Deep Learning for Synchronization and Channel Estimation in NB-IoT Random Access Channel

The central challenge in supporting massive IoT connectivity is the uncoordinated, random access by sporadically active devices. The random access protocol and activity detection have been widely studied, while the auxiliary procedures, such as synchronization, channel estimation and equalization, have received much less attention. However, once the protocol is fixed, the access performance can only be improved by a more effective receiver, through more accurate execution of the auxiliary procedures. This motivates the pursuit of joint synchronization and channel estimation, rather than the traditional approach of handling them separately. The prohibitive complexity of the conventional analytical solutions leads us to employ the tools of deep learning in this paper. Specifically, the proposed method is applied to the random access protocol of Narrowband IoT (NB-IoT), preserving its standard preamble structure. We obtain excellent performance in estimating Time-of-Arrival (ToA), Carrier-Frequency Offset (CFO), channel gain and collision multiplicity from a received mixture of transmissions. The proposed estimator achieves a ToA Root-Mean-Square Error (RMSE) of 0.99 us and a CFO RMSE of 1.61 Hz at 10 dB Signal-to-Noise Ratio (SNR), whereas a conventional estimator using two cascaded stages have RMSEs of 15.85 us and 8.05 Hz, respectively.