Multi-Connectivity Control via Machine Learning Link Probabilities
Find Innovative SolutionsGenerate Solutions
Solution Overview
Problem
In wireless communication systems, especially those employing high-frequency bands like millimeter waves, the variability of mobile backhaul networks due to mobile backhaul base stations' mobility and environmental changes poses challenges in efficiently managing dual-connectivity and multi-connectivity, leading to increased installation costs and potential service disruptions.
Innovation Solution
A method and apparatus utilizing machine learning to calculate link available and blocking probabilities, enabling adaptive control of multi-connectivity between communication nodes and fixed or mobile backhaul base stations based on real-time communication status and environmental information, thereby optimizing link configurations and service quality.
Engineering Contradictions & Design Principles
Engineering Contradiction Analysis
1Productivity
If wireless terminals serve as mobile backhaul base stations to enable highly-dense base stations deployment, then coverage and service capability are improved, but installation costs and network complexity increase
Solution Approach 1:
Wireless terminals perform machine learning operations locally to compute link probabilities and determine multi-connectivity configurations autonomously, without requiring complex centralized control. The terminals self-manage their connectivity by processing communication status information and environment information locally, reducing network control complexity while enabling dense deployment
Solution Approach 2:
The system dynamically adjusts multi-connectivity configurations based on real-time link probabilities computed through machine learning. As wireless terminals move and communication environments change, the link probabilities are updated iteratively, allowing the network to adaptively reconfigure connections without manual intervention, thus managing complexity through dynamic self-optimization
2Reliability
If multi-connectivity is controlled adaptively to communication environmental changes, then service stability is improved, but computational complexity and processing requirements increase
Solution Approach 1:
The computational task is segmented into iterative machine learning operations where link probabilities are computed step-by-step based on communication status information and environment information. This segmentation allows complex adaptive control to be broken down into manageable computational stages, reducing the burden on individual processing operations while maintaining service stability
Solution Approach 2:
The system computes link probabilities iteratively with sufficient precision to make reliable connectivity decisions, rather than requiring complete convergence of all parameters. This partial action approach provides adequate service stability without the excessive computational overhead of exhaustive optimization, balancing reliability with processing requirements
Data Source
AI summary
A method for managing links, performed by a first communication node in a communication system, includes: obtaining, through an interface, communication status information including communication quality information for each link between the first communication node and at least one other communication node of the communication system; obtaining communication environment information including movement information and location information of each of the at least one other communication node; and obtaining a link probability computational model outputting a first link probability according to input of the communication status information by iteratively performing a machine learning operation based on the communication status information and the communication environment information, wherein the first link probability is used by the first communication node to control multi-connectivity with the at least one other communication node.