Machine learning (ML) has recently been adopted in vehicular networks for applications such as autonomous driving, road safety prediction and vehicular object detection, due to its model-free characteristic, allowing adaptive fast response. However, most of these ML applications employ centralized learning (CL), which brings significant overhead for data transmission between the parameter server and vehicular edge devices. Federated learning (FL) framework has been recently introduced as an efficient tool with the goal of reducing transmission overhead while achieving privacy through the transmission of model updates instead of the whole dataset. In this paper, we investigate the usage of FL over CL in vehicular network applications to develop intelligent transportation systems. We provide a comprehensive analysis on the feasibility of FL for the ML based vehicular applications, as well as investigating object detection by utilizing image-based datasets as a case study. Then, we identify the major challenges from both learning perspective, i.e., data labeling and model training, and from the communications point of view, i.e., data rate, reliability, transmission overhead, privacy and resource management. Finally, we highlight related future research directions for FL in vehicular networks.
University of Sindh（信德大学）；Munster Technological University（芒斯特理工大学）；Nearby Computing（Nearby Computing公司）
The applications concerning vehicular networks benefit from the vision of beyond 5G and 6G technologies such as ultra-dense network topologies, low latency, and high data rates. Vehicular networks have always faced data privacy preservation concerns, which lead to the advent of distributed learning techniques such as federated learning. Although federated learning has solved data privacy preservation issues to some extent, the technique is quite vulnerable to model inversion and model poisoning attacks. We assume that the design of defense mechanism and attacks are two sides of the same coin. …
Semantic Communication-Enhanced Split Federated Learning for Vehicular Networks: Architecture, Challenges, and Case Study
School of Computer Science and Engineering, University of Electronic Science and Technology of China（电子科技大学计算机科学与工程学院）；Faculty of Information Technology, University of Jyväskylä（于韦斯屈莱大学信息科技学院）；Center for Intelligent Networking and Communications (CINC), University of Electronic Science and Technology of China（电子科技大学智能网络与通信中心）
Adaptive and Parallel Split Federated Learning in Vehicular Edge Computing
School of Computer Science and Engineering, University of Electronic Science and Technology of China（电子科技大学计算机科学与工程学院）；Xidian University（西安电子科技大学）；Guangzhou Institute of Technology, Xidian University（西安电子科技大学广州研究院）；Faculty of Information Technology, University of Jyväskylä（于韦斯屈莱大学信息技术学院）
Jiangnan University（江南大学）；State Key Laboratory of Integrated Services Networks (Xidian University)（综合业务网理论及关键技术国家重点实验室（西安电子科技大学））；Qualcomm（高通公司）；Tsinghua University（清华大学）；University of Kent（肯特大学）
Vehicular networks enable vehicles support real-time vehicular applications through training data. Due to the limited computing capability, vehicles usually transmit data to a road side unit (RSU) at the network edge to process data. However, vehicles are usually reluctant to share data with each other due to the privacy issue. For the traditional federated learning (FL), vehicles train the data locally to obtain a local model and then upload the local model to the RSU to update the global model, thus the data privacy can be protected through sharing model parameters instead of data. The tradi…
Recently, federated learning (FL) has received intensive research because of its ability in preserving data privacy for scattered clients to collaboratively train machine learning models. Commonly, a parameter server (PS) is deployed for aggregating model parameters contributed by different clients. Decentralized federated learning (DFL) is upgraded from FL which allows clients to aggregate model parameters with their neighbours directly. DFL is particularly feasible for vehicular networks as vehicles communicate with each other in a vehicle-to-vehicle (V2V) manner. However, due to the restric…
Noise-Resilient Quantum Aggregation on NISQ for Federated ADAS Learning
Research Scholar, Dept. of CSE（研究学者，计算机科学与工程系）；Dept. of CSE, School of Engineering（计算机科学与工程系，工程学院）；PES University, RR Nagar, Bangalore, India（PES大学）；Dayananda Sagar University, Bangalore, India（Dayananda Sagar大学）
Federated learning (FL) is a machine learning technique that aims at training an algorithm across decentralized entities holding their local data private. Wireless mobile networks allow users to communicate with other fixed or mobile users. The road traffic network represents an infrastructure-based configuration of a wireless mobile network where the Connected and Automated Vehicles (CAV) represent the communicating entities. Applying FL in a wireless mobile network setting gives rise to a new threat in the mobile environment that is very different from the traditional fixed networks. The thr…
Dynamic Scheduling for Vehicle-to-Vehicle Communications Enhanced Federated Learning
Beijing National Research Center for Information Science and Technology, Department of Electronic Engineering, Tsinghua University（北京信息科学与技术国家研究中心，电子工程系，清华大学）；School of Electronic and Information Engineering, Beijing Jiaotong University（电子信息工程学院，北京交通大学）
Fraunhofer Institute for Transportation and Infrastructure Systems IVI（弗劳恩霍夫交通与基础设施系统研究所IVI）；Technical University of Munich（慕尼黑工业大学）；Technische Hochschule Ingolstadt（英戈尔施塔特应用技术大学）
Deep learning is a key approach for the environment perception function of Cooperative Intelligent Transportation Systems (C-ITS) with autonomous vehicles and smart traffic infrastructure. In today's C-ITS, smart traffic participants are capable of timely generating and transmitting a large amount of data. However, these data can not be used for model training directly due to privacy constraints. In this paper, we introduce a federated learning framework coping with Hierarchical Heterogeneity (H2-Fed), which can notably enhance the conventional pre-trained deep learning model. The framework ex…
University of Oulu（奥卢大学）；Virginia Tech（弗吉尼亚理工学院暨州立大学）；Huawei France R&D（华为法国研发中心）
In this paper, a novel joint transmit power and resource allocation approach for enabling ultra-reliable low-latency communication (URLLC) in vehicular networks is proposed. The objective is to minimize the network-wide power consumption of vehicular users (VUEs) while ensuring high reliability in terms of probabilistic queuing delays. In particular, a reliability measure is defined to characterize extreme events (i.e., when vehicles' queue lengths exceed a predefined threshold with non-negligible probability) using extreme value theory (EVT). Leveraging principles from federated learning (FL)…
Privacy-Preserving Offloading for Large Language Models in 6G Vehicular Networks
School of Science and Engineering, Al Akhawayn University in Ifrane（科学与工程学院，阿尔阿赫韦因大学）；Department of Electrical and Computer Engineering, Université du Québec à Trois-Rivières（电气与计算机工程系，魁北克大学Trois-Rivières分校）
Proactive handover can avoid frequent handovers and reduce handover delay, which plays an important role in maintaining the quality of service (QoS) for mobile users in millimeter-wave vehicular networks. To reduce the communication cost of training the learning model for proactive handover, we propose a federated learning (FL) framework. The proposed FL framework can accommodate the limited storage capacity of each user, increase the number of users who participate in the FL, and adapt to the dynamic mobility pattern. Simulation results validate the effectiveness of the proposed FL framework.…
Vehicular networks, an enabling technology for Intelligent Transportation System (ITS), smart cities, and autonomous driving, can deliver numerous on-board data services, e.g., road-safety, easy navigation, traffic efficiency, comfort driving, infotainment, etc. Providing satisfactory Quality of Service (QoS) in vehicular networks, however, is a challenging task due to a number of limiting factors such as erroneous and congested wireless channels (due to high mobility or uncoordinated channel-access), increasingly fragmented and congested spectrum, hardware imperfections, and anticipated growt…
The proliferation of connected vehicles along with the high demand for rich multimedia services constitute key challenges for the emerging 5G-enabled vehicular networks. These challenges include, but are not limited to, high spectral efficiency and low latency requirements. Recently, the integration of cache-enabled networks with non-orthogonal multiple access (NOMA) has been shown to reduce the content delivery time and traffic congestion in wireless networks. Ac-cordingly, in this article, we envisage cache-aided NOMA as a technology facilitator for 5G-enabled vehicular networks. In particul…
Vehicular networks will play an important role in enhancing road safety, improving transportation efficiency, and providing seamless Internet service for users on the road. Reaping the benefit of vehicular networks is contingent upon meeting stringent wireless communication performance requirements, particularly in terms of delay and reliability. In this paper, a dependence control mechanism is proposed to improve the overall reliability of vehicular networks. In particular, the dependence between the communication delays of different vehicle-to-vehicle (V2V) links is first modeled. Then, the …
We develop an analytical framework to examine the line-of-sight (LOS) coverage area in vehicular networks with roadside units (RSU) and vehicle relays. In practical deployment scenarios, RSUs and vehicle relays are spatially correlated and we characterize this by employing Cox point processes to model the locations of RSUs and vehicle relays simultaneously. Leveraging the random blockage model, we model the LOS coverage area as Boolean models on these Cox point processes. The LOS coverage area is then evaluated by its area fraction. We show that relays can increase the area fraction of LOS cov…
This paper presents a novel spatially consistent approach for modeling line-of-sight (LOS) paths in vehicular networks. We use stochastic geometry to model transmitters, obstacles, and receivers located in three parallel lines, respectively. Their geometric interactions are leveraged to characterize the existence of LOS paths. Specifically, the proposed approach focuses on the role of obstacles in blocking one or more LOS paths, which has been overlooked in most statistical models for blockage. Under the proposed framework, we derive the probability that a typical vehicle is in LOS with respec…
Intelligent reflecting surface (IRS) has recently received much attention from the research community due to its potential to achieve high spectral and power efficiency cost-effectively. In addition to traditional cellular networks, the use of IRS in vehicular networks is also considered. Prior works on IRS-aided vehicle-to-everything communications focus on deploying reflection surfaces on the facades of buildings along the road for sidelink performance enhancement. This paper goes beyond the state of the art by presenting a novel paradigm coined Intelligent Reflecting Vehicle Surface (IRVS).…
As a worldwide pandemic, the coronavirus disease-19 (COVID-19) has caused serious restrictions in people's social life, along with the loss of lives, the collapse of economies and the disruption of humanitarian aids. Despite the advance of technological developments, we, as researchers, have witnessed that several issues need further investigation for a better response to a pandemic outbreak. Therefore, researchers recently started developing ideas to stop or at least reduce the spread of the pandemic. While there have been some prior works on wireless networks for combating a pandemic scenari…
As one key enabler of Intelligent Transportation System (ITS), Vehicular Ad Hoc Network (VANET) has received remarkable interest from academia and industry. The emerging vehicular applications and the exponential growing data have naturally led to the increased needs of communication, computation and storage resources, and also to strict performance requirements on response time and network bandwidth. In order to deal with these challenges, Mobile Edge Computing (MEC) is regarded as a promising solution. MEC pushes powerful computational and storage capacities from the remote cloud to the edge…
The effective deployment of connected vehicular networks is contingent upon maintaining a desired performance across spatial and temporal domains. In this paper, a graph-based framework, called SMART, is proposed to model and keep track of the spatial and temporal statistics of vehicle-to-infrastructure (V2I) communication latency across a large geographical area. SMART first formulates the spatio-temporal performance of a vehicular network as a graph in which each vertex corresponds to a subregion consisting of a set of neighboring location points with similar statistical features of V2I late…
Vehicular congestion is directly impacting the efficiency of the transport sector. A wireless sensor network for vehicular clients is used in Internet of Vehicles based solutions for traffic management applications. It was found that vehicular congestion detection by using Internet of Vehicles based connected vehicles technology are practically feasible for congestion handling. It was found that by using Fog Computing based principles in the vehicular wireless sensor network, communication in the system can be improved to support larger number of nodes without impacting performance. In this pa…
Vehicular communication is an important application of the fifth generation of mobile communication systems (5G). Due to its low cost and energy efficiency, intelligent reflecting surface (IRS) has been envisioned as a promising technique that can enhance the coverage performance significantly by passive beamforming. In this paper, we analyze the outage probability performance in IRS-assisted vehicular communication networks. We derive the expression of outage probability by utilizing series expansion and central limit theorem. Numerical results show that the IRS can significantly reduce the o…
Cellular Vehicle-to-everything (C-V2X) communication is a major V2X solution proposed and developed by the 3rd Generation Partnership Project (3GPP). Our previous work has studied scalability aspects of C-V2X and demonstrated its potential for accommodating large numbers of vehicles in dense vehicular scenarios. However, existing studies in the scientific literature mostly have a network-level approach to the problem and do not assess the temporal and spatial dynamics of C-V2X networks in heavy network load situations. In this work we shed light on the spatio-temporal characteristics of these …
Edge computing technology has great potential to improve various computation-intensive applications in vehicular networks by providing sufficient computation resources for vehicles. However, it is still a challenge to fully unleash the potential of edge computing in edge computing-enabled vehicular networks. In this paper, we develop the energy-efficient cooperative offloading scheme for edge computing-enabled vehicular networks, which splits the task into multiple subtasks and offloads them to different roadside units (RSUs) located ahead along the route of the vehicle. We first establish nov…
The staggering growth of the number of vehicles worldwide has become a critical challenge resulting in tragic incidents, environment pollution, congestion, etc. Therefore, one of the promising approaches is to design a smart vehicular system as it is beneficial to drive safely. Present vehicular system lacks data reliability, security, and easy deployment. Motivated by these issues, this paper addresses a drone-enabled intelligent vehicular system, which is secure, easy to deploy and reliable in quality. Nevertheless, an increase in the number of operating drones in the communication networks …
Vehicular communications networks (VANETs) enable information exchange among vehicles, other end devices and public networks, which plays a key role in road safety/infotainment, intelligent transportation system, and self-driving system. As the vehicular connectivity soars, and new on-road mobile applications and technologies emerge, VANETs are generating an ever-increasing amount of data, requiring fast and reliable transmissions through VANETs. On the other hand, a variety of VANETs related data can be analyzed and utilized to improve the performance of VANETs. In this article, we first revi…
This paper studies the physical layer security (PLS) of a vehicular network employing a reconfigurable intelligent surface (RIS). RIS technologies are emerging as an important paradigm for the realisation of smart radio environments, where large numbers of small, low-cost and passive elements, reflect the incident signal with an adjustable phase shift without requiring a dedicated energy source. Inspired by the promising potential of RIS-based transmission, we investigate two vehicular network system models: One with vehicle-to-vehicle communication with the source employing a RIS-based access…
This paper studies the physical layer security of a vehicular communication network in the presence of interference constraints by analysing its secrecy capacity. The system considers a legitimate receiver node and an eavesdropper node, within a shared network, both under the effect of interference from other users. The double-Rayleigh fading channel is used to capture the effects of the wireless communication channel for the vehicular network. We present the standard logarithmic expression for the system capacity in an alternate form, to facilitate analysis in terms of the joint moment genera…
The provision of reliable connectivity is envisioned as a key enabler for future autonomous driving. Anticipatory communication techniques have been proposed for proactively considering the properties of the highly dynamic radio channel within the communication systems themselves. Since real world experiments are highly time-consuming and lack a controllable environment, performance evaluations and parameter studies for novel anticipatory vehicular communication systems are typically carried out based on network simulations. However, due to the required simplifications and the wide range of un…
To enlarge the perception range and reliability of individual autonomous vehicles, cooperative perception has been received much attention. However, considering the high volume of shared messages, limited bandwidth and computation resources in vehicular networks become bottlenecks. In this paper, we investigate how to balance the volume of shared messages and constrained resources in fog-based vehicular networks. To this end, we first characterize sum satisfaction of cooperative perception taking account of its spatial-temporal value and latency performance. Next, the sensing block message, co…
The Software-Defined Air-Ground integrated Vehicular (SD-AGV) networks have emerged as a promising paradigm, which realize the flexible on-ground resource sharing to support innovative applications for UAVs with heavy computational overhead. In this paper, we investigate a vehicular cloud-assisted task scheduling problem in SD-AGV networks, where the computation-intensive tasks carried by UAVs, and the vehicular cloud are modeled via graph-based representation. To map each component of the graph tasks to a feasible vehicle, while achieving the trade-off among minimizing UAVs' task completion t…
