Abstract
To solve the complex beam alignment issue in non-line-of-sight (NLOS) millimeter wave communications, this paper presents a deep neural network (DNN) based procedure to predict the angle of arrival (AOA) and angle of departure (AOD) both in terms of azimuth and elevation, i.e., AAOA/AAOD and EAOA/EAOD. In order to evaluate the performance of the proposed procedure under practical assumptions, we employ a trajectory prediction method by considering dynamic window approach (DWA) to estimate the location information of the user equipment (UE), which is utilized as the input parameter of the trained DNN to generate the prediction of AAOA/AAOD and EAOA/EAOD. The robustness of the prediction procedure is analyzed in the presence of prediction errors, which proves that the proposed DNN is a promising tool to predict AOA and AOD in NLOS scenarios based on the estimated UE location. Simulation results shows that the prediction errors of the AOA and AOD can be maintained within an acceptable range of ±2°.
Highlights
T HE explosive demand in users’ mobile data experience makes an increasing strain on the network’s use of the available wireless spectrum
We first predict the angle of arrival (AOA) and angle of departure (AOD) with the trained deep neural network (DNN) using some of given user equipment (UE) locations
We evaluate the performance of the predication algorithm in the presence of errors showing its robustness
Summary
T HE explosive demand in users’ mobile data experience makes an increasing strain on the network’s use of the available wireless spectrum. We create a NLOS simulation model to generate the datasets, consisting of received power, location, and the number of clusters from raw data obtained by Kmeans, which is used to train a DNN without UE monility prediction. This trained DNN is used to estimate the AOA and AOD in given positions. With the dataset including, received power, location, and the number of clusters from raw data obtained by K-means, the trained neural network can predict the AOA/AOD of NLOS beams in the azimuth and elevation.
Talk to us
Join us for a 30 min session where you can share your feedback and ask us any queries you have