Sensing-Based Channel Estimation in 6G mmWave Ultra-Dense Networks

As a key enabler for 6th generation (6G) communications, millimeter-wave (mmWave) ultra-dense network (UDN) has been studied. To utilize beamforming technique in mmWave UDN, accurate channel information is needed. By exploiting the small coverage of a BS in UDN, we can obtain accurate channel information via sensing-based channel estimation. Using sensing images and deep learning technique, the proposed sensing-based channel estimation technique can accurately extract the positions of mobile devices as well as the positions and orientations of wireless entities influencing signal propagation. From simulations, we observe that the proposed scheme achieves more than 52% channel estimation accuracy gain over conventional schemes.