Bipartite queueing networks with unknown statistics, where jobs are routed to and queued at servers and yield job-type and server-dependent utilities upon completion, model a wide range of problems in communications and related research areas (e.g., call routing in call centers, task assignment in crowdsourcing, job dispatching to cloud servers). Additionally, many such problems have additional routing constraints, such as quality of service or budgeted server cost constraints. The utility maximization problem in a bipartite queueing network with unknown statistics and subject to additional routing constraints is a constrained bandit learning problem with delayed feedback that depends on the server queueing delay. In this paper, we propose an efficient algorithm that overcomes the technical shortcomings of the state-of-the-art and effectively balances utility regret and peak job completion delay, while achieving constant peak constraint violation for the additional sample path routing constraints. Empirically, our algorithm is shown to simultaneously achieve low regret, peak delay, and peak constraint violation compared to existing algorithms.

This paper investigates the feasibility and optimization of 24/7 remote monitoring in the Arctic using Low Earth Orbit (LEO) satellite constellations, specifically Starlink. Through rigorous link analysis incorporating Equivalent Isotropic Radiated Power (EIRP), Gain-to-Noise Temperature ratio (G/T), free space path loss, and rain attenuation, we assess the Carrier-to-Noise Ratio (CNR) for a specified Arctic location. To enhance system reliability, Particle Swarm Optimization (PSO) is applied to optimize satellite constellation parameters, substantially improving visibility from an initial 92.2% to 96.67%. Further optimization via the Walker-Star constellation achieves an unprecedented 100% visibility for a three-month duration. Results highlight the critical impact of atmospheric conditions, satellite configuration, and elevation angles on the overall communication performance, demonstrating a robust methodology for ensuring continuous, reliable Arctic communication. MATLAB (R2024a), MATLAB Satellite Communications Toolbox ver. 24.1, and Aerospace Toolbox ver. 24.1 were used for the analysis in this paper. Some analysis in this paper was done using the computing resources provided by BC DRI Group and Digital Research Alliance of Canada. The satellite data was retrieved from space-track.org.

With electric vehicles (EVs) and charging facilities as a bridge, the coupling of transportation network (TN) and distribution network (DN) is getting closer, and EV charging navigation considering TN-DN convergence is a current research hotspot. In order to reduce the total cost of EV charging navigation and the impact of charging load on the grid, this paper proposes a novel bi-layer coordinated charging navigation model (Bi-CCNM). The upper layer model is to minimize the total cost of EV charging navigation. To precisely estimate travel costs, a dynamic spatio-temporal energy consumption estimation model is established, which considers the impact of dynamic traffic flow on EV travel resistance. The lower layer model aims to reduce energy exchange between the charging station (CS) and the main grid, and maximize the utilization of local renewable energy sources. To cope with the intermittent nature of renewable energy generation, this paper utilizes Vehicle-to-Grid (V2G) technology to effectively mitigate the impact of EV charging loads on the grid. To efficiently tackle the Bi-CCNM, the Joint Optimization algorithm combining Generalized Benders Decomposition and Logarithmic Barrier Function Method (JO-GBLB) is developed. Ultimately, an optimal solution can be obtained through the interaction of information between the two layers. Real-world case validates the effectiveness of the proposed the Bi-CCNM, energy consumption estimation model, and JO-GBLB algorithm. The results indicate which it provides a low-cost charging navigation solution while significantly reducing the power exchange between the CS and the main grid, effectively preventing safety issues caused by load fluctuations. Besides, the accuracy of energy consumption estimation of EVs increases by 5.1% - 6.7%.

Mobile edge computing (MEC) enhances data processing by enabling users to offload tasks to edge servers with enough computation resource. In multi-user and multi-server scenario, the offloading scheduling is overwhelming complex and significantly influences the processing delay, which makes deep learning (DL) become an appealing approach. Yet, prior DL-based methods often overlook dynamic topology challenges due to the inflexibility of fixed neural network structures, leading to constrained performance. To tackle this challenge, a novel reinforcement learning framework named dynamic topology adaptive reinforcement learning (DTA-RL) is proposed in this paper. The MEC network is modeled as a graph based on the communication relationships between users and servers, and the offloading process is formulated as a Markov decision process (MDP). Building on the graph model and MDP, DTA-RL leverages graph attention networks to handle dynamic observation spaces and incorporates an attention mechanism for decision-making in environments with evolving action spaces. Simulation results illustrate that DTA-RL effectively reduces task processing delays and offloading failure rates within the MEC system. Furthermore, the pre-trained model can be seamlessly implemented in networks with new topology without experiencing significant performance degradation. The code is available at https://github.com/UNIC-Lab/DTA-RL.

Bipartite queueing networks with unknown statistics, where jobs are routed to and queued at servers and yield server-dependent utilities upon completion, model a wide range of problems in communications and related research areas (e.g., call routing in call centers, task assignment in crowdsourcing, job dispatching to cloud servers). The utility maximization problem in bipartite queueing networks with unknown statistics is a bandit learning problem where the delayed semi-bandit feedback depends on the server queueing delay. In this paper, we propose an efficient algorithm that overcomes the technical shortcomings of the state-of-the-art and achieves square root regret, queue length, and feedback delay. Our approach also accommodates additional constraints, such as quality of service, fairness, and budgeted cost constraints, with constant expected peak violation and zero expected violation after a fixed timeslot. Empirically, our algorithm’s regret is competitive with the state-of-the-art for some problem instances and outperforms it in others, with much lower delay and constraint violation.

6G Internet of Things (IoT) is envisioned to provide large-scale network connections and high data transmission rates to satisfy the diverse needs of IoT nodes. The wireless powered communication network (WPCN) is the essential part of the future 6G IoT, which can provide nodes with reliable and efficient data and energy transmission. In complex environments, wireless power transmissions are inefficient due to transmission distance and obstacles. To address these concerns, we propose a novel quality of experience (QoE)-driven framework for aerial intelligent reflective surface (IRS)-assisted WPCN, which exploits the maneuverability of unmanned aerial vehicle (UAV) to improve the network performance. In the framework, we construct a nonlinear satisfaction function to quantify the QoE and design an adaptive reflective units configuration scheme based on the QoE to reduce resource consumption (e.g., energy) while satisfying the QoE requirements. The optimization problem of maximizing average throughput is formulated by jointly optimizing the aerial IRS flight trajectory, node association variable, time slot allocation ratio, and IRS phase. The existence of coupling between optimization variables and the nonconvexity lead to the difficulty of solving the optimization problem directly. To effectively solve the above optimization problem, the block coordinate descent (BCD) algorithm is utilized to decompose the optimization problem into four subproblems to be solved separately. Simulation results demonstrate that the proposed scheme can significantly enhance the throughput compared with other schemes.

A reliable driving trajectory prediction of surrounding vehicles is an essential reference for decision-making and safe driving of an autonomous vehicle. Although predicting short-term trajectories can be well achieved, it is still very challenging for long-term prediction of trajectories since the prediction space grows exponentially. In this paper, we propose a novel architecture for trajectory prediction from factored intention estimation (I2T), which decouples the trajectory prediction space into a high-level space for intention estimation and a low-level space for motion prediction. The long-term dependencies between intention cues and future motions during driving are naturally extended to the internal sharing mechanism of I2T, leading to improved performance. Furthermore, we design a Prioriformer model to serve as the backbone network for I2T so that it can accurately capture the long-term dependency couplings related to the task of intention estimation or motion prediction. Prioriformer model adopts a personalized normalization method, which facilitates learning latent representations of long-term features and avoids getting stuck on local optimum. A designed multi-scale fusion encoder extracts features from various receptive fields and then learns richer information from the representation subspaces. An efficient non-autoregressive decoder reduces the pressure in long-term prediction of trajectories while avoiding cumulative errors. Experiments on three real-world motion datasets show that I2T can significantly outperform the state-of-the-art.

In the task of traffic flow forecasting, various external factors need to be considered to interfere with the flow, such as weather conditions, traffic accidents, emergency events, and Points of Interest (POIs). While capturing the spatio-temporal dependencies, it is essential to effectively capture the external factors. However, existing studies cannot effectively cascade the information contained in these external factors to traffic features, and lack the co-capture of spatio-temporal features. To address these challenges, we present a Knowledge Representation learning-actuated Spatio-Temporal Graph Neural Network (KR-STGNN) for traffic flow prediction. The Gated Feature Fusion Module (GFFM) is utilized to combine the knowledge embedding with the traffic features, and the traffic features are updated adaptively and dynamically according to the importance of external factors. To conduct the co-capture of spatio-temporal dependencies, we subsequently propose a spatio-temporal feature synchronous capture module combining dilation causal convolution with GRU. Experimental results on a real-world traffic dataset demonstrate that KR-STGNN has superior forecasting performances with different prediction steps, especially for short-term prediction.

Driven by the ever-increasing computing capabilities of mobile devices, the next-generation wireless networks are evolving toward a distributed networking and computing platform, which enables in-network computing and unified resource/service provisioning. The evolution leads to a growing research interest in wireless computing networks that operate under both the high dynamics of the wireless environment and the resource heterogeneity, which complicates resource allocation, scheduling among network flows, and overall optimization. In this paper, we aim to study a low-complexity efficient solution to jointly allocate both networking resources (e.g., links to forward packets between connected computing nodes) and computing resources (e.g., computing power at each node for packet processing). We formulate a novel network utility maximization problem under computing and networking resource constraints and develop an enhanced backpressure-based dynamic scheduling and routing algorithm. Finally, we verify the effectiveness of the algorithm with extensive simulations.

Bandits with arm selection constraints and bandits with switching costs have both gained recent attention in wireless networking research. Pessimistic-optimistic algorithms, which combine bandit learning with virtual queues to track the constraints, are commonly employed in the former. Block-based algorithms, where switching is disallowed within a block, are commonly employed in the latter. While efficient algorithms have been developed for both problems, it remains challenging to guarantee low regret and constraint violation in a bandit problem that includes both arm selection constraints and switching costs due to the tight coupling between the two. Here, switching may be necessary to decrease the constraint violation but comes at the cost of increased switching regret. In this paper, we tackle the constrained bandits with switching costs problem, for which we design a block-based pessimistic-optimistic algorithm. We identify three timely wireless networking applications for this framework in edge computing, mobile crowdsensing, and wireless network selection. We also prove that our algorithm achieves sublinear regret and vanishing constraint violation and corroborate these results with synthetic simulations and extensive trace-based simulations in the wireless network selection setting.

Accurately forecasting the future motions of road participants is essential for proactive hazard avoidance and safety planning of autonomous vehicles. Existing methods for motion prediction based on probabilistic generative models are limited to low-accuracy likelihood calculations and relatively finite mode distributions. Recent studies show that score-based models can naturally overcome these limitations. In this work, we present a novel paradigm of conditional score-based models for vehicle motion prediction, called Motion-CSM. First, we model scene contextual representations of interaction regions at the feature level via graph convolutional networks. We then interpolate these representations as conditions into the solution process of the continuous-time reverse stochastic differential equation (SDE) to guide trajectory generation, which progressively converts the known prior distributions into multimodal trajectories including the ground truth modes. The designed stacked Transformer structure with dual control conditions is adopted to learn the score function approximation of the Gaussian perturbation kernel. Finally, we develop multiple consistency constraints to align the inference results of Motion-CSM in reverse SDE solving to improve the self-consistency and stability of multimodal trajectory generation. Experimental results on the real-world motion dataset demonstrate that the multimodal forecasting accuracy of Motion-CSM outperforms state-of-the-art methods.

Motivated by ever-increasing computational resources at edge devices and increasing privacy concerns, a new machine learning (ML) framework called federated learning (FL) has been proposed. FL enables user devices, such as mobile and Internet of Things (IoT) devices, to collaboratively train an ML model by only sending the model parameters instead of raw data. FL is considered the key enabling approach for privacy-preserving, distributed ML systems. However, FL requires frequent exchange of learned model updates between multiple user devices and the cloud/edge server, which introduces a significant communication overhead and hence imposes a major challenge in FL over wireless networks that are limited in communication resources. Moreover, FL consumes a considerable amount of energy in the process of transmitting learned model updates, which imposes another challenge in FL over wireless networks that usually include unplugged devices with limited battery resources. Besides, there are still other privacy issues in practical implementations of FL over wireless networks. In this survey, we discuss each of the mentioned challenges and their respective state-of-the-art proposed solutions in an in-depth manner. By illustrating the tradeoff between each of the solutions, we discuss the underlying effect of the wireless network on the performance of FL. Finally, by highlighting the gaps between research and practical implementations, we identify future research directions for engineering FL over wireless networks.

Federated Learning (FL) is considered the key approach for privacy-preserving, distributed machine learning (ML) systems. However, due to the transmission of large ML models from users to the server in each iteration of FL, communication on resource-constrained networks is currently a fundamental bottleneck in FL, restricting the ML model complex-ity and user participation. One of the notable trends to reduce the communication cost of FL systems is gradient compression, in which techniques in the form of sparsification or quantization are utilized. However, these methods are pre-fixed and do not capture the redundant, correlated information across parameters of the ML models, user devices' data, and iterations of FL. Further, these methods do not fully take advantage of the error-correcting capability of the FL process. In this paper, we propose the Federated Learning with Autoencoder Compression (FLAC) approach that utilizes the redundant information and error-correcting capability of FL to compress user devices' models for uplink transmission. FLAC trains an autoencoder to encode and decode users' models at the server in the Training State, and then, sends the autoencoder to user devices for compressing local models for future iterations during the Compression State. To guarantee the convergence of the FL, FLAC dynamically controls the autoencoder error by switching between the Training State and Compression State to adjust its autoencoder and its compression rate based on the error tolerance of the FL system. We theoretically prove that FLAC converges for FL systems with strongly convex ML models and non-i.i.d. data distribution. Our extensive experimental results'over three datasets with different network architectures show that FLAC can achieve compression rates ranging from 83x to 875x while staying near 7 percent of the accuracy of the non-compressed FL systems.

Multi-armed bandit frameworks, including combinatorial semi-bandits and sleeping bandits, are commonly employed to model problems in communication networks and other engineering domains. In such problems, feedback to the learning agent is often delayed (e.g. communication delays in a wireless network or conversion delays in online advertising). Moreover, arms in a bandit problem often represent entities required to be treated fairly, i.e. the arms should be played at least a required fraction of the time. In contrast to the previously studied asymptotic fairness, many real-time systems require such fairness guarantees to hold even in the short-term (e.g. ensuring the credibility of information flows in an industrial Internet of Things (IoT) system). To that end, we develop the Learning with Delays under Fairness (LDF) algorithm to solve combinatorial semi-bandit problems with sleeping arms and delayed feedback, which we prove guarantees strong (short-term) fairness. While previous theoretical work on bandit problems with delayed feedback typically derive instance-dependent regret bounds, this approach proves to be challenging when simultaneously considering fairness. We instead derive a novel instance-independent regret bound in this setting which agrees with state-of-the-art bounds. We verify our theoretical results with extensive simulations using both synthetic and real-world datasets.

Unmanned aerial vehicles (UAVs) serve as aerial base stations to provide controlled wireless connections for ground users. Due to their constraints on both mobility and energy consumption, a key problem is how to deploy UAVs adaptively in a geographic area with changing traffic demand of mobile users, while meeting the aforementioned constraints. In this article, we propose a Quality of Experience (QoE)-driven and energy-efficient adaptive deployment strategy for multi-UAV networks based on hybrid deep reinforcement learning (DRL) to solve the problem of incomplete information game, where the UAVs can adjust their moving directions and distance to serve users who move randomly in the target area. Through the hybrid DRL with centralized training and distributed testing, UAVs can be trained offline to obtain the global state information and learn a completely distributed control strategy, with which each UAV only needs to take actions based on its observed state in the real deployment to be fully adaptive. Moreover, in order to improve the speed and effect of learning, we improve hybrid reinforcement learning, by adding genetic algorithms and temporal difference error-based resampling optimization mechanism. The simulation results show that the hybrid DRL algorithm has better efficiency and robustness in multi-UAV control, and has better performance in terms of QoE, energy consumption, and average throughput, by which average throughput can be increased by 20%–60%.

Next-generation intelligent transportation systems (ITS) are envisioned to greatly improve transportation safety and efficiency by incorporating wireless communications and informatics technologies into transportation systems. As the cornerstone for ITS, vehicular communication networks enable vehicles on the go to exchange information with other vehicles and the external environments, which expect to play a significant role in supporting a variety of services such as road safety, traffic management, and infotainment. However, the existing terrestrial networks including dedicated shortrange communications (DSRC)-based networks and cellular networks alone cannot serve the vehicular applications very well in different scenarios, due to the inherent issues of deployment, coverage, and capacity. It is imperative to exploit other communication infrastructures, such as low-earth orbit (LEO) satellites, unmanned aerial vehicles (UAVs), and high-altitude platforms, to support vehicular applications better, resulting in space-air-ground integrated networks (SAGIN). SAGIN can provide more comprehensive and three-dimensional network connectivity for moving vehicles, anywhere and anytime, by exploiting their respective advantages in terms of coverage, flexibility, reliability, and availability.

How to alleviate the traffic congestion and improve the traffic capacity of road networks through smart prediction has become a top priority for the realization of Intelligent Transportation Systems (ITS). It is necessary to capture the complex spatio-temporal correlation through the traffic data of road networks to achieve an accurate traffic prediction. In this paper, we propose a prediction method of spatio-temporal optimal graph neural network (STOG). It can obtain the spatio-temporal features of road networks through diffusion graph convolution (DGC) and recurrent neural network (RNN). We further leverage a new spatial attention mechanism to gain the aggregated features of the sampled nodes through pooling operations. It not only avoids excessive parameters, but also makes the model pays more attention to the sampled nodes, thereby reducing the prediction error. Through comparison with various baseline methods on METR-LA dataset, the results show that the proposed model can achieve higher prediction accuracy.

Vehicle trajectory prediction technology is of great significance in autonomous driving and intelligent transportation systems. Ego-vehicles can judge the future motion state considering nearby vehicles by predicting their trajectories, which facilitates safe and effective decisions to avoid collisions. It is a challenging task to accurately predict the future trajectories of surrounding vehicles. To solve this problem, we propose a Self-Attention Social Generative Adversarial Networks (SA-SGAN) model to predict trajectories of surrounding vehicles. We use the Self-Attention mechanism to capture the correlation between the features in the vehicle trajectory sequence to effectively solve the problem of missing important information due to a long input sequence, and use training characteristic of Generative Adversarial Networks (GAN) to effectively learn the distribution of real trajectory data and improve prediction accuracy. We evaluate the proposed model through NGSIM dataset, use the trained model to investigate the vehicle trajectory in the next 5s in a three-segment scenario of the US-101 highway, and use the Average Displacement Error (ADE) and Final Displacement Error (FDE) as the evaluation indicators. Compared with baseline methods, the proposed model reduces the evaluation indicators to 4.97 and 8.92 respectively.

State-of-the-art mechanisms against eavesdropping first encrypt all packet payloads in the application layer and then split the packets into multiple network paths. However, versatile eavesdroppers could simultaneously intercept several paths to intercept all the packets, classify the packets into streams using transport fields, and analyze the streams by brute-force. In this article, we propose a programming protocol-independent packet processors (P4)-based network immune scheme (P4NIS) against the intractable eavesdropping. Specifically, P4NIS is equipped with three lines of defenses to provide a softwarized network immunity. Packets are successively processed by the third, second, and first line of defenses. The third line basically encrypts all packet payloads in the application layer using cryptographic mechanisms. Additionally, the second line re-encrypts all packet headers in the transport layer to distribute the packets from one stream into different streams, and disturbs eavesdroppers to classify the packets correctly. Besides, the second line adopts a programmable design for dynamically changing encryption algorithms. Complementally, the first line uses programmable forwarding policies which could split all the double-encrypted packets into different network paths disorderly. Using a paradigm of programmable data planes-P4, we implement P4NIS and evaluate its performances. Experimental results show that P4NIS can increase difficulties of eavesdropping and transmission throughput effectively compared with state-of-the-art mechanisms. Moreover, if P4NIS and state-of-the-art mechanisms have the same level of defending eavesdropping, P4NIS can decrease the encryption cost by 69.85%-81.24%.

Unmanned Aerial Vehicle (UAV) Networks have recently attracted great attention as being able to provide convenient and fast wireless connections. One central question is how to allocate a limited number of UAVs to provide wireless services across a large number of regions, where each region has dynamic arriving flows and flows depart from the system once they receive the desired amount of service (referred to as the flow-level dynamic model). In this article, we propose a MaxWeight-type scheduling algorithm taking into account sharp flow-level dynamics that efficiently redirect UAVs across a large number of regions. However, in our considered model, each flow experiences an independent fading channel and will immediately leave the system once it completes its service, which makes its evolution quite different from the traditional queueing model for wireless networks. This poses significant challenges in our performance analysis. Nevertheless, we incorporate sharp flow-dynamic into the Lyapunov-drift analysis framework, and successfully establish both throughput and heavy-traffic optimality of the proposed algorithm. Extensive simulations are performed to validate the effectiveness of our proposed algorithm.

We consider a setting in which a rotary-wing unmanned aerial vehicle (UAV) acts as an aerial base station to provide emergency communication service to an area of unknown and inhomogeneous user distribution. The UAV has communication with a ground node deployed to the area, which acts as a charging station. We are interested in two important problems in this setting, namely the path planning and coverage mapping problems. In the path planning problem, the UAV must plan its path starting and ending at the charging station, visiting a series of waypoints over which it hovers to provide coverage to surrounding users. On the other hand, the coverage mapping problem focuses on learning the distribution of user coverage over the area. We highlight the importance of learning this distribution to collect valuable data in an emergency situation. We then propose an online algorithm that simultaneously solves the path planning and coverage mapping problems using a deep learning model. We highlight the interplay and conflicting goals of path planning and coverage mapping, but show through Monte Carlo simulation that, under the correct parameters, the algorithm is able to achieve success on both problems.

Unmanned aerial vehicles (UAVs) can be used as air base stations to provide fast wireless connections for ground users. Due to their constraints on both mobility and energy consumption, a key problem is how to deploy UAVs adaptively in a geographic area with changing traffic demand of mobile users, while meeting the aforemetioned constraints. In this paper, we propose an adaptive deployment strategy for UAV-aided networks based on hybrid deep reinforcement learning, where a UAV can adjust its movement direction and distance to serve users who move randomly in the target area. Through hybrid deep reinforcement learning, UAVs can be trained offline to obtain the global state information and learn a completely distributed control strategy, with which each UAV only needs to take actions based on its observed state in the real deployment to be fully adaptive. Moreover, in order to improve the speed and effect of learning, we improve hybrid reinforcement learning, by adding genetic algorithms and TD-error-based resampling optimization mechanism. Simulation results show that the hybrid deep reinforcement learning algorithm has better efficiency and robustness in multi-UAV control, and has better performance in terms of coverage, energy consumption and average throughput, by which average throughput can be increased by 20% to 60%.

With the ubiquitous deployment of mobile sensors and smart devices, the scope of Internet of things (IoT) has extended to the space of mobile networks, where IoT terminals are moving around instead of being fixed in buildings, ground infrastructures, etc. In this paper, we consider such mobile Internet of things (MIoT), and propose an autonomous rate control (RC) scheme for the uplink transmission from MIoT terminals to access stations. A deep reinforcement learning (DRL) based approach is designed to capture the channel variations of the link and to improve the effectiveness of the rate selection for each egress frame. Extensive simulations are conducted for MIoT terminals including vehicles and UAVs and show significant throughput performance improvement comparing with traditional methods, as well as the robustness and scalability of the DRL-RC algorithm. The proposed DRL-RC can provide inspirations for efficient and scalable link adaptation schemes for MIoT terminals.

The deployment of drone small cells has emerged as a promising solution to agile provisioning of Internet backbone access for Internet of Things devices, and many other types of users/devices. In this paper, we consider the problem of deploying a set of drone cells operating on multiple channels in a target area to provide access to the backbone/core network, which is formulated as a combinatorial network utility maximization problem. Since an offline and centralized solution to such a problem is not feasible, a low-complexity and distributed online algorithm is highly desired. Therefore, we propose a measurement-aided dynamic planning (MAD-P) algorithm, where the dispatched drones perform position and channel configurations autonomously on the fly based on the real-time measurement of network throughput to solve the problem in a distributed fashion during flight with minimal centralized control. We prove that the proposed MAD-P algorithm is asymptotically optimal, and investigate how long it takes for the convergence to stationarity under the MAD-P algorithm by giving a mixing time analysis. We also derive an upper bound of the performance gap in presence of measurement errors. Simulation results are provided to validate our analytic results and demonstrate the effectiveness of our algorithm.

We consider the problem of scheduling real-time traffic with hard deadlines in a wireless ad hoc network. In contrast to existing real-time scheduling policies that merely ensure a minimal timely throughput, our design goal is to provide guarantees on both the timely throughput and data freshness in terms of age-of-information (AoI), which is a newly proposed metric that captures the "age" of the most recently received information at the destination of a link. The main idea is to introduce the AoI as one of the driving factors in making scheduling decisions. We first prove that the proposed scheduling policy is feasibility-optimal, i.e., satisfying the per-traffic timely throughput requirement. Then, we derive an upper bound on a considered data freshness metric in terms of AoI, demonstrating that the network-wide data freshness is guaranteed and can be tuned under the proposed scheduling policy. Interestingly, we reveal that the improvement of network data freshness is at the cost of slowing down the convergence of the timely throughput. Extensive simulations are performed to validate our analytical results. Both analytical and simulation results confirm the capability of the proposed scheduling policy to improve the data freshness without sacrificing the feasibility optimality.

Next-generation intelligent transportation systems (ITS) are envisioned to greatly improve the transportation safety and efficiency by incorporating wireless communication and informatics technologies in the transportation system [1][2][3].As the cornerstone for ITS, vehicular communication networks enable vehicles to exchange information with other vehicles and the external environments and play a significant role in supporting a variety of services such as road safety, traffic management, and entertainment Vehicular communication networks face many technical challenges such as network scalability, highly dynamic topology, vulnerable wireless links, energy consumption of roadside units, poor network coverage, and bursty traffic.To address these challenges, various emerging technologies have been introduced in vehicular communication networks, such as software defined space-air-ground integrated vehicular network [4], fog computing in vehicular networks [5], droneassisted vehicular networks [6], and machine learning for data delivery [7].This special issue collection aims to present the vision, research, and dedicated efforts on the emerging technologies for vehicular communication networks.In this special issue, there are 15 submissions in total.After peerreview, 6 papers are selected for publication.The first article, "Software-Defined Collaborative Offloading for Heterogeneous Vehicular Networks" by W. Quan et al., proposes a software-defined collaborative offloading (SDCO) solution for heterogeneous vehicular networks, to efficiently manage the offloading nodes and paths.The offloading controller is equipped with two specific functions:

Data delivery in vehicular networks (VANETs) is a challenging task due to the high mobility and constant topological changes. In common routing protocols, multihop V2V communications suffer from higher network delay and lower packet delivery ratio (PDR), and excessive dependence on GPS may pose threat on individual privacy. In this paper, we propose a novel data delivery scheme for vehicular networks in urban environments, which can improve the routing performance without relying on GPS. A fuzzy‐rule‐based wireless transmission approach is designed to optimize the relay selection considering multiple factors comprehensively, including vehicle speed, driving direction, hop count, and connection time. Wireless V2V transmission and wired transmissions among RSUs are both utilized, since wired transmissions can reduce the delay and improve the reliability. Each RSU is equipped with a machine learning system (MLS) to make the selected relay link more reliably without GPS through predicting vehicle speed at next moment. Experiments show the validity and rationality of the proposed method.

Clustering has been extensively used in Vehicular Ad- hoc NETworks (VANETs) for routing optimization and radio resource management, and continues to be considered to facilitate data dissemination in heterogeneous vehicular networks with the ever- increasing data traffic demands. Most of the existing clustering mechanisms in VANETs operate in a distributed mode. However, there is redundant control overhead and transmission decisions, such as cluster maintenance, parameter tuning and forwarding scheduling, which are costly in distributed modes. In this paper, a centralized clustering based hybrid vehicular networking architecture (CC-HVNA) is proposed, in which the collaborative control between IEEE 802.11p and LTE is realized to achieve clustering and to coordinate message delivery. In CC-HVNA, a volatile node state SN is set to reflect ever-changing network topology and to update clusters. Location-based Vehicle to Infrastructure (V2I) communications are utilized to gather regional information so as to perform centralized clusters partition and maintain cluster info table in infrastructures. We leverage a control center to integrate cluster info from the Evolved Node (eNodeB) and Road Side Units (RSUs). Owing to the possession of global cluster info, cluster changes can be detected and targeted data dissemination can be supported according to content-oriented service. The performance evaluation demonstrates that the proposed CC-HVNA clustering scheme can achieve a significant improvement of safety data dissemination.

To improve the safety, traffic efficiency, and fairness among vehicles at intersections, it is urgent to study intelligent collaborative strategies and make intersections smarter. In this paper, a 3-Level Buffer (TLB) based Virtual Traffic Light (VTL) scheme, named TLB-VTL, is proposed for intelligent collaborative intersections. The intersection is divided into three adaptive areas according to the traffic flow of each lane, and the sequence of each timing cycle is calculated in realtime according to the flow in TLB around an intersection. To ensure fairness, the difference in probability of each lane to pass an intersection is restricted to a lower level. The VTL is realized based on communications of vehicle-to-vehicle (V2V), vehicle-to-roadside (V2R), and vehicle-to- infrastructure (V2I), which could improve the safety and fairness without involving traffic lights. Moreover, a Cooperative Collision Avoidance Predictive control (CCAP) algorithm is proposed, which can assist vehicles to go across the next intersection without stopping through predicting the time conflict and generating an efficient traffic schedule for the entire road network. The simulation results indicate that the proposed TLB-VTL algorithm improves the fairness by 331%, decreases the average delay by 88%, and improves the ability to solve congestion by 12% compared with the traditional traffic light algorithm. Besides, the CCAP algorithm increases the traffic fluency by 45% at the intersection.

The TV white spaces (TVWS) enabled infostation has received significant attention due to its wide area coverage for cost-effective and media-rich content dissemination. In this paper, we engineer WhiteFi infostation, which is dedicated for Internet-based vehicular media streaming by leveraging geolocation database. After demonstrating the empirical observations of unique TVWS features and analyzing the real-world TVWS data collected from geolocation database, we first propose an optimal TVWS network planning to deploy WhiteFi infostation with the objective of maximizing network-wide throughput. The proposed TVWS network planning jointly considers the multi-radio configuration and the channel-power tradeoff, which can be realized by decentralized Markov approximation. Furthermore, we introduce a location-aware contention-free multi-polling access scheduling scheme for vehicular media streaming, which considered both the realistic vehicular applications and dynamics of wireless channel conditions. Through extensive simulations with real-world empirical TVWS data and urban vehicular traces, we demonstrate that our WhiteFi infostation solution can well support both the delay-sensitive and delay-tolerant vehicular media streaming services.

Abstract Radio Frequency Identification (RFID) technology provides a seamless link between physical world and the information system in cyber space. However, the emerging Internet of Things and cloud systems are full of security holes, which introduce new challenging security problems in both tag identification and data privacy. In this paper, we present efficient methods for identity authentication and data encryption to enhance RFID privacy. The proposed techniques aim to ensure no adversary interacting with the tags and the reader, to infer any information on a tag's identity from the communication. The main idea, a symmetric cryptography technique, termed as Advanced Encryption Standard, was applied to implement both mutual authentication and data encryption between the front and back ends of RFID systems. The Advanced Encryption Standard cryptographic algorithm was adopted because of its low hardware complexity and high security strength. In addition, the proposed key management protocol is proved resistant to several known RFID attacks such as Man‐in‐the‐Middle, Denial‐of‐Service, replay, clone attack, and backward/forward traceability. The computational time complexity of the proposed scheme through the entire identity authentication and data encryption phases is 3Tencrypt + 1Tnonce + 4Txor, which is superior to most existing approaches. The proposed scheme was also proved to be able to provide higher data encryption performance than other symmetric cryptographic algorithms with regard to the same level of security strength. Copyright © 2016 John Wiley & Sons, Ltd.

In this paper, we study opportunistic traffic offloading in a vehicular environment, where the cellular traffic of vehicular users (VUs) is offloaded through carrier-WiFi networks deployed by the mobile network operator (MNO). By jointly considering users' satisfaction, the offloading performance, and the MNO's revenue, two WiFi offloading mechanisms are proposed: auction game-based offloading (AGO) and congestion game-based offloading (CGO). Moreover, we introduce an approach to predict WiFi offloading potential and access cost and incorporate it in the offloading mechanisms. Specifically, with the AGO mechanism, the MNO employs auctions to sell WiFi access opportunities; VUs decide whether to bid according to their utilities and are capable of using WiFi if the auction is won. With the CGO mechanism, a VU calculates utility considering other VUs' strategies and makes offloading decisions accordingly. We show that the AGO mechanism can maximize social welfare and increase the MNO's revenue, whereas the CGO mechanism can achieve a better performance of average VU utility and fairness. Additionally, both AGO and CGO mechanisms can improve the overall WiFi offloading performance. Through simulations, we demonstrate that both AGO and CGO mechanisms can achieve higher average utility of VUs and lower average service delay and offload much more cellular traffic compared with existing offloading mechanisms.

We study user cooperation to enhance the physical layer security. Specifically, the source cooperates with friendly intermediate nodes to transmit message securely in the presence of multiple eavesdroppers. We propose a cooperative framework, whereby the source selects multiple partners and stimulates them by granting an amount of reward. First, multiple cooperative relays and jammers are selected by the source using greedy or cross-entropy based approaches. Then, the source and the partners negotiate for the payment and transmission power, which is modeled as a two-layer game. At the top layer, a buyer-seller game is utilized, where the source buys the service provided by the partners. At the bottom layer, all the partners share the reward by determining their transmission powers in a distributed way, which is formulated as a non-cooperative power selection game. By analyzing the game, the partners can determine the transmission powers for cooperation, while the source can select the best payment. To further improve the utility of the source, a set of reward allocation coefficients are introduced and optimized using particle swarm optimization approach. Simulation results are provided to demonstrate the performance of the proposed schemes.

In this paper, we present an analytical framework for offloading cellular traffic by outdoor WiFi network in the vehicular environment. Specifically, we consider a generic vehicular user with Poisson data service arrivals to download/upload data from/to the Internet through the cost-effective WiFi network (want-to) or the cellular network providing full service coverage (have-to). Under this scenario, the WiFi offloading performance, characterized by offloading effectiveness, is analyzed in terms of desired average service delay which is the average time the data services can be deferred for WiFi availability. We establish an explicit relation between offloading effectiveness and average service delay by an M/G/l/K queueing model, and the tradeoff between the two is examined. We validate our analytical framework through simulations based on a VANET simulation tool VANETMobisim and real map data sets. Our analytical framework should be valuable for providing offloading guidelines to both vehicular users and network operators.

Providing various wireless connectivities for vehicles enables the communication between vehicles and their internal and external environments. Such a connected vehicle solution is expected to be the next frontier for automotive revolution and the key to the evolution to next generation intelligent transportation systems (ITSs). Moreover, connected vehicles are also the building blocks of emerging Internet of Vehicles (IoV). Extensive research activities and numerous industrial initiatives have paved the way for the coming era of connected vehicles. In this paper, we focus on wireless technologies and potential challenges to provide vehicle-to-x connectivity. In particular, we discuss the challenges and review the state-of-the-art wireless solutions for vehicle-to-sensor, vehicle-to-vehicle, vehicle-to-Internet, and vehicle-to-road infrastructure connectivities. We also identify future research issues for building connected vehicles.

In this paper, risk-aware cooperative spectrum access schemes for cognitive radio networks (CRNs) with multiple channels are proposed, whereby multiple primary users (PUs) operating over different channels choose trustworthy secondary users (SUs) as relays to improve throughput, and in return SUs gain transmission opportunities. To study the multi-channel cooperative spectrum access, cooperation over single channel is investigated first, which involves a PU selecting the suitable SU and granting a period of access time to the selected SU as a reward, considering trustworthiness of SUs. The above procedure is modeled as a Stackelberg game, through which access time allocation and power allocation are obtained. Based on the above results, cooperation over multiple channels is studied from the perspectives of the primary network and secondary network, respectively. Two schemes are proposed accordingly: the primary network-centric matching (PCM) scheme and the secondary network-centric cluster-based (SCC) scheme. In PCM scheme, cooperating SU for each channel is determined to maximize the total utility of the primary network, which is formulated as a maximum weight matching problem. In SCC scheme, SUs first form a cluster to share the channel state information (CSI), and the best SUs are selected for cooperation with PUs over different channels to obtain the maximum aggregate access time for the secondary network. Then, SUs share the obtained resource using congestion game and quadrature signalling. Numerical results demonstrate that, with the proposed schemes, PUs can achieve higher throughput, while SUs can obtain longer average access time, compared with the random channel access approach.

In this paper, we investigate the asymptotic performance limits (throughput capacity and average packet delay) of social-proximity vehicular networks. The considered network involves N vehicles moving and communicating on a scalable grid-like street layout following the social-proximity model: Each vehicle has a restricted mobility region around a specific social spot and transmits via a unicast flow to a destination vehicle that is associated with the same social spot. Moreover, the spatial distribution of the vehicle decays following a power-law distribution from the central social spot toward the border of the mobility region. With vehicles communicating using a variant of the two-hop relay scheme, the asymptotic bounds of throughput capacity and average packet delay are derived in terms of the number of social spots, the size of the mobility region, and the decay factor of the power-law distribution. By identifying these key impact factors of performance mathematically, we find three possible regimes for the performance limits. Our results can be applied to predict the network performance of real-world scenarios and provide insight on the design and deployment of future vehicular networks.

In this paper, an opportunistic channel access for cognitive radio networks (CRNs) with multiple channels is proposed, whereby the secondary users (SUs) cooperate with primary users (PUs) to improve the latter's throughput and gain transmission opportunities in return. Cooperation on single channel is studied first, which is modeled by the Stackelberg game. By analyzing the game, the access time allocation of the PU and the optimal transmission power of the SU can be obtained. Then, based on the outcome of the above game, cooperation on multiple channels in the network is studied. To better exploit transmission opportunities on different channels, a cluster-based cooperation scheme (CBC) is proposed, whereby SUs first form a cluster, select best SUs to obtain the maximum sum of the access time using maximum weight matching, and then share the obtained channels fairly using congestion game and quadrature signalling. The condition for Nash Equilibrium (NE) of the congestion game is provided and an algorithm for CBC scheme is proposed. Numerical results demonstrate that, with the proposed scheme, the SUs can get more average access time and achieve higher fairness, compared with the random channel access approach.

The booming smart grid produces a large amount of data that should be transmitted to the utility control center (UCC), typically by means of the cellular network. This may pose a prohibitive transmission cost and choke the cellular network. As an effort to address this issue, we propose a vehicle assisted data delivery method to offload the cellular network, in which vehicles are utilized to carry and deliver the data from distributed locations to the UCC through the deployed roadside units. Two data forwarding schemes are developed based on the theory of optimal stopping rules to increase the data delivery probability. Simulation results are given to demonstrate that the proposed method can achieve high data delivery ratio through the roadside network so that it can efficiently offload the cellular network and reduce the communication cost.

The current coding standard employs differential coding to reduce the coding rate. Decoding error may propagate in the following frames after a loss-unrecoverable frame. Since most of the current electronic devices are implemented with multiple interfaces, such as the 3G and WiFi, one way to solve the error propagation problem is to use cooperative strategies, which leverage on the ‘uncorrelatedness’ of the clients' channels (different channels may experience different channel losses). The cooperative strategies helping to repair the primary network's (base station to client) losses via the neighboring clients' packets sharing (client to client) through the second network interface and optimally allocating the modulation and coding schemes to the limited network resource can improve the clients' received quality massively. The inherent problem is how to solve the resource allocation problem with the cooperative strategies. In this paper, we jointly consider the resource allocation and the cooperative repair for the video streaming. We formulate the problem into the optimization problem, i.e. maximizing the clients' received video quality, and apply the structured network coding to further improve the overall performance. Simulation results show that the proposed approach outperforms the other competing schemes by at least 1.5dB in term of the received video quality in typical network scenarios.

In this paper, we propose an electronic mail system, namely VeMail, for handling messages between vehicles and Intelligent Transportation Systems (ITS), to improve the efficiency of transportation management. After elaborating the reasons of using Internet email as a basis of messaging for ITS, we describe the key components of the VeMail system, including mail server, mail client, and mail proxy. Considering the intermittent connectivity of vehicles to the mail server, we propose an optimal probabilistic message retrieval (OPMR) scheme for VeMail, in which each vehicle optimally selects an online period for email retrieval. Simulation is used to evaluate the performance and the results demonstrate that the proposed scheme outperforms the regular mail retrieval method in terms of the connection time with the mail server.

In this paper, we investigate cooperative networking in cognitive radio networks (CRNs), which targets to help the primary users (PUs) for secure communications and provide transmission opportunities to secondary users (SUs). Two cooperation schemes: relay-jammer (R-J) scheme and cluster-beamforming (C-B) scheme, are proposed. In R-J cooperation scheme, two individual SUs, a relay and a friendly jammer, are leveraged by the PU to improve communication secrecy via cooperation; In return, the PU allocates a fraction of access time for SUs' transmission. To achieve the maximum secrecy rate, joint time and power allocation is considered. In C-B cooperation scheme, the PU cooperates with a cluster of SUs, which enhance the secrecy of primary link via collaborative beamforming and gain spectrum access opportunities as a reward. With the objective of maximizing the secrecy rate, the optimal weights and time allocation are studied. Numerical results validate the proposed schemes and demonstrate that the PU can significantly enhances the secrecy through cooperation with the cooperating SUs by allocating time and transmission power optimally.

In cognitive radio networks (CRNs), secure information transfer is of paramount importance for primary users (PUs), while secondary users (SUs) mainly desire to ease the starvation for transmission opportunities. To meet such different requirements, cooperation between PUs and SUs can be leveraged and therefore create a win-win situation. In this paper, we investigate cooperative spectrum access for CRNs, which targets to improve the secure transmission of PUs via cooperating SUs that would be incented by certain transmission opportunities. Two types of cooperation schemes are proposed, whereby the PU either cooperates with two individual SUs or a cluster of SUs, which are referred to as relay-jammer (R-J) scheme and cluster-beamforming (C-B) scheme, respectively. In R-J scheme, two individual SUs act as a relay and a friendly jammer to improve the PU's secrecy; In return, the PU allocates a fraction of access time for the SUs' transmission. To achieve the maximum secrecy rate, joint time and power allocation is considered. Particularly, the cooperating relay and jammer determine the optimal transmission power, while the PU decides the optimal time allocation strategy. In C-B scheme, the PU cooperates with a cluster of SUs to enhance the secrecy of the primary link via collaborative beamforming, where three different approaches are proposed for the scenarios with one eavesdropper, with multiple eavesdroppers, and without eavesdroppers' information, respectively. To maximize the secrecy rate, the weight selection and time allocation are also studied. Simulation results are given to validate the proposed schemes and demonstrate that the PU can significantly enhance the secrecy through cooperation.

Access infrastructure, such as Wi-Fi access points and cellular base stations (BSs), plays a vital role in providing pervasive Internet services to vehicles. However, the deployment costs of different access infrastructure are highly variable. In this paper, we make an effort to investigate the capacity-cost tradeoffs for vehicular access networks, in which access infrastructure is deployed to provide a downlink data pipe to all vehicles in the network. Three alternatives of wireless access infrastructure are considered, i.e., cellular BSs, wireless mesh backbones (WMBs), and roadside access points (RAPs). We first derive a lower bound of downlink capacity for each type of access infrastructure. We then present a case study based on a perfect city grid of 400 km2with 0.4 million vehicles, in which we examine the capacity-cost tradeoffs of different deployment solutions in terms of capital expenditures (CAPEX) and operational expenditures (OPEX). The rich implications from our results provide fundamental guidance on the choice of cost-effective access infrastructure for the emerging vehicular networking.

Vehicular communication networks, such as the 802.11p and Wireless Access in Vehicular Environments (WAVE) technologies, are becoming a fundamental platform for providing real-time access to safety and entertainment information. In particular, infotainment applications and, consequently, IP-based communications, are key to leverage market penetration and deployment costs of the 802.11p/WAVE network. However, the operation and performance of IP in 802.11p/WAVE are still unclear as the WAVE standard guidelines for being IP compliant are rather minimal. This paper studies the 802.11p/WAVE standard and its limitations for the support of infrastructure-based IP applications, and proposes the Vehicular IP in WAVE (VIP-WAVE) framework. VIP-WAVE defines the IP configuration for extended and non-extended IP services, and a mobility management scheme supported by Proxy Mobile IPv6 over WAVE. It also exploits multi-hop communications to improve the network performance along roads with different levels of infrastructure presence. Furthermore, an analytical model considering mobility, handoff delays, collisions, and channel conditions is developed for evaluating the performance of IP communications in WAVE. Extensive simulations are performed to demonstrate the accuracy of our analytical model and the effectiveness of VIP-WAVE in making feasible the deployment of IP applications in the vehicular network.

In vehicular ad hoc networks (VANETs), improving uploading efficiency is crucial to enabling the copious applications such as reporting sensed data for traffic management or environment monitoring. Depending on the applications, the contents to be uploaded can be of large volumes. Therefore, there exist the fundamental demands of the delivery with high throughput. In this paper, we derive the achievable throughput capacity scaling law for such applications in VANETs as Θ(1/log n), with the number of road-side units scaling as Θ(n/log n). Furthermore, by exploring the mobility diversity among vehicles, we propose a novel two-hop forwarding scheme to improve the throughput performance approaching the throughput capacity. Specifically, the source vehicle distributes the contents to multiple relay vehicles with the largest mobility diversity so that the number of concurrent transmissions can be increased. The simulation results demonstrate the effectiveness of the proposed transmission scheme in terms of the increased throughput performance.

In this paper, a cooperative framework in cognitive radio networks, which addresses energy efficiency of the primary users (PUs) and trustworthiness of secondary users (SUs), is proposed. Specifically, the cooperation involves a PU selecting the most suitable SU as the cooperative relay and allocating the spectrum access intervals for relaying its message and rewarding the SU for its help in relaying the PU's message. Based on the PU's strategy, the selected SU determines its optimal transmission power. The above sequential decision procedure, with the PU as the leader and the SU as the follower, is formulated as a Stackelberg game. The outcomes of the proposed cooperative strategy, including partner selection, cooperation in an untrustworthy environment, and energy efficiency consideration, are analyzed. Numerical results demonstrate that, with the proposed relay selection scheme, the PU can achieve high energy saving through cooperation with the trustworthy SU.

In this paper, the asymptotic capacity and delay performance of social-proximity urban vehicular networks with inhomogeneous vehicle density are analyzed. Specifically, we investigate the case of N vehicles in a grid-like street layout while the number of road segments increases linearly with the population of vehicles. Each vehicle moves in a localized mobility region centered at a fixed social spot and communicates to a destination vehicle in the same mobility region via a unicast flow. With a variant of the two-hop relay scheme applied, we show that social-proximity urban networks are scalable: a constant average per-vehicle throughput can be achieved with high probability. Furthermore, although the throughput and delay of a unicast flow may degrade in a high density area, almost constant per-vehicle throughput Ω(1/log (N)) and almost constant delay O(log2(N)) (except for the polylogarithmic factor) are still achievable with high probability. By identifying the key impact factors of performance mathematically, our results should provide insight on the design and deployment of future vehicular networks.

Vehicular wireless communication should be able to provide vehicles with reliable and efficient data transmissions for various applications, especially safety applications. We present a dedicated multi- channel MAC protocol that has an adaptive broadcasting mechanism, specifically designed to provide collision-free and delay-bounded transmissions for safety applications under various traffic conditions. Besides defining the implementation of this protocol, we conducted simulation evaluations showing that it has promising performance on critical statistics.