A Decision-Tree Solution for the Outdated CQI Feedback Problem in 5G Networks

Accurately reporting a Channel Quality Indicator (CQI) value that reflects the current channel condition is crucial for 5G networks. However, the delay between measuring the channel condition and effectively utilizing it by the base station can render the CQI outdated, negatively impacting UE communication. This paper proposes a Decision-Tree solution that considers Signal-to-Interference plus Noise Ratio (SINR) and user context to estimate the updated SINR for translating into a CQI value. While various machine learning (ML) models are proposed in the literature, this study focuses on decision trees, which are explainable artificial intelligence (XAI) models capable of elucidating decision-making processes. The results demonstrate that our solution achieves high accuracy and performance similar to the ideal one, with an absolute difference of only 0.001 in both throughput and spectral efficiency metrics. This underscores the feasibility of our approach in addressing the outdated CQI feedback problem.