arXivDaily arXiv每日学术速递 周一至周五更新
arXiv 1809.03014cs.ITmath.IT
收藏

用于位置辅助毫米波波束训练的在线学习

Online Learning for Position-Aided Millimeter Wave Beam Training

Vutha Va, Takayuki Shimizu, Gaurav Bansal, Robert W. Heath

AI总结:

针对毫米波波束扫描开销大的问题,本文基于多臂老虎机提出风险感知UCB波束对选择与改进乐观优化波束细化算法,可在线快速学习位置辅助波束并在低训练预算下超过穷举搜索性能。

摘要:

精确的波束对准对于基于波束的毫米波通信至关重要。传统的波束扫描方案通常具有较大的开销,这对于车辆到一切(vehicle-to-everything)等移动应用是不可接受的。利用位置等传感器数据来识别良好波束方向的基于学习的方案,是降低开销的一种途径。然而,大多数现有方案属于监督学习,其训练数据是事先收集的。在本文中,我们使用多臂老虎机框架来开发用于波束对选择和细化的在线学习算法。波束对选择算法学习某个预定义波束码本中的粗略波束方向,例如由3dB波束宽度分隔的离散角度。波束细化则对所识别的方向进行微调,以匹配该位置处功率角谱的峰值。波束对选择采用上置信界(UCB),并加入了一种新提出的风险感知特性;而波束细化则使用一种改进的乐观优化算法。所提出的算法能够快速学习并推荐良好的波束对。当发射机和接收机均使用16×16阵列时,在仅30个波束对的训练预算下,该算法可在100个时间步内,相对于未细化码本上的穷举搜索(在271×271个波束对上进行)平均实现1dB的增益。

英文摘要:

Accurate beam alignment is essential for beam-based millimeter wave communications. Conventional beam sweeping solutions often have large overhead, which is unacceptable for mobile applications like vehicle-to-everything. Learning-based solutions that leverage sensor data like position to identify good beam directions are one approach to reduce the overhead. Most existing solutions, though, are supervised-learning where the training data is collected beforehand. In this paper, we use a multi-armed bandit framework to develop online learning algorithms for beam pair selection and refinement. The beam pair selection algorithm learns coarse beam directions in some predefined beam codebook, e.g., in discrete angles separated by the 3dB beamwidths. The beam refinement fine-tunes the identified directions to match the peak of the power angular spectrum at that position. The beam pair selection uses the upper confidence bound (UCB) with a newly proposed risk-aware feature, while the beam refinement uses a modified optimistic optimization algorithm. The proposed algorithms learn to recommend good beam pairs quickly. When using 16x16 arrays at both the transmitter and receiver, it can achieve on average 1dB gain over the exhaustive search (over 271x271 beam pairs) on the unrefined codebook within 100 time-steps with a training budget of only 30 beam pairs.

机构、总结、中文摘要均由AI分析而来,可能存在错误,请以论文正文为准。

↑