Wireless Networks最新文献

The growth of social networks and cloud computing has resulted in the production of enormous amounts of data, which poses significant challenges for intrusion detection systems (IDS). Big data management in the IDS system presents several important issues, such as delayed reaction times, imbalanced datasets, reduced detection rates, and false alarm rates. To overcome those drawbacks, this work introduces a novel Intrusion Detection System from the perspective of big data handling. Here, input data is handled with the Apache Spark. In the first phase (preprocessing), improved min–max normalization is performed. Subsequently, improved correlation and flow features are extracted since the information extraction from the data is more important to determine the appropriate class differences during attack detection. Subsequently, intrusion detection is done by a hybrid model, which fuses the long short term memory and optimized convolutional neural network (CNN). Then, the optimization-assisted training algorithm called elephant adapted cat swarm optimization (EA-CSO) is proposed that tunes the optimal weights of CNN to enhance the performance of detection. Finally, the performance of the adopted model is validated over the traditional models in terms of positive, negative and other metrics, and the proposed work shows its better performance over the other models. The accuracy of detecting the intrusions using the HC + EA-CSO model at 90th LP is high around 95.029 while other conventional models obtain minimal accuracy.

Load balancing is essential in cloud computing (CC) to manage the increasing load on servers efficiently. This article proposes a load balancing strategy utilizing constraint measures to distribute the load evenly amongst the servers while minimizing power consumption. Firstly, the capacity and load of every Virtual Machine (VM) is evaluated, and tasks are assigned using the African Vultures Algorithm (AVA) when the load exceeds a predefined threshold. This approach aim is to minimize energy consumption, makespan, and data center usage. Additionally, a load balancing method computes critical features for each VM and assesses their load, followed by calculating selection factors for tasks. Tasks with superior selection factors are assigned to VMs. The proposed Efficient Load Balancing in Cloud Computing under African Vultures Algorithm (ELB-CC-AVA) demonstrates better performance in cloud environments, achieving lower makespan by 32.82%, 30.47%, and 25.32%, along with higher resource utilization rates of 38.22%, 40.21%, and 25.46% compared to the existing methods.

In securing wireless communication, radio-frequency (RF) fingerprints, rooted in physical-layer security, are seriously affected by various types of noise. As a result, effective RF fingerprint extraction and identification for device authentication present a significant challenge. To address this, we propose a comprehensive and robust approach using continuous wavelet transform (CWT) for RF feature extraction, along with U-Net for RFF identification. Initially, the received signal undergoes CWT into a stable time-frequency representation, while the U-Net algorithm is employed to denoise in RFF feature extraction and identification. The experiment results show, remarkable accuracies of 95.4% and 89.5% are achieved (SNR@ 10dB and 5dB), respectively, for 11 Wi-Fi devices with the same model. This underscores the potential of the proposed algorithms to enhance wireless communication security, providing a valuable contribution to RFF identification.

This research investigates power allocation in wireless device-to-device (D2D) networks using spatio-temporal graph neural networks (STGNNs). Specifically, we address the challenge of sum-rate maximization in D2D networks by formulating it as a reinforcement learning problem. In our approach, STGNNs act as agents, generating optimal power allocations to maximize the reward function, which is the overall sum-rate of the network. Our study operates under the realistic assumption of delayed, local channel state information (CSI). Various user mobility patterns, including constant positions, velocities, and accelerations are simulated. The robustness of our proposed method is evaluated against delayed and noisy CSI, which are crucial factors in real-world scenarios. Furthermore, the fairness of our approach is compared to the well-established load-spillage algorithm, which is guaranteed to converge to the globally optimal solution of the alpha-fair utility maximization problem. Finally, the convergence behavior of our method is analyzed in comparison to the policy gradient approach. Our empirical results demonstrate that the proposed STGNN significantly outperforms both the WMMSE benchmark and memoryless graph neural networks (GNNs) across all simulated scenarios, and converges to the globally optimal solution of the load-spillage algorithm, with lower computational complexity. Specifically, it achieves a remarkable performance gap of over 400% compared to the WMMSE algorithm and approximately 10% improvement over the memoryless GNN. These findings underscore the efficacy of STGNNs in addressing power allocation challenges in wireless D2D networks.

Energy efficiency (EE) is a key enabler for sustainable green millimeter wave (mmWave) communication. However, conventional hybrid beamforming methods suffer from energy efficiency performance loss due to hardware limitations and the connected structure. To overcome these limitations, this work investigates a novel adaptive connected (AC) hybrid beamforming (HBF) design for multi-user mmWave systems. We formulate the problem as an EE maximization problem subject to the constraints of the adaptive connected structure, constant modulus, and power budget. Addressing this complicated non-convex problem, we harness the characteristics of the AC structure and introduce an iterative HBF design algorithm grounded in fractional programming. Numerical results demonstrate the effectiveness and flexibility of the proposed AC-based HBF design in terms of EE enhancement.

The most crucial thing about the Wireless Sensor Network (WSN) application is the validation of dangerous as well as remote sensing fields, which are expensive to perform by human insights. Further, these features may lead to the self-managed networking model, in which it faces numerous confronts in the network lifetime, fault tolerance, and energy consumption depending upon the non-renewable energy resources. The major advantages of the WSNs are regarded as the monitoring process as well as the nodes used in this network model are positioned commonly in harsh environments. Network management and its efficiency are considered as the most significant factor in network operation. Then, the faults in the WSN have been categorized in terms of persistence, behavior, and underlying causes according to the observation time. Due to its underlying causes in the WSN, the faults are categorized as incorrect computation fault, timing, omission, crash, and fail and stop. Consequently, due to the persistence, the faults are then categorized as a transient fault, intermittent, and permanent, and due to the behaviors, the fault is categorized as a soft and hard fault. As the recent conventional fault detection models failed to provide significant applications in WSN, this work suggests a new way of performing fault tolerance in WSN. In this research, a newly derived technique is implemented by using two functions like energy level checker and a routing manager for fault tolerance to detect malicious nodes in WSN. Here, the Energy level checker checks the residual energy for each communication. If the energy dissipation for a particular communication is less or higher than the threshold it does not send the packet, instead, it forwards the warning messages of the transmitted node that is further sent to the energy level checker. Next, the routing manager sends the path verification packets to the path, if acknowledgment is received, then, the packet is transmitted, and also Certificate Authority is issued to the trusted node based upon the amount of data packets transmitted and the amount of data packets that are successfully obtained. Finally, the prevention of fault nodes is done by selecting the trusted node using a new optimization algorithm known as the Modified Sandpiper Optimization Algorithm derived from the Sandpiper Optimization Algorithm. Another contribution of this WSN network for routing is the Cluster Head selection, which is carried out by solving the multi-objective function regarding constraints like trust, residual energy, distance, and delay. Moreover, the simulations have shown comparatively more success over others.

In the energy harvesting self-sustaining distributed base-station system (SS-DBS), the problem of optimal resource allocation for secure transmission at the downlink physical layer is studied, including the energy sharing mode, the power allocation, and the remote radio frequency unit (RRFU) selection. First, considering the existence of the eavesdropping user, an SS-DBS model, consisting of a baseband processing subsystem, an energy subsystem, and a radio frequency subsystem, is established for downlink secure transmission at the physical layer. Among the model, the remote radio frequency units are divided into secure remote radio frequency units that transmit secure information to the legitimate user and friendly cooperative remote radio frequency units that transmit artificial noise to interfere with the eavesdropping user. On this basis, a joint optimization problem of energy sharing, power allocation, and RRFU selection with the objective of maximizing the secure information rate of system is formulated. To solve this optimization problem, the problem is decomposed into an energy scheduling optimization subproblem and a RRFU selection optimization subproblem to solve separately. Through mathematical analysis and solution, the condition for the SS-DBS to adopt the partial energy sharing mode or the full energy sharing mode, the optimal power allocation of the RRFUs, and the RRFU selection algorithm for secure transmission at the physical layer of the SS-DBS downlink are obtained. Finally, Monte Carlo simulation is carried out and the simulation results verify the validity of the model and also show that the proposed algorithm has superior performance in terms of secure information rate and secure energy efficiency.

With the rapid development of science and technology, there are many derivatives of Artificial Intelligence (AI) technology based on wireless networks in the field of education, including intelligent learning systems. The learning strategy of English listening and speaking ability based on the intelligent learning system is studied to improve students’ English listening and speaking ability effectively. Firstly, the literature analysis method is used to analyze the problems that need attention in cultivating English listening and speaking abilities. Then, the current situation of students’ English listening and speaking learning is investigated through questionnaire surveys. Also, the problems existing in the learning process are sorted out and analyzed. Next, the feasibility of applying the intelligent learning system based on the AI wireless network to learning English listening and speaking ability is studied. A feasible strategy based on the intelligent learning system is proposed. Finally, based on the proposed strategy, the class with relatively poor English listening and speaking ability is used as the experimental object for experimental teaching. In addition, the data in the experimental process and the test before and after the experiment are analyzed to verify the effectiveness of the intelligent learning system in improving English listening and speaking ability. The results show that the learning strategy of an intelligent learning system based on an AI wireless network can effectively improve English listening and speaking ability and enhance students’ interest in learning English listening and speaking. The average listening ability of the students after the experiment is higher than that of 4.65 points before the experiment, the significance is 0.406 > 0.05, and the significant value in the homogeneous variance test is F = 0.045 < 0.05. The results indicate that there is a significant difference in the listening and speaking ability of the students before and after the experiment, and the listening and speaking ability of the students in the experimental group is significantly improved. Students have a high degree of recognition of the English listening and speaking learning system. This paper provides new ideas for applying and expanding AI technology in English teaching.

Device-to-Device (D2D) communication stands as a pivotal technology revolutionizing conventional base station-to-device (B2D) communication paradigms. It facilitates direct data exchange among Internet of Things (IoT) devices without intermediaries such as servers or cloud services. However, the direct link between devices poses significant security risks, such as data leaks and unauthorized access. In this paper, a novel Secure data Transmission using Crystals Kyber (STUCK) technique has been proposed to secure device-to-device communication efficiently. STUCK encompasses four pivotal phases: token generation, device discovery, link configuration, and secure data transmission, ensuring robust protection against potential security breaches. Leveraging the Crystals Kyber cryptographic technique, STUCK adeptly manages key operations, encrypts and decrypts data, thus ensuring the integrity of data transmission across devices. Experimental validation conducted in MATLAB validates the efficacy of the proposed system, revealing noteworthy performance metrics encompassing processing time, communication overhead, and encryption duration. Comparative analysis demonstrates superior performance of STUCK, showcasing processing time increases of 23.07%, 44.23%, and 65.38% compared to existing techniques such as B-IoMV, LMECC, and QSAP, respectively.

In this paper, we investigate the joint placement of aerial Base Stations (BSs) and power control of BSs and users’ association to maximize the sum of the receive rates of end users. We formulate this problem as a mixed integer nonlinear optimization problem and propose a heuristic algorithm based on clustering. The algorithm focuses on a set of users with the lowest rates and clusters them into k groups. The centroid of each group is considered as a candidate for the initial placement of an aerial BS. The optimization loop starts by locating an aerial BS and then proceeds to three subalgorithms: updating power control, users’ association update, and aerial BS location. The results show that adding a single aerial BS improves the average user rate by approximately 18%, while reducing the total transmission power by 44%. Moreover, our proposed algorithm outperforms baseline PSO (Particle Swarm Optimization) schemes in terms of average user rate.