发表机构
Institute for Intelligent Networked Systems, Northeastern University; SoftBank Research Institute of Advanced Technology（东北大学智能网络系统研究所; 软银先进技术研究院）
机构由 AI 辅助整理，请以论文原文为准。AI 中文总结
提出NOSTRAdAMUS预测性链路自适应框架，通过预测重传修正MCS选择，在不重新训练下提升吞吐量71.5%并减少重传71.8%。
AI 中文摘要
5G NR中的链路自适应（LA）本质上是反应式的，依赖于信道测量和HARQ反馈，当信道快速变化时，这些信息可能很快过时。这些数据也带有噪声，难以准确跟踪，并且必须馈送给实时控制器，而反馈回路效应难以排查。这解释了为什么大多数实际部署选择简单但稳健的算法，这些算法接受滞后可能导致调度器以过于激进或不必要的保守速率运行，从而以频谱效率换取可预测的性能。在本文中，我们通过NOSTRAdAMUS改进了这一现状，这是一个预测性LA框架，在不替换或重新设计现有算法的情况下为其增加前瞻性。NOSTRAdAMUS根据最近的HARQ历史预测下一个无线帧中是否会发生重传，并对底层策略选择的调制与编码方案（MCS）应用修正。我们基准测试了几种机器学习模型，并表明梯度提升实现了82.9%的总体准确率，高置信度干预的正确率为94.2%，推理延迟为5.5微秒。我们基于在X5G测试平台上通过空中（OTA）收集的数据训练模型，使用开源OpenAirInterface（OAI）5G协议栈、NVIDIA Aerial以及商用现货（COTS）O-RAN无线电单元和用户设备。该模型随后作为dApp部署，我们通过OTA以及在硬件在环信道仿真器的各种信道上进行评估，包括3GPP TDL和CDL信道、SISO和MIMO配置，以及步行和车载移动性。我们的评估表明，在没有重新训练的情况下，跨这些多样场景，该dApp增强了两种SOTA LA算法，将吞吐量提高多达71.5%，同时将重传减少多达71.8%。这证明了我们方法的稳健性和泛化能力。
英文摘要
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.
Comments6 pages, 15 figures
