Intelligent Vehicular Networks Research Articles

A multiple-input fluid queue model for performance evaluation of fog server in an intelligent vehicular network

Nowadays, there is a growing trend towards fog computing which is a relatively new concept that has been introduced as an extension of cloud computing. It is considered as a promising paradigm for intelligent vehicular networks due to its ability to reduce delays and enhance network efficiency. The utilization of fog computing plays a crucial role in tackling the distinct obstacles encountered in vehicular computing, including issues like real-time data processing, and limitations on bandwidth. By relocating computational resources closer to the network’s edge, it enhances the effectiveness, dependability, and safety of vehicular applications while simultaneously boosting privacy and security measures. In addition, fog offloading has played a pivotal role in fog computing and edge computing structures. Its objective is to efficaciously allocate the data and assign the processing of tasks among edge devices, fog nodes, and cloud resources. Efficient fog offloading strategies are adaptable, scalable, and are able to handle faults, making them indispensable for optimizing these architectures. Although efficiency and quality of service are crucial objectives in a fog computing based intelligent vehicular network environment, performance remains a significant concern that cannot be overlooked. In light of this, to evaluate the efficacy of the probabilistic offloading approach on a fog server, a thorough performance evaluation is necessary. This research proposes a fluid queue approach that accounts for the constant flow of data packets while evaluating a fog server’s performance. For a fog computing-based intelligent vehicular network (FCIVN) with numerous heterogeneous smart vehicles (SVs), we construct a multiple-input fluid queue to model the tasks handed over to the fog server in order to evaluate its performance. In an FCIVN, the arrivals are drawn from various sources at the fog server. Accordingly, in the proposed model the fluid queue is modulated by more than one independent and distinct finite-state birth–death processes (BDPs) which control the variable inflow, and another BDP which controls the variable outflow. We present the details concerning an intermediate fog server’s buffer occupancy distribution within an FCIVN. Further, we assess the performance measures in terms of the offered load, expected buffer-level, average throughput and average latency of the tasks in an FCIVN. Finally, quantitative illustrations are presented to demonstrate the appropriateness of the fluid queue model developed in this study. The results are found to be in consistence with the expected behaviour of these performance indicators.

Special Issue: Recent Advances in Intelligent Vehicular Networks and Communications

Over the last few decades, research on intelligent vehicular networks and communications has grown significantly due to the increasing demand for advanced vehicular technologies and the need for enhanced road safety, traffic management, and efficient transportation systems [...]

An Intelligent Transport System Using Vehicular Network for Smart Cities

Aims and background: The integration of communication tools has allowed for effective decision-making in smart cities and Internet-of-Things (IoT). One major issue that people who commute to cities everyday encounter is traffic congestion. Thanks to the progress and backing of ICTs, transportation solutions have been designed and implemented, leading to the development of ITSs and the provision of numerous innovative services. Objectives and Methods: These services include ones that guarantee safety, provide drivers with useful information, enable greater street movement, and avoid congestion, among many others. In industrialized nations, traffic data is collected by specialized sensors that can anticipate future patterns. Commuters are kept informed of any traffic updates through the Internet. When there is little or no physical infrastructure and Internet connection, these methods become unworkable. Internet access is still a problem in rural regions, and there are no roadside units in underdeveloped nations. This article presents an architecture for smart cities' intelligent vehicular networks that can impromptu accept data from nearby vehicles in real time and use it to choose routes. As embedded devices in vehicles, we utilized Android-based smartphones with Wi-Fi Direct capabilities. To set up our smart transportation system, we utilized a vehicular ad hoc network. Results: Data was collected and processed using separate methods between two major cities in a developing nation. Resource utilization, transmission delay, packet loss, and total trip time were measured against several fixed- and dynamic-route-selection algorithms to assess the framework's performance. Conclusions: When equated to a conventional fixed-route-selection procedure, our results reveal a 33.3% reduction in trip times.

Vehicle Selection and Resource Allocation for Federated Learning-Assisted Vehicular Network

To exploit the massive amounts of onboard data in vehicular networks while protecting data privacy and security, federated learning (FL) is regarded as a promising technology to support enormous vehicular applications. Despite that FL has great potential to improve the architecture of intelligent vehicular networks, the mobility of the vehicles and the dynamic nature of wireless channels make the integration of FL and vehicular networks more challenging. In this paper, we propose a vehicle mobility- and channel dynamic-aware FL (MADCA-FL) scheme to fit vehicular networks and enhance learning performances. This novel scheme enables the RSU to select appropriate vehicles and weightedly average the local models. Afterward, MADCA-FL formulates a problem to maximize the model accuracy while assuring the latency and energy restrictions, by jointly optimizing the computation and communication resources. With a mixed- integer non-linear programming structure, the problem is NP-hard. Firstly, we utilize the successive convex approximation algorithm to handle the non-convexity, and then apply the Lagrange multiplier method and the block coordinate descent method to obtain the optimal solution. Extensive experiments are conducted to confirm the effectiveness of our proposed scheme.

SECURING AND ADVANCING ROAD SAFETY IN INTELLIGENT VEHICULAR NETWORKS FOR SEAMLESS AND SECURE COMMUNICATION

Intelligent vehicular networks leverage communication technologies to enable vehicles to interact with each other and with infrastructure elements, such as roadside units and traffic signals, to enhance road safety and efficiency. However, the open nature of these networks exposes them to various security threats, including data interception, tampering, and unauthorized access. Traditional encryption methods may not suffice to address these challenges, necessitating the adoption of advanced cryptographic techniques like ECC and RSA. Prior research in the field has primarily focused on either enhancing communication protocols or improving security measures independently. However, there is a notable gap in research that comprehensively addresses both aspects simultaneously. This study aims to fill this void by proposing an integrated approach that ensures both seamless communication and robust security in intelligent vehicular networks. The proposed methodology involves the design and implementation of a hybrid cryptographic scheme combining ECC and RSA algorithms. This scheme will be integrated into the existing communication infrastructure of intelligent vehicular networks. The performance of the system will be evaluated through simulations and real-world experiments to assess its effectiveness in securing communication channels while minimizing overhead. The results show the effectiveness of the proposed ECC-RSA hybrid encryption scheme in securing communication channels within intelligent vehicular networks. The integration of ECC and RSA protocols not only enhances the security of data transmission but also ensures seamless communication, thereby advancing road safety in intelligent vehicular environments.

Hyperbolic-Embedding-Aided Geographic Routing in Intelligent Vehicular Networks

Intelligent vehicular networks can not only connect various smart terminals to manned or unmanned vehicles but also to roads and people’s hands. In order to support diverse vehicle-to-everything (V2X) applications in dynamic, intelligent vehicular networks, efficient and flexible routing is fundamental but challenging. Aimed to eliminate routing voids in traditional Euclidean geographic greedy routing strategies, we propose a hyperbolic-embedding-aided geographic routing strategy (HGR) in this paper. By embedding the network topology into a two-dimensional Poincaré hyperbolic disk, greedy forwarding is performed according to nodes’ hyperbolic coordinates. Simulation results demonstrated that the proposed HGR strategy can greatly enhance the routing success rate through a smaller stretch of the routing paths, with little sacrifice of routing computation time.

Real‐time Internet of LoRa Things (IoLT)‐based accident detection and prevention system in vehicular networks towards smart city

SummaryVehicle utilization has increased on a broader scale in today's reality. Because of insufficient emergency services, increased motor traffic has resulted in the rise of traffic collisions, and widespread accidents lead to the demise of lives and property. Generally, the consequence death rate happens each year, originating from delays in rescue activities. However, vehicles are embedded with trend technology. Still, the accident count will rise day by day due to delays in transmitting the information to the concerned person or delays in rescue activities. The proposed work offers an effective solution to the aforementioned issue by assisting low‐power and long‐range (LoRa) architecture with edge node ultrasonic sensors for identifying the abnormalities and to provide an efficient transport ambulance from the unexpected mishap spot to the closest hospital where emergency well‐being can be provided with the help of cloud technology. Also, emergency information can be sent to the cloud immediately, and its response is the way of alerting the surroundings and notifying the appropriate hospital with the aid of a GPS‐enabled LoRa‐shield. Further, comparing the proposed technology with other LPWAN (low‐power wide area networks) in terms of coverage, cost, capacity, and energy consumption proves efficient communication in the development of intelligent vehicular networks towards a smart city.

Age of Information, Latency, and Reliability in Intelligent Vehicular Networks

Autonomous driving and intelligent transportation have posed stringent requirements on different performance metrics of vehicle-to-everything (V2X) communications depending on the wireless service being carried. Such coexisting heterogeneous performance requirements bring about increasing challenge in managing modern vehicular networks. In this article, we categorize wireless vehicular traffic into two kinds, namely, status update service and data communication service, where in safety-related applications the former is concerned with age of information (AoI) while the latter cares about latency and reliability in general. Afterwards, we uncover the relationship among AoI, latency, and reliability, and propose a novel graphical packet delivery model that is powerful for analyzing AoI performance. To unify the AoI, latency, and reliability management for different services, we further develop an intelligent resource allocation framework validated by a quantitative case study. Finally, we explore key challenges and opportunities to address the coexistence of status update and data communication services in intelligent vehicular networks.

Blind reconfigurable intelligent surface-aided fixed non-orthogonal multiple access for intelligent vehicular networks

In intelligent vehicular networks, vehicles should be able to communicate with their surroundings while traveling. This results in more efficient, safer, and comfortable driving experiences, as well as new commercial prospects in a variety of industries. Connected vehicles and autonomous vehicles expect 100% reliable connectivity without any compromise in quality. However, due to challenges such as difficult channel terrains in urban scenarios and dead zones, the reliability of current vehicle-to-infrastructure (V2I) and vehicle-to-vehicle communication systems cannot be guaranteed. The performance of vehicular networks can be considerably enhanced with reconfigurable intelligent surfaces (RIS). Non-orthogonal multiple access (NOMA) allows for massive connectivity with the surroundings. In vehicular networks, the RIS-assisted NOMA can ensure regulated channel gains, better coverage, throughput, and energy efficiency. In this work, a blind RIS-assisted fixed NOMA (FNOMA) system is proposed for a downlink V2I scenario. The closed-form analytical outage probability and throughput expressions are derived by considering RIS as an intelligent reflector and as a roadside unit. It is observed that the analytical and Monte Carlo simulation results are closely related. In simulations, it has been discovered that RIS-assisted FNOMA outperforms the traditional NOMA variants in terms of outage and throughput. Even without precise channel knowledge, blind RIS transmission outperforms traditional NOMA variants due to huge array gain. The increase in the number of reflective elements also results in a significant improvement in signal-to-noise ratio gains.

Modeling and Analysis of Edge Caching for 6G mmWave Vehicular Networks

As one of the most promising solutions, edge caching is emerging to reduce the content retrieval latency and relieve the huge burden on the backhaul links in the 6th generation (6G) millimeter wave (mmWave) intelligent vehicular networks. In this paper, we first formulate the optimization problem in terms of request hit probability and investigate two crucial factors, which impact the effectiveness of cache placement in device-to-device (D2D) enabled mmWave vehicular networks. Then, the general mathematical expressions for optimization of the request hit probability with the constraints of caching capacity are derived. Moreover, a group caching scheme (GCS) is proposed to obtain the sub-optimal results by utilizing relaxation method and Karush-Kuhn-Tucker (KKT) conditions. Inspired from the Matern hard-core processes and by exploiting the spatially correlated characteristics of users distribution, hard-cored based caching algorithm (HCCA) is proposed to avoid the simultaneous caching for a particular file. In addition, a joint caching and scheduling strategy is investigated which maximizes the number of concurrent transmissions by D2D enabled vehicle pairs matching and antennas adjustment. Comprehensive simulations validate our theoretical analysis and demonstrate that the proposed scheme can achieve higher performance in terms of request hit probability and the number of concurrent transmissions compared to the existing methods. Consequently, the proposed caching scheme has great potential in future intelligent vehicular applications.

Priority based V2V data offloading scheme for FiWi based vehicular network using reinforcement learning

Intelligent vehicular network is one of the popular paradigms for sixth-generation (6G) networks. With the growth in vehicular traffic density, it is essential to ensure safety and security by providing ultra reliable low latency (URLL) services for vehicular communication. Moreover, along with the URLL services, it is also essential that these services are energy-efficient. These requirements can be fulfilled by the integration of optical fiber at the back-end with wireless front-end, commonly referred to as fiber-wireless (FiWi) networks. In this work, we consider a FiWi-based vehicular network that consists of a optical fiber back-end network with wireless vehicular-to-infrastructure (V2I) network at the front-end. Specifically, to ensure that high priority vehicular traffic has lower latency and energy consumption, we propose a reinforcement learning (RL) based double deep Q-network (DDQN) scheme that chooses the cluster-head for vehicular communication. The proposed algorithm uses energy and latency aware cluster-head selection that meets the intelligent transportation system (ITS) requirements. The proposed algorithm is compared with the non-RL-based approach such as, random and max-queue based cluster-head selection. The simulation results demonstrate the efficiency of the proposed algorithm in terms of energy, latency, throughput, and reliability.

Concurrent Downlink and Uplink Joint Communication and Sensing for 6G Networks

Joint communication and sensing (JCAS) is a promising technology for 6th Generation (6G) mobile networks, such as intelligent vehicular networks, intelligent manufacturing, and so on. Equipped with two spatially separated antenna arrays, the base station (BS) can perform downlink active JCAS in a mono-static setup. This paper proposes a Concurrent Downlink and Uplink (CDU) JCAS system where the BS can use the echo of transmitted dedicated signals for sensing in the uplink timeslot, while performing reliable uplink communication. A novel successive interference cancellation-based CDU JCAS processing method is proposed to enable the estimation of uplink communication symbols and downlink sensing parameters. Extensive simulation results verify the feasibility of the CDU JCAS system, showing a performance improvement of more than 10 dB compared to traditional JCAS methods while maintaining reliable uplink communication.

Toward the Age of Intelligent Vehicular Networks for Connected and Autonomous Vehicles in 6G

Twenty-two years after the advent of the firstgeneration vehicular network, i.e., dedicated short-range communications (DSRC) standard/IEEE 802.11p, the vehicular technology market has become very competitive with a new player, Cellular Vehicle-to-Everything (C-V2X). Currently, C-V2X technology likely dominates the race because of the big advantages of comprehensive coverage and high throughput/reliability. Meanwhile, DSRC-based technologies are struggling to survive and rebound with many hopes betting on success of the secondgeneration standard, IEEE P802.11bd. While the standards battle to attract automotive makers and dominate the commercial market landing, the research community has started thinking about the shape of the next-generation vehicular networks. This article details the state-of-the-art progress of vehicular networks, particularly the cellular V2X-related technologies in specific use cases, compared to the features of the current generation. Through the typical examples, we also highlight why 5G is inadequate to provide the best connectivity for the vehicular applications and then 6G technologies can fill up the vacancy.

Intelligent Caching for Mobile Video Streaming in Vehicular Networks with Deep Reinforcement Learning

Caching-enabled multi-access edge computing (MEC) has attracted wide attention to support future intelligent vehicular networks, especially for delivering high-definition videos in the internet of vehicles with limited backhaul capacity. However, factors such as the constrained storage capacity of MEC servers and the mobility of vehicles pose challenges to caching reliability, particularly for supporting multiple bitrate video streaming caching while achieving considerable quality of experience (QoE). Motivated by the above challenges, in this paper, we propose an intelligent caching strategy that takes into account vehicle mobility, time-varying content popularity, and backhaul capability to improve the QoE of vehicle users effectively. First, based on the mobile video mean opinion score (MV-MOS), we designed an average download percentage (ADP) weighted QoE evaluation model. Then, the video content caching problem is formulated as a Markov decision process (MDP) to maximize the ADP weighted MV-MOS. Owing to the prior knowledge of video content popularity and channel state information that may not be available at the road side unit in practical scenarios, we propose a deep reinforcement learning (DRL)-based caching strategy to solve the problem while achieving a maximum ADP weighted MV-MOS. To accelerate its convergence speed, we further integrate the prioritized experience replay, dueling, and double deep Q-network technologies, which improve the performance of DRL algorithm. Numerical results demonstrate that the proposed DRL-based caching strategy significantly improves QoE, and achieves better video delivery reliability compared to existing non-learning approaches.

Enhanced Artificial Gorilla Troops Optimizer Based Clustering Protocol for UAV-Assisted Intelligent Vehicular Network

The increasing demands of several emergent services brought new communication problems to vehicular networks (VNs). It is predicted that the transmission system assimilated with unmanned aerial vehicles (UAVs) fulfills the requirement of next-generation vehicular network. Because of its higher flexible mobility, the UAV-aided vehicular network brings transformative and far-reaching benefits with extremely high data rates; considerably improved security and reliability; massive and hyper-fast wireless access; much greener, smarter, and longer 3D communications coverage. The clustering technique in UAV-aided VN is a difficult process because of the limited energy of UAVs, higher mobility, unstable links, and dynamic topology. Therefore, this study introduced an Enhanced Artificial Gorilla Troops Optimizer–based Clustering Protocol for a UAV-Assisted Intelligent Vehicular Network (EAGTOC-UIVN). The goal of the EAGTOC-UIVN technique lies in the clustering of the nodes in UAV-based VN to achieve maximum lifetime and energy efficiency. In the presented EAGTOC-UIVN technique, the EAGTO algorithm was primarily designed by the use of the circle chaotic mapping technique. Moreover, the EAGTOC-UIVN technique computes a fitness function with the inclusion of multiple parameters. To depict the improved performance of the EAGTOC-UIVN technique, a widespread simulation analysis was performed. The comparison study demonstrated the enhancements of the EAGTOC-UIVN technique over other recent approaches.

Multi-Vehicle Tracking and ID Association Based on Integrated Sensing and Communication Signaling

The integrated sensing and communication (ISAC) technology, which performs vehicle state sensing and communications simultaneously, has been widely regarded as a key to enable future intelligent vehicular networks. However, the communications information is in general vehicle-specific, which requires the RSU to distinguish vehicle identities (IDs). Conventionally, the vehicles feed back their IDs to the RSU, since they are not contained in the sensing echoes. This letter develops a novel approach for multi-vehicle tracking and ID association using the ISAC signals. In particular, the ID association is done by comparing the similarity of the distributions of estimated and predicted locations based on the Kullback-Leibler divergence (KLD). With the aid of the proposed approach, frequent uplink ID feedback is avoided, leading to a reduced communication overhead as well as latency. We further design a high-efficiency predictive beamforming scheme, which predicts the angular parameters in the following time instant relying on the estimated states. Simulation results show that our proposed scheme can effectively associate different vehicle IDs and improve the communications performance.

Resource Management for Intelligent Vehicular Edge Computing Networks

To overcome the inherent defect of centralized data processing in cloud computing, the mobile edge computing (MEC) brings data storage and computing capacities, to the edge closer to end users. However, the uneven distribution of access vehicles, as well the volume of computing data, cause the workload diversity among various mobile edge computing servers (MECSs). In this paper, we propose a hierarchical model with quality of service (QoS)-aware and power-aware resource management for the cooperative edge-computing-based intelligent vehicular network (CEC-IoV), and the system latency and energy efficiency at MECSs are respectively optimized. Specifically, considering the changing response times versus MECSs’ workloads, the Minimum Latency with Migration Loads (MLML) scheme is developed for workload balance among multiple MECSs. By selecting the appropriate response time threshold and migration loads from overloading MECSs to idle MECSs simultaneously, the load-balancing problem can be efficiently solved for multiple MECSs with unbalanced workloads. On the other hand, through performing workload redistribution and dynamic reconfiguration of virtual machines (VMs) instantiated onto the parallel computing platform at one MECS, the energy-efficiency can be also optimized while guaranteeing the QoS requirement on the processing delay. With the latency constraint, the power minimization problem is formulated to be a convex one, and the semi-closed forms for optimal solutions of VMs’ workloads and processing rates are provided using KKT conditions. Compared with the performance obtained by benchmark schemes, numerical results exhibit that our resource management schemes gain lower system latency and higher energy efficiency.

Graph-Enabled Intelligent Vehicular Network Data Processing

Intelligent vehicular network (IVN) is the underlying support for the connected vehicles and smart city, but there are several challenges for IVN data processing due to the dynamic structure of the vehicular network. Graph processing, as one of the essential machine learning and big data processing paradigm, which provide a set of big data processing scheme, is well-designed to processing the connected data. In this paper, we discussed the research challenges of IVN data processing and motivated us to address these challenges by using graph processing technologies. We explored the characteristics of the widely used graph algorithms and graph processing frameworks on GPU. Furthermore, we proposed several graph-based optimization technologies for IVN data processing. The experimental results show the graph processing technologies on GPU can archive excellent performance on IVN data.

Introducing Intelligence in Vehicular Ad Hoc Networks Using Machine Learning Algorithms

The automotive industry has gained popularity in the past decade, leading to tremendous advancements in intelligent vehicular networks. The increase in the number of vehicles on the roads makes it essential for vehicles to act intelligently as humans do. The concept of machine learning is that when vehicles learn and improve to operate by the previously processed data. The machine learning techniques have helped the automotive industry develop the driverless car. With the help of sensors and cameras, it is quite possible to use the machine learning algorithms and provide the user with its benefits. It helps to allow the vehicle to perform specific tasks that actually can replace the vehicle's driver. The Artificial Intelligence (AI) chips integrated into the vehicles enable the vehicle to navigate roads. This paper provides insight into the machine learning algorithms widely used by the automotive industries, and a comparison is made between them concerning the Vehicular Ad Hoc Network (VANET) applications.

An efficient heuristic switch migration scheme for software-defined vehicular networks

Software-Defined Vehicular Networks (SDVNs) have been a vital addition to the design of intelligent vehicular networks. SDVNs elevate the constraints of static hardware network devices by using programmable units, providing a global view of the network status, and standardizing the interface between different wireless access technologies. However, the static deployment and assignment of switches to control units do not consider vehicular network's rapid mobility changes and diverse densities. In this article, we propose a mobility-based heuristic switch migration scheme for software-defined vehicular networks. The proposed approach utilizes vehicles' mobility among switch-enabled roadside units to efficiently migrate selected switches between different controllers. The proposed scheme efficiently migrated switch-enabled roadside units between distributed control units while maintaining low vehicles' migration delay and cost. We have evaluated the proposed method under different environments and scenarios and reported its migration cost and delay performance.