Optimized Usage of Multi-User Diversity to Enhance Spectral Efficiency in (5G) Wireless Networks

Wireless networks keep evolving to handle an increase of the number of users equipment and services. One of the main challenge is to enhance spectral efficiency as it lead to higher throughput and system capacity. Traditional scheduler, such as Maximum Signal-to-Noise Ratio (MaxSNR), Proportional Fair (PF) perform well in specific context, but can be outperformed in others. Moreover, there is many possible scheduler to try in order to find the best ones for diverse contexts. An approach that uses Artificial Intelligence (AI) becomes a conceivable solution. In this paper we introduce a new AI tool that selects and evaluates schedulers that enhance spectral efficiency for different contexts. Our approach is to train the AI model on several traffic load, to evaluate and select schedulers based on a general scheduling formula, resulting in an explainable model for traffic scheduling. After the training, the appropriate scheduler is used for each traffic load conditions. In addition, our tool detects terms of the formula that does not have a positive impact on enhancing spectral efficiency. Simulation results show that the obtained scheduler outperform state of the art algorithms such as RR, MaxSNR and PF.