Network Slice Management via Particle Swarm Optimization
Find Innovative SolutionsGenerate Solutions
Solution Overview
Problem
Existing network slicing technologies are inflexible and resource-intensive, lacking real-time performance monitoring and dynamic adjustment capabilities, making it difficult to analyze and predict network issues effectively.
Innovation Solution
A network slices management system that includes a network management plane and user plane, utilizing a network slices management platform to receive user scenarios and service requirements, orchestrate end-to-end slicing services, and employ a particle swarm algorithm for dynamic optimization and predictive maintenance, enabling customizable and adaptable network slices.
Engineering Contradictions & Design Principles
Engineering Contradiction Analysis
1Ease of manufacture
If network slices are allocated according to predefined scenarios, then network deployment is simplified, but customization according to user needs is lost and resources are wasted
Solution Approach 1:
The system dynamically adjusts network slice configurations based on real-time user feedback and performance data. The management platform enables continuous optimization of slice parameters (bandwidth, latency, resource allocation) rather than using fixed predefined scenarios, allowing the network to adapt to changing user needs while maintaining deployment efficiency through automated orchestration.
Solution Approach 2:
The patent implements a closed-loop feedback mechanism where user satisfaction data and network performance metrics are continuously collected and used to adjust slice allocations. This feedback system enables the network to learn from actual usage patterns and optimize resource distribution, resolving the contradiction between simplified deployment and user customization by making the system adaptive rather than static.
2Device complexity
If network slices are deployed without performance monitoring, then system complexity is reduced, but predictive maintenance and problem analysis become impossible
Solution Approach 1:
The system implements self-service monitoring and automated anomaly detection capabilities. Network slices automatically report their performance metrics to the management platform, which uses machine learning algorithms to detect patterns and predict potential failures before they occur. This self-monitoring approach enables reliable predictive maintenance without significantly increasing operational complexity, as the system manages its own health assessment autonomously.
3Device complexity
If static network slice allocation is used, then resource management is simplified, but resource utilization efficiency decreases
Solution Approach 1:
The patent implements dynamic resource allocation where network slice parameters (bandwidth, computing resources, storage) are continuously adjusted based on real-time demand signals from users and performance feedback from the network. This dynamic approach maximizes resource utilization by allocating resources to high-priority slices during peak demand while maintaining simplified management through automated orchestration algorithms that handle the complexity of real-time adjustments.
Data Source
AI summary
A method for managing network slices for the benefit of users monitors and obtains key performance indicators configured by a user, the indicator values being collected in real time and visually presented. When a user wants to optimize the network slices, weightings, value intervals, and variables are applied by the user to target key performance indicators. The network slices are optimized by a particle swarm algorithm configured by the user. A device and a computer readable and permanent storage medium for executing the network slices management method are also disclosed.