Deep Learning for an Effective Nonorthogonal Multiple Access Scheme

By Guan Gui, Hongji Huang, Yiwei Song, Hikmet Sari. IEEE Transactions on Vehicular Technology, 2018

453 citations recorded by the source corpus.

Nonorthogonal multiple access (NOMA) has been considered as an essential multiple access technique for enhancing system capacity and spectral efficiency in future communication scenarios. However, the existing NOMA systems have a fundamental limit: high computational complexity and a sharply changing wireless channel make exploiting the characteristics of the channel and deriving the ideal allocation methods very difficult tasks. To break this fundamental limit, in this paper, we propose a novel and effective deep learning (DL)-aided NOMA system, in which several NOMA users with random deployment are served by one base station. Since DL is advantageous in that it allows training the input signals and detecting sharply changing channel conditions, we exploit it to address wireless NOMA channels in an end-to-end manner. Specifically, it is employed in the proposed NOMA system to learn a completely unknown channel environment. A long short-term memory (LSTM) network based on DL is incorporated into a typical NOMA system, enabling the proposed scheme to detect the channel characteristics automatically. In the proposed strategy, the LSTM is first trained by simulated data under different channel conditions via offline learning, and then the corresponding output data can be obtained based on the current input data used during the online learning process. In general, we build, train and test the proposed cooperative framework to realize automatic encoding, decoding and channel detection in an additive white Gaussian noise channel. Furthermore, we regard one conventional user activity and data detection scheme as an unknown nonlinear mapping operation and use LSTM to approximate it to evaluate the data detection capacity of DL based on NOMA. Simulation results demonstrate that the proposed scheme is robust and efficient compared with conventional approaches. In addition, the accuracy of the LSTM-aided NOMA scheme is studied by introducing the well-known tenfold cross-validation procedure.

Subfields: Artificial Intelligence, Electrical and Electronic Engineering

View Paper: https://www.semanticscholar.org/paper/62f06cc675675c3f585369d1bf659b9c04fdfd83

How researchers see this paper

The researchers whose trusted networks rank it highest, strongest advocate first. Every researcher gets a different order.

In Artificial Intelligence

In Electrical and Electronic Engineering

Citations in the corpus

Quantum Machine Learning for 6G Communication Networks: State-of-the-Art and Vision for the Future (2019, methodology): “Furthermore, a DL-aided NOMA scheme has been proposed in [232], where DL has been used for learning channel conditions in an end-to-end learning fashion.”
Future Intelligent and Secure Vehicular Network Toward 6G: Machine-Learning Approaches (2020, unknown): “[68] modeled the conventional user activity/data detection as an unknown nonlinear mapping problem and correspondingly proposed an approximation algorithm to solve it by using long short-term memory (LSTM) to model the spatial–temporal relationship between the input signals and the sharply changing ”
Machine Learning for Resource Management in Cellular and IoT Networks: Potentials, Current Solutions, and Open Challenges (2019, methodology): “in [182], the authors proposed a novel approach using DL in NOMA system where single BS serves multiple users deployed in a single cell.”
Ten Challenges in Advancing Machine Learning Technologies toward 6G (2020, methodology): “For example, deep learning with a long short-term memory (LSTM) network is employed to incorporate into a typical sys-tem for improving automatic encoding, decoding and channel detection in 5G and beyond (i.e., 6G) systems [11].”
Grant-Free Non-Orthogonal Multiple Access for IoT: A Survey (2019, background): “In [180], authors use deep learning to solve the high computational complexity of traditional channel estimation and detection algorithms that is mainly due to the fast-changing wireless channel.”
Non-Orthogonal Multiple Access: Common Myths and Critical Questions (2018, methodology): “[14] G.”
An Intrusion Detection Model Based on Feature Reduction and Convolutional Neural Networks (2019, unknown): “The era of ‘‘big data’’ emerges over time [5]–[7].”
Evolution of NOMA Toward Next Generation Multiple Access (NGMA) for 6G (2021, background): “From the perspective of NOMA, ISaC introduces a new mechanism of acquiring CSI, which improves the quality of NOMA transmission.”
Deep Learning for Physical-Layer 5G Wireless Techniques: Opportunities, Challenges and Solutions (2019, methodology): “The DNN with 18 layers is used to process an enormous quantity of data including original transmitted signals and channel vectors [7].”
6G: Opening New Horizons for Integration of Comfort, Security, and Intelligence (2020, background): “Developed DNN models for wireless communication are also limited [15-18], and are mainly borrowed from the fields of computer vision.”