Title: Machine Learning Based Channel Prediction for UAV Communications in Urban Environments
Time: 2019.07.31 15:00
Venue: 物联网科技园大楼西五楼物联网研究院 会议室
Speaker: Dr. Gan Zheng, Loughborough University, UK
Low-altitude small unmanned aerial vehicles (UAV) provide a promising alternative communications solution to boost mobile coverage and connectivity. However, one of the foremost challenges of using UAVs for reliable communications is to predict the channel information between an arbitrary UAV location in the air and a node on the ground, especially in urban environments.
In this talk, I will introduce machine learning based approaches to predict the air to ground channel in urban environments. First, given a probabilistic channel model, neural networks are used to predict channel model parameters based on the received signal strength data. Next, when there is no prior information about the channel model, Gaussian Process is employed to predict the channel information based on measurement. Both methods can keep refining channel prediction and UAV trajectory planning as more measurement data are obtained. Numerical results will be presented to demonstrate the performance of the proposed approaches.
Bio:Dr. Gan Zheng is currently Reader of Signal Processing for Wireless Communications in the Wolfson School of Mechanical, Electrical and Manufacturing Engineering, Loughborough University, UK. He received the PhD degree in Electrical and Electronic Engineering from The University of Hong Kong in 2008. His research focus on signal processing for 5G and beyond wireless networks, with current emphasis on edge caching, UAV communications, and artificial intelligence for wireless communications. He has published over 100 papers in international journals and conferences with more than 5000 citations. He received six international best paper awards. Currently he serves as an Associate Editor for IEEE Communications Letters.
郑淦博士现为英国拉夫堡大学副教授，他的研究主要关注于无线通信网络的信号处理和网络资源优化技术，目前研究方向为边缘缓存、 无人机通信以及人工智能在通信系统中的应用。他在权威国际学术期刊和主要国际会议上发表学术论文 100余篇， Google Scholar 引用超过5000次。他6次获得IEEE最佳论文奖,现担任IEEE Communications Letters编委。