AI Network Slicing Control for Low-Latency Edge Cloud
Find Innovative SolutionsGenerate Solutions
Solution Overview
Problem
Current cloud platform architectures in 5G mobile networks lack flexibility and efficiency in managing network resources for mission critical applications, leading to unpredictable end-to-end latency and inefficient resource allocation.
Innovation Solution
Implementing an edge cloud platform with an AI-powered network slicing controller (NSC) that manages network slicing instances using artificial intelligence and machine learning to optimize traffic policies and resource allocation based on real-time network metrics, reducing latency and enhancing throughput.
Engineering Contradictions & Design Principles
Engineering Contradiction Analysis
1Productivity
If traditional cloud platform architectures are used for managing network resources, then infrastructure simplicity is maintained, but resource allocation efficiency and latency control deteriorate for mission critical applications
Solution Approach 1:
The patent segments the network into multiple network slices, each dedicated to specific mission critical applications with guaranteed performance characteristics. This segmentation allows independent resource allocation and latency control for different application types, resolving the contradiction by enabling efficient resource allocation while maintaining low latency through dedicated slices.
Solution Approach 2:
The patent introduces a new dimensional approach by deploying edge computing nodes at the network edge, creating a multi-dimensional architecture that combines cloud, fog, and edge layers. This dimensional change enables resources to be physically closer to users, reducing latency while maintaining centralized cloud management capabilities for efficient resource allocation.
2Reliability
If more network resources are allocated to mission critical applications, then service quality improves, but resource utilization efficiency for non-critical applications deteriorates
Solution Approach 1:
The patent implements dynamic resource allocation where network slice resources can be flexibly adjusted based on real-time demand. During peak mission critical periods, resources are dynamically allocated to ensure service quality, while during off-peak periods, resources can be reallocated to non-critical applications, maintaining overall resource utilization efficiency through time-varying allocation strategies.
Solution Approach 2:
The patent changes the parameter of resource allocation from static to dynamic by introducing orchestrators that continuously monitor and adjust resource distribution. This allows the system to maintain high service quality for mission critical applications when needed while optimizing overall resource utilization by allocating remaining capacity to other applications, effectively resolving the contradiction through parameter optimization.
3Adaptability or versatility
If manual network resource management is used, then system complexity is reduced, but adaptability to changing traffic patterns and application requirements deteriorates
Solution Approach 1:
The patent implements self-service mechanisms where network slice orchestrators automatically monitor traffic patterns, detect performance degradation, and reallocate resources without human intervention. This self-service capability enables the system to adapt to changing traffic patterns and application requirements while keeping operational complexity low, as the automated systems handle the complexity internally without requiring complex manual management procedures.
Solution Approach 2:
The patent incorporates continuous feedback loops where performance metrics are monitored and fed back to orchestrators, which then automatically adjust resource allocation. This feedback mechanism enables the system to adapt to changing conditions in real-time, improving versatility while managing complexity through automated closed-loop control rather than complex manual management systems.
4Reliability
If network slicing is implemented for mission critical applications, then service differentiation and quality improve, but network management complexity increases
Solution Approach 1:
The patent implements universal orchestrator components that can manage multiple network slices across different technologies and deployment scenarios. This multi-functionality reduces management complexity by providing a unified control plane that handles diverse slice requirements through standardized procedures, enabling service differentiation while avoiding the complexity of separate management systems for each slice type.
Data Source
AI summary
A method implements a network slicing controller to manage network slicing instances in an edge cloud platform. The method includes receiving at least one policy change from an artificial intelligence powered smart traffic controller (APSTC) or an artificial intelligence powered edge traffic controller (APETC), determining whether the at least one policy change is valid based on local monitoring information, and sending the at least one policy change to a common control network function in a 5G mobile network.