1. What contributions have the authors mentioned in the paper "Learning-based predictive transmitter-receiver beam alignment in millimeter wave fixed wireless access links" ?
Millimeter wave ( mmwave ) fixed wireless access is a key enabler of 5G and beyond small cell network deployment, exploiting the abundant mmwave spectrum to provide Gbps backhaul and access links.. To address this issue, in this paper the authors propose a predictive transmit-receive beam alignment process.. The authors construct an explicit mapping between transmit ( or receive ) beams and physical coordinates via a Gaussian process, which can incorporate environmental uncertainties.. To make full use of underlying correlations between transmitter and receiver and accumulated experiences, the authors further construct a hierarchical Bayesian learning model and design an efficient beam predictive algorithm.. To reduce dependency on physical position measurements, a reverse mapping that predicts physical coordinates from beam experiences is further constructed.. Secondly, in contrast to most existing algorithms that only predict one beam in each timeslot, the designed algorithms generate the most promising beam subset, which improves robustness to environment uncertainties.
read more
2. What is the simplest way to model the change of the elevation angle?
To incorporate external effects in terms of time-dimension, a damped periodical stochastic process is used to model the change of the elevation angle β.
read more
3. How can the authors improve the robustness of a beam?
To improve robustness, instead of predicting and sweeping one single beam, the authors sweep the beams within an interval, which is referred to as beam confidence interval (BCI), i.e.,Icσ = μ(xn+1)− cσ(xn+1), μ(xn+1) + cσ(xn+1) , (12) 3The mean function can be directly parameterized via NNs.
read more
4. What is the way to achieve the goal of obtaining a good performance for the small?
Thanks to the Bayesian learning based design paradigm, the authors can obtain a good and robust performance in terms of both EAR and PSA for the small sample setting.
read more
