AI SON Platform Optimizes Mobile Network Cell Antenna Parameters
Find Innovative SolutionsGenerate Solutions
Solution Overview
Problem
Current methods for optimizing mobile network cell performance are labor-intensive and lack scalability, as they require manual adjustments by RF engineers and only consider the impact on individual cells, neglecting neighboring cells, and do not automate optimization across groups of cells.
Innovation Solution
An AI & ML assisted SON platform that receives cell property and performance data to determine if performance thresholds are met, identifies impacted cells, and adjusts antenna parameters to optimize coverage and capacity across groups of cells, ensuring minimal impact on neighboring cells.
Engineering Contradictions & Design Principles
Engineering Contradiction Analysis
1Manufacturing precision
If manual adjustments by RF engineers are used to optimize cell performance, then individual cell performance can be improved, but the process becomes labor-intensive and lacks scalability
Solution Approach 1:
The system enables self-service optimization through automated algorithms that independently analyze cell performance data, identify optimization opportunities, and execute parameter adjustments without requiring manual RF engineer intervention for each cell, thereby maintaining precision while dramatically improving productivity
Solution Approach 2:
The patent replaces the mechanical manual process of RF engineer adjustments with an automated computational system that uses algorithms and software to analyze performance metrics and execute optimizations, eliminating labor-intensive operations while preserving optimization quality
2Ease of operation
If manual optimization methods are used, then adjustments can be made to individual cells, but the impact on neighboring cells is neglected and optimization cannot be automated across groups of cells
Solution Approach 1:
The system merges multiple cells into optimization groups or clusters, allowing simultaneous optimization of neighboring cells while considering their interdependencies. This approach maintains operational simplicity by treating groups as unified entities while achieving comprehensive automation across the network
3Manufacturing precision
If RF engineers manually tune each antenna, then individual cell coverage can be optimized, but the process is labor intensive and does not scale to thousands of cells
Solution Approach 1:
The system segments the large-scale network optimization problem into manageable cell groups that can be processed independently and in parallel. This segmentation allows the automated system to handle thousands of cells efficiently while maintaining the precision of individual antenna tuning through algorithmic analysis
Data Source
AI summary
A device may receive cell property data associated with a cell in a mobile network and performance data associated with the cell. The device may determine whether the performance data associated with the cell satisfies a performance threshold. The device may identify, based on determining that the performance data associated with the cell satisfies the performance threshold, one or more impacted cells, in the mobile network, associated with the cell. The device may determine one or more antenna adjustment parameters based on at least the cell property data associated with the cell, the performance data associated with the cell, and performance data associated with the one or more impacted cells. The device may perform, based on the one or more antenna adjustment parameters, an action in connection with at least one of an antenna associated with the cell or another antenna associated with the one or more impacted cells.