Predicting retransmissions to improve 5G link adaptation accuracy
Improving 5G AI-RAN MCS Selection by Predicting Retransmissions
Networking and Internet ArchitectureArtificial Intelligence
Summary
5G wireless connections often struggle because they react slowly to changing signal conditions, which can cause slow or interrupted data transfers. The authors created a system called NOSTRAdAMUS that predicts if a message will need to be resent soon, allowing the network to adjust settings ahead of time. This approach improves data speed and reduces wasted transmissions without replacing existing methods. They tested their system on real hardware and simulations, showing it works well in different environments and speeds.
What this means in practice
- •For cellular network operators: Deploy network controllers that predict retransmissions and adjust 5G data rates proactively to boost throughput and reliability in real deployments.
- •For wireless hardware testers: Use a predictive retransmission model integrated into testing setups with channel emulators to measure improvements in 5G adaptive rate controls.
Authors
Tamerlan Aghayev, Maxime Elkael, Michele Polese, Reshma Prasad, Salvatore D'Oro, Yunseong Lee, Koichiro Furueda, Tommaso Melodia
Abstract
Link Adaptation (LA) in 5G NR is inherently reactive, relying on channel measurements and HARQ feedback that may become quickly obsolete when the channel changes quickly. This data is also noisy, making it hard to track accurately, and has to be fed to real-time controllers with feedback-loop effects which are hard to troubleshoot. This explains why most practical deployments select simple but robust algorithms, which accept that the lag can leave the scheduler operating at overly aggressive or unnecessarily conservative rates, trading spectrum efficiency for predictable performance. In this paper, we improve on this status-quo with NOSTRAdAMUS, a predictive LA framework which adds foresight to existing algorithms without replacing or redesigning them. NOSTRAdAMUS predicts whether a retransmission will occur in the next radio frame from recent HARQ history, and applies corrections to the Modulation and Coding Scheme (MCS) selected by the underlying policy. We benchmark several ML models and show that Gradient Boosting achieves 82.9% accuracy overall with high-confidence interventions that are correct 94.2% of the time, and an inference latency of 5.5 μs. We train the model based on data collected Over-the-Air (OTA) on the X5G testbed, using the open-source OpenAirInterface (OAI) 5G stack, NVIDIA Aerial, and COTS O-RAN Radio Units and User Equipments. The model is then deployed as a dApp, which we evaluate OTA as well as on various channels with hardware-in-the-loop channel emulators. This includes 3GPP TDL and CDL channels, SISO and MIMO configurations, and pedestrian and vehicular mobility. Our evaluation shows that without retraining, and across this variety of scenarios, the dApp augments two SOTA LA algorithms, and increases goodput by up to 71.5% while reducing retransmissions by up to 71.8%. This demonstrates the robustness and generalization capabilities of our approach.