Cell Positioning Anomaly Detection From Distance and Azimuth Data
Find Innovative SolutionsGenerate Solutions
Solution Overview
Problem
Cellular Service Providers face inaccuracies in documenting antenna configuration parameters due to human error and environmental factors, leading to issues like increased latency, decreased coverage, and inefficient system planning.
Innovation Solution
A computer system employs a machine learning model to analyze control plane signaling data, calculating distance and azimuth values for each cell and generating classifications to detect anomalies, using GPS location information and communication timing data to improve accuracy.
Engineering Contradictions & Design Principles
Engineering Contradiction Analysis
1Productivity
If manual installation and configuration of radio antennas is performed, then deployment can be completed, but human errors occur leading to incorrect configuration parameters
Solution Approach 1:
The system performs self-diagnosis by automatically detecting and verifying antenna configuration parameters against actual physical conditions. The anomaly detection system compares reported configuration data with measured values from multiple sources (MDT reports, drive tests, network measurements) to identify and correct errors without manual intervention, enabling the network to self-verify and self-correct configuration accuracy.
Solution Approach 2:
The system implements continuous feedback loops where configuration parameters are monitored, measured, and verified in real-time. Multiple measurement sources provide feedback on actual antenna positioning and coverage, which is compared against configured values. When discrepancies are detected, the system generates alerts and enables corrective actions, creating a closed-loop system that maintains configuration accuracy.
2Productivity
If configuration parameters are not verified, then system operation continues without interruption, but errors in parameters lead to decreased coverage and increased latency
Solution Approach 1:
The system performs preliminary verification of configuration parameters before they cause performance degradation. By continuously monitoring and detecting anomalies in antenna positioning and coverage patterns, the system identifies configuration errors early in their development, allowing corrective actions to be taken before they significantly impact network performance, coverage, or latency.
Solution Approach 2:
The patent replaces manual mechanical verification methods (physical inspection, manual testing) with automated electronic detection systems. The anomaly detection system uses software-based analysis of network measurements, MDT reports, and signal data to automatically verify configuration parameters, substituting human-operated mechanical processes with automated computational methods that provide continuous, real-time verification without interrupting network operations.
3Measurement precision
If manual checking of towers and antennas is performed to detect errors, then anomaly detection is possible, but the process is time-consuming and limited to small areas
Solution Approach 1:
The anomaly detection system serves multiple functions simultaneously: it monitors configuration parameters, analyzes coverage patterns, detects positioning anomalies, validates antenna orientations, and generates corrective recommendations all through a single integrated platform. The system processes data from multiple sources (MDT reports, drive tests, network measurements) and performs multiple types of analyses concurrently, making the detection process both comprehensive and efficient without requiring separate manual procedures for each verification task.
Solution Approach 2:
The system transitions from two-dimensional manual inspection (physical presence at tower locations) to multi-dimensional automated analysis by incorporating data from multiple spatial and temporal sources. It analyzes MDT reports from numerous user devices across wide geographic areas, combines drive test data from multiple routes and times, and processes network measurement data from various network elements, creating a comprehensive multi-dimensional view of antenna performance that vastly exceeds the coverage and resolution of manual checking.
4Reliability
If existing detection methods are used, then some anomalies can be detected, but they struggle to address errors effectively across large networks
Solution Approach 1:
The system segments the large-scale network into manageable analysis units by processing configuration data and measurements for individual cells, antenna groups, or geographic regions separately. The anomaly detection algorithm analyzes each segment independently, comparing local configuration parameters against local measurement data, then aggregates results to provide comprehensive network-wide coverage. This segmentation enables the system to handle large networks efficiently while maintaining high detection accuracy for each individual component.
Data Source
AI summary
A method for detecting cell positioning anomalies is disclosed. Control plane signaling data packets are collected associated with multiple cells of a communications network. Distance and azimuth values for individual communication sessions are calculated for each cell. A machine learning model is executed using various communication parameters as input to generate a classification for each cell. A list identifying which cells are experiencing anomalies is generated.