MU-MIMO User Selection via Server Inference
Find Innovative SolutionsGenerate Solutions
Solution Overview
Problem
There is a lack of effective data collection and learning data usage methods for implementing machine learning to infer optimal user selection in Multi-User Multi Input Multi Output (MU-MIMO) communication.
Innovation Solution
A communication device is designed to transmit specific information to a server for inference, including channel matrix information, throughput, CQI, delay, packet loss rate, location, and radio wave conditions, to determine optimal user selection for MU-MIMO communication.
Engineering Contradictions & Design Principles
Engineering Contradiction Analysis
1Productivity
If machine learning is used to determine user selection in MU-MIMO communication, then communication quality and efficiency are improved, but there is a lack of effective data collection and learning data usage methods
Solution Approach 1:
The patent applies preliminary action by collecting communication data in advance during normal MU-MIMO operations. The access point continuously gathers channel state information, user equipment data, and communication outcomes, storing them as a dataset before machine learning model training. This pre-collected data serves as the foundation for subsequent model learning and inference, enabling optimal user selection without requiring complex real-time data collection mechanisms during critical communication phases.
Solution Approach 2:
The patent introduces an intermediary machine learning model that acts as a mediator between raw communication data and user selection decisions. The model is trained offline using collected data and then deployed to infer optimal user selections during MU-MIMO communication. This intermediary approach separates the complex data processing from real-time communication, simplifying the overall system architecture while maintaining high communication efficiency.
2Measurement precision
If comprehensive communication data is collected for machine learning inference, then user selection accuracy is improved, but information transmission overhead increases
Solution Approach 1:
The patent applies the extraction principle by selectively collecting only the most relevant communication data elements needed for machine learning inference. Instead of transmitting all possible communication parameters, the system extracts key features such as channel state information, user equipment capabilities, and historical communication outcomes. This selective extraction maintains user selection accuracy while minimizing information transmission overhead and avoiding unnecessary data processing.
Data Source
AI summary
A communication device performs transmitting, to a server, part or all of information being included in a user selection request, wherein the request requests an inference of quality of communication between the communication device and another communication device in accordance with user selection in Multi-User Multi Input Multi Output (MU-MIMO) communication, acquiring a result of the inference by the server from the server, and preforming MU-MIMO communication with the other communication device based on information acquired from the server.