The performance of millimeter-wave (mmWave) and sub-terahertz (sub-THz) communication systems is significantly impaired by sensitivity to sudden blockages. In this work, we employ machine learning (ML) and our physics-based simulation tool to warn about the upcoming blockage tens of 5G frames ahead for highway speeds, providing a sufficient time for a proactive response. Performance of this ML-aided early-warning-of-blockage (ML-EW) algorithm is analyzed for realistic outdoor mobile environments with diverse reflectors and antenna arrays placed at the base station (BS) and user equipment (UE) over a range of mmWave and sub-THz frequencies. ML accuracy of about 90% or higher is demonstrated for highway UE, blocker, and reflector speeds, multiple-input-multiple-output (MIMO) systems, and frequencies in the mmWave/sub-THz range.

Code diversity integrates space-time coding with beamforming by using a small number of feedback bits to select from a family of space-time codes. Different codes lead to different induced channels at the receiver, where Channel State Information (CSI) is used to instruct the transmitter how to choose the code. Feedback can be combined with sub-optimal low complexity decoding of the component codes to match Maximum-Likelihood (ML) decoding performance of any individual code in the family. It can also be combined with ML decoding of the component codes to improve performance beyond ML decoding performance of any individual code. Prior analysis of code diversity did not take into account the effect of the mobile speed and the delay in the feedback channel. This paper demonstrates the practicality of code diversity in space-time coded systems by showing that performance gains based on instantaneous feedback are largely preserved when long-range prediction of time-varying correlated fading channels is employed to compensate for the effect of the feedback delay. To maintain prediction accuracy for realistic SNR, noise reduction that employs oversampled pilots is used prior to fading prediction. We also propose a robust low pilot rate method that utilizes interleaving to improve the spectral efficiency. Simulations are presented for two channel models: the conventional Jakes model and a realistic physical channel model where the parameters associated with the reflectors vary in time and the arrival rays have different strengths and asymmetric arrival angles.

The long range fading prediction algorithm for Slow Frequency Hopping (SFH) systems is proposed and demonstrated to enable combined adaptive modulation and adaptive frequency diversity to mitigate the effects of fading and partial-band interference. Significant performance gains are demonstrated relative to non-adaptive methods in realistic mobile radio SFH channels where the total bandwidth does not exceed approximately 15 times the coherence bandwidth.

Adaptive orthogonal frequency division multiplexing (AOFDM) modulation is a promising technique for achieving high data rates required for wireless multimedia services. To accomplish efficient adaptive channel loading, the channel state information (CSI) needs to be fed back to the transmitter. Since the fading channel varies rapidly for fast vehicle speeds, long range fading prediction (LRP) is required for mobile radio AOFDM to insure reliable adaptation. We use past channel observations to predict future CST and perform adaptive bit and power allocation for the OFDM system. We derive the minimum mean-square-error (MMSE) long-range channel prediction that utilizes the time and frequency domain correlation functions of the Rayleigh fading channel. Since the channel statistics are usually unknown, robust prediction methods that do not require the knowledge of the correlation functions are developed. Statistical model of the prediction error is created and used in the design of reliable adaptive modulation. In addition, several methods that significantly reduce the feedback load for mobile radio AOFDM systems are developed and compared. We use a standard sum-of-sinusoids model and our realistic physical model to validate performance of proposed methods. Simulation results demonstrate reliable performance and robustness of the proposed techniques, thus validating feasibility of AOFDM for rapidly varying mobile radio channels

Adaptive transmission techniques, such as adaptive modulation and coding, adaptive power control, adaptive transmitter antenna diversity, etc., generally require precise channel estimation and feedback of channel state information (CSI). For fast vehicle speeds, reliable adaptive transmission also requires long-range prediction of future CSI, since the channel conditions are rapidly time variant. In this paper, we propose using past channel observations of one carrier to predict future CSI and perform adaptive modulation without feedback for another correlated carrier. We derive the minimum mean-square error (MMSE) long-range channel prediction that uses the time- and frequency-domain correlation function of the Rayleigh fading channel. An adaptive MMSE prediction method is also proposed. A statistical model of the prediction error that depends on the frequency and time correlation is developed and is used in the design of reliable adaptive modulation methods. We use a standard stationary fading channel model (Jakes model) and a novel physical channel model to test our algorithm. Significant gains relative to nonadaptive techniques are demonstrated for sufficiently correlated channels and realistic prediction range.

Previously, the authors introduced a novel algorithm for long range prediction of flat fading channels that can reliably predict future fading coefficients far beyond the coherence time. This prediction capability provides enabling technology for power and bandwidth efficient adaptive modulation and coding methods. In this paper, we extend our results to the direct sequence code division multiple access (DS/CDMA) channels. It is demonstrated that frequency selective channels encountered in CDMA can also be predicted far ahead, and that the proposed prediction methods can be combined with RAKE receivers. In addition, we utilize prediction to improve performance of the selective transmitter diversity system proposed for the third generation CDMA.