Machine Learning on Camera Images for Fast mmWave Beamforming
This addresses the slow beamforming issue in mmWave WiFi and 5G systems, offering a significant speed improvement for indoor settings.
The paper tackles the problem of slow beamforming in mmWave bands by using a machine learning approach with two sequential CNNs that leverage camera images to rapidly identify node locations and return the optimal beam pair. The results show a 93% reduction in beamforming exploration time with less than 1% error compared to standard methods.
Perfect alignment in chosen beam sectors at both transmit- and receive-nodes is required for beamforming in mmWave bands. Current 802.11ad WiFi and emerging 5G cellular standards spend up to several milliseconds exploring different sector combinations to identify the beam pair with the highest SNR. In this paper, we propose a machine learning (ML) approach with two sequential convolutional neural networks (CNN) that uses out-of-band information, in the form of camera images, to (i) rapidly identify the locations of the transmitter and receiver nodes, and then (ii) return the optimal beam pair. We experimentally validate this intriguing concept for indoor settings using the NI 60GHz mmwave transceiver. Our results reveal that our ML approach reduces beamforming related exploration time by 93% under different ambient lighting conditions, with an error of less than 1% compared to the time-intensive deterministic method defined by the current standards.