The standard beam management procedure in 5G requires the user equipment (UE) to periodically measure the received signal reference power (RSRP) on each of a set of beams proposed by the basestation (BS). It is prohibitively expensive to measure the RSRP on all beams and so the BS should propose a beamset that is large enough to allow a high-RSRP beam to be identified, but small enough to prevent excessive reporting overhead. Moreover, the beamset should evolve over time according to UE mobility. We address this fundamental performance/overhead trade-off via a Bayesian optimization technique that requires no or little training on historical data and is rooted on a low complexity algorithm for the beamset choice with theoretical guarantees. We show the benefits of our approach on 3GPP compliant simulation scenarios.

翻译：5G标准中的波束管理流程要求用户设备（UE）定期测量基站（BS）提议的每个波束集合上的接收信号参考功率（RSRP）。对所有波束进行RSRP测量成本过高，因此基站需要在保证足够大的波束集合以识别高RSRP波束的同时，限制集合规模以避免过度的报告开销。此外，波束集合应根据UE移动性随时间动态演进。我们通过一种贝叶斯优化技术来解决这一性能与开销的根本性权衡问题，该技术无需或仅需少量历史数据训练，基于一种具有理论保障的低复杂度波束集合选择算法。我们在符合3GPP规范的仿真场景中展示了该方法的优势。