ML Load Distribution for Overlapping RAN Cells
Find Innovative SolutionsGenerate Solutions
Solution Overview
Problem
Current load management schemes in Radio Access Networks (RAN) fail to efficiently distribute traffic among overlapping cells, leading to suboptimal user throughput and performance, as they do not account for the performance of individual cells.
Innovation Solution
A machine learning-based load management system that processes input data to determine recommended load distribution parameters, optimizing user throughput by considering the performance models of individual cells and distributing traffic accordingly to maximize aggregated user throughput.
Engineering Contradictions & Design Principles
Engineering Contradiction Analysis
1Stability of the object's composition
If load management schemes distribute traffic to equalize load among cells, then load balance is improved, but user throughput performance deteriorates
Solution Approach 1:
The system changes the parameters used for load distribution from simple load metrics to performance models that predict user throughput. By using performance models that incorporate cell-specific parameters and user equipment characteristics, the system optimizes traffic distribution to maximize aggregate user throughput rather than merely equalizing load across cells.
2Productivity
If machine learning models are used to optimize load distribution, then user throughput is improved, but system complexity increases
Solution Approach 1:
The system performs preliminary actions by pre-training machine learning models using historical data and performance models before actual load distribution. The models are trained offline on training sets that include cell characteristics, user equipment data, and observed performance metrics. This preliminary training enables the models to make accurate predictions during operation without requiring complex real-time computations.
Solution Approach 2:
The system uses performance models that create simplified representations or copies of complex cellular network behaviors. These performance models capture the essential relationships between load distribution and user throughput without requiring full simulation of the entire network, thereby reducing computational complexity while maintaining optimization effectiveness.
Data Source
AI summary
Systems, methods, and software for load management among a plurality of cells that overlap a sector within a Radio Access Network (RAN). In one embodiment, a system receives, at a machine learning system, input data for a sector of the RAN having a plurality of cells overlapping at the sector. The system processes the input data at the machine learning system to determine recommended load distribution parameters for the sector based on a machine learning model, where the recommended load distribution parameters are configured to maximize an aggregated user throughput of the sector. The system applies the recommended load distribution parameters in the sector to distribute users among the cells.