VNF Group Scheduling for Higher VDU Deployment Success
Find Innovative SolutionsGenerate Solutions
Solution Overview
Problem
Conventional network function virtualization (NFV) technologies face inefficiencies in deploying virtual network functions (VNFs) due to resource allocation at a single VDU granularity, leading to failed deployments when hardware resources are insufficient, especially in scenarios with discrete resource requirements and shared host aggregates.
Innovation Solution
The method involves grouping multiple VDUs as a whole and performing unified scheduling at a group level, associating them with workload group objects to manage resource allocation, ensuring all VDUs in a group obtain resources or adjusting allocation until successful, thereby improving deployment success rates.
Engineering Contradictions & Design Principles
Engineering Contradiction Analysis
1Adaptability or versatility
If resource allocation is performed at a single VDU granularity, then individual VDU deployment flexibility is improved, but deployment success rate deteriorates when hardware resources are insufficient
Solution Approach 1:
The patent merges multiple VDUs into a VDU group and performs unified resource allocation at the group level rather than individually. The resource allocation module allocates hardware resources to the entire VDU group based on aggregate resource requirements, ensuring that all VDUs in the group can be deployed successfully when resources are sufficient, thereby resolving the contradiction between individual flexibility and overall deployment success rate.
2Productivity
If unified group scheduling is performed on multiple VDUs, then resource allocation rationality is improved, but computation complexity increases
Solution Approach 1:
The patent segments the scheduling process into two distinct phases: (1) resource allocation at the VDU group level to determine which groups can be deployed, and (2) individual VDU deployment within allocated groups. This segmentation reduces computation complexity by performing unified scheduling on groups rather than on each individual VDU, while still maintaining resource allocation rationality through group-level optimization.
Solution Approach 2:
The patent introduces a new dimension of grouping to organize VDUs, transforming the scheduling problem from one-dimensional (individual VDU) to two-dimensional (group level and individual level). This dimensional change allows unified resource allocation to be performed at the group level, improving resource allocation rationality while reducing the overall computation burden compared to scheduling every individual VDU separately.
3Ease of operation
If multiple VDUs are deployed individually, then deployment independence is improved, but overall deployment efficiency deteriorates due to repeated computation
Solution Approach 1:
The patent performs preliminary resource allocation at the VDU group level before individual VDU deployment. The resource allocation module pre-determines which VDU groups can be successfully deployed based on aggregate resource requirements, avoiding repeated computation during individual VDU deployment. This preliminary action maintains deployment independence while significantly improving overall deployment efficiency by eliminating redundant resource checking for each individual VDU.
Data Source
AI summary
This application provides a virtual network function deployment method and deployment apparatus. According to the deployment method provided in this application, when resources are allocated to VDUs required by a to-be-deployed VNF, all of the required VDUs are used as an entire group, to compute, in one computation periodicity at a granularity of a group, resources required for scheduling all the VDUs, until the corresponding resources are obtained for scheduling the entire group of VDUs or scheduling of the entire group of VDUs fails. When deployment locations of the VDUs for the to-be-deployed VNF are computed at the granularity of a group, an allocation manner that is not conducive to overall deployment is recomputed and adjusted, so that a success rate of VNF deployment is improved.