Generative Adversarial Estimation of Channel Covariance in Vehicular Millimeter Wave Systems
By Xiaofeng Li, Ahmed Alkhateeb, Cihan Tepedelenlioglu. 2018
43 citations recorded by the source corpus.
Enabling highly-mobile millimeter wave (mmWave) systems is challenging because of the huge training overhead associated with acquiring the channel knowledge or designing the narrow beams. Current mmWave beam training and channel estimation techniques do not normally make use of the prior beam training or channel estimation observations. Intuitively, though, the channel matrices are functions of the various elements of the environment. Learning these functions can dramatically reduce the training overhead needed to obtain the channel knowledge. In this paper, a novel solution that exploits machine learning tools, namely conditional generative adversarial networks (GAN), is developed to learn these functions between the environment and the channel covariance matrices. More specifically, the proposed machine learning model treats the covariance matrices as 2D images and learns the mapping function relating the uplink received pilots, which act as RF signatures of the environment, and these images. Simulation results show that the developed strategy efficiently predicts the covariance matrices of the large-dimensional mmWave channels with negligible training overhead.
How researchers see this paper
The researchers whose trusted networks rank it highest, strongest advocate first. Every researcher gets a different order.
- Jihong Park
- Medhi Bennis
- Sumudu Samarakoon
- Merouane Debbah
- Abdelrahman Taha
- Muhammad Alrabeiah
- Mingzhe Chen
- Ahmed Alkhateeb
Citations in the corpus
- Wireless Network Intelligence at the Edge (2018, methodology): “To overcome mmWave’s link sensitivity to blockage [23], a GAN-aided long-term channel estimation [24] and a reinforcement learning (RL)-based beam alignment technique [25] were proposed.”
- DeepMIMO: A Generic Deep Learning Dataset for Millimeter Wave and Massive MIMO Applications (2019, background): “Examples include predicting the beamforming and channel matrices based on the user RF signature [11], [12], or based on the user location [14], [22], [23] and predicting the future blockage based on the sequence of previously selected beams [15].”
- Enabling Large Intelligent Surfaces With Compressive Sensing and Deep Learning (2019, methodology): “Deep learning solutions have been proposed in the literature for addressing design challenges in mmWave and massive MIMO systems [18]–[20].”