Real-time Prediction of Non-stationary Wireless Channels

Modern wireless systems are increasingly dense and dynamic that makes the channel highly non-stationary, rendering conventional receivers sub-optimal in practice. Predicting the channel characteristics for non-stationary channels has the distinct advantage of pre-conditioning the waveform at the transmitter to match the expected fading profile. The difficulty lies in extracting an accurate model for the channel, especially if the underlying variables are uncorrelated, unobserved and immeasurable. Our work implements this prescience by assimilating the Channel State Information (CSI), obtained as feedback from the receiver, over time and space to adjust the modulation vectors such that the channel impairments are significantly diminished at the receiver, improving the Bit Error Rate (BER). We design a channel recommender, in which an adaptive smoother is used to filter the noise in CSI, while a tensor factorization & completion approach is used to track the ephemeral changes in non-stationary channel statistics by observing the changes in certain measurable parameters. V2X communication is used as an example of non-stationary channels to shows the efficacy of this approach. Overall, the system is shown to operate with a prediction accuracy of 10(-3) MSE even in dense scattering environments over space and time, improving the BER at the receiver by 90% for higher-order modulations.