Broad Echo State Network for Channel Prediction in MIMO-OFDM Systems

Sui, Yongbo; He, Yigang; Cheng, Tongtong; Yuan, Hongxing; Ning, Shuguang

doi:10.1109/tvt.2020.3025913

Cited by 6 publications

(14 citation statements)

References 38 publications

Supporting

Mentioning

Contrasting

Unclassified

Order By: Relevance

“…For the sake of simplicity but without loss of generality, we excluded the indices of the antenna elements. Sui et al [30] proposed a channel prediction framework called group forward variable selection-based BESN (GFVS-BESN). It considers a broad learning system and reduces the time consumed during the training stage compared to prediction schemes using other neural networks.…”

Section: B Conventional Channel Prediction Algorithmsmentioning

confidence: 99%

“…According to the WSSUS, correlations exist only for same transmitting path [30]. Therefore, the hybrid network predicts the channel for the n th path by using the same path for every antenna pair.…”

Section: Proposed Channel Prediction Scheme For the Amc Solution A Network Architecture For Channel Predictionmentioning

confidence: 99%

“…Although existing prediction schemes that utilize not only LSTM but also other neural network structures predict multi-path channels as a whole, most focus on modeling flat-fading multiple-input multiple-output (MIMO) channels. Some previous studies have focused on frequency-selective channels [17], [24]- [30]. Semmelrodt and Kattenbach [17] and Jiang and Schotten [24]- [26] predicted channels by converting the frequency-selective channel into independent frequency-flat channels considering orthogonal frequencydivision multiplexing (OFDM).…”

Section: Introductionmentioning

confidence: 99%

“…However, their assumption may not hold depending on the environment. Finally, Liu et al [29] and Sui et al [30] proposed channel prediction in the time-delay domain. Liu et al [29] were the first to propose a MIMO-OFDM channel prediction model in time domain, and Sui et al [30] introduced a channel prediction framework based on the temporal and spatial correlations in MIMO-OFDM systems to prevent overfitting and ensure efficient learning.…”

Section: Introductionmentioning

confidence: 99%

“…Finally, Liu et al [29] and Sui et al [30] proposed channel prediction in the time-delay domain. Liu et al [29] were the first to propose a MIMO-OFDM channel prediction model in time domain, and Sui et al [30] introduced a channel prediction framework based on the temporal and spatial correlations in MIMO-OFDM systems to prevent overfitting and ensure efficient learning. Sui et al [30] also argued that correlations exist only for the same transmitting path in the channel impulse response based on the wide-sense stationary uncorrelated scattering (WSSUS).…”

Section: Introductionmentioning

confidence: 99%

See 4 more Smart Citations

Hybrid Neural Network-Based Fading Channel Prediction for Link Adaptation

Eom

Lee

2021

IEEE Access

View full text Add to dashboard Cite

We propose an artificial intelligence-based channel prediction scheme that can potentially facilitate link adaptation in customized communication systems. Link adaptation is a key process for wireless communication that requires accurate channel state information (CSI). However, the CSI may be outdated because of computational and propagation delays. In addition, a subframe with no CSI reference signal cannot provide CSI feedback. The proposed scheme solves these problems by predicting future channels. Although traditional stochastic methods suffer from marginal prediction accuracy or unacceptable computational complexity, neural networks allow time series prediction for channels even considering constraints for practical application. We introduce a hybrid architecture for improving the prediction accuracy of the neural network when extracting meaningful features. The proposed scheme uses a single hybrid network that can predict channels in different environments. Simulations were performed using a spatial channel model to evaluate the performance at the system-level, and the results indicated that the proposed scheme effectively increases the prediction accuracy for the channel quality indicator and spectral efficiency.

show abstract

Section: B Conventional Channel Prediction Algorithmsmentioning

confidence: 99%

Section: Proposed Channel Prediction Scheme For the Amc Solution A Network Architecture For Channel Predictionmentioning

confidence: 99%