Network Function Chain Optimization via Locality Constraints
Find Innovative SolutionsGenerate Solutions
Solution Overview
Problem
Existing methods for optimizing the deployment of cloud services composed of virtualized software network functions do not adequately consider characteristics of wide-area networks and specific network function requirements, leading to suboptimal resource usage and energy consumption.
Innovation Solution
A computer-implemented network function optimization method that annotates network functions with constraints and modifies the structure of network function chains based on these constraints to optimize placement and resource utilization, considering key performance indicators and network characteristics.
Engineering Contradictions & Design Principles
Engineering Contradiction Analysis
1Adaptability or versatility
If network functions are implemented in software with virtual machines and containers, then flexibility in placement and dynamic behavior are improved, but resource usage and energy consumption increase
Solution Approach 1:
The patent applies local quality by annotating network functions with specific constraints related to their placement requirements, such as locality constraints that ensure functions are deployed close to their data sources or consumers. This allows the system to optimize resource usage by placing functions in appropriate locations rather than uniformly distributing them, thereby reducing unnecessary resource consumption and energy usage while maintaining flexibility.
Solution Approach 2:
The system changes parameters by dynamically adjusting placement constraints and annotations based on network conditions, function types, and resource availability. The optimization engine modifies deployment parameters to balance flexibility with resource efficiency, allowing the system to adapt placement decisions to minimize energy consumption while preserving the benefits of software-based virtualization.
2Ease of manufacture
If network functions are deployed without considering wide-area network characteristics, then deployment simplicity is improved, but performance and resource efficiency deteriorate
Solution Approach 1:
The patent applies preliminary action by annotating network functions with constraints and characteristics before deployment. The system pre-configures placement rules, locality requirements, and function-specific parameters that guide the optimization engine. This preliminary annotation process maintains deployment simplicity while ensuring that resource efficiency considerations are built into the deployment strategy from the outset.
3Adaptability or versatility
If network functions are placed without considering locality, then deployment flexibility is improved, but resource consumption and performance deteriorate
Solution Approach 1:
The patent applies local quality by implementing locality-aware placement through function annotations. The system identifies functions that benefit from being placed close to their data sources or consumers and applies appropriate constraints to ensure optimal localization. This reduces resource consumption by minimizing data transfer distances and network bandwidth usage while preserving deployment flexibility through the configurable annotation system.
4Loss of energy
If network function chains are optimized based on constraints, then resource usage is reduced, but system complexity increases
Solution Approach 1:
The patent applies self-service by enabling the optimization engine to automatically process function annotations, evaluate constraints, and generate optimized deployment configurations without requiring manual intervention. The system self-manages the complexity of constraint evaluation and chain optimization, reducing resource usage through automated decision-making while keeping the user interface simple and manageable.
Data Source
AI summary
A network function optimization method, system, and computer program product include optimizing network function chain components of a software by modifying a structure of the network function chain components by removing a function of the network function chain components.