The advent of fifth generation communication networks has led to novel opportunities and problems that were absent in legacy networks. Stringent line-of-sight demands necessitated by fast attenuating nature of millimeter waves (mmWave) through obstacles, pose to be one of the central problems of the field. mmWave links are easily disrupted due to obstacles, both static and dynamic. Handling static obstacles is easy, while dynamic obstacles are usually tracked by expensive additional hardware like cameras and radars, which undoubtedly lead to increased deployment costs. In this manuscript, we propose a novel approach to estimate the trajectories of multiple dynamic obstacles in an ultra dense mmWave network, solely based on link failure information, without resorting to any specialized tracking hardware. We keep a track of link failures over a short window of time and use that knowledge to extrapolate the trajectories of dynamic obstacles. After proving its NP-completeness, we employ a greedy set cover based approach for this. We then use the obtained trajectories to tag upcoming links as per their blockage possibility. We simulate on real world data to validate our approach based on its accuracy, sensitivity, and precision. Our approach is also shown to outperform an existing one.

翻译：第五代通信网络的出现带来了传统网络中不存在的新机遇与挑战。毫米波信号因穿透障碍物时快速衰减的特性，对通信链路提出严格的视距要求，这已成为该领域的核心问题之一。静态与动态障碍物均易导致毫米波链路中断。处理静态障碍物相对简单，而动态障碍物通常需借助摄像头、雷达等昂贵附加硬件进行追踪，这无疑增加了部署成本。本文提出一种新颖方法，仅基于链路失效信息即可在超密集毫米波网络中估计多个动态障碍物的运动轨迹，无需任何专用追踪硬件。我们通过短时间窗口内的链路失效记录，利用这些知识外推动态障碍物的轨迹。在证明该问题的NP完全性后，采用基于贪心集合覆盖的方法进行求解。随后利用所得轨迹对即将接入的链路进行阻塞可能性标注。基于真实数据的仿真实验验证了该方法在准确性、灵敏度和精度方面的表现，且性能优于现有方案。