AI-Assisted MU Pairing for Massive MIMO Scheduling
Find Innovative SolutionsGenerate Solutions
Solution Overview
Problem
The computation complexity of multi-user (MU) scheduling in massive MIMO systems is significantly increased due to the need to support more antennas, UEs per cell, and cells per base station, without changing hardware conditions.
Innovation Solution
A method is introduced where a first network node determines a first retransmission UE and uses a first AI network to generate a MU pairing recommendation result, which is then transmitted to a second network node to assist in MU scheduling, thereby reducing the computation complexity.
Engineering Contradictions & Design Principles
Engineering Contradiction Analysis
1Productivity
If massive MIMO technology is implemented to support more antennas and UEs per cell, then system capacity and coverage are improved, but computation complexity of MU scheduling is significantly increased
Solution Approach 1:
An AI network is introduced as an intermediary component between the physical layer and the MU scheduling function. The AI network processes channel state information and predicts optimal MU pairing configurations, transforming the complex combinatorial optimization problem into a more manageable prediction task that can be solved with lower computational complexity while maintaining high system capacity
Solution Approach 2:
The MU scheduling process is segmented into multiple stages: channel state information collection, AI-based prediction of optimal pairings, and final scheduling decision. This segmentation allows the computationally intensive part to be handled by the AI network separately, reducing the real-time computation burden on the base station processor
2Device complexity
If traditional MU scheduling methods are used without AI assistance, then implementation is simpler, but computation complexity increases with more antennas and UEs
Solution Approach 1:
The traditional mechanical/combinatorial optimization approach for MU scheduling is replaced with an AI-based predictive system. Instead of exhaustively evaluating all possible UE pairings through computational algorithms, the system uses the AI network to predict optimal configurations based on learned patterns from historical data, significantly improving scheduling efficiency
Solution Approach 2:
The AI network performs preliminary analysis of channel conditions and predicts optimal MU pairings in advance before the actual scheduling decision is made. This preliminary action prepares the scheduling information ahead of time, reducing the computational burden during critical real-time scheduling moments
Data Source
AI summary
Embodiments of the present disclosure provide a communication method, a network node, a storage medium and a program product, and relate to fields such as communication and artificial intelligence. In an example method, a first network node determines a first retransmission UE, determines an MU pairing recommendation result using a first AI network based on the first retransmission UE, and transmits the MU pairing recommendation result to a second network node, so that the computation of MU scheduling of the second network node can be assisted, and the computation complexity of MU scheduling of the second network node can be reduced. Optionally, the method performed by a network node can be performed by an artificial intelligence mode