Toward Deterministic Wireless Communication: Latency Prediction Using Network Measurement Data

Deterministic latency communication is the foundation of many emerging applications in the fifth generation wireless communication. In addition to latency reduction techniques, it is important for operators to estimate to what extent deterministic latency can be achieved in network systems. As a step toward deterministic wireless communication, this work aims to develop techniques for predicting radio access network (RAN) latency using network measurement data. We leverage machine learning algorithms to construct models that capture the relationship between network latency and RAN risk factors. Our results demonstrate the potential of data-driven approaches for facilitating deterministic communication, while future work is needed regarding adaption of our proposed methods into practically relevant scenarios and model robustness analysis.