Cellular Network Parameter Optimization via Temporal Data Partitioning
Find Innovative SolutionsGenerate Solutions
Solution Overview
Problem
The operation and management of cellular networks are complex, leading to high operating expenditures due to the need for continuous monitoring of Key Performance Indicators (KPIs) and Key Quality Indicators (KQIs across thousands of base stations, which often relies on manual optimization and trial-and-error methods, resulting in sub-optimal performance.
Innovation Solution
A method that partitions configuration management data into distinct time intervals, identifies temporal points of interest based on configuration changes, and performs regression analysis to determine the impact of features on target KPIs, utilizing AI-based CM solutions to automate parameter optimization and recommend optimal settings.
Engineering Contradictions & Design Principles
Engineering Contradiction Analysis
1Reliability
If manual optimization and trial-and-error methods are used for parameter configuration, then operators can continuously monitor and adjust KPIs, but operating expenditures increase and optimization efficiency decreases
Solution Approach 1:
The system enables self-service through automated parameter optimization where the network system itself performs configuration adjustments based on monitored KPIs and machine learning predictions, eliminating the need for continuous manual intervention while maintaining or improving network performance
Solution Approach 2:
Manual mechanical optimization processes are replaced with an automated electronic system that uses machine learning models, regression analysis, and algorithmic decision-making to determine optimal parameter configurations, significantly improving optimization efficiency
2Reliability
If manual optimization methods are used, then operators can adjust parameters, but the process becomes time-consuming and results in sub-optimal performance
Solution Approach 1:
The system performs preliminary action by pre-calculating optimal parameter configurations using historical data and machine learning models before actual network conditions change, allowing rapid deployment of optimized settings without time-consuming manual analysis
Solution Approach 2:
Time-consuming manual trial-and-error processes are replaced with automated machine learning-based prediction systems that can evaluate multiple parameter configurations and identify optimal settings in minutes rather than hours or days
3Reliability
If continuous monitoring of KPIs across thousands of base stations is performed manually, then service quality can be maintained, but operating expenditures increase
Solution Approach 1:
The system implements self-service monitoring where automated agents continuously collect, analyze, and report KPI data from thousands of base stations without human intervention, maintaining service quality while eliminating the operational complexity of manual monitoring across the entire network
Solution Approach 2:
A universal automated monitoring platform is deployed that can simultaneously track multiple KPIs across thousands of base stations using standardized protocols and interfaces, reducing operational complexity by consolidating what would otherwise require multiple specialized manual processes
Data Source
AI summary
A method includes partitioning a set of configuration management (CM) data for one or more cellular network devices into multiple distinct time intervals. The method also includes determining one or more temporal points of interest in each time interval based on whether CM changes exist during that time interval. The method also includes, for each temporal point of interest in each time interval, identifying a first set of data samples before that temporal point of interest and a second set of data samples after that temporal point of interest, and averaging features and a target key performance indicator (KPI) in the first set of data samples and in the second set of data samples. The method also includes performing regression analysis to determine an impact of the features on the target KPI.