If VNFs are placed on specific cores based on memory zone efficiency, then packet processing efficiency is improved, but system complexity increases due to placement optimization requirements
Solution Approach 1:
The patent applies parameter changes by using a measurable memory zone efficiency index to guide VNF placement decisions. The system calculates this index based on packet processing parameters such as packet copy operations and memory access patterns. By transforming the complex placement optimization problem into a parameter-based selection process, the system achieves improved packet processing efficiency while managing complexity through quantifiable metrics rather than complex algorithms.
Data Source
Figure 1
Figure 2A~2B
Figure 3
AI summary
Examples herein relate to identifying a placement of a virtual network function (VNF) to increase a network affinity index. For example a method, executable by a network controller, determines for the VNF the network affinity index over a period of time. The network affinity index identifies a number of packets received by the VNF from a data locality corresponding to a processing unit hosting the VNF. The method proceeds to identify a placement of the VNF extrinsic to the processing unit hosting the VNF to increase the network affinity index.