Polymorphic Network Slice Orchestrator for Multi-Tier Latency Reduction
Find Innovative SolutionsGenerate Solutions
Solution Overview
Problem
Current network slicing technologies face challenges in harmonizing algorithms with different time granularities and scopes, leading to high communication latencies and inefficient resource management across centralized and distributed networks, particularly in next-generation wireless networks.
Innovation Solution
A polymorphic algorithm-based network slice orchestrator service is introduced, which operates across multiple tiers of a network with configurable time granularities, allowing for goal function normalization and efficient resource allocation through a multi-tier framework, including centralized, edge, and far edge tiers, using AI and ML frameworks for optimization and self-configuring capabilities.
Engineering Contradictions & Design Principles
Engineering Contradiction Analysis
1Adaptability or versatility
If algorithms with different time granularities and scopes are harmonized across centralized and distributed networks, then network slice management capability is improved, but communication latency increases
Solution Approach 1:
The network is divided into multiple tiers (centralized, edge, and far edge) with each tier handling algorithms at different time granularities and scopes. This segmentation allows local decisions to be made at edge and far edge tiers without requiring constant communication with the centralized tier, thereby reducing communication latency while maintaining comprehensive network slice management capability across all tiers.
2Productivity
If algorithms are executed across multiple tiers with different time granularities, then resource allocation efficiency is improved, but system complexity increases
Solution Approach 1:
The system employs dynamic algorithm execution where algorithms are selectively activated based on current network conditions, time granularity requirements, and scope of control needed. Rather than statically configuring all algorithms across all tiers, the system dynamically determines which algorithms execute at which tiers, reducing unnecessary complexity while maintaining efficient resource allocation when needed.
Solution Approach 2:
Different tiers of the network are assigned different algorithmic capabilities and time granularities appropriate to their local requirements. The far edge tier handles immediate local resource allocation with fine time granularity, while the centralized tier handles broader network-wide optimization with coarser granularity. This local quality approach ensures each tier has the complexity it needs without imposing unnecessary complexity on other tiers.
3Adaptability or versatility
If network slicing is implemented across centralized and distributed architectures, then service capability is improved, but resource load and churn increase
Solution Approach 1:
The system performs preliminary resource allocation and algorithm selection at higher tiers before deploying resources to lower tiers. By pre-configuring network slices and algorithm execution plans at the centralized and edge tiers, the system reduces the need for frequent resource reallocation and churn at the far edge tier, thereby maintaining high service capability while reducing overall resource load and instability.
Data Source
AI summary
A method, a device, and a non-transitory storage medium are described in which a polymorphic algorithm-based network slice orchestrator service is provided. The service may manage network slices based on radio access network performance metrics, core network performance metrics, network slice performance metrics, a machine learning framework, and polymorphic algorithms. The service may be applied to a multi-tier network. The service may include management of a data network access point of the network slice on a per-tier basis.