For the future millimeter wave (mmWave) systems, communication using massive antennas has been considered for exploiting the large scale antenna array gain enabled by the decrease in wavelength. Hybrid beamforming (HBF) is a promising technology to balance between the hardware constraints and achievable data rate for the mmWave systems. However, precise beamforming is required since the beam width is very narrow as the number of antennas increases in such mmWave systems. This requires a high computational complexity and makes to apply HBF even harder as the number of users increases. To address this problem, we propose a deep reinforcement learning (DRL) based HBF design for multi-user multiple-input single-output (MU-MISO) systems. Simulation results show that the proposed DRL adopting a dueling architecture based HBF enhances the average throughput compared to the existing supervised learning (SL) based algorithms. In addition, the average throughput maintains competitive performance compared to unconstrained conditions without quantization loss and unsupervised learning (USL) based schemes.

For the future wireless communication systems, millimeter wave (mmWave) frequency bands have been considered as an attractive candidate since the bands can meet high data rate requirements by utilizing a broadband spectrum. However, transmitting signals over the long distances is difficult in the bands compared to typical microwave bands due to the property of mmWave’s intense straightness, which leads densely deployed mmWave base stations (BSs). The probability that user equipments (UEs) experience frequent handover (HO) also increases as the number of BSs increases. Therefore, an elaborate HO strategy is required since inadequate HO leads frequent ping-pong or radio link failure (RLF) which is critical for the communication link quality. Meanwhile, 3GPP introduced conditional handover (CHO) in Release 16. Since CHO allows UEs to decide whether to carry out HO or not, CHO is different from the legacy HO method. By focusing on this potential of CHO, we propose a novel CHO management scheme based on a deep reinforcement learning (DRL) for mmWave systems to balance HO rates and a spectral efficiency in this paper. The simulation results show that the proposed DRL based-CHO scheme has superior performance compared to the conventional hysteresis-based HO decision.

This paper investigates the simulation performances of vehicle-to-anything (V2X) communications based on the IEEE 802.11p wireless access in vehicular environments (WAVE) system in practical small-scale fading models. The main contributions of this paper are as follows. First, we modify the experimental fading models reported by Georgia Institute of Technology to be applied to the computer simulation of V2X communications. Second, an enhanced linear minimum mean square error smoothing-aided decision directed (LSA-DD) channel estimator is proposed to track the time variation of fading channels and mitigate noise enhancement.

In this paper, we propose a new digital duplexing scheme, called synchronous digital duplexing (SDD), which can increase data efficiency and flexibility of resource by transmitting uplink signal and downlink signal simultaneously in wireless communication. In order to transmit uplink and downlink signals simultaneously, the proposed SDD obtains mutual information among subscriber stations (SSs) with a mutual ranging symbol. This information is used for selection of transmission time, decision on cyclic suffix (CS) insertion, determination of CS length, and re-establishment of FFT starting point. It is shown that in terms of efficiency and flexibility the proposed SDD is better equipped as a duplexing scheme for indoor wireless environments than conventional time division duplexing (TDD) and frequency division duplexing (FDD).

In this paper, we propose an efficient estimation technique for time-varying multipath channels by exploiting two dimensional delay-time nature in pilot inserted orthogonal frequency division multiplexing (OFDM) systems. The proposed technique consists of multipath snapshot estimation at periodic channel observation instances over an OFDM block and the linear interpolation of two consecutive multipath snapshots. Two decision-directed data utilizing schemes, data removed and data added correlation schemes, are proposed to enhance the performance of the multipath snapshot estimation.

In this paper, an enhanced time-domain cancellation method is proposed for inter-carrier interference (ICI) reduction in OFDM systems. The conventional time-domain cancellation does not work well in deep fades. In order to supplement the conventional method, the simple repetition (de-)coding and the modulation order increasing are employed in the time-domain cancellation. The approximated repetition decoding provides reliable symbols in the regeneration operation, and the increased modulation order maintains the spectral efficiency. Simulation results indicate that the proposed method using 16QAM significantly improves the BER performance compared to the conventional method using QPSK, while maintains the spectral efficiency. Moreover, the proposed method using 64QAM concurrently improves both the BER performance and the spectral efficiency.

In this paper, we investigate the conventional windowed DFT-based channel estimation for OFDM systems with guard bands. The conventional method suffers from the edge effect and the pilot position mismatch. In order to solve the problems, we propose an enhanced DFT-based channel estimation using virtual interpolation with guard bands prediction, where linear minimum mean square error (LMMSE) smoothing/prediction and circular frequency shifting are employed. This technique can efficiently mitigate the edge effect caused by the DFT of the truncated channel impulse response and compensate the pilot position mismatch that pilot symbols are not allocated at the first and the last subcarriers in a useful band. Simulation results show that the proposed method has about 5 dB SNR gain at BER=10-3compared to the conventional method and is as good as the frequency-domain LMMSE method

A two-dimensional pilot-symbol aided (2-D PSA) channel estimation technique for coherent orthogonal frequency-division multiplexing (OFDM) systems with transmitter diversity is proposed. The 2-D PSA channel estimator and the corresponding orthogonality condition of the set of pilot symbols are derived under minimum mean-square error (MMSE) criterion for OFDM systems with transmitter diversity. The proposed estimator is shown to be accurate and effective for tracking variations of channels between multiple transmitter antennas and receiver antennas.

We propose an efficient channel estimation technique for orthogonal frequency-division multiplexing (OFDM) systems with transmitter diversity. The proposed technique estimates uniquely all channel frequency responses needed in space-time coded OFDM systems using "comb-type" training symbols. The computational complexity of the proposed technique is reduced dramatically, compared with the previous minimum mean-squared error (MMSE) technique, due to the all the processing being done in the frequency-domain. Also, several other techniques for mitigating the random noise effect and tracking channel variation are discussed to further improve the performance of the proposed approach. The performances of the proposed approach are demonstrated by computer simulation for mobile wireless channels.

A loss of subchannel orthogonality due to time-variant multipath channels in orthogonal frequency division multiplexing (OFDM) systems leads to interchannel interference (ICI) which increases the error floor in proportion to the Doppler frequency. A simple frequency-domain equalization technique which can compensate for the effect of ICI in a multipath fading channel is proposed. In this technique, the equalization of the received OFDM signal is achieved by using the assumption that the channel impulse response (CIR) varies in a linear fashion during a block period and by compensating for the ICI terms that significantly affect the bit-error rate (BER) performance.

In this paper, an equalization technique for OFDM and MC-CDMA systems in a time-varying multipath fading environment is described. A loss of subchannel orthogonality due to time-variation of multipath channels leads to interchannel interference (ICI) which increases the error floor in proportion to Doppler frequency. A simple frequency domain equalizer which can compensate the effect of time-variation in a multipath fading channel is proposed by taking into account only the ICI terms significantly affecting the error performance and by modifying the previous frequency-domain equalization techniques. The effectiveness of the proposed approach is demonstrated via computer simulation by applying it to OFDM system when the multipath fading channel is time-varying.

In this paper, an adaptive data predistortion technique which can compensate for the nonlinear effect of a TWT high-power amplifier (HPA) in orthogonal frequency-division multiplexing (OFDM) systems is proposed. It is shown that the convergence time and MSE of an adaptive data predistorter can be significantly reduced by using a broadcasting technique and by designing appropriate training signals.