Gated Recurrent Units for Blockage Mitigation in mmWave Wireless

PROCEEDINGS OF THE INT'L ACM SYMPOSIUM ON MOBILITY MANAGEMENT AND WIRELESS ACCESS, MOBIWAC 2023(2023)

引用 0|浏览3
暂无评分
摘要
Millimeter-Wave (mmWave) communication is susceptible to blockages, which can significantly reduce the signal strength at the receiver. Mitigating the negative impacts of blockages is a key requirement to ensure reliable and high throughput mmWave communication links. Previous research on blockage mitigation has introduced several model and protocol based blockage mitigation solutions that focus on one technique at a time, such as handoff to a different base station or beam adaptation to the same base station. In this paper, we address the overarching problem: what blockage mitigation method should be employed? and what is the optimal sub-selection within that method? To address the problem, we developed a Gated Recurrent Unit (GRU) model that is trained using periodically exchanged messages in mmWave systems. We gathered extensive amount of simulation data from a commercially available mmWave simulator, show that the proposed method does not incur any additional communication overhead, and that it achieves outstanding results in selecting the optimal blockage mitigation method with an accuracy higher than 93%. We also show that the proposed method significantly increases the amount of transferred data compared to several other blockage mitigation policies.
更多
查看译文
关键词
MmWave Wireless,Blockage Mitigation,Recurrent Neural Networks,Deep Learning
AI 理解论文
溯源树
样例
生成溯源树,研究论文发展脉络
Chat Paper
正在生成论文摘要