ML Model Predicts Mobile Network Test Stability
Find Innovative SolutionsGenerate Solutions
Solution Overview
Problem
Current mobile network testing methods require numerous drive testing campaigns to achieve statistically significant results, which is time-consuming and costly, and the training of machine learning models for quality prediction poses additional challenges.
Innovation Solution
A method and system that utilize a testing device connected to a mobile network to run predefined test procedures, gather temporal test metrics, and train a machine learning model to predict a temporal test stability score, simplifying network quality prediction by using a machine learning model that simulates user behavior and evaluates signal strength, SNR, and other metrics.
Engineering Contradictions & Design Principles
Engineering Contradiction Analysis
1Measurement precision
If traditional drive testing campaigns are run to achieve statistically significant results, then measurement precision is improved, but loss of time and productivity deteriorate
Solution Approach 1:
The system performs preliminary actions by continuously collecting and storing network measurement data in advance during normal network operations. This pre-collected data is then used to train machine learning models, eliminating the need for time-consuming dedicated testing campaigns while maintaining statistical significance through the use of historically significant data volumes.
Solution Approach 2:
The system creates a virtual copy of the testing environment by using machine learning models to simulate network conditions and predict test outcomes. Instead of physically running numerous drive testing campaigns, the ML model replicates the testing process virtually, providing statistically significant results without the time cost of actual field tests.
2Measurement precision
If multiple testing campaigns are run to obtain sufficient data for quality evaluation, then measurement precision is improved, but productivity deteriorates
Solution Approach 1:
The system merges multiple data sources and measurement types into a unified machine learning model. By combining various network parameters, user behavior patterns, and historical test results into a single predictive model, the system achieves comprehensive quality evaluation without needing to run separate testing campaigns for each metric, thereby maintaining productivity.
Solution Approach 2:
The system transforms the approach from collecting raw measurement data through multiple campaigns to using engineered features and parameters that capture essential quality aspects. The ML model processes transformed parameters such as aggregated statistics, trend indicators, and composite metrics, achieving accurate quality evaluation with a single integrated testing process.
3Productivity
If machine learning models are trained for quality prediction, then productivity is improved, but device complexity increases
Solution Approach 1:
The system introduces an intermediary layer between raw network measurements and quality predictions. The machine learning model acts as a mediator that processes complex network data and translates it into interpretable quality scores and predictions. This intermediary approach simplifies the overall system by centralizing complexity in the ML model while keeping the interface and data collection mechanisms relatively simple.
Data Source
AI summary
A method of training a test system, including: running a predefined set of test procedures on the testing device in order to obtain a temporal test metric; evaluating the temporal test metric via a machine learning model by a processing circuit; and training the machine learning model by the processing circuit to predict a temporal course of a test stability score based on the temporal test metric obtained, wherein the training of the machine learning model is based on the temporal test metric together with a known binary test result, and wherein the temporal course of the test stability score indicates the probability of a respective binary test result throughout the entire duration of a test. A test system and a method for mobile network testing are also described.