Machine Learning Inspired Hybrid Precoding for Wideband Millimeter-Wave Massive MIMO Systems

Mir, Talha; Siddiqi, Muhammed Zain; Mir, Usama; MacKenzie, Richard; Hao, Mo

doi:10.1109/access.2019.2916883

Cited by 34 publications

(21 citation statements)

References 27 publications

Supporting

Mentioning

Contrasting

Order By: Relevance

“…While [4] per-forms a search over the candidate set of precoders, [5]- [7], [9] perform a channel decomposition to identify the most promising angular directions. Other solutions include machine learning techniques to obtain the hybrid precoders, like [10], [11].…”

Section: Introductionmentioning

confidence: 99%

See 1 more Smart Citation

Wideband Hybrid Precoding Using Time Modulated Arrays

González-Coma

Castedo

2020

IEEE Access

View full text Add to dashboard Cite

Hybrid digital-analog precoding is a cost effective solution for transmitting over the large bandwidths and huge antenna arrays available in the millimeter wave frequency bands. In this work we focus on the transmission of wideband signals over hybrid precoders that utilize Time-Modulated Arrays in the analog domain. We consider analog precoders constructed with Single-Pole-Double-Throw switches which are both flexible and efficient. We pose two Orthogonal Frequency-Division Multiplexing symbol configurations to cope with the harmonic interference introduced by the Time-Modulated Array. One does not take advantage of the wireless channel frequency diversity and the other does. We optimize digital and analog precoders to maximize the achievable rate in both symbol configurations. Optimization takes into account the switching devices efficiency and the inherent losses of this antenna technique. Finally, we show the excellent performance obtained with the proposed approach, in terms of achievable rate, compared to that of conventional phased arrays.

show abstract

Section: Introductionmentioning

confidence: 99%

“…Some works further reduce the power consumption by considering limited resolution PSs [7], [10], [12] or partially connected structures [12], at the expense of smaller array gains. Nevertheless, none of the previous works contemplate the large Insertion Lossess (ILs) introduced by the PSs.…”

Section: Introductionmentioning

confidence: 99%

Wideband Hybrid Precoding Using Time Modulated Arrays

González-Coma

Castedo

2020

IEEE Access

View full text Add to dashboard Cite

show abstract

“…For conventional fully-digital precoding, it is easy to extend from narrowband to wideband by simply employing the orthogonal frequency division multiplexing (OFDM) (i.e., by converting the frequency-selective wideband channel into a series of frequency-flat subchannels) [18]. However, this simple extension cannot work for hybrid precoding.…”

mentioning

confidence: 99%

“…In hybrid precoding, the digital precoder is realized by RF chains and it has to be designed on per-subcarrier basis. Conversely, the network of phase-shifters is used to implement the analog precoder and it needs to be designed by considering the entire wideband [18]. This distinct feature of hybrid precoding for wideband mmWave channels makes it more challenging compared to the conventional fully-digital precoding [19].…”

mentioning

confidence: 99%

Joint Hybrid Precoder and Combiner for Wideband Millimeter-Wave Massive MIMO Systems

et al. 2020

Self Cite

View full text Add to dashboard Cite

Hybrid precoding and combining is a key technique to provide an appropriate antenna gain in millimeter-wave (mmWave) massive multiple-input multiple-output (MIMO) systems. In wideband mmWave channels, the analog precoder and combiner is designed in the time domain and remain unchanged over the whole bandwidth. In contrast, digital precoders and combiners are optimized on a per-subcarrier basis which makes the resultant problem very difficult. To solve this problem, we combine the well-known turbo-equalizer with the tabu-search (TS)-algorithm developed in artificial intelligence and propose TSbased joint hybrid precoding and combining scheme to intelligently search the near-optimum pair of hybrid precoder and combiner. Specifically, our scheme consists of two key steps. At first, a base station (BS) and a mobile station (MS) develop the turbo-like (TL)-joint search by using the idea of iterative information exchange between them. Then, to find out the near-optimum pair of hybrid precoder and combiner in each iteration of the TL-joint search, the TS-algorithm is employed. Simulation results are shown to verify the significant sum-rate performance of the proposed solution with low-complexity compared to some existing solutions.

show abstract

“…[m]] :,:,3 ] i,j = Im{[G (n,g) [m]] i,j }, 12: Output for MC-HBNet: z (t) HB = z (t) as in (26). 13: for 1 ≤ m ≤ M do 14: Input for MC-CENet: X…”

mentioning

confidence: 99%

Deep Learning Design for Joint Antenna Selection and Hybrid Beamforming in Massive MIMO

Elbir

Mishra

2019

2019 IEEE International Symposium on Antennas and Propagation and USNC-URSI Radio Science Meeting

View full text Add to dashboard Cite

Hybrid analog and digital beamforming transceivers are instrumental in addressing the challenge of expensive hardware and high training overheads in the next generation millimeter-wave (mm-Wave) massive MIMO (multiple-input multiple-output) systems. However, lack of fully digital beamforming in hybrid architectures and short coherence times at mm-Wave impose additional constraints on the channel estimation. Prior works on addressing these challenges have focused largely on narrowband channels wherein optimization-based or greedy algorithms were employed to derive hybrid beamformers. In this paper, we introduce a deep learning (DL) approach for joint channel estimation and hybrid beamforming for frequencyselective, wideband mm-Wave systems. In particular, we consider a massive MIMO Orthogonal Frequency Division Multiplexing (MIMO-OFDM) system and propose three different DL frameworks comprising convolutional neural networks (CNNs), which accept the received pilot signal as input and yield the hybrid beamformers at the output. Numerical experiments demonstrate that, compared to the current state-of-the-art optimization and DL methods, our approach provides higher spectral efficiency, lesser computational cost, and higher tolerance against the deviations in the received pilot data, corrupted channel matrix, and propagation environment.Index Terms-Channel estimation, deep learning, hybrid beamforming, mm-Wave, wideband massive MIMO.

show abstract

Machine Learning Inspired Hybrid Precoding for Wideband Millimeter-Wave Massive MIMO Systems

Cited by 34 publications

References 27 publications

Wideband Hybrid Precoding Using Time Modulated Arrays

Wideband Hybrid Precoding Using Time Modulated Arrays

Joint Hybrid Precoder and Combiner for Wideband Millimeter-Wave Massive MIMO Systems

Deep Learning Design for Joint Antenna Selection and Hybrid Beamforming in Massive MIMO

Contact Info

Product

Resources

About