AUTHOREA
Log in Sign Up Browse Preprints

A Pragmatic Look at Power-Domain NOMA

Guan Gui

and 1 more

Non-Orthogonal Multiple Access (NOMA) received significant attention in the field of wireless communications during the last ten years, particularly focusing on Power-Domain NOMA (PD-NOMA) that uses a successive interference cancellation (SIC) receiver. This review paper reexamines PD-NOMA from a pragmatic angle and sheds light on its virtues and limitations in uplink and downlink scenarios. We observe that the concept of PD-NOMA in the downlink can be seen as a pure signal constellation design and that a simple threshold detector is sufficient at the receiver end. For the uplink, we first address the fairness concerns arising from the mismatch between the users' data rates that can be achieved by the SIC receiver and the fair rates suggested by the power distribution among users. Furthermore, we discuss findings from a recent analysis comparing PD-NOMA to MultiUser MIMO under a common system framework. This study reveals that assigning the same power levels to users, thereby aligning PD-NOMA with MultiUser MIMO, optimizes performance in terms of average bit error rate. These insights raise questions about the fundamental utility of PD-NOMA and suggest that its best application is hierarchical multiple access, where devices with different power capabilities are paired together.
Machine Learning Aided Air Traffic Flow Analysis Based on Aviation Big Data

G G

and 4 more

Timely and efficient air traffic flow management (ATFM) is a key issue in future dense air traffic. The emerging demands for unmanned aerial vehicles and general aviation aircraft aggravate the burden of the ATFM. Thanks to the advanced automatic dependent surveillance-broadcast (ADS-B) technique, the aerial vehicles can be tracked and monitored in a real-time and accurate manner, providing possibility for establishing a more intelligent ATFM architecture. In this paper, we first form an aviation big data platform by using the distributed ADS-B ground stations and the obtained ADS-B messages. By exploring the constructed dataset and mapping the extracted information to the routes, the air traffic flow between different cities can be counted and predicted, where the prediction task is implemented on the basis of two machine learning methods, respectively. The experimental results based on real-world data demonstrate that the proposed traffic flow prediction model adopting long short-term memory (LSTM) can achieve better performance, especially when abnormal factors in traffic control are considered.
Automatic Modulation Classification for MIMO Systems via Deep Learning and Zero-Forci...

G G

and 8 more

Automatic modulation classification (AMC) is one of the most critical technologies for non-cooperative communication systems. Recently, deep learning (DL) based AMC (DL-AMC) methods have attracted significant attention due to their preferable performance. However, the study of most of DL-AMC methods are concentrated in the single-input and single-output (SISO) systems, while there are only a few works on DL-based AMC methods in multiple-input and multiple-output (MIMO) systems. Therefore, we propose in this work a convolutional neural network (CNN) based zero-forcing (ZF) equalization AMC (CNN/ZF-AMC) method for MIMO systems. Simulation results demonstrate that the CNN/ZF-AMC method achieves better performance than the artificial neural network (ANN) with high order cumulants (HOC)-based AMC method under the condition of the perfect channel state information (CSI). Moreover, we also explore the impact of the imperfect CSI on the performance of the CNN/ZF-AMC method. Simulation results demonstrated that the classification performance is not only influenced by the imperfect CSI, but also associated with the number of the transmit and receive antennas.
6G: Opening New Horizons for Integration of Comfort, Security and Intelligence

G G

and 4 more

The innovations of sixth generation wireless communication (6G) as compared to fifth generation (5G) are considered in this paper based on the analysis of related works. With the aim of improving multiple communication targets in each service, five 6G core services are identified for different target requirements. Two centricities and eight key performance indices (KPIs) are detailed to describe these services, and enabling technologies are discussed to satisfy the KPIs. A 6G architecture is proposed as an integrated system of the enabling technologies, and is then illustrated using four typical application scenarios. Potential challenges for development of 6G technology is then discussed and possible solutions are proposed. Finally, opportunities for exploring 6G are analyzed in order to guide future research.
Optimized Lightweight Federated Learning for Botnet Detection in Smart Critical Infra...

Segun Popoola

and 5 more

In this paper, we propose an optimized lightweight Federated Deep Learning (FDL) method for botnet attack detection in smart critical infrastructure. First, an optimization method is developed to determine the most appropriate combination of model hyperparameters for local Deep Learning (DL) at the edge nodes. Then, an oversampling algorithm is combined with the optimal DL model to improve the classification performance when the training data is highly imbalanced, without a significant increase in the overall computation time. Furthermore, a feature dimensionality reduction method is used to reduce the amount of memory space required to store the network traffic data at the edge nodes.
Optimizing Deep Learning Model Hyperparameters for Botnet Attack Detection in IoT Net...

Segun Popoola

and 5 more

Deep Learning (DL) models can be trained to automatically learn the underlying features of the traffic patterns in IoT networks to detect complex botnet attacks. However, the performance of a neural network model largely depends on the set of hyperparameters that is used for the model development. In this paper, an algorithm is proposed to determine the optimal set of hyperparameters (the numbers of hidden layers and hidden units, the learning rate, the optimiser, the activation function, the batch size, and the number of epochs) for efficient DL-based botnet detection in IoT networks. The DL models employ a Deep Neural Network (DNN) architecture for binary and multi-class classification. DNN-based botnet detection models are developed and experiments are performed with the Bot-IoT and N-BaIoT datasets to validate the effectiveness of the hyperparameter optimisation method. Experiment results showed that the proposed method produced DNN models that achieved high botnet attack detection rates, low false alarm rates, and near real-time computation speed.