The Experts below are selected from a list of 7908 Experts worldwide ranked by ideXlab platform
Shi Jin - One of the best experts on this subject based on the ideXlab platform.
-
deep learning based csi Feedback approach for time varying massive mimo channels
IEEE Wireless Communications Letters, 2019Co-Authors: Tianqi Wang, Chao-kai Wen, Shi JinAbstract:Massive multiple-input multiple-output (MIMO) systems rely on channel state information (CSI) Feedback to perform precoding and achieve performance gain in frequency division duplex networks. However, the huge number of antennas poses a challenge to the conventional CSI Feedback reduction methods and leads to excessive Feedback Overhead. In this letter, we develop a real-time CSI Feedback architecture, called CsiNet-long short-term memory (LSTM), by extending a novel deep learning (DL)-based CSI sensing and recovery network. CsiNet-LSTM considerably enhances recovery quality and improves tradeoff between compression ratio (CR) and complexity by directly learning spatial structures combined with time correlation from training samples of time-varying massive MIMO channels. Simulation results demonstrate that CsiNet-LSTM outperforms existing compressive sensing-based and DL-based methods and is remarkably robust to CR reduction.
-
deep learning based csi Feedback approach for time varying massive mimo channels
arXiv: Information Theory, 2018Co-Authors: Tianqi Wang, Chao-kai Wen, Shi JinAbstract:Massive multiple-input multiple-output (MIMO) systems rely on channel state information (CSI) Feedback to perform precoding and achieve performance gain in frequency division duplex (FDD) networks. However, the huge number of antennas poses a challenge to conventional CSI Feedback reduction methods and leads to excessive Feedback Overhead. In this article, we develop a real-time CSI Feedback architecture, called CsiNet-long short-term memory (LSTM), by extending a novel deep learning (DL)-based CSI sensing and recovery network. CsiNet-LSTM considerably enhances recovery quality and improves trade-off between compression ratio (CR) and complexity by directly learning spatial structures combined with time correlation from training samples of time-varying massive MIMO channels. Simulation results demonstrate that CsiNet- LSTM outperforms existing compressive sensing-based and DLbased methods and is remarkably robust to CR reduction.
-
Deep learning for massive MIMO CSI Feedback
IEEE Wireless Communications Letters, 2018Co-Authors: Chao-kai Wen, Wan Ting Shih, Shi JinAbstract:In frequency division duplex mode, the downlink channel state information (CSI) should be sent to the base station through Feedback links so that the potential gains of a massive multiple-input multiple-output can be exhibited. However, such a transmission is hindered by excessive Feedback Overhead. In this letter, we use deep learning technology to develop CsiNet, a novel CSI sensing and recovery {mechanism} that learns to effectively use channel structure from training samples. CsiNet learns a transformation from CSI to a near-optimal number of representations (or codewords) and an inverse transformation from codewords to CSI. We perform experiments to demonstrate that CsiNet can recover CSI with significantly improved reconstruction quality compared with existing compressive sensing (CS)-based methods. Even at excessively low compression regions where CS-based methods cannot work, CsiNet retains effective beamforming gain.
-
deep learning for massive mimo csi Feedback
arXiv: Information Theory, 2017Co-Authors: Chao-kai Wen, Wan Ting Shih, Shi JinAbstract:In frequency division duplex mode, the downlink channel state information (CSI) should be conveyed to the base station through Feedback links so that the potential gains of a massive multiple-input multiple-output can be exhibited. However, the excessive Feedback Overhead remains a bottleneck in this regime. In this letter, we use beep learning technology to develop CsiNet, a novel CSI sensing and recovery network that learns to effectively use channel structure from training samples. In particular, CsiNet learns a transformation from CSI to a near-optimal number of representations (codewords) and an inverse transformation from codewords to CSI. Experiments demonstrate that CsiNet can recover CSI with significantly improved reconstruction quality compared with existing compressive sensing (CS)-based methods. Even at excessively low compression regions where CS-based methods cannot work, CsiNet retains effective beamforming gain.
-
A PMI Feedback Scheme for Downlink Multi-User MIMO Based on Dual-Codebook of LTE-Advanced
2012 IEEE Vehicular Technology Conference (VTC Fall), 2012Co-Authors: Yongyu Dai, Shi Jin, Xiqi Gao, Lei Jiang, Ming LeiAbstract:In order to achieve a better tradeoff between Overhead and performance, this paper proposes a separately selected dual-codebook (SSDC) based best companion cluster (BCC) approach. In this scheme, each UE selects its best and worst longterm precoding matrix indicators (PMI1), and feeds them back as the cluster indicators (CIs) for UE pairing. The final precoder W is determined by two precoders indicated by the best PMI1 and the short-term Feedback PMI2. Besides, channel quality indicators (CQIs) are calculated for UE scheduling. To compare with SSDC-based BCC, we also discuss and propose a jointly selected dual-codebook (JSDC) based BCC scheme. Simulation results show that SSDC-based BCC has a comparable throughput performance with JSDC-based BCC but with a substantially reduced complexity and Feedback Overhead for 8Tx.
Chao-kai Wen - One of the best experts on this subject based on the ideXlab platform.
-
deep learning based csi Feedback approach for time varying massive mimo channels
IEEE Wireless Communications Letters, 2019Co-Authors: Tianqi Wang, Chao-kai Wen, Shi JinAbstract:Massive multiple-input multiple-output (MIMO) systems rely on channel state information (CSI) Feedback to perform precoding and achieve performance gain in frequency division duplex networks. However, the huge number of antennas poses a challenge to the conventional CSI Feedback reduction methods and leads to excessive Feedback Overhead. In this letter, we develop a real-time CSI Feedback architecture, called CsiNet-long short-term memory (LSTM), by extending a novel deep learning (DL)-based CSI sensing and recovery network. CsiNet-LSTM considerably enhances recovery quality and improves tradeoff between compression ratio (CR) and complexity by directly learning spatial structures combined with time correlation from training samples of time-varying massive MIMO channels. Simulation results demonstrate that CsiNet-LSTM outperforms existing compressive sensing-based and DL-based methods and is remarkably robust to CR reduction.
-
deep learning based csi Feedback approach for time varying massive mimo channels
arXiv: Information Theory, 2018Co-Authors: Tianqi Wang, Chao-kai Wen, Shi JinAbstract:Massive multiple-input multiple-output (MIMO) systems rely on channel state information (CSI) Feedback to perform precoding and achieve performance gain in frequency division duplex (FDD) networks. However, the huge number of antennas poses a challenge to conventional CSI Feedback reduction methods and leads to excessive Feedback Overhead. In this article, we develop a real-time CSI Feedback architecture, called CsiNet-long short-term memory (LSTM), by extending a novel deep learning (DL)-based CSI sensing and recovery network. CsiNet-LSTM considerably enhances recovery quality and improves trade-off between compression ratio (CR) and complexity by directly learning spatial structures combined with time correlation from training samples of time-varying massive MIMO channels. Simulation results demonstrate that CsiNet- LSTM outperforms existing compressive sensing-based and DLbased methods and is remarkably robust to CR reduction.
-
Deep learning for massive MIMO CSI Feedback
IEEE Wireless Communications Letters, 2018Co-Authors: Chao-kai Wen, Wan Ting Shih, Shi JinAbstract:In frequency division duplex mode, the downlink channel state information (CSI) should be sent to the base station through Feedback links so that the potential gains of a massive multiple-input multiple-output can be exhibited. However, such a transmission is hindered by excessive Feedback Overhead. In this letter, we use deep learning technology to develop CsiNet, a novel CSI sensing and recovery {mechanism} that learns to effectively use channel structure from training samples. CsiNet learns a transformation from CSI to a near-optimal number of representations (or codewords) and an inverse transformation from codewords to CSI. We perform experiments to demonstrate that CsiNet can recover CSI with significantly improved reconstruction quality compared with existing compressive sensing (CS)-based methods. Even at excessively low compression regions where CS-based methods cannot work, CsiNet retains effective beamforming gain.
-
deep learning for massive mimo csi Feedback
arXiv: Information Theory, 2017Co-Authors: Chao-kai Wen, Wan Ting Shih, Shi JinAbstract:In frequency division duplex mode, the downlink channel state information (CSI) should be conveyed to the base station through Feedback links so that the potential gains of a massive multiple-input multiple-output can be exhibited. However, the excessive Feedback Overhead remains a bottleneck in this regime. In this letter, we use beep learning technology to develop CsiNet, a novel CSI sensing and recovery network that learns to effectively use channel structure from training samples. In particular, CsiNet learns a transformation from CSI to a near-optimal number of representations (codewords) and an inverse transformation from codewords to CSI. Experiments demonstrate that CsiNet can recover CSI with significantly improved reconstruction quality compared with existing compressive sensing (CS)-based methods. Even at excessively low compression regions where CS-based methods cannot work, CsiNet retains effective beamforming gain.
Robert W. Heath - One of the best experts on this subject based on the ideXlab platform.
-
channel Feedback based on aod adaptive subspace codebook in fdd massive mimo systems
IEEE Transactions on Communications, 2018Co-Authors: Wenqian Shen, Byonghyo Shim, Linglong Dai, Zhaocheng Wang, Robert W. HeathAbstract:Channel Feedback is essential in frequency division duplexing (FDD) massive multiple-input multiple-output (MIMO) systems. Unfortunately, prior work on multiuser MIMO has shown that the Feedback Overhead scales linearly with the number of base station (BS) antennas, which is large in massive MIMO systems. To reduce the Feedback Overhead, we propose an angle-of-departure (AoD) adaptive subspace codebook for channel Feedback in FDD massive MIMO systems. Our key insight is to leverage the observation that path AoDs vary more slowly than the path gains. Within the angle coherence time, by utilizing the constant AoD information, the proposed AoD-adaptive subspace codebook is able to quantize the channel vector in a more accurate way. From the performance analysis, we show that the Feedback Overhead of the proposed codebook only scales linearly with a small number of dominant (path) AoDs instead of the large number of BS antennas. Moreover, we compare the proposed quantized Feedback technique using the AoD-adaptive subspace codebook with a comparable analog Feedback method. Extensive simulations show that the proposed AoD-adaptive subspace codebook achieves good channel Feedback quality, while requiring low Overhead.
-
coordinated beamforming with limited Feedback in the mimo broadcast channel
IEEE Journal on Selected Areas in Communications, 2008Co-Authors: Chanbyoung Chae, David Mazzarese, Nihar Jindal, Robert W. HeathAbstract:In this paper, we propose a new joint optimization of linear transmit beamforming and receive combining vectors for the multiple-input multiple-output (MIMO) broadcast channel. We consider the transmission of a single information stream to two users with two or more receive antennas. Unlike past work in which iterative computation is required to design the beamformers, we derive specific formulations for the transmit beamformers for two active users via a power iteration and a generalized eigen analysis. To enable practical implementation, a new limited Feedback algorithm is proposed that exploits the structure of the algorithm to avoid full channel quantization. The Feedback Overhead of the proposed algorithm is independent of the number of receive antennas. Monte Carlo simulations are used to evaluate the bit error rate and the sum rate performances of the proposed algorithm. Simulation results show that the proposed method performs close to the sum capacity of the MIMO broadcast channel even with limited Feedback.
-
interpolation based multi mode precoding for mimo ofdm systems with limited Feedback
IEEE Transactions on Wireless Communications, 2007Co-Authors: N Khaled, Robert W. Heath, Bishwarup Mondal, Geert Leus, Frederik PetreAbstract:Spatial multiplexing with multi-mode precoding provides a means to achieve both high capacity and high reliability in multiple-input multiple-output orthogonal frequency-division multiplexing (MIMO-OFDM) systems. Multi-mode precoding uses linear transmit precoding that adapts the number of spatial multiplexing data streams or modes, according to the transmit channel state information (CSI). As such, it typically requires complete knowledge of the multi-mode precoding matrices for each subcarrier at the transmitter. In practical scenarios where the CSI is acquired at the receiver and fed back to the transmitter through a low-rate Feedback link, this requirement may entail a prohibitive Feedback Overhead. In this paper, we propose to reduce the Feedback requirement by combining codebook-based precoder quantization, to efficiently quantize and represent the optimal precoder on each subcarrier, and multi-mode precoder frequency down-sampling and interpolation, to efficiently reconstruct the precoding matrices on all subcarriers based on the Feedback of the indexes of the quantized precoders only on a fraction of the subcarriers. To enable this efficient interpolation-based quantized multimode precoding solution, we introduce (1) a novel precoder codebook design that lends itself to precoder interpolation, across subcarriers, followed by mode selection, (2) a new precoder interpolator and, finally, (3) a clustered mode selection approach that significantly reduces the Feedback Overhead related to the mode information on each subcarrier. Monte-Carlo bit-error rate (BER) performance simulations demonstrate the effectiveness of the proposed quantized multi-mode precoding solution, at reasonable Feedback Overhead
David J. Love - One of the best experts on this subject based on the ideXlab platform.
-
noncoherent trellis coded quantization a practical limited Feedback technique for massive mimo systems
IEEE Transactions on Communications, 2013Co-Authors: Junil Choi, David J. Love, Zachary Chance, Upamanyu MadhowAbstract:Accurate channel state information (CSI) is essential for attaining beamforming gains in single-user (SU) multiple-input multiple-output (MIMO) and multiplexing gains in multi-user (MU) MIMO wireless communication systems. State-of-the-art limited Feedback schemes, which rely on pre-defined codebooks for channel quantization, are only appropriate for a small number of transmit antennas and low Feedback Overhead. In order to scale informed transmitter schemes to emerging massive MIMO systems with a large number of transmit antennas at the base station, one common approach is to employ time division duplexing (TDD) and to exploit the implicit Feedback obtained from channel reciprocity. However, most existing cellular deployments are based on frequency division duplexing (FDD), hence it is of great interest to explore backwards compatible massive MIMO upgrades of such systems. For a fixed Feedback rate per antenna, the number of codewords for quantizing the channel grows exponentially with the number of antennas, hence generating Feedback based on look-up from a standard vector quantized codebook does not scale. In this paper, we propose noncoherent trellis-coded quantization (NTCQ), whose encoding complexity scales linearly with the number of antennas. The approach exploits the duality between source encoding in a Grassmannian manifold (for finding a vector in the codebook which maximizes beamforming gain) and noncoherent sequence detection (for maximum likelihood decoding subject to uncertainty in the channel gain). Furthermore, since noncoherent detection can be realized near-optimally using a bank of coherent detectors, we obtain a low-complexity implementation of NTCQ encoding using an off-the-shelf Viterbi algorithm applied to standard trellis coded quantization. We also develop advanced NTCQ schemes which utilize various channel properties such as temporal/spatial correlations. Monte Carlo simulation results show the proposed NTCQ and its extensions can achieve near-optimal performance with moderate complexity and Feedback Overhead.
-
duplex distortion models for limited Feedback mimo communication
IEEE Transactions on Signal Processing, 2006Co-Authors: David J. LoveAbstract:The use of limited Feedback in multiple-input multiple-output (MIMO) wireless communications has grown in interest over the last few years. Research has shown that Feedback can be used to increase achievable data rates and add resilience against fading. Most of the work to this point, however, has ignored the data rate Overhead associated with Feedback. Models that do not consider Feedback Overhead are valid in wireless systems with ever present control channels, but they fail to capture the data rate cost of Feedback when control channels are not present. In this paper, we present a new system model, called a duplex model, that captures the true loss (or cost) of Feedback. A new distortion function for use with codebook design follows from the duplex system model. This system model is used to derive bounds on the amount of Feedback needed under different antenna, signal-to-noise ratio, and bandwidth assumptions. Simulation results show the necessity of taking Feedback into account.
-
On the design of limited Feedback MIMO with Feedback Overhead
VTC-2005-Fall. 2005 IEEE 62nd Vehicular Technology Conference 2005., 2005Co-Authors: David J. LoveAbstract:Limited Feedback sent from the receiver to the transmitter can be used in multiple-input multiple-output (MIMO) wireless communications to increase achievable data rates and to add resilience against fading. The majority of the limited Feedback research, however, has ignored the data rate Overhead associated with Feedback. Models that do not consider Feedback Overhead are valid in wireless systems with ever present control channels where the Feedback rate is free, but they fail to capture the data rate cost when Feedback consumes a portion of the reverse link data rate. In this paper, we study a new MIMO system model, called a duplex model, that captures the true cost of Feedback. This duplex Feedback model is used to derive necessary conditions on the maximum amount of Feedback under different signal-to-noise ratio, antenna, coherence time, and bandwidth assumptions.
Tianqi Wang - One of the best experts on this subject based on the ideXlab platform.
-
deep learning based csi Feedback approach for time varying massive mimo channels
IEEE Wireless Communications Letters, 2019Co-Authors: Tianqi Wang, Chao-kai Wen, Shi JinAbstract:Massive multiple-input multiple-output (MIMO) systems rely on channel state information (CSI) Feedback to perform precoding and achieve performance gain in frequency division duplex networks. However, the huge number of antennas poses a challenge to the conventional CSI Feedback reduction methods and leads to excessive Feedback Overhead. In this letter, we develop a real-time CSI Feedback architecture, called CsiNet-long short-term memory (LSTM), by extending a novel deep learning (DL)-based CSI sensing and recovery network. CsiNet-LSTM considerably enhances recovery quality and improves tradeoff between compression ratio (CR) and complexity by directly learning spatial structures combined with time correlation from training samples of time-varying massive MIMO channels. Simulation results demonstrate that CsiNet-LSTM outperforms existing compressive sensing-based and DL-based methods and is remarkably robust to CR reduction.
-
deep learning based csi Feedback approach for time varying massive mimo channels
arXiv: Information Theory, 2018Co-Authors: Tianqi Wang, Chao-kai Wen, Shi JinAbstract:Massive multiple-input multiple-output (MIMO) systems rely on channel state information (CSI) Feedback to perform precoding and achieve performance gain in frequency division duplex (FDD) networks. However, the huge number of antennas poses a challenge to conventional CSI Feedback reduction methods and leads to excessive Feedback Overhead. In this article, we develop a real-time CSI Feedback architecture, called CsiNet-long short-term memory (LSTM), by extending a novel deep learning (DL)-based CSI sensing and recovery network. CsiNet-LSTM considerably enhances recovery quality and improves trade-off between compression ratio (CR) and complexity by directly learning spatial structures combined with time correlation from training samples of time-varying massive MIMO channels. Simulation results demonstrate that CsiNet- LSTM outperforms existing compressive sensing-based and DLbased methods and is remarkably robust to CR reduction.
