Optimized Paging System for Wireless Mobility Management
Find Innovative SolutionsGenerate Solutions
Solution Overview
Problem
Modern telecommunication networks face significant overhead in signal load due to paging events, with approximately 29% of signal load in Mobility Management Entity (MME) systems being attributed to paging, and there is no existing system integrated with the telecom core network that optimizes paging messages based on actual UE mobility data.
Innovation Solution
A method is introduced that utilizes a core network node and a paging server to manage UE mobility by generating a mobility model based on tracking areas and filtering base stations, reducing unnecessary paging messages through a three-stage paging system that includes periodic location registrations, mobility modeling, and optimized paging message transmission.
Engineering Contradictions & Design Principles
Engineering Contradiction Analysis
1Loss of information
If traditional paging procedures are used to maintain UE location registration, then location accuracy is ensured, but signal load overhead increases significantly (29% of MME signal load)
Solution Approach 1:
The system performs preliminary actions by predicting UE location in advance using machine learning models before actual paging is needed. The mobility prediction model pre-calculates likely tracking areas based on historical mobility patterns, allowing the network to prepare optimized paging lists that reduce subsequent signaling overhead while maintaining accurate location registration.
Solution Approach 2:
The patent replaces the traditional mechanical paging system with an intelligent prediction-based system. Instead of broadcasting paging messages to all possible tracking areas, the system uses machine learning algorithms to substitute the mechanical paging approach with a smart selection process that identifies the most probable UE location, thereby reducing signal load while preserving location registration accuracy.
2Reliability
If paging messages are transmitted to all base stations in tracking areas to ensure UE reachability, then connection reliability is maintained, but message overhead and network complexity increase
Solution Approach 1:
The patent introduces an intermediary paging list optimization mechanism between the core network and base stations. The machine learning model acts as a mediator that processes mobility data and generates optimized paging lists, filtering out unnecessary base stations from the paging process. This intermediary layer maintains UE reachability by ensuring the UE is included in the optimized list while reducing the number of base stations that need to process paging messages.
Solution Approach 2:
The system changes the parameters of the paging process by dynamically adjusting the paging list based on predicted UE mobility patterns. Instead of using static tracking area lists, the system modifies the paging parameters (which base stations receive paging messages) based on real-time mobility predictions, thereby maintaining reliability while reducing network complexity and message overhead.
3Measurement precision
If tracking area updates are performed frequently to maintain accurate location information, then location precision is improved, but signaling overhead and network resource consumption increase
Solution Approach 1:
The system performs preliminary location prediction using machine learning models before actual location updates are needed. By pre-calculating the UE's likely tracking area based on historical mobility patterns, the system reduces the frequency of actual tracking area updates while maintaining location precision, thereby decreasing signaling overhead and network resource consumption.
Solution Approach 2:
The patent implements a feedback mechanism where the system continuously learns from actual UE mobility patterns and refines its predictions. The machine learning model receives feedback from location registration events and adjusts its predictions accordingly, allowing the system to maintain high location precision with fewer tracking area updates by adapting to individual UE mobility behaviors.
Data Source
AI summary
Implementations for providing a mobility management with optimized paging system in a wireless communication system comprising a core network (CN) node and a user equipment (UE) in operative communication with one another through a base station are disclosed. The paging system may, by way of example, be provided in three stages. The first stage is determining whether the destination base station is the same as the source base station, resulting in either first paging if they are the same or to subjecting the base stations belonging to the tracking area list where the UE is found to filtering if they are not the same. The second paging takes place if the destination base station is present in a list of predicted base stations that come as a result of the filtered base stations. The third paging may take place if the destination base stations is not present in the list of predicted base stations.