Resource-Aware Load Balancer for NFV CPU Utilization
Find Innovative SolutionsGenerate Solutions
Solution Overview
Problem
Balancing load across multiple NFV servers is challenging due to diverse service costs, server and flow heterogeneity, and dynamic workload conditions, making it difficult to ensure reliable and efficient network function virtualization (NFV) performance.
Innovation Solution
A resource-aware load balancer, NFVBalance, models CPU load on NFV servers to guide load balancing policies, using a software-based approach that predicts CPU utilization and processing costs to efficiently distribute traffic across multiple processing threads and cores, thereby achieving high performance and reliability.
Engineering Contradictions & Design Principles
Engineering Contradiction Analysis
1Reliability
If replication is used to ensure reliability and improve NF performance, then reliability and performance are improved, but load balancing complexity increases due to diverse service costs, server heterogeneity, and dynamic workload conditions
Solution Approach 1:
The patent changes the parameter representation from raw CPU usage to a normalized load metric that accounts for heterogeneous server capabilities. By introducing a load factor that combines CPU usage with server-specific weights, the system transforms complex heterogeneous load characteristics into a unified parameter that simplifies load balancing decisions across diverse NFV servers
Solution Approach 2:
The patent introduces an intermediary load balancing controller that mediates between incoming traffic and heterogeneous NFV servers. This controller normalizes load information from diverse servers, applies weighted round-robin algorithms with dynamically adjusted weights, and makes centralized load balancing decisions, thereby simplifying the overall system complexity while maintaining reliability across replicated instances
2Ease of operation
If traditional load balancing methods are used, then implementation is simple, but load distribution is uneven and CPU usage is high
Solution Approach 1:
The patent transitions from static load balancing weights to dynamic weights that are continuously adjusted based on real-time CPU usage monitoring. The system periodically updates server weights according to current load conditions, enabling adaptive load distribution that responds to changing workload patterns and server performance, thereby improving productivity while maintaining operational simplicity through automated adjustments
Data Source
AI summary
Software-based data planes for network function virtualization may use a modular approach in which network functions are implemented as modules that can be composed into service chains. Infrastructures that allow these modules to share central processing unit resources are particularly appealing since they support multi-tenancy or diverse service chains applied to different traffic classes. Systems, methods, and apparatuses introduce schemes for load balancing considering central processing unit utilization of a next hop device when processing a packet that uses a service chain.