Deep Reinforcement Learning for Throughput Improvement of the Uplink Grant-Free NOMA System

Zhang, Jiazhen; Tao, Xiaofeng; Wu, Huici; Zhang, Ning; Zhang, Xuefei

doi:10.1109/jiot.2020.2972274

Cited by 94 publications

(48 citation statements)

References 36 publications

Supporting

Mentioning

Contrasting

Order By: Relevance

“…On the other hand, the complexity mainly comes from the MMSE-SIC calculations at the receiver with the maximum decodable number of packets in a sub-frame. According to the literature [28]- [29], the complexity of MMSE-SIC detector can be expressed as O(K 3 max ), whereK max is defined as the maximum decodable number of connections overall with K max ≤ θ max L. To further reduce the complexity of the MMSE-SIC detector, some low-complexity MMSE-SIC detection techniques could also be exploited in the RPC scheme [30]- [31]. Besides, the complexity of SIC for each replica of the proposed scheme is just the same as that of CRDSA-like schemes, and it grows with the achievable throughput and the average number of packet replicas of each device.…”

Section: A Computational Complexitymentioning

confidence: 99%

Randomly Pre-Coded Packets Based Random Access Scheme for IoT-Oriented Satellite Networks

Ren

Wang

et al. 2020

IEEE Access

View full text Add to dashboard Cite

In this paper, a novel random pre-coding (RPC) based random access (RA) scheme is proposed to improve the system performance in the Internet of Things-oriented satellite networks. In this scheme, each device randomly selects a non-orthogonal multi-level complex sequence from a pre-defined pre-coding sequence set to pre-code the transmitted packets in a sub-frame, by which multiple superimposed packets in the sub-frame can be successfully decoded by using the minimum mean squared error (MMSE) based successive interference cancellation (SIC) detection algorithm. Besides, by combining the proposed RPC with the existing contention resolution diversity slotted ALOHA (CRDSA) scheme, which the RPC-CRDSA scheme is generated. The SIC processing should be carried out across sub-frames to remove the received signals that are already recovered, which can further significantly improve the system throughput. The performance of the RPC-RA scheme is evaluated via both theoretical analysis and computer simulation. The collision probabilities of both preamble and pre-coding sequences and an upper bound of throughput are derived, respectively. Simulation results show that the peak normalized throughput of RPC-CRDSA with the pre-coding sequence length L = 8 can reach 1.87 bits/symbol, which largely outperforms traditional schemes.INDEX TERMS Random pre-coding (RPC), random access, satellite networks, MMSE-SIC, CRDSA

show abstract

Section: A Computational Complexitymentioning

confidence: 99%

Randomly Pre-Coded Packets Based Random Access Scheme for IoT-Oriented Satellite Networks

Ren

Wang

et al. 2020

IEEE Access

View full text Add to dashboard Cite

show abstract

“…To avoid collisions, two techniques can be leveraged. One is to apply novel multiple access techniques, such as non-orthogonal multiple access (NOMA) [5]. The other is to exploit learning algorithms so users can distributively adjust their transmissions, minimizing collisions.…”

Section: Introductionmentioning

confidence: 99%

“…The use of reinforcement learning (RL) for uncoordinated spectrum access has recently garnered some attention. To maximize the accumulated data rate and the number of successful transmissions, [3] and [4] adopt Q-learning, while [5] considers a NOMA system and applies deep RL. The related framework of multi-player multi-armed bandits (MAB) [9] has also been widely used to study uncoordinated spectrum access.…”

Section: Introductionmentioning

confidence: 99%

“…is a counter of the number of times m was accessed by k without collision until timeslot t. y t k (m) is the sum reward achieved by k over m until timeslot t. Estimate means:μ(k, m) = y t k (m)/V t k (m), ∀m ∈ M. 10: end for 2-Matching Phase: for the next c 1 l 1+δ timeslots, play according to the dynamics described in section III-A. 11: If S t k = C, choose the action to play according to (5). If S t k = D, choose the action according to (6).…”

mentioning

confidence: 99%

See 1 more Smart Citation

Stochastic Multi-Player Multi-Armed Bandits with Multiple Plays for Uncoordinated Spectrum Access

Youssef

Veeravalli

Farah

et al. 2020

2020 IEEE 31st Annual International Symposium on Personal, Indoor and Mobile Radio Communications

View full text Add to dashboard Cite

In this paper, an algorithm based on the multiplayer multi-armed bandit (MAB) framework is proposed to solve an uncoordinated spectrum access problem. The proposed technique does not require any communication or coordination between users. The case of varying channel rewards across users is considered. In contrast to previous work, the users are permitted to choose multiple channels for transmission, resulting in a MAB model with multiple plays. The proposed algorithm has an expected regret of the order O(log 2 T), which is validated by simulation results. Index Terms-uncoordinated spectrum access, multi-armed bandits with multiple plays, varying reward distribution.

show abstract

“…Then, this high potential of DL networks has attracted great attention by the community [21], [22] and the DL networks applications have been implemented in more timely topics such as index modulations [23] and mmWave communications [24]. Therefore, the DL-based algorithms have also been implemented in NOMA schemes where grantfree and multi-user detection are investigated in CD-NOMA [25]- [27] and along with PD-NOMA schemes for classification/optimization [28]- [30], resource allocation [31], [32], modulation design [33], [34], signal detection [35]- [40]. However, all aforementioned studies assume basic downlink and/or uplink NOMA schemes and to the best of the authors' knowledge, there is no study to design DL-aided joint signal detection to improve the error performance of C-NOMA, yet.…”

mentioning

confidence: 99%

Deep Learning Empowered Semi-Blind Joint Detection in Cooperative NOMA

et al. 2021

View full text Add to dashboard Cite

In this paper, we propose a multi-user symbol detection in cooperative-non-orthogonal multiple access (C-NOMA) schemes via deep learning (DL). We use a DL-based detection (DLDet) in both users instead of conventional detectors. Therefore, an iterative detector (i.e., successive interference canceler (SIC)) at the near user (UE1) and a combining plus optimum detector (i.e., maximum ratio combining (MRC) and maximum-likelihood (ML) detector) at the far user (UE2) are not required anymore. The proposed DLDet can detect symbols at the both users simultaneously. Besides, the DLDet does not require an additional channel estimation algorithm to acquire the channel state information (CSI) at the receivers. The multi-user symbol detection is performed based on the received pilot responses simultaneously, thus calling semi-blind. We train the proposed DLDet offline over Rayleigh fading channel and then, we use the offline-trained DLDet as an online detection algorithm. We compare the error performance of the DLDet with two benchmarks: conventional C-NOMA and threshold-based selective C-NOMA (TBS-C-NOMA). With the extensive simulations over Rayleigh fading channels, we reveal that the DLDet outperforms both C-NOMA and TBS-C-NOMA and achieves the full diversity order (i.e., 2). Besides, this performance gain is up to ∼ 10 dB and ∼ 3 − 7 dB in C-NOMA and TBS-C-NOMA, respectively, which is very promising for the energy-limited networks. Moreover, in order to improve the error performance of the C-NOMA, the TBS-C-NOMA introduces two disadvantages, which are a signaling overhead to obtain the optimum threshold value and a capacity performance decay due the silence of the relay when the threshold is not satisfied. To this end, without using a threshold, outperforming TBS-C-NOMA is essential to revoke these disadvantages. The DLDet accomplish this; hence, the power of the DLDet is unveiled in coping with the error propagation. Then, to reveal the robustness of the DLDet against different fading conditions, we use the offline-trained DLDet as an online detector over different fading channels (i.e., Nakagami-and Rician). We show that the DLDet outperforms conventional detectors over those fading channels and again outperforms the conventional C-NOMA and TBS-C-NOMA performances, although it is trained over Rayleigh fading channel. Indeed, the DLDet has better performance than the C-NOMA and TBS-C-NOMA even though they are assumed to have perfect CSI whereas the DLDet uses only a single pilot signal. The DLDet again provides the full diversity order (i.e., 2 for Nakagami-and 2 for Rician). This proves the robustness of the DLDet and shows that the DLDet performs well regardless of the fading conditions once it is trained for any fading channel.INDEX TERMS cooperative NOMA, deep learning, error performance, joint symbol detection, semi-blind detection I. INTRODUCTION5G and beyond networks are keen to divided into three main aspects/vertical sectors in terms of quality of service criteria. These pioneer areas are grouped as: enhanced mo...

show abstract

Deep Reinforcement Learning for Throughput Improvement of the Uplink Grant-Free NOMA System

Cited by 94 publications

References 36 publications

Randomly Pre-Coded Packets Based Random Access Scheme for IoT-Oriented Satellite Networks

Randomly Pre-Coded Packets Based Random Access Scheme for IoT-Oriented Satellite Networks

Stochastic Multi-Player Multi-Armed Bandits with Multiple Plays for Uncoordinated Spectrum Access

Deep Learning Empowered Semi-Blind Joint Detection in Cooperative NOMA

Contact Info

Product

Resources

About