Cooperative wideband spectrum sensing effectively overcomes the limitations of single-user sensing, which becomes unreliable in practical environments due to shadowing and multipath fading. Nowadays, most studies of cooperative wide-band signal reconstruction problem are based on thel2;1-norm regularization, which is ineffective in exploiting signal sparsity. We propose an arctangent regularization iterative thresholding (ARIT) algorithm for collaborative wideband spectrum sensing. To address the challenge of solving subproblems with the arctangent penalty, a high-dimensional matrix optimization problem is reduced toNindependent scalar problems. Consequently, a closed-form proximity operator of an arctangent penalty is derived, which is expressed as hyperbolic functions of sine and cosine. Additionally, to overcome high complexity in manual parameter optimization in ARIT, a signal reconstruction network is put forward which combines ARIT with deep learning (DL) technique through deep unfolding, called ARIT-Net. Parameters in ARIT-Net, such as regularization parameter and penalty factor, are learned in an end-to-end manner by DL rather than being adjusted manually. This network architecture not only preserves the theoretical interpretability of ARIT but also enhances reconstruction performance and efficiency through data-driven adaptive parameter optimization. Simulation results demonstrate that ARIT-Net achieves a reconstruction error reduction of 15.6% compared with ADMM-Net.

Building, managing, upgrading, and diagnosing networks becomes increasingly difficult due to the increased complexity in protocol design, enlarged network scale, rapidly-growing types of network applications, and the uncertainty of network faults and cyber attacks. It is not satisfactory to rely on network simulators/emulators for conducting these tasks because of different defects including poor fidelity, long implementing time, and weak interconnection with physical networks. To enable the interplay of networks and their virtual counterparts, this paper aims to build a Network Functions Virtualization (NFV)-empowered digital twin cyber platform (DTCP) for enabling network innovation and test with high fidelity, low complexity, and high timeliness. First, after regulating the paradigm of DTCP, a six-dimensional model is defined to profile a DTCP. Second, the architecture of the DTCP is detailed along with the key enabling technologies. Third, a prototype implementation of the DTCP is shortly introduced. Lastly, a use case based on fault diagnosis for video conference system is tested on the prototype. Results show that our DTCP prototype is a good platform for conducting different types of network operations without explicitly providing the mapping model between physical and virtual networks.

Abstract To support artificial intelligence (AI)‐involved tasks offloaded from the mobile devices (MDs), it is necessary to equip the Unmanned Aerial Vehicle (UAV) with custom‐made co‐processor (CP) for handling AI workloads in multi‐UAV‐empowered Edge Intelligence. Existing CPU‐oriented task scheduling algorithm cannot apply to the CPU+CP heterogeneous architecture. In this backdrop, this paper first formulates the joint service function placement, collaborative task scheduling, UAV deployment, and MD position determination problem as a Mixed Integer Non‐Linear Programming problem. Then, an alternating optimization‐based algorithm is put forward to derive a sub‐optimal solution of the problem utilizing Differential Evolution and Greedy‐based Hungarian algorithms. A series of experiments are conducted to evaluate the performance of the proposal. Results show that authors' proposal can achieve an overall revenue that is roughly 50% higher than those of existing methods.

In spite of unique advantages like higher recognition accuracy and better generalization capability, automatic modulation classification (AMC)-oriented deep neural networks (ADNNs) are still vulnerable to adversarial examples (AEs). Recent results revealed that an attacker can easily fool ADNNs through adding a small and imperceptible perturbation to the original signal. Among different AE generation methods, universal adversarial perturbation (UAP) has unique characteristics, including input agnostic and shift invariance. However, applying UAP directly to RF signals faces three main challenges, i.e., perturbation neutralization, high perceptibility, and dependency of original signals. In this backdrop, a novel UAP under frequency and data constraints (UAP-FD) attack is put forward for solving these problems in this article. First, an individual perturbation is filtered based on the representation visualization algorithm to counter the neutralization problem in perturbation integration. Second, the high-frequency components in the integrated UAP is eliminated through signal decomposition and reconstruction for promoting the imperceptibility. Third, a proxy signal generation method is proposed to help UAP-FD adapt to data-free black-box settings. A series of experiments is conducted to evaluate the aggressiveness and imperceptibility of UAP-FD attack in different settings on a public data set. Results show that, compared with the existing proposal, UAP-FD has a 40% higher fooling rate, and it can reduce the accuracy of the ADNN model from 83% to 9% while maintaining a good imperceptibility and shift-invariance property. In addition, UAP-FD is applied to real-world captured signals over the transmission channel; and it can reduce the model accuracy from 98.3% to 12.5%.

Unmanned aerial vehicle (UAV)-empowered edge computing has been widely investigated in obstacle-free scenarios, where a moving UAV is in charge of handling offloaded singleton tasks from mobile devices on the ground. However, little attention has been paid to the scenario, in which the UAV serves a complex area withmultiple obstaclesanddependent tasks. A dependent task can be formulated as a directed acyclic graph (DAG) that contains a number of subtasks; and each subtask can be executed by a corresponding service function (SF) deployed on the UAV. In this backdrop, the joint UAV trajectory planning, DAG task scheduling, and SF deployment is formulated as an optimization problem in this article. Afterwards, a deep reinforcement learning (DRL)-based algorithm is presented to tackle the NP-hard problem. The state space, action space, and the reward function of the agent, i.e., the UAV, are defined, respectively, under the DRL framework. To evaluate the effectiveness of the proposal, a series of experiments is conducted with different parameter settings. Results show that the DRL-based algorithm performs much better than three heuristic algorithms in success rate of trajectory planning, the number of executed tasks, and the average task response latency.

Efficient grant-free uplink transmission is critical in minimizing Age of Information (AoI) in multichannel Internet of Things (IoT) networks. But less attention has been paid to this topic especially when dynamic channel access attacks (DCAAs) exist. To bridge this gap, this article formulates the distributed channel access problem in AoI-oriented IoT networks, and then a reinforcement learning-based solution is put forward based on the theoretical results of the game theory. First, a utility maximization problem is formulated for each sensor node based on its average AoI under DCAAs with probabilistic ACK feedback. Second, the problem is transformed into two ordinary potential game (OPG) models, which are both proved to have at least one nash equilibrium (NE); and a distributed learning algorithm is proposed to reach the NE. Finally, extensive simulations are conducted to evaluate the proposal’s performance. Simulation results verify the effectiveness of the proposed algorithm in various parameters settings.

Mobile applications in the present have created tremendous pressure on the computational capabilities of user equipments. Against this background, mobile edge computing (MEC) has been proposed to tackle this issue, e.g., by shifting the computational workload to the edge server. We in this paper consider a caching enabled task offloading in MEC, for the sake of joint optimization of task offloading and caching. We consider both energy consumption and response latency in the optimization problem and solve the problem by an alternate optimization algorithm. Extensive experiments have been conducted to evaluate the algorithm and the simulation results have shown its advantages such as rapid response latency and powerful convergence capability.

A combination of mobile edge computing (MEC) and cloud computing paradigms has the potential to greatly alleviate the challenges facing Internet of Things (IoT). We consider a tiered IoT infrastructure in which data generated by an IoT sensor/device is delivered to a data center for processing through an intermediate MEC server. The MEC server can either directly transmit the data to the data center or pre-process the data and then transmit it to the data center over a shared channel. The goal is to maintain the freshness of the data delivered to the data center. In this paper, we assume a probabilistic model for pre-processing by the MEC server. Sensor data is assumed to be generated as a Poisson process and the transmission times over the two paths are assumed to have general distributions.We use Age of Information (AoI) as a measure of data freshness at the data center. We perform stationary distribution analysis in this system and obtain closed form expressions for average AoI and average peak AoI. We focus on selecting the offloading probabilities in conjunction with the mean service times for each server for optimal operation determined by average AoI and peak AoI. Our numerical results show the effect of path diversity in the selection of best offloading probability and service times.

Abstract Low‐rate Distributed Denial of Service (LDDoS) attacks, in which the attackers send packets to a victim at a sufficiently low rate to avoid being detected, are considered to be a subtype of DDoS attacks and a potential threat to Internet security. However, an overwhelming attack paradigm on the Internet has rarely been reported due to the harsh requirements for launching LDDoS attacks; therefore, most existing LDDoS attacks are constructed and evaluated through theoretical deduction and/or simulation tests. In this backdrop, the authors aim to figure out what the conditions for launching a successful LDDoS attack are, and how harmful an attack could be. They first analyse the characteristics of LDDoS attacks, and derive the conditions and parameters for initiating LDDoS attacks using a queuing model. Based on the analysis results, an LDDoS algorithm is presented. Then, an LDDoS validation prototype is built on a Network Function Virtualization network to validate the derived parameters and conditions. Finally, a series of experiments are conducted on the testbed, and the results show that a successful LDDoS attack could be achieved based on the derived algorithm; however, its attack effect only lasts for a short time compared with its DDoS counterparts.

Indoor robots, in particular AI-enhanced robots, are enabling a wide range of beneficial applications. However, great cyber or physical damages could be resulted if the robots’ vulnerabilities are exploited for malicious purposes. Therefore, a continuous active tracking of multiple robots’ positions is necessary. From the perspective of wireless communication, indoor robots are treated as radio sources. Existing radio tracking methods are sensitive to indoor multipath effects and error-prone with great cost. In this backdrop, this paper presents an indoor radio sources tracking algorithm. Firstly, an RSSI (received signal strength indicator) map is constructed based on the interpolation theory. Secondly, a YOLO v3 (You Only Look Once Version 3) detector is applied on the map to identify and locate multiple radio sources. Combining a source’s locations at different times, we can reconstruct its moving path and track its movement. Experimental results have shown that in the typical parameter settings, our algorithm’s average positioning error is lower than 0.39 m, and the average identification precision is larger than 93.18% in case of 6 radio sources.

This paper focuses on the joint optimization of the Age of Information (AoI) and Signal to Interference plus Noise Ratio‐ (SINR‐) oriented channel access problem under attack in the Wireless Sensor Networks (WSNs). Firstly, to overcome the uncertain, dynamic, and incomplete information constrains, an active probability model and a controlling channel model are proposed for the sensors and the receiving end, respectively. Secondly, to ensure the AoI and SINR of the data generated by the sensors when transmitted under attack, one utility function based on average AoI and SINR is defined. Then, considering the distributed feature of the channel access process, the joint optimization problem is formulated under the game theory structure. Then, a distributed learning algorithm is proposed to reach the Nash Equilibrium (NE) of the game. Finally, simulation results have verified the correctness and effectiveness of the proposed method.

Mobile edge computing (MEC) can greatly reduce the latency experienced by mobile devices and their energy consumption through bringing data processing, computing, and caching services closer to the source of data generation. However, existing edge caching mechanisms usually focus on predicting the popularity of contents or data chunks based on their request history. This will lead to a slow start problem for the newly arrived contents and fail to fulfill MEC's context-aware requirements. Moreover, the dynamic nature of contents as well as mobile devices has not been fully studied. Both of them hinder the further promotion and application of MEC caching. In this backdrop, this paper aims to tackle the caching problem in wireless edge caching scenarios, and a new dynamic caching architecture is proposed. The mobility of users and the dynamics nature of contents are considered comprehensively in our caching architecture rather than adopting a static assumption as that in many current efforts. Based on this framework, a Similarity-Aware Popularity-based Caching (SAPoC) algorithm is proposed which considers a content's freshness, short-term popularity, and the similarity between contents when making caching decisions. Extensive simulation experiments have been conducted to evaluate SAPoC's performance, and the results have shown that SAPoC outperforms several typical proposals in both cache hit ratio and energy consumption.

Coping with diverse channel access attacks (CAAs) has been a major obstacle to realize the full potential of wireless networks as a basic building block of smart applications. Identifying and classifying different types of CAAs in a timely manner is a great challenge because of the inherently shared nature and randomness of the wireless medium. To overcome the difficulties encountered in existing methods, such as long latency, high data collection overhead, and limited applicable range, a deep learning-based CAA detection framework is proposed in this paper. First, we show the challenges of CAA classification by analyzing the impacts of CAAs on wireless network performance using an event-driven network simulator. Second, a state-transition model is built for the channel access process at a node, whose output sequences characterize the changing patterns of the node's transmission status in different CAA scenarios. Third, a deep learning-based CAA classification framework is presented, which takes state transition sequences of a node as input and outputs predicted CAA types. The performance of three deep neural networks, i.e., fully-connected, convolutional, and Long Short-Term Memory (LSTM) network, for classifying CAAs are evaluated under our CAA classification framework in five CAA scenarios and the normal scenario without CAA. Experimental results show that LSTM outperforms the other two neural network architectures, and its CAA classification accuracy is higher than 95%. We successfully transferred the learned LSTM model to classify CAAs on other nodes in the same network and the nodes in other networks, which verifies the generality of our proposed framework.

We in this paper consider a scenario where multiple vehicles jointly provision computing resources to obtain their benefits in the contexts of vehicular fog computing. A community that vehicles can freely join and leave is sponsored by a road side unit (RSU) and thus a resource pool is established such that tasks can be performed by sufficient computing resources. RSU as a coordinator takes in charge of decision making for task scheduling. A permutation of community members is established in advance and updated periodically so as to make the most suitable decision. A task scheduling strategy is proposed from the perspective of service oriented architecture. We have carried out the experiments to investigate our approach and the experimental results have revealed our approach has a great advantage over other approaches in terms of pursuing the values of the community.

Internet of Medical Things (IoMT), intended for real-time health monitoring, are generating quantity of health data such as electrocardiogram, oxygen saturation, and blood pressure every second. The captured data should be processed and analyzed in a delay sensitive way which is vital to the survival rate for cardiovascular and cerebrovascular diseases. In this regard, Unmanned Aerial Vehicles (UAVs) have already demonstrated the enormous potentials. To begin with, due to better line-of-sight, wider communication and more flexible on-demand deployment, UAVs can realize seamless wireless connection to IoMT. Furthermore, UAVs can act as fog nodes to provision services for IoMTs such as task performing and data analysis. We in this paper focus on a sub-problem, i.e., the placement of UAVs over the serving area when they function as fog nodes. In the airborne fog computing, the placement of UAVs has an important influence on energy consumption and exploration area, let alone the communication coverage of the personal health devices on the ground. Therefore, we in this paper propose a particle swarm optimization (PSO) based algorithm to optimize the UAV placement over the serving area for the IoMT devices. We have conducted extensive simulations to evaluate it. The results show that our approach can significantly reduce the number of UAVs needed to deploy while considering the communication coverage and other factors.

Vehicular edge computing (VEC) brings the computing resources to the edge of the networks and thus provisions better computing services to the vehicles in terms of response latency. Meanwhile, the edge server can earn their revenues by leasing the computing resources. However, a higher price does not always bring forth more benefits for the edge server in VEC, since it may discourage vehicles from renting more computing resources from VEC. To the best of our knowledge, few of previous works have focused on the real-time pricing problem for VEC. We investigate in this paper the pricing problem from the viewpoints of both vehicles and the edge server, so as to optimize the utility values and revenues of vehicles and the edge server, respectively. We resort to the Stackelberg game for modeling the interactions between vehicles and edge server, and a distributed algorithm for this pricing problem is proposed in the paper. Experimental results have displayed the efficiency and effectiveness of the proposed algorithm.

Recently, Unmanned Aerial Vehicle (UAVs) have been widely adopted to collect data in dangerous or inaccessible areas due to their unique characteristics, including on-demand deployment, flexibility, low-cost, and mobility. However, limited power supply severely restricts the transmission range of a UAV, thus the sensed data needs to be transmitted to the ground control station (GCS) with the help of multiple UAVs in a multi-hop manner. This paper firstly describes the general process of the UAV relay network deployment, and analyzes the number of relay UAVs needed by two types of straightforward static model, i.e. track-based dynamic routing model with planned path and the infrastructure-based dynamic routing model with uncertain path. Deploying the relay UAVs in a static way as current works do cannot fulfill the requirements for an ideal UAV relay network, such as high reliability, low-cost and guaranteed quality of service. Thus, we detail our prediction-based dynamic relay network deployment model, and prove that our proposal is feasible and requires less number of relay UAVs while providing higher communication quality compared with state-of-the-art methods. Based on this model, an Elastic Relay Network Construction (ERNetC) algorithm is proposed. Finally, a series of simulation experiments are conducted on OMNeT++ simulation platform to evaluate the performance of ERNetC algorithm. Simulation results show that ERNetC algorithm outperforms existing algorithms in total interruption time as well as goodput.

In addition to military applications, Unmanned Aerial Vehicles (UAVs) have attracted more and more attention in civilian applications such as the post-disaster relief assistance. Indeed, advantages including better line-of-sight (LOS), wider communication range and more flexible on-demand deployment make UAVs play a unique role in rescue and disaster scenarios. Emergency tasks assigned to UAVs such as people search and rescue usually require real-time responses, since it is a life-and-death matter regarding the post-disaster relief. Considering the limited computing resources and harsh energy supply replenishment for UAVs in the post-disaster relief operations, we in this paper propose a hybrid fog computing paradigm called H-FVFC that integrates UAVs and vehicular fog computing (VFC) to run the highly demanding tasks with strict latency requirements. An architecture of H-FVFC consisting of three layers is proposed and investigated in this paper, with hope to explore the possibilities of applying this computing paradigm to post-disaster relief operations. Experiments are carried out to evaluate the task offloading in H-FVFC compared to UAV-to-Cloud scheduling strategy. The results show that task offloading in the UAV-to-Vehicle way can significantly reduce the response latency. Issues not addressed in this paper are also discussed with purpose of providing some insights to the application of integration of UAV and fog-enabled vehicle in the post-disaster relief.

Unmanned aerial vehicles (UAVs) are considered a promising solution for carrying communications and computational facilities to increase the flexibility of cloud-to-thing continuum, where short-range and long-range wireless links are adopted to connect mobile devices to the fog node and the fog node to the remote data center, respectively. Most existing UAV-involved resource allocation algorithms focus mainly on the radio resource allocation problem, and much less attention has been paid to the allocation of computational resources. Moreover, the dynamic arrival of tasks and the queueing delay at each computation entity is usually neglected. In this paper, a joint optimization problem is formulated that takes the weighted sum of energy consumption and delay experienced by tasks as the objective function. Processing frequencies and transmission powers of mobile devices and the fog node are the decision variables in the problem. To solve this problem, three decision-making algorithms are presented. The first one is used to decide the UAV's position. The processing frequency, transmission power, and task assignment results at mobile devices are determined by the second algorithm. The last one is adopted by the fog node to optimize its processing frequency and transmission power. A series of simulation experiments are conducted to evaluate the effectiveness of the proposed algorithms. Compared with the random task assignment scheme with fixed parameters, the combination of our three algorithms always perform much better for a wide range of parameter settings.

Multi‐hop wireless network (MHWN) can be easily attacked by jammers for its shared nature and open access to the wireless medium. Jamming attack may pose a significant threat to MHWN by occupying wireless channel used by legitimate users. A number of anti‐jamming countermeasures have been put forward to eliminate the impact of communication disruption caused by jamming attacks. As an important building block of anti‐jamming strategies, jammer localisation attracts much attention in recent years and several algorithms have been presented. However, how to locate multiple co‐existing jammers receives little attention, and the efficiency and accuracy of the existing methods are still unsatisfactory. In this study, the authors focus on the localisation of sequential opening multi‐jammers and put forward the multi‐jammers localisation algorithm based on time series analysis (MLTSA) algorithm. The main process of MLTSA consists of four steps: detection of jamming attack, collection of received jamming signal strength, anomaly detection and separation of nodes, the existence determination and localisation of jammers. Finally, a series of simulation experiments are conducted to evaluate the correctness and effectiveness of the proposed algorithm. Experimental results show that the localisation accuracies of MLTSA are better than those of several state‐of‐the‐art solutions.

Multihop Wireless Networks (MHWNs) can be easily attacked by the jammer for their shared nature and open access to the wireless medium. The jamming attack may prevent the normal communication through occupying the same wireless channel of legal nodes. It is critical to locate the jammer accurately, which may provide necessary message for the implementation of antijamming mechanisms. However, current range-free methods are sensitive to the distribution of nodes and parameters of the jammer. In order to improve the localization accuracy, this article proposes a jammer localization method based on Gravitational Search Algorithm (GSA), which is a heuristic optimization evolutionary algorithm based on Newton’s law of universal gravitation and mass interactions. At first, the initial particles are selected randomly from the jammed area. Then, the fitness function is designed based on range-free method. At each iteration, the mass and position of the particles are updated. Finally, the position of particle with the maximum mass is considered as the estimated jammer’s position. A series of simulations are conducted to evaluate our proposed algorithms and the simulation results show that the GSA-based localization algorithm outperforms many state-of-the-art algorithms.

With the proliferation of the Internet of Things (IoT), the current "cloud-only" architectures cannot efficiently handle IoT's data processing and communications needs, while providing satisfactory service latency to support emerging mobile applications on the horizon that require almost real-time responses. fog computing is introduced as a new computing paradigm that distributes computation, communication, control, and storage closer to the end users along the "cloud- to-things" continuum. In this paper, we present a deadline-aware task scheduling mechanism for fog computing in a tiered IoT infrastructure, where service providers exploit the collaboration between their own fog nodes and the rented cloud resources to efficiently execute users' offloaded tasks, at large geographical scale. We first formulate the task-scheduling problem in such a cloud-fog environment as a multi-dimensional 0-1 knapsack problem that is NP-hard, and then propose an efficient algorithmic solution based on ant colony optimization heuristic. The main objective is to maximize the profits of fog service provider while meeting the tasks' deadline constraint. Extensive experimental results show that our proposed optimization and solution significantly improves the system performance compared with existing heuristics.

The control packets in the data center networks (DCNs) have to contest with the data packets although they are usually much shorter in size and much more important in network management. Moreover, the uneven distribution of the packets may create potential traffic hotspots in the DCN which could degrade network performance drastically. To bridge these gaps, a layout-independent constructing algorithm and a scheduling method are put forward towards layout-independent wireless facility in data centers. First of all, a conflict aware spanning tree algorithm is developed to construct the wireless facility network (WFN). Secondly, a scheduling method which contains three steps, route calculation, traffic estimation, and flow scheduling, is presented. In the route calculation step, a route set between each node pair is calculated in advance for later usage. The scheduler estimates the traffic loads on the links on a regular basis in the traffic estimation step. Then, arrived data and control flows are scheduled according to multiple policies based on given route sets and scheduling objectives in the flow scheduling step. Finally, a series of experiments have been conducted on NS3 based on two typical data center layouts. Experimental results in both scenarios have validated our proposal’ effectiveness.