Fast Position-Aided MIMO Beam Training via Noisy Tensor Completion

Chou, Tzu-Hsuan; Michelusi, Nicolò; Love, David J.; Krogmeier, James V.

doi:10.1109/jstsp.2021.3063837

Cited by 21 publications

(6 citation statements)

References 50 publications

Supporting

Mentioning

Contrasting

Order By: Relevance

“…Feedback-based schemes adapt the beam training according to the feedback information sent from the receiver in an online fashion [31] or learn and leverage the UEs' mobility as in [32], [33]. Data-assisted schemes perform the beam training by leveraging side information from other available sources, e.g., GPS positional information [42], lower-frequency communication [41], radar [39], and LIDAR [40]. Multipath estimation schemes exploit the channel sparsity of the MIMO channel via compressed sensing (CS) to acquire the associated channel parameters, e.g., angles of arrival (AOAs), angles of departure (AODs), time delays, and path gains.…”

Section: A Prior Workmentioning

confidence: 99%

“…Over the last decade, much research has focused on MIMO channel estimation in mmWave and (sub-)THz bands. Various approaches based on the idea of beam alignment have been investigated in recent years, including feedback-based schemes [31]- [38], data-assisted schemes [39]- [42], to multipath estimation [11]- [24], [30]. Feedback-based schemes adapt the beam training according to the feedback information sent from the receiver in an online fashion [31] or learn and leverage the UEs' mobility as in [32], [33].…”

Section: A Prior Workmentioning

confidence: 99%

See 1 more Smart Citation

Compressed Training for Dual-Wideband Time-Varying Sub-Terahertz Massive MIMO

Chou¹,

Michelusi²,

Love³

et al. 2022

Preprint

Self Cite

View full text Add to dashboard Cite

Designers of beyond-5G systems are planning to use new frequencies in the millimeter wave (mmWave) and sub-terahertz (sub-THz) bands to meet ever-increasing demand for wireless broadband access. Sub-THz communication, however, will come with many challenges of mmWave communication and new challenges associated with the wider bandwidths, larger numbers of antennas and harsher propagation characteristics. Notably the frequency-and spatial-wideband (dual-wideband) effects are significant at sub-THz. To address these challenges, this paper presents a compressed training framework to estimate the sub-THz time-varying MIMO-OFDM channels. A set of frequency-dependent array response matrices are constructed, enabling the channel recovery from multiple observations across subcarriers via multiple measurement vectors (MMV). Capitalizing on the temporal correlation, MMV least squares (MMV-LS) is designed to estimate the channel on the previous beam index support, followed by MMV compressed sensing (MMV-CS) on the residual signal to estimate the time-varying channel components. Furthermore, a channel refinement algorithm is proposed to estimate the path coefficients and time delays of the dominant paths. To reduce the computational complexity, a sequential search method using hierarchical codebooks is proposed for greedy beam selection. Numerical results show that MMV-LS-CS achieves a more accurate and robust channel estimation than state-of-the-art algorithms on time-varying dual-wideband MIMO-OFDM.

show abstract

Section: A Prior Workmentioning

confidence: 99%

Section: A Prior Workmentioning

confidence: 99%

Compressed Training for Dual-Wideband Time-Varying Sub-Terahertz Massive MIMO

Chou¹,

Michelusi²,

Love³

et al. 2022

Preprint

Self Cite

View full text Add to dashboard Cite

show abstract

“…The BS groups the source tasks by the batch size of V and updates the NN parameters with V source tasks in each iteration. The BS uses the mini-batch stochastic gradient descent (SGD) method [39] using the batch size of V to update the inner-task parameters of the t-th source task, Ω Tr,t , Ω Tr,t ← Ω Tr,t − α∇ ΩTr,t Loss DSup(t) (Ω Tr,t ), t = 1, ..., V, (7) where α represents the inner-task learning rate and Loss DSup(t) denotes the loss function on D Sup (t). We use the MSE between the target value q (i) Sup,t and the predicted value q(i) Sup,t as the loss function…”

Section: Meta-training Stagementioning

confidence: 99%

“…This is problematic because user equipment (UE) mobility can cause the BS's channel state information (CSI) to become quickly outdated [2], [3]. One possible solution is to predict the current channel with the past CSI [4]- [7].…”

Section: Introductionmentioning

confidence: 99%

Massive MIMO Channel Prediction Via Meta-Learning and Deep Denoising: Is a Small Dataset Enough?

Kim¹,

Choi²,

Love³

2022

Preprint

View full text Add to dashboard Cite

Accurate channel knowledge is critical in massive multiple-input multiple-output (MIMO), which motivates the use of channel prediction. Machine learning techniques for channel prediction hold much promise, but current schemes are limited in their ability to adapt to changes in the environment because they require large training overheads. To accurately predict wireless channels for new environments with reduced training overhead, we propose a fast adaptive channel prediction technique based on a meta-learning algorithm for massive MIMO communications. We exploit the model-agnostic meta-learning (MAML) algorithm to achieve quick adaptation with a small amount of labeled data. Also, to improve the prediction accuracy, we adopt the denoising process for the training data by using deep image prior (DIP). Numerical results show that the proposed MAML-based channel predictor can improve the prediction accuracy with only a few fine-tuning samples. The DIP-based denoising process gives an additional gain in channel prediction, especially in low signal-tonoise ratio regimes.

show abstract

“…Despite their simplicity, these schemes do not incorporate mobility dynamics, leading to large beam-training overhead in high mobility scenarios [2]. Moreover, beam-training may still be required even when contextual information is available [15], [16], to compensate for noise and inaccuracies in contextual information, or due to privacy concerns (e.g., sharing GPS coordinates as in [15]- [18]).…”

mentioning

confidence: 99%

Learning and Adaptation for Millimeter-Wave Beam Tracking and Training: a Dual Timescale Variational Framework

Hussain¹,

Michelusi²

2021

Preprint

Self Cite

View full text Add to dashboard Cite

Millimeter-wave vehicular networks incur enormous beam-training overhead to enable narrow-beam communications. This paper proposes a learning and adaptation framework in which the dynamics of the communication beams are learned and then exploited to design adaptive beam-training with low overhead: on a long-timescale, a deep recurrent variational autoencoder (DR-VAE) uses noisy beamtraining observations to learn a probabilistic model of beam dynamics; on a short-timescale, an adaptive beam-training procedure is formulated as a partially observable (PO-) Markov decision process (MDP) and optimized via point-based value iteration (PBVI) by leveraging beam-training feedback and a probabilistic prediction of the strongest beam pair provided by the DR-VAE. In turn, beam-training observations are used to refine the DR-VAE via stochastic gradient ascent in a continuous process of learning and adaptation. The proposed DR-VAE mobility learning framework learns accurate beam dynamics: it reduces the Kullback-Leibler divergence between the ground truth and the learned beam dynamics model by 86% over the Baum-Welch algorithm and by 92% over a naive mobility learningapproach that neglects feedback errors. The proposed dual-timescale approach yields a negligible loss of spectral efficiency compared to a genie-aided scheme operating under error-free feedback and foreknown mobility model. Finally, a low-complexity policy is proposed by reducing the POMDP to an error-robust MDP. It is shown that the PBVI-and error-robust MDP-based policies improve the spectral efficiency by 85% and 67%, respectively, over a policy that scans exhaustively over the dominant beam pairs, and by 16% and 7%, respectively, over a state-of-the-art POMDP policy. I. INTRODUCTIONMillimeter-wave (mm-wave) has emerged as the most promising technology to enable multigigabit communication in vehicular communications, thanks to large bandwidth availability [2].By operating at carrier frequencies ranging from 30 GHz up to hundreds of GHz, mm-wave communications suffer from high isotropic path loss, overcome by using large antenna arrays

show abstract

Fast Position-Aided MIMO Beam Training via Noisy Tensor Completion

Cited by 21 publications

References 50 publications

Compressed Training for Dual-Wideband Time-Varying Sub-Terahertz Massive MIMO

Compressed Training for Dual-Wideband Time-Varying Sub-Terahertz Massive MIMO

Massive MIMO Channel Prediction Via Meta-Learning and Deep Denoising: Is a Small Dataset Enough?

Learning and Adaptation for Millimeter-Wave Beam Tracking and Training: a Dual Timescale Variational Framework

Contact Info

Product

Resources

About