5G Base Station Mode Selection Using ML for Dual Connectivity
Find Innovative SolutionsGenerate Solutions
Solution Overview
Problem
Current techniques for selecting between dual connectivity and carrier aggregation modes in 5G NR systems are based on static configurations and limited dynamic selection, leading to inefficient resource utilization and lower performance for user equipment.
Innovation Solution
A machine learning computing system is integrated into the radio access network to predict the optimal mode of operation for user equipment based on real-time patterns and needs, dynamically selecting between dual connectivity and carrier aggregation modes using a machine learning model that considers time data, traffic data, and signal quality.
Engineering Contradictions & Design Principles
Engineering Contradiction Analysis
1Productivity
If static configurations are used for mode selection, then device complexity is reduced, but resource utilization efficiency deteriorates
Solution Approach 1:
The patent implements dynamic mode selection between dual connectivity and carrier aggregation based on real-time machine learning predictions of user equipment behavior patterns. The system continuously monitors traffic characteristics, time of day, and network conditions to adaptively switch modes, replacing static configurations with a living, evolving selection mechanism that optimizes resource utilization without requiring overly complex manual configuration.
Solution Approach 2:
The machine learning model enables the network to autonomously predict optimal mode selection based on historical data and patterns. The system self-adjusts without requiring manual intervention by automatically learning from past performance data, traffic characteristics, and user behavior patterns, thereby improving resource utilization while keeping the operational complexity manageable through automation.
2Reliability
If limited dynamic selection is used, then device complexity is reduced, but performance for user equipment deteriorates
Solution Approach 1:
The system incorporates feedback loops where performance data from both dual connectivity and carrier aggregation modes is collected and fed into the machine learning model. This feedback mechanism allows the model to continuously refine its predictions about which mode performs best for specific user equipment, improving reliability through data-driven optimization while managing complexity through automated learning from actual performance outcomes.
Solution Approach 2:
The patent changes key parameters such as selection criteria from static rules to dynamic machine learning predictions based on multiple factors including traffic type, time of day, network load, and user equipment capabilities. This parameter transformation enables the system to adapt to changing conditions and improve user equipment performance without requiring overly complex manual selection mechanisms.
3Productivity
If static mode selection is used, then ease of operation is improved, but throughput and latency performance deteriorate
Solution Approach 1:
The machine learning-based system performs self-service by automatically learning optimal mode selection patterns from historical data and traffic characteristics. This eliminates the need for manual configuration while achieving superior throughput and latency performance through adaptive, data-driven decisions about when to use dual connectivity versus carrier aggregation, thus maintaining ease of operation while dramatically improving performance.
Solution Approach 2:
The patent replaces the mechanical/manual system of static configuration with an intelligent system using machine learning algorithms. This substitution allows the network to automatically analyze traffic patterns, predict optimal modes, and execute selections without human intervention, thereby maintaining operational simplicity while achieving significantly improved throughput and latency performance through sophisticated automated decision-making.
Data Source
AI summary
Systems and methods for machine learning based dynamic selection of dual connectivity or carrier aggregation are provided. In an example, a system includes BBU(s), RU(s) communicatively coupled to the BBU(s), and antenna(s) communicatively coupled to the RU(s). Each respective RU of the RU(s) is communicatively coupled to a respective subset of the antenna(s). The BBU(s), the RU(s), and the antenna(s) are configured to implement a base station for wirelessly communicating with user equipment. The system further includes a machine learning computing system configured to receive time data and traffic data, and determine a predicted mode of operation for a UE based on the time data and the traffic data. Component(s) of the system are configured to receive a request from the UE, and dynamically select a dual connectivity mode or a carrier aggregation mode for operation of the UE based on the predicted mode of operation for the UE.