Deep Learning-Based Non-orthogonal Multiple Access for 5G and Beyond Networks

Driven by the rapid escalation of the wireless capacity requirements imposed by advanced multimedia applications (e.g., ultrahigh-definition video, virtual reality, etc.), as well as the dramatically increasing demand for user access required for the Internet of Things (IoT), the fifth-generation (5G) networks face challenges in terms of supporting large-scale heterogeneous data traffic. Nonorthogonal multiple access (NOMA), which has been recently proposed for the third-generation partnership projects long-term evolution advanced (3GPP-LTE-A), constitutes a promising technology of addressing the aforementioned challenges in 5G networks by accommodating several users within the same orthogonal resource block. By doing so, significant bandwidth efficiency enhancement can be attained over conventional orthogonal multiple-access (OMA) techniques. This motivated numerous researchers to dedicate substantial research contributions to this field. In this context, we provide a comprehensive overview of the state of the art in power-domain multiplexing-aided NOMA, with a focus on the theoretical NOMA principles, multiple-antenna-aided NOMA design, on the interplay between NOMA and cooperative transmission, on the resource control of NOMA, on the coexistence of NOMA with other emerging potential 5G techniques and on the comparison with other NOMA variants. We highlight the main advantages of power-domain multiplexing NOMA compared to other existing NOMA techniques. We summarize the challenges of existing research contributions of NOMA and provide potential solutions. Finally, we offer some design guidelines for NOMA systems and identify promising research opportunities for the future.

Non-orthogonal multiple access (NOMA) is one of the most effective techniques for meeting the spectrum efficiency (SE) requirements of 5G and beyond networks. This paper presents two novel methods for improving the SE of the downlink (DL) NOMA power domain (PD) integrated with a cooperative cognitive radio network (CCRN) in a 5G network using single-input and single-output (SISO), multiple-input and multiple-output (MIMO), and massive MIMO (M-MIMO) in the same network and in a single cell. In the first method, NOMA users compete for free channels in a competing channel (C-CH) on the CCRN. The second method provides NOMA users with a dedicated channel (D-CH) with high priority. The proposed methods are evaluated using the Matlab software program using the three scenarios with different distances, power location coefficients, and transmitting power. Four users are assumed to operate on 80 MHz bandwidths (BWs) and use the quadrature phase shift keying (QPSK) modulation technique in all three scenarios. Successive interference cancellation (SIC) and unstable channel conditions are also considered when evaluating the performance of the proposed system under the assumption of frequency selective Rayleigh fading. The best four-user SE performance obtained by user U4 was 3.9 bps/Hz/cell for SISO DL NOMA, 5.1 bps/Hz/cell for SISO DL NOMA with CCRN with C-CH, and 7.2 bps/Hz/cell for SISO DL NOMA with CCRN with D-CH at 40 dBm transmit power. While 64 × 64 MIMO DL NOMA improved SE performance of the best-use U4 by 51%, 64 × 64 MIMO DL NOMA with C-CH CCRN enhanced SE performance by 64%, and 64 × 64 MIMO DL NOMA with D-CH CCRN boosted performance by 65% SE compared to SISO DL NOMA at 40 dB transmit power. While 128 × 128 M-MIMO DL NOMA improved SE performance for the best U4 user by 79%, 128 × 128 M-MIMO DL NOMA with C-CH CCRN boosted SE performance by 85%, and 128 × 128 M-MIMO DL NOMA with D-CH CCRN enhanced SE performance by 86% when compared to SISO DL NOMA SE performance at 40 dB transmit power. We discovered that the second proposed method, when using D-CH with CCR-NOMA, produced the best SE performance for users. On the other hand, the spectral efficiency is significantly increased when applying MIMO and M-MIMO techniques.

This paper presents a non-orthogonal multiple access (NOMA) concept for cellular future radio access (FRA) towards the 2020s information society. Different from the current LTE radio access scheme (until Release 11), NOMA superposes multiple users in the power domain although its basic signal waveform could be based on the orthogonal frequency division multiple access (OFDMA) or the discrete Fourier transform (DFT)-spread OFDM the same as LTE baseline. In our concept, NOMA adopts a successive interference cancellation (SIC) receiver as the baseline receiver scheme for robust multiple access, considering the expected evolution of device processing capabilities in the future. Based on system-level evaluations, we show that the downlink NOMA with SIC improves both the capacity and cell-edge user throughput performance irrespective of the availability of the frequency-selective channel quality indicator (CQI) on the base station side. Furthermore, we discuss possible extensions of NOMA by jointly applying multi-antenna/site technologies with a proposed NOMA/MIMO scheme using SIC and an interference rejection combining (IRC) receiver to achieve further capacity gains, e.g., a three-fold gain in the spectrum efficiency representing a challenging target for FRA.

Non-orthogonal multiple access (NOMA) is promoted as a key component of 5G cellular networks. As the name implies, NOMA operation introduces intracell interference (i.e., interference arising within the cell) to the cellular operation. The intracell interference is managed by careful NOMA design (e.g., user clustering and resource allocation) along with successive interference cancellation. However, most of the proposed NOMA designs are agnostic to intercell interference (i.e., interference from outside the cell), which is a major performance limiting parameter in 5G networks. This paper sheds light on the drastic negative-impact of intercell interference on the NOMA performance and advocates interference-aware NOMA design that jointly accounts for both intracell and intercell interference. To this end, a case study for fair NOMA operation is presented and intercell interference mitigation techniques for NOMA networks are discussed. This paper also investigates the potential of integrating NOMA with two important 5G transmission schemes, namely, full duplex and device-to-device communication. This is important since the ambitious performance defined by the third generation partnership project for 5G is foreseen to be realized via seamless integration of several new technologies and transmission techniques.

In this research work, the authors propose an error constrained data transmission approach using non-orthogonal multiple access (NOMA) protocol with hybrid automatic repeat request (HARQ) and different packet combining schemes. In this proposed work, the transmitter simultaneously transmits two data packets to the users (UEs) by considering the superposition coding technique in the power domain. The decoding scheme of the receiver changes according to the message decoding status in the previous rounds. This combined protocol has the capability of realizing ultra-reliability, error correction power in high error prone wireless links. The receiver adopts successive interference cancelation (SIC) to decode its own packet. Retransmission process is performed when the data is erroneously received by the destination and the receiver corrects the error by applying HARQ with Packet Combining (HARQ-PC) and HARQ with Aggressive Packet Combining (HARQ-APC) schemes. This paper analyzes the data rates, outage probabilities and bit error rates of UEs for downlink NOMA systems with respect to the transmit power using some basic parameters. The proposed schemes can greatly outperform the conventional NOMA with HARQ (NOMA-HARQ) in terms of data rates, outage probability and bit error rate in dynamic wireless channels.

Non-orthogonal multiple access (NOMA) is considered a potential technique in fifth-generation (5G). Nevertheless, it is relatively complex when applying NOMA to a massive access scenario. Thus, in this paper, a hybrid NOMA/OMA scheme is considered for uplink wireless transmission systems where multiple cognitive users (CUs) can simultaneously transmit their data to a cognitive base station (CBS). We adopt a user-pairing algorithm in which the CUs are grouped into multiple pairs, and each group is assigned to an orthogonal sub-channel such that each user in a pair applies NOMA to transmit data to the CBS without causing interference with other groups. Subsequently, the signal transmitted by the CUs of each NOMA group can be independently retrieved by using successive interference cancellation (SIC). The CUs are assumed to harvest solar energy to maintain operations. Moreover, joint power and bandwidth allocation is taken into account at the CBS to optimize energy and spectrum efficiency in order to obtain the maximum long-term data rate for the system. To this end, we propose a deep actor-critic reinforcement learning (DACRL) algorithm to respectively model the policy function and value function for the actor and critic of the agent (i.e., the CBS), in which the actor can learn about system dynamics by interacting with the environment. Meanwhile, the critic can evaluate the action taken such that the CBS can optimally assign power and bandwidth to the CUs when the training phase finishes. Numerical results validate the superior performance of the proposed scheme, compared with other conventional schemes.

Non-orthogonal multiple access (NOMA) utilizing transmit power difference and advanced successive interference canceller (SIC) receivers has been considered as a candidate radio access technology for future wireless communication systems. Single-user multiple-input multiple-output (SU-MIMO) is one of the key technologies in Long-Term-Evolution (LTE) systems. Thus, it has been proved to combine with NOMA for further system performance improvement. In previous studies, SIC receiver is adopted at cell center users (UEs), while SIC processing is not taken into account at cell-edge UEs, considering the feasibility of UE receiver and control signaling overhead. However, it may put limitation on the performance of NOMA. To further enhance the performance of NOMA with SU-MIMO, advanced receiver can be considered at cell-edge UEs. In this paper, we investigate the impact of applying the SIC receiver at cell-edge UEs in downlink NOMA with SU-MIMO. The detail SIC detection schemes at cell-edge UE will be discussed, including ideal SIC processing and non-ideal SIC processing. The simulation results show that performance gains of NOMA can be improved with SIC processing at cell-edge UEs. It indicates that more advanced receiver can be considered for cell-edge UE to achieve upper-bound performance.

In this work, resource allocation of Cooperative Power Domain Non-Orthogonal Multiple Access (PD-NOMA) with energy harvesting technique using Multiple Input Single Output (MISO) is examined. This paper focuses on improvement of bit error rate (BER), spectral efficiency and capacity compared to conventional Non-Orthogonal Multiple Access (NOMA). Two users scenario is considered, where an user is near to the base station (BS) while the other one is far away from the base station. As both users with different power levels exist in the same spectrum, co-channel interference is inevitable. To alleviate this, an interference cancellation technique known as Successive Interference Cancellation (SIC) is used. The simulation results of cooperative NOMA with energy harvesting are compared with conventional NOMA and it can be inferred that cooperative NOMA performance is better than NOMA.

In this paper, the concept of grant-free non-orthogonal multiple access (NOMA) for uplink data transmission is elaborated. NOMA in combination with grant-free can be applied to ultra reliability low latency communication (URLLC), massive machine type communication (mMTC), enhanced mobile broadband (eMBB) small packet and two-step random-access channel (RACH) scenarios. The advantages of grant-free NOMA are low latency and signaling overhead, high access capability and efficient resource utilization. Candidate uplink NOMA schemes are summarized and preliminary comparison among a subset of schemes are presented. Furthermore, design aspects for grant-free NOMA are discussed, with special notes on particular issues such as blind UE identification and transmitter/ receiver (Tx/Rx) impairments in realistic deployment.

5G has achieved large-scale commercialization across the world and the global 6G research and development is accelerating. To support more new use cases, 6G mobile communication systems should satisfy extreme performance requirements far beyond 5G. The physical layer key technologies are the basis of the evolution of mobile communication systems of each generation, among which three key technologies, i.e., duplex, waveform and multiple access, are the iconic characteristics of mobile communication systems of each generation. In this paper, we systematically review the development history and trend of the three key technologies and define the Non-Orthogonal Physical Layer (NOPHY) concept for 6G, including Non-Orthogonal Duplex (NOD), Non-Orthogonal Multiple Access (NOMA) and Non-Orthogonal Waveform (NOW). Firstly, we analyze the necessity and feasibility of NOPHY from the perspective of capacity gain and implementation complexity. Then we discuss the recent progress of NOD, NOMA and NOW, and highlight several candidate technologies and their potential performance gain. Finally, combined with the new trend of 6G, we put forward a unified physical layer design based on NOPHY that well balances performance against flexibility, and point out the possible direction for the research and development of 6G physical layer key technologies.

Non-orthogonal multiple access (NOMA) has been viewed as a promising technology in future cellular network to increase channel capacity and frequency efficiency. This NOMA system utilizes power domain to improve the performance of multiple access. Signal detection of a near user is operated by successive interference cancellation (SIC). With SIC, the near user cancels out the signal of far user and decodes its own data. Thereafter, the near user drops the cancelled data if SIC is successful. On the other hand, the far user still needs that the far user data may be retransmitted in case of far user reception failure, i.e., no-acknowledgement. Therefore, retransmission to the far user via the near user is efficient when the near user reuses its cancelled data. In this paper, we investigate more efficient way to conduct hybrid automatic repeat request (HARQ) in NOMA. If the SIC procedure of near user is successful, there is an effective approach to recycle the interference-cancelled data. This concept contains full duplex MIMO technique on near user to support the far user. It is found that the proposed retransmission method provides improvements in view of outage probability, symbol error rate (SER), and throughput of far user.

Non-orthogonal multiple access (NOMA) enables the messages of multiple users to be multiplexed in the power domain by superposition coding at the transmitter side and to be decoded by successive interference cancelation (SIC) at the receiver side. This non-orthogonality enables each user to occupy the whole time–frequency resources such that it overcomes the loss of degree-of-freedom (DoF) caused by orthogonal multiple access (OMA). Therefore, NOMA can achieve higher spectrum efficiency, support massive connectivity, and reduce latency. In this chapter, NOMA is introduced to millimeter wave (mmWave) networks to further improve the spectrum efficiency and support massive connectivity. The unicast, multicast, and cooperative multicast transmissions for mmWave-NOMA networks are studied. Their performance in terms of coverage probability, outage probability, and sum rate is also provided.

Vehicular networking belongs to one of the most attractive techniques under the context of 5th Generation (5G) and Beyond 5G (B5G) wireless communication system. It opens diverse new concepts and applications, e.g. Vehicular-to-Vehicular (V2V), Vehicular-to-Infrastructure (V2I). One of the key components to support autonomous driving is to allow vehicles to share information about their awareness of the environment, i.e. perception layer of neighbor vehicles. In this paper, we focus on low overhead, low latency MAC layer design, enabling perception layer sharing in V2V environment, and PHY layer design, enabling Multi-User Detection (MUD) with V2V environment by means of Non-Orthogonal Multiple Access (NOMA), which is one of the key physical layer technologies of 5G New Radio (NR). Numerical results of link level simulation exhibit that our solution generates and exchanges the NOMA user signature flexibly, i.e. supports both synchronous and asynchronous traffic with low bit error rate. Furthermore, it enables small packet communication with low computational complexity, thus low latency.

In this paper, a unified framework of non-orthogonal multiple access (NOMA) networks is proposed, which can be applied to code-domain NOMA (CD-NOMA) and power-domain NOMA (PD-NOMA). Since the detection of NOMA users mainly depend on efficient successive interference cancellation (SIC) schemes, both imperfect SIC (ipSIC) and perfect SIC (pSIC) are taken into considered. To characterize the performance of this unified framework, the exact and asymptotic expressions of outage probabilities as well as delay-limited throughput for CD/PD-NOMA with ipSIC/pSIC are derived. Based on the asymptotic analysis, the diversity orders of CD/PD-NOMA are provided. It is confirmed that due to the impact of residual interference (RI), the outage probability of the n-th user with ipSIC for CD/PD-NOMA converges to an error floor in the high signal-to-noise ratio (SNR) region. Numerical simulations demonstrate that the outage behavior of CD-NOMA is superior to that of PD-NOMA.

NOMA (Non- orthogonal Multiple Access) is an early candidate for 5G that concentrates on networks capacity expansion. It can be broadly classified into two major categories; Power-Domain NOMA (PD-NOMA) and Code-Domain NOMA (CD-NOMA). This research focuses on PD-NOMA. The significance of PD- NOMA is that concurrent transmission and reception can be accomplished on the same frequency and with this spectral efficiency can be enhanced. The objective of this research is to investigate the impact of error propagation caused due to AWGN (Additive White Gaussian Noise) channel in PD-NOMA 5G system. A 2 × 2 PD-NOMA system is simulated in Matlab version 2019a. In the Uplink, the raw data is BPSK modulated and transmitted to the Base Station (BS). In the downlink, from the BS, User 1 data is transmitted with a power level of 0.25 watts and User 2 with 0.75 watts based on their placement. In the Reception section, Successive Interference Cancellation (SIC) is executed to segregate the data which is further recovered through decoding process. To analyze the performance, AWGN channel is introduced in the proposed simulated system model. The Signal to Noise Ratio is varied from 5 to 25 dB. From the results obtained, it is inferred that, Bit Error Rate experienced by the users varies from 0.1 to 1.