Geolocation Prediction Using Cell List Centroids
Find Innovative SolutionsGenerate Solutions
Solution Overview
Problem
Current methods for determining the geolocation of user equipment (UE) in cellular communication systems are resource-intensive and lack accuracy, especially in dense urban areas with high cell density and frequent handovers, due to the complexity of signal obstructions and changes in cell and UE locations.
Innovation Solution
A method that utilizes machine learning (ML) to predict geolocation by receiving call records with truth data, calculating centroids for cell lists, and building an ML model based on signal detail data to improve geolocation prediction accuracy, allowing for efficient resource allocation and enhanced accuracy in dense urban environments.
Engineering Contradictions & Design Principles
Engineering Contradiction Analysis
1Measurement precision
If conventional statistical calculation methods are used to determine geolocation, then geolocation can be obtained for each RRC call setup and handover, but resource consumption increases significantly
Solution Approach 1:
The system pre-calculates and stores geolocation centroids for multiple cell lists in advance, creating a lookup table of pre-computed results. When a geolocation request arrives, the system simply retrieves the pre-computed centroid matching the current cell list rather than performing new statistical calculations, thereby eliminating redundant computation and reducing resource consumption.
Solution Approach 2:
The system creates simplified representations (centroids) of complex geolocation data by calculating the center point of geographic regions associated with specific cell lists. These centroid copies serve as surrogate data structures that enable fast retrieval and comparison without requiring access to the full underlying statistical datasets, reducing memory access complexity and processing overhead.
2Measurement precision
If geolocation is calculated using statistical methods for each call and handover, then location data is obtained, but the process consumes large quantities of computational resources
Solution Approach 1:
The system performs geolocation centroid calculations in advance during idle periods or data collection phases, storing results in a pre-computed database. During actual call setup and handover operations, the system only needs to perform lightweight matching operations to retrieve pre-calculated centroids, dramatically improving processing efficiency during high-traffic periods without sacrificing accuracy.
Solution Approach 2:
The system extracts only the essential geolocation information (centroid coordinates) from complex statistical datasets and stores these extracted features separately. This separation allows the system to discard or archive the full statistical data while retaining only the critical location information needed for rapid retrieval during operations, reducing both storage and computational requirements.
3Reliability
If conventional geolocation methods are used in dense urban areas with high cell density, then coverage is provided, but the number of geolocation requests and resource consumption increase due to frequent handovers
Solution Approach 1:
The system pre-computes and caches geolocation centroids for all possible cell list combinations that may occur during handovers in dense urban areas. When handovers occur frequently, the system can rapidly retrieve matching centroids from cache rather than performing new calculations, enabling the network to handle high volumes of handover requests without proportional increases in processing resource consumption.
Data Source
AI summary
A method includes receiving call records from a control plane, each call record including a cell list identifying the server cell for the UE call session at the time the call record was generated and an ordered set of neighbor cells, ordered based on a characteristic of signals from the neighbor cells. Call records having truth data are selected, wherein the truth data includes geolocation (GL) data reported to be a GL associated with the call record. GL data of the selected call records is stored in association with the cell list for the selected call records. A centroid is determined as a function of the GL data associated with each of the selected call records that includes the associated cell list. The centroids are stored in association with the corresponding cell list, and can be retrieved as a prediction for a GL based on submission of a cell list.