Network Function Placement Optimizes Pod Resource Utilization
Find Innovative SolutionsGenerate Solutions
Solution Overview
Problem
The challenge in network function virtualization (NFV) is to minimize optical/electrical/optical (O/E/O) conversions and optimize network function placement to reduce capital and operational expenditures, while ensuring efficient resource utilization and traffic flow routing in cloud/data centers.
Innovation Solution
A method for network function placement that sorts network functions by resource demand and available resources in pods, dynamically selecting pods for each function and adding resources from a pod pool when necessary, to minimize the number of O/E/O conversions and optimize resource utilization.
Engineering Contradictions & Design Principles
Engineering Contradiction Analysis
1Productivity
If network functions are placed on multiple pods to distribute load, then resource utilization improves, but the number of O/E/O conversions increases
Solution Approach 1:
The patent merges multiple network functions onto fewer pods where possible, consolidating workloads to reduce the number of inter-pod traffic flows. This combining approach maintains resource utilization while minimizing O/E/O conversions by keeping related functions co-located on the same physical infrastructure.
Solution Approach 2:
The patent applies local quality by placing network functions that communicate frequently on the same pod or nearby pods, creating localized function groups. This spatial arrangement reduces long-distance traffic flows and minimizes O/E/O conversions for functions that have high interaction requirements.
2Loss of energy
If network functions are placed on fewer pods to reduce O/E/O conversions, then energy loss decreases, but resource utilization efficiency worsens
Solution Approach 1:
The patent implements dynamic network function placement that adapts to changing traffic patterns and resource availability. Functions can be migrated between pods based on real-time conditions, allowing the system to optimize for energy efficiency during low-traffic periods while maintaining resource utilization during high-traffic periods.
Solution Approach 2:
The patent makes pods multi-functional by hosting multiple different network functions on the same physical infrastructure. This universal approach allows a single pod to serve multiple purposes, reducing the total number of pods needed while maintaining high resource utilization across diverse function types.
3Productivity
If network functions are dynamically placed to optimize resource utilization, then productivity improves, but system complexity increases
Solution Approach 1:
The patent implements self-service mechanisms where network functions automatically select suitable pods for deployment based on predefined criteria and available resources. This autonomous placement reduces the need for complex centralized management systems while maintaining efficient resource utilization through decentralized decision-making.
Solution Approach 2:
The patent performs preliminary analysis of resource requirements and pod capabilities before placing network functions. By pre-evaluating compatibility and optimizing placement decisions in advance, the system avoids complex real-time adjustments while maintaining high resource utilization efficiency.
Data Source
Figure 1
Figure 2A~2B
Figure 3
AI summary
A method implemented for network function placement is disclosed. The method optimizes network function placement for each traffic flow, to minimize the overall inter-pod traffic volume. For each traffic flow going through a data center, the method initiates a pod list. The network functions of the traffic flow is sorted in a descending order by resource demanded. Then one network function is selected one at a time according to the descending order. For each network function, the pods in the pod list is sorted in an ascending order by resource available in each pod. The method selects a first pod for the network function when possible. When no pod in the pod list has enough resource for the network function, the method adds a pod with the most available resource from a pod pool to the pod list, and selects the added pod for the network function.