Performance Analysis and Deep Learning Design of Wireless Powered Cognitive NOMA IoT Short-Packet Communications With Imperfect CSI and SIC

Vu, Thai-Hoc; Nguyen, Toan-Van; Nguyen, Sang Quang; Kim, Sunghwan

doi:10.1109/jiot.2021.3121421

Cited by 36 publications

(28 citation statements)

References 44 publications

Supporting

Mentioning

Contrasting

Order By: Relevance

“…It performed DL-based detection of NOMA signals to increase the SER of the user, but the effect of imperfect SIC on the system was not demonstrated. In contrast, [21] presented a multi-output DL-based model for analyzing the block error rate, considering the imperfect CSI and SIC. The work proposed in [21] provided higher throughput, but × × × M. A. Aref et al [15] × × × J. Fu et al [13] × × × Y. Xie et al [20] × × × T.-H.…”

Section: R1a2b5b01001994)mentioning

confidence: 99%

“…In contrast, [21] presented a multi-output DL-based model for analyzing the block error rate, considering the imperfect CSI and SIC. The work proposed in [21] provided higher throughput, but × × × M. A. Aref et al [15] × × × J. Fu et al [13] × × × Y. Xie et al [20] × × × T.-H. Vu et al [21] × × S. Gao et al [16] × × × A. Emır et al [17] × × × C. Lin et al [18] × × × Y. Cao et al [19] × × × J.-M. Kang et al [14] × × C.-J.…”

Section: R1a2b5b01001994)mentioning

confidence: 99%

“…The work proposed in [21] provided higher throughput, but × × × M. A. Aref et al [15] × × × J. Fu et al [13] × × × Y. Xie et al [20] × × × T.-H. Vu et al [21] × × S. Gao et al [16] × × × A. Emır et al [17] × × × C. Lin et al [18] × × × Y. Cao et al [19] × × × J.-M. Kang et al [14] × × C.-J. Chun et al [22] × × × J. Liao et al [23] × × Presented article the effect of incomplete CSI on the SIC process for NOMA users was not specifically investigated.…”

Section: R1a2b5b01001994)mentioning

confidence: 99%

See 2 more Smart Citations

Deep Learning aided SIC for Wavelet-based Massive MIMO-NOMA

Ahmad¹,

Shin²

2022

Preprint

View full text Add to dashboard Cite

In this study, a deep neural network (DNN) for a massive multiple-input-multiple-output (mMIMO) nonorthogonal multiple access (NOMA) system’s channel estimation and detection is presented. The proposed network applies deep learning (DL) to a discrete wavelet transform (DWT) based orthogonal frequency-division-multiplexing (OFDM) to reduce the noise and inter-channel interference (ICI) while maintaining compatibility with the existing networks. The transmission overhead is reduced because the presented network is trained to estimate and detect symbols with and without pilot signals. The results of this study demonstrate that our provided DL-based successive interference cancellation (SIC) method performs better than the conventional SIC-based signal detection in the mMIMONOMA network. The suggested wavelet-based mMIMO-NOMA is also compared to the traditional fast-Fourier-transform (FFT) based mMIMO-NOMA, particularly in terms of symbol error rate (SER).

show abstract

Section: R1a2b5b01001994)mentioning

confidence: 99%

Section: R1a2b5b01001994)mentioning

confidence: 99%

Section: R1a2b5b01001994)mentioning

confidence: 99%

See 1 more Smart Citation

Deep Learning aided SIC for Wavelet-based Massive MIMO-NOMA

Ahmad¹,

Shin²

2022

Preprint

View full text Add to dashboard Cite

show abstract

“…NOMA allows multiple users to be served on the same wireless resource, hence improves spectral efficiency of the system and scales up the number of connected users (or devices). NOMA can be flexibly combined with other emerging technologies, for instance, heterogeneous networks (HetNet) [1], [2] millimeter wave (mmWave) communication [3], [4], [5], and others [6]- [9]. Densification of the current cellular networks can be achieved by deploying small base stations (SBSs) underlaid with the macro base stations (MBSs) to form a HetNet, which is an essential part of the beyond 5G communication system [10].…”

Section: Introductionmentioning

confidence: 99%

Performance Analysis of sub-6 GHz/mmWave NOMA Hybrid-HetNets Using Partial CSI

Swami

Mishra

Bhatia

et al. 2022

IEEE Trans. Veh. Technol.

View full text Add to dashboard Cite

The ever-increasing number of wireless users (or devices) and their varied demand require the need for an advanced architecture for the future wireless network. To support massive connectivity, non-orthogonal multiple access (NOMA) has been recognized as a promising solution. NOMA increases the number of simultaneous connections using available resources for users with varying demands. Furthermore, recent measurements and experiments suggest that wide underutilized bandwidth available at millimeter-wave (mmWave) frequencies provide high data rate and therefore are capable of addressing the issue of spectrum scarcity at sub-6 GHz bands utilized by the 4G network. Consequently, co-existence of multi-radio access technologies (RATs) for 5G and beyond networks has been of interest to both industries and academia. In this context, this work studies the co-existence of the two RATs, namely, sub-6 GHz and mmWave communication using NOMA-enabled hybrid heterogeneous network (NOMA-HHN) for massive connectivity. The application of NOMA requires ordering users, which in turn requires the knowledge of users' channel state information (CSI). However, gathering and processing CSI of such a large number of users is difficult to implement in practice. Thus, a solution based on partial CSI is proposed. Additionally, a feedback scheme for user scheduling and RAT selection using dual association is proposed to reduce the initial access delay in beam-training at the mmWave network. Moreover, utilizing directional nature of the mmWave communication, random beamforming is used to reduce system overhead in a network with massive users. The analytical results are confirmed using Monte-Carlo simulation, and various significant advantages are noted for the proposed NOMA-HHN over existing architectures.

show abstract

“…Subsequently, Vu et al [26] leveraged a DNN framework for the ergodic capacity prediction towards real-time configurations of EH CR non-orthogonal multiple-access (NOMA) dual-hop relay IoT networks. In [27], an extension of the DNN model in [26], called a deep multi-output neural network, was designed to simultaneously predict the NOMA users' throughput and E2E BLER of wireless-powered CR NOMA IoT SPC systems. In addition to the DNN and CNN advantages, the recurrent neural network (RNN) was further utilized for performance prediction in terms of the OP and throughput, where the network model of the dual-hop coordinated direct relay transmissions and underlay CR NOMA was considered [28].…”

mentioning

confidence: 99%

IoT Short-Packet URLLCs for MIMO Underlay Cognitive Multihop Relaying with Imperfect CSI

Hoang¹,

Hoang²,

Lee³

2022

Preprint

View full text Add to dashboard Cite

In this work, we investigate short-packet communications for multiple-input multiple-output underlay cognitive multihop relay internet-of-things (IoT) networks with multiple primary users, where IoT devices transmit and receive short packets to provide low-latency and ultra-reliable communications (uRLLCs). For performance evaluation, the closed-form expressions of the end-to-end (E2E) block error rate (BLER) for the considered systems are derived in a practical scenario under imperfect channel state information of the interference channels, from which the E2E throughput, energy efficiency (EE), latency, reliability, and asymptotic analysis are also studied. Based on the analytical results, we adapt some state-of-the-art machine learning (ML)-aided estimators to predict the system performance in terms of the E2E throughput, EE, latency, and reliability for real-time configurations in IoT systems. We also obtain the closed-form expressions for the optimal power-allocation and relay-location strategies to minimize the asymptotic E2E BLER under the proportional tolerable interference power and uRLLC constraints, which require negligible computational complexity and offer significant power savings. Furthermore, the ML-based evaluation achieves equivalent performance while significantly reducing the execution time compared to conventional analytical and simulation methods. Among the ML frameworks, the extreme gradient boosting model is demonstrated to be the most efficient estimator for future practical IoT applications.

show abstract

Performance Analysis and Deep Learning Design of Wireless Powered Cognitive NOMA IoT Short-Packet Communications With Imperfect CSI and SIC

Cited by 36 publications

References 44 publications

Deep Learning aided SIC for Wavelet-based Massive MIMO-NOMA

Deep Learning aided SIC for Wavelet-based Massive MIMO-NOMA

Performance Analysis of sub-6 GHz/mmWave NOMA Hybrid-HetNets Using Partial CSI

IoT Short-Packet URLLCs for MIMO Underlay Cognitive Multihop Relaying with Imperfect CSI

Contact Info

Product

Resources

About