Deep Learning-based mmWave MIMO Channel Estimation using sub-6 GHz Channel Information: CNN and UNet Approaches

Future wireless multiple-input multiple-output (MIMO) systems will integrate both sub-6 GHz and millimeter wave (mmWave) frequency bands to meet the growing demands for high data rates. MIMO link establishment typically requires accurate channel estimation, which is particularly challenging at mmWave frequencies due to the low signal-to-noise ratio (SNR). In this paper, we propose two novel deep learning-based methods for estimating mmWave MIMO channels by leveraging out-of-band information from the sub-6 GHz band. The first method employs a convolutional neural network (CNN), while the second method utilizes a UNet architecture. We compare these proposed methods against deep-learning methods that rely solely on in-band information and with other state-of-the-art out-of-band aided methods. Simulation results show that our proposed out-of-band aided deep-learning methods outperform existing alternatives in terms of achievable spectral efficiency.

Channel Estimation for mmWave MIMO using sub-6 GHz Out-of-Band Information

Future wireless multiple-input multiple-output (MIMO) communication systems will employ sub-6 GHz and millimeter wave (mmWave) frequency bands working cooperatively. Establishing a MIMO communication link usually relies on estimating channel state information (CSI) which is difficult to acquire at mmWave frequencies due to a low signal-to-noise ratio (SNR). In this paper, we propose three novel methods to estimate mmWave MIMO channels using out-of-band information obtained from the sub-6GHz band. We compare the proposed channel estimation methods with a conventional one utilizing only in-band information. Simulation results show that the proposed methods outperform the conventional mmWave channel estimation method in terms of achievable spectral efficiency, especially at low SNR and high K-factor.

Evaluation of stationarity regions in measured non-WSSUS 60 GHz mmWave V2V channels

Due to high mobility in multipath propagation environments, vehicle-to-vehicle (V2V) channels are generally time and frequency variant. Therefore, the criteria for wide-sense stationarity (WSS) and uncorrelated scattering (US) are just satisfied over very limited intervals in the time and frequency domains, respectively. We test the validity of these criteria in measured vehicular 60 GHz millimeter wave (mmWave) channels, by estimating the local scattering functions (LSFs) from the measured data. Based on the variation of the LSFs, we define time-frequency stationarity regions, over which the WSSUS assumption is assumed to be fulfilled approximately. We analyze and compare both line-of-sight (LOS) and non-LOS (NLOS) V2V communication conditions. We observe large stationarity regions for channels with a dominant LOS connection, without relative movement between the transmitting and receiving vehicle. In the same measured urban driving scenario, modified by eliminating the LOS component in the post-processing, the channel is dominated by specular components reflected from an overpassing vehicle with a relative velocity of 56 km/h. Here, we observe a stationarity bandwidth of 270 MHz. Furthermore, the NLOS channel, dominated by a single strong specular component, shows a relatively large average stationarity time of 16 ms, while the stationarity time for the channel with a rich multipath profile is much shorter, in the order of 5 ms.