Enhanced Machine Learning Techniques for Early HARQ Feedback Prediction in 5G
This work addresses latency and reliability challenges in 5G networks for applications requiring URLLC, presenting an incremental improvement over prior E-HARQ methods by integrating machine learning.
The paper tackles the problem of predicting decoding outcomes early in 5G transmissions to meet ultra-reliable low-latency communication (URLLC) requirements, showing that machine learning-enhanced early HARQ feedback schemes outperform regular HARQ and existing non-ML E-HARQ schemes across various conditions.
We investigate Early Hybrid Automatic Repeat reQuest (E-HARQ) feedback schemes enhanced by machine learning techniques as a path towards ultra-reliable and low-latency communication (URLLC). To this end, we propose machine learning methods to predict the outcome of the decoding process ahead of the end of the transmission. We discuss different input features and classification algorithms ranging from traditional methods to newly developed supervised autoencoders. These methods are evaluated based on their prospects of complying with the URLLC requirements of effective block error rates below $10^{-5}$ at small latency overheads. We provide realistic performance estimates in a system model incorporating scheduling effects to demonstrate the feasibility of E-HARQ across different signal-to-noise ratios, subcode lengths, channel conditions and system loads, and show the benefit over regular HARQ and existing E-HARQ schemes without machine learning.