Low latency in establishing a communication link is a key to maximize the performance of vehicle-to-vehicle wireless LANs (V2V WLANs), as contact duration of vehicles is often limited due to their fast mobility. However, previous works have mainly addressed Vehicle-to-Infrastructure (V2I) link setup latency on legacy Wi-Fi standards (IEEE 802.11b/g). Moreover, there has been a lack of performance evaluation regarding V2V link setup latency with current Wi-Fi technology and IEEE 802.11ai standard defines Fast Initial Link Setup (FILS), which simplifies the link setup process to reduce the latency. In this paper, we investigate the characteristics of V2V link setup latency with regular Extensible Authentication Protocol (EAP) authentication (EAP-TLS) and FILS with current Wi-Fi technology. The evaluation was conducted in general vehicular scenarios with different combinations of inter-vehicle distance, vehicle speed and type of roads (i.e., urban roads vs highways). FILS achieved the average link setup latency of 0.32 seconds, outperforming EAP-TLS that resulted in the average latency of 2.35 seconds. The link setup latency was stable in most of the scenarios we tested regardless of inter-vehicle distance, speed and Wi-Fi signal strength. The only exception was on highways, where significantly longer link setup latency was observed when the relative speed and distance changed rapidly, line-of-sight (LoS) was fully blocked by other vehicles and there were no other objects (e.g., buildings and vegetation) that form indirect signal propagation paths.

Vehicular Knowledge Networking (VKN) is a paradigm where vehicles exchange knowledge instead of data. Named Data Networking (NDN) provides a resilient architecture for data sharing between vehicles without requiring details of the hosting vehicle. However, NDN as well as state-of-art NDN simulation environments lack knowledge representation and reasoning (KRR) support to process, understand and optimize knowledge exchange between vehicles. In this paper, we present an open-source co-simulation framework tailored to VKN, integrating NDN, traffic, perception, and control simulators with an AI-as-a-Service (AIaaS) platform for KRR. This paper describes the APIs between various simulators and tools and demonstrates on a proof-of-concept the benefits of KRR for NDN by dividing NDN response time by a factor of five, while reducing NDN storage size by a factor of two.

Modern cars monitor their surroundings and record video to deter intruders, but current surveillance systems operate independently without communication. Connected vehicles can share detected features of suspicious individuals, improving tracking and alerting approaching drivers before they park in vulnerable spots. This paper explores this use case, where connected vehicles exchange features over the network upon detecting suspicious individuals. Real-world data analysis shows that connected vehicle surveillance improves detection accuracy by 38%.

Connected vehicles use Vehicle-to-Everything (V2X) communication to improve situational awareness. However, transmitting raw or irrelevant data may congest the communication channel, and limit the scalability and effectiveness of safety applications. This paper introduces the Context-Aware V2X concept, which assesses message relevance and adds contextual meaning before transmission, ensuring that only essential information reaches relevant receivers. We demonstrate the effectiveness of the Context-Aware V2X concept through simulations of the tailgating scenario, where results show that Context-Aware V2X can improve driver awareness and reduce risks associated with tailgating.

Edge computing is becoming ever more relevant to offload compute-heavy tasks in vehicular networks. In this context, the concept of vehicular micro clouds (VMCs) has been proposed to use compute and storage resources on nearby vehicles to complete computational tasks. As many tasks in this application domain are time critical, offloading to the cloud is prohibitive. Additionally, task deadlines have to be dealt with. This paper addresses two main challenges. First, we present a task migration algorithm supporting deadlines in vehicular edge computing. The algorithm is following the earliest deadline first model but in presence of dynamic processing resources, i.e., vehicles joining and leaving a VMC. This task offloading is very sensitive to the mobility of vehicles in a VMC, i.e., the so-called dwell time a vehicles spends in the VMC. Thus, secondly, we propose a machine learning-based solution for dwell time prediction. Our dwell time prediction model uses a random forest approach to estimate how long a vehicle will stay in a VMC. Our approach is evaluated using mobility traces of an artificial simple intersection scenario as well as of real urban traffic in cities of Luxembourg and Nagoya. Our proposed approach is able to realize low-delay and low-failure task migration in dynamic vehicular conditions, advancing the state of the art in vehicular edge computing.

Decentralized content distribution over vehicle-to-vehicle (V2V) WLANs holds promise to mitigate load on cellular networks. The delay in establishing a communication link is a key to maximize V2V data transfer opportunity, as contact duration of vehicles is often limited due to their fast mobility. IEEE 802.11ai standard defines Fast Initial Link Setup (FILS), which simplifies the link setup process to reduce latency. In this paper, we investigate the benefit and limitations of FILS in V2V WLANs. We develop a testbed involving multiple vehicles, and compare the link setup latency of FILS with regular EAP authentication. Counterintuitively, regular EAP achieved equivalent performance in V2V WLANs due to architectural constraints of FILS.

We present the performance analysis of TCP CUBIC/BBR over V2V Wi-Fi (IEEE 802.11ac). Our measurements focus on three static parking scenarios with different distances at the office area. The results reveal the impact of TCP CUBIC and BBR on data transfer time and TCP metrics. (i) There are two major reasons of fluctuated TCP throughput. The first reason is narrow available bandwidth over V2V Wi-Fi. The second reason is delayed TCP connection establishment due to delayed SYN+ACK and SYN packet retransmission. (ii) The bytes in-flight of TCP CUBIC are dynamically changed by packet retransmission events on V2V Wi-Fi. The loss-based congestion control is not promising the high throughput. We believe that our analysis results provide implications for efficient data transfer over V2V Wi-Fi.

Recently, demand has been growing for development data in research on driver assistance systems. However, important scenes in research vary widely from person to person. For example, developers are interested in collision avoidance might be interested in pedestrian darting out or approaching vehicles. On the other hand, some developers may be interested in traffic scenes. Thus, user preferences vary and making the detection of important scenes are complex. We propose a novel approach to detect important scenes based on user's preferences, novelty of a driving scene and driving data. We annotate important scenes from the NuScenes dataset and confirmed improvement in accuracy from existing important scene detection model.

Fall-on-car incidents (e.g., trees or branches falling on a car) are an underestimated hazard during weather events, mainly affecting vehicles. Unfortunately, drivers are usually unaware of this danger until it occurs. On the other hand, connected vehicles can sense their surroundings, analyze this data with weather forecasts, and alert the driver if there is a risk of a fall-on-car incident. This paper focuses on this use case and demonstrates the Fall-on-Car Prevention (FoP) system. FoP system detects trees and tree branches and alerts drivers when windy conditions are forecasted, allowing early preventative action to be taken while parking. Our evaluation compared to 12 human experts demonstrates that the FoP system can enhance driver awareness of the risk of falling objects.

Vehicular Micro Cloud (VMC) is a group of connected vehicles where vehicles collaborate on a task over the vehicular network. A potential use case of VMC is that micro cloud members transfer data to each other via Vehicle-to-Vehicle (V2V) links, and the data is collaboratively uploaded to remote server (e.g., data center) when the connected vehicles are connected to a Wi-Fi network. In this paper, we focus on this use case and propose collaborative upload by VMC. We demonstrated the feasibility of the proposed method through the large-scale urban simulation (Los Angeles downtown traffic model). Our simulation results showed that the proposed method can reduce the upload data of traditional cellular network-based data upload by 50%.

Vehicular communication enables advanced incident management to overcome non-recurrent disruptions and severe congestion. While traditional stationary vehicular clouds, fixed to roadside infrastructure are innovative, they could experience extensive data traffic and infrastructure communication delays. Dynamic vehicular clouds could provide a promising solution to overcome these challenges to reduce communication latency through cooperative message dissemination whilst maintaining stable vehicle maneuvers. This study offers a comparative performance analysis of freeway incident management, using speed and lane-changing advisories, deployed with stationary and platoon-based dynamic vehicular micro clouds (VMCs). The system-level communication features, driving safety, and vehicular mobility are measured to evaluate the efficacy of both systems under incident-induced traffic management. The communication latency and packet loss ratio of the stationary cloud is on average 6.2% and 4.8% higher than those of the dynamic clouds, respectively. In addition, the dynamic cloud shows advantages in reducing travel time delay and risk of collisions, even at high connected vehicle penetration rates. Our work also aims to highlight the novel communication features of cellular technologies (4G LTE, 5G), that could reduce communication delay and interference with the deployment of advanced traffic management strategies. The research sets a foundation to deploy novel vehicle communication architectures while quantifying the advantages of vehicular clouds for managing freeway traffic.

A Vehicular Micro Cloud (VMC) is a group of connected vehicles where vehicles collaborate on tasks through vehicular networks. VMCs may overlap with other vehicular micro clouds in certain regions (e.g., intersections), known as overlapping zones. In overlapping zones, micro cloud members may have to switch between multiple VMCs back and forth, which degrades the functionality of the VMC. In this paper, we address this problem and propose to regroup micro cloud members when VMCs overlap. VMCs share their information with a remote server. The remote server controls and swaps members among VMCs in overlapping zones. We test the feasibility of the proposed approach through a simulation study. Extensive simulations in different settings demonstrate that controlled membership swaps can reduce the member switches among VMCs in overlapping zones by about 85%.

Modern cars can detect unsafe driving by comparing the observed behavior of the subject vehicle (i.e., rear vehicles) with normal driving. However, normal driving does not have a standard definition. It changes depending on the situation. In this work, we address this problem and propose edge-assisted unsafe driving detection. In our proposal, instead of learning normal driving, the edge infers the most common unsafe driving patterns. It then shares this knowledge with cars. Cars look for such patterns to detect unsafe driving. Analysis of real-world traffic data shows that edge-assisted unsafe driving detection could detect unsafe behavior of subject vehicles with 90% accuracy.

Unsafe driving has evolved into a public safety crisis. More than half of fatal crashes are due to distracted and aggressive driving. Modern cars have systems to monitor and notify drivers when erratic driving is detected. However, such systems do not help when other nearby vehicles drive unsafely. In this paper, we focus on this use case. We propose a nearby erratic driving detection method in which the ego vehicle observes its surroundings and identifies anomalous driving. We develop and test the proposed method through simulation. Then, we check the feasibility of the proposed method in field trials with multiple test vehicles. Evaluation results show that the proposed method can detect erratic driving on average 4 seconds before the risk of collision becomes maximum with 70% accuracy.

Modern cars can monitor rear vehicles and detect unsafe driving before the risk of rear-end collision becomes maximum. In this paper, we focus on this use case. We propose a Rear Vehicle Behavior Awareness (RVBA) system to prevent rear-end collisions. RVBA detects unsafe driving of rear vehicles and alerts the driver with guidance to reduce the risk of rearend collisions. We tested the RVBA in field experiments using a test vehicle. Experimental results show that RVBA can detect unsafe driving of rear vehicles in 4 seconds on average, with 70% accuracy, before the risk of rear-end collision becomes maximum. Index Terms–erratic movement patterns, rear-end collisions, rear vehicle behavior awareness, unsafe driving detection

In the field of vehicular networks, multiple approaches have been proposed to share and reuse data acquired by participating hosts. In this context, vehicular micro clouds extend the concept of Mobile Edge Computing (MEC) and bring data storage and processing to the vehicles, solving application tasks that need to be done in real-time. A critical point in shared computing tasks and storage is to keep all nodes synchronized and to maintain consistency. For the first time, we study the relevance of data versions in micro clouds offering intersection management service at four-way stop intersections and we investigate how different versions of data affect both road traffic and wireless communications. Our results validate the intuition that an increase in the amount of different data versions in the micro cloud has negative effects on both road traffic and wireless channel usage. Yet, the choice of the data sharing algorithm can make a huge difference and reduce these effects on a large scale. We found that synchronicity of data versions can be increased by up to 20% through small changes, e.g., keeping small amounts of data history in the applied algorithm.

It is estimated that the data volume between connected vehicles and edge/cloud server(s) will be about 100 petabytes per month by 2025. The networking framework we have, on the other hand, is the existing cellular network in which the most connected vehicles function today. However, such a network suffers from several issues and may not work under this predicted data demand. To address such a dilemma, a new paradigm, Vehicular Knowledge Networking (VKN), is recently introduced. In VKN, the data is transformed into knowledge and it is distributed with various lifetimes/relevance. To benefit from the knowledge, on the other hand, it should be placed intelligently such that a high number of vehicles can access and consume it. In this paper, we tackle this issue and propose mobility-aware smart knowledge placement. In the proposed method, vehicle mobility is analyzed to measure the centrality degree of a region. The computed centrality degrees are then further analyzed to identify the most central zones. The knowledge is placed on these zones to increase availability. We demonstrate the benefits of the proposed method through a simulation. Our preliminary result has shown that the mobility-aware smart knowledge placement makes knowledge accessible from vehicles over short range communication. Through such short-range availability of knowledge, vehicles can use the free spectrum to download it which decreases the cellular communication cost significantly.

Aggressive driving is the leading cause of many fatal crashes. Ego vehicles should detect such dangerous driving behavior on other cars and guide drivers to mitigate collision risk. In this paper, we focus on that use case. We demonstrate a nearby aggressive driving detection system. In nearby aggressive driving detection, the ego vehicle observes the follower vehicle and detects aggressive driving behavior on the follower vehicle. It notifies its driver whenever the follower vehicle exhibits aggressive driving.

Today, modern vehicles can detect other nearby distracted drivers. The next step could be the management of distracted driving, in which a system guides innocent drivers around distracted drivers. The ego vehicle can share detected nearby distracted drivers with the remote server. The remote server tracks them and generates control suggestions (i.e., speed and lane change advisories) to keep innocent drivers away from distracted drivers. In this paper, we focus on that use case. We propose to generate control suggestions (e.g., speed and lane change advisories) for connected vehicles around inattentive drivers. Extensive simulations show that distracted driving management could decrease the collision risk by 78%.

Vehicular Micro Clouds (VMCs) are an emerging development in the domain of vehicular networks posed to provide local services to users without the need for external infrastructure. This can significantly improve the user experience, in particular due to the low latencies that such systems can achieve. Due to the distributed nature of such a VMC, effective local coordination is important while using minimal communication resources. To this end, it is important to know, how long vehicles will be participating in, and contributing to a VMC. In this work, we investigate, how previous, heuristic-based approaches can be improved by incorporating local, learning-based techniques. Our analysis indicates a potential improvement of the accuracy of the prediction, and resulted in an improved simulation environment within which the learning-based approach can be deployed.

Aggressive driving became a public safety crisis in the USA. Aggressive drivers tailgate and weave among lanes, which may cause risky events ending up in collisions. Vehicles should be aware of such nearby aggressive driving and notify drivers to keep them away from aggressive ones. In this paper, we focus on that use case. The ego vehicle observes the movements of other nearby cars and detects aggressive driving. We tested the feasibility of the proposed approach through a simulation. Simulation results show that the ego vehicle could identify aggressive driving on other cars with about 94% accuracy.

The riskiness of the roadway environment needs to be known in advance to improve driving safety. Such knowledge brings strong benefit to drivers and could be used to reduce the risk of collision. For example, vehicles can support a driver with guidance before arriving at the risky zones. In this paper, we focus on this use case. We propose risk avoidance by Vehicular Knowledge Networking (VKN). The proposed method mines the maneuver conflicts to determine risky zones. According to identified zones, guidance (e.g., speed and lane change suggestions) is shared with vehicles to help drivers pass these risky regions smoothly. Extensive simulations in different settings have shown that risk avoidance by VKN could decrease the collision risk by approximately 50%.

Vehicular edge computing is enabling a variety of new services that better assist safety and comfort of driving. However, vehicles cannot offload an unlimited amount of computational tasks and input sensor data to a remote edge server because of the limitations in network bandwidth. In this paper, we design a learning-based task of floading mechanism that selects a small subset of input sensor data, which are expected to improve the application performance if processed by a rich and resource-intensive algorithm, hosted by the edge server. As a case study, we apply this framework to a vision-based object tracking application. The simulation results show that the proposed solution significantly improves object tracking accuracy with the same amount of resource consumption.

The detection of abnormal driving behavior is important for safety. However, driving is a combination of both internal (e.g., skills) and external (e.g., road type, traffic conditions) factors that make abnormal driving behavior detection largely subjective. On the other hand, this subjectivity could be handled through the analysis of driving data at multiple levels including the low-level driving action recognition up to high-level inference of a road section. In this paper, we tackle this problem and propose a Hierarchical Abnormal Driving Behavior Detection System (H-ABDS) that is not only mining individual behavior of vehicles but also runs a statistical learning-based technique to understand human driving data at multiple levels. We design a hierarchical architecture to enable abnormal driving behavior detection at the city-scale and demonstrate its benefits through extensive simulations conducted on simulated traffic data. Our preliminary result has shown that H-ABDS can identify all driving anomalies by about 75% accuracy under a certain degree of connected vehicle penetration rates.

Vehicular micro cloud is a promising solution in which connected vehicles offer their resources as services to others and collaborate on tasks through vehicular networks. The properties of the vehicular micro cloud are generally set when it is formed at the core area and they remain static. However, a change in the environment could leave the micro cloud unable to respond adequately as its static properties become obsolete. Reacting to changes in the environment, on the other hand, requires dynamic updates on the properties of the vehicular micro cloud. In this paper, we address this dilemma and propose a chain of interdependent vehicular micro clouds. To respond to the changes in the environment, interdependent micro clouds are formed around the first vehicular micro cloud. Guidance information is transmitted before members of the dependent micro clouds arriving at the core area of the first micro cloud. Extensive simulations in different vehicular micro cloud settings show that the chain of interdependent vehicular micro clouds significantly improves the ability to respond to changes within the first micro cloud. Through the provided guidance information, members of dependent micro clouds are collectively prepared before they arrive at the core area.

In this work, we propose the use of hybrid offloading of computing tasks simultaneously to edge servers (vertical offloading) via LTE communication and to nearby cars (horizontal offloading) via V2V communication, in order to increase the rate at which tasks are processed compared to local processing. Our main contribution is an optimized resource assignment and scheduling framework for hybrid offloading of computing tasks. The framework optimally utilizes the computational resources in the edge and in the micro cloud, while taking into account communication constraints and task requirements. While cooperative perception is the primary use case of our framework, the framework is applicable to other cooperative vehicular applications with high computing demand and significant transmission overhead. The framework is tested in a simulated environment built on top of car traces and communication rates exported from the Veins vehicular networking simulator. We observe a significant increase in the processing rate of cooperative perception sensor frames when hybrid offloading with optimized resource assignment is adopted. Furthermore, the processing rate increases with V2V connectivity as more computing tasks can be offloaded horizontally.

Signal Phase and Timing (SPaT) refers to the current signal state of an intersection and the time duration that the state will last for each lane. Learning SPaT information constitutes a building block for many connected vehicle applications such as light duration advisory and start-stop control. However, retrieving SPaT information is not an easy task. One alternative approach to learn SPaT information could be the analysis of vehicles' mobility patterns. This paper investigates the design and feasibility of such an approach and proposes a system namely Virtual SPaT (V-SPaT). In V-SPaT, a group of connected vehicles form a Vehicular Cloud (VC) and collaborate to act as a virtual infrastructure at an intersection. Cloud members not only analyze their mobility patterns to predict the current phase and a residual time of that phase but also keep the SPaT information through collaborative data storage so that vehicles approaching the intersection can obtain this information over Vehicle-to-Vehicle (V2V) networks. The simulation results show that V-SPaT can identify the current phase and estimate the residual time by about 85% accuracy under a certain degree of V2V communications penetration rates.

Vehicles are expected to generate and consume an increasing amount of data, but how to perform risk reasoning over relevant data is still not yet solved. Location, time of day and driver behavior change the risk dynamically and make risk assessment challenging. This paper introduces a new paradigm, transferring information from raw sensed data to knowledge and explores the knowledge of risk reasoning through vehicular maneuver conflicts. In particular, we conduct a simulation study to analyze the driving data and extract the knowledge of risky road users and risky locations. We use knowledge to facilitate reduced volume and share it through a Vehicular Knowledge Network (VKN) for better traffic planning and safer driving.

Dynamic Spectrum Access (DSA) improves spectrum utilization by allowing secondary users (SUs) to opportunistically access temporary idle periods in the primary user (PU) channels. Previous studies on utility maximizing spectrum access strategies mostly require complete network state information, therefore, may not be practical. Model-free reinforcement learning (RL) based methods, such as Q-learning, on the other hand, are promising adaptive solutions that do not require complete network information. In this paper, we tackle this research dilemma and propose deep Q-learning originated spectrum access (DQLS) based decentralized and centralized channel selection methods for network utility maximization, namely DEcentralized Spectrum Allocation (DESA) and Centralized Spectrum Allocation (CSA), respectively. Actions that are generated through centralized deep Q-network (DQN) are utilized in CSA whereas the DESA adopts a non-cooperative approach in spectrum decisions. We use extensive simulations to investigate spectrum utilization of our proposed methods for varying primary and secondary network sizes. Our findings demonstrate that proposed schemes outperform model-based RL and traditional approaches, including slotted-Aloha and Whittle index policy, while % 87 of optimal channel access is achieved.

This paper investigates the design and feasibility of Co-Park, where a group of connected vehicles in a parking facility collaborate with each other to find available parking spots in a timely fashion. Vehicles measure occupancy of the surrounding parking spots by their on-board sensors, and share the occupancy information with other group members over vehicular networks. Based on prediction of the short-term occupancy variation and coordination among group members, the vehicles strategically plan efficient paths to search for an available spot. Simulation results show that the system can significantly reduce the trip time in a parking facility.

The automotive industry is under a major change and new vehicles are being enriched by the recent advances in communication. Not only business plans are changing due to connected and urbanized lifestyle, but also transportation is becoming more intelligent with smart roads that connect smart cars. Technology coined as the vehicular ad-hoc network (VANET) is harmonizing with Intelligent Transportation System (ITS) and Intelligent Traffic System (ITF). However, ITS and ITF systems suffer from the scarcity of radio frequency spectrum. Visible light communication (VLC) that uses modulated optical radiation in the visible light spectrum is an alternative medium being researched. To date, the majority of research on vehicular VLC was aimed at achieving high data rates provided that high lighting quality is achieved without any concern on dimmable LED lights. Auto-dimmable headlights gain attention due to danger caused by sudden glare on drivers at night conditions which makes dimming in VLC necessary. In this paper, we first present the latest concept of vehicular VLC on ITS and ITF systems and address dimming utility. We then demonstrate experimentally that dimming is a key parameter in VLC which affects data dissemination and received power signal strength.

Quality of user experience in Distributed Interactive Applications(DIAs) highly depends on the network latencies during the system execution. In DIAs, each user is assigned to a server and communication with any other client is performed through its assigned server. Hence, latency measured between two clients, called interaction time, consists of two components. One is the latency between the client and its assigned server, and the other is the inter-server latency, that is the latency between servers that the clients are assigned. In this paper, we investigate a real-time client to server assignment scheme in a DIA where the objective is to minimize the interaction time among clients. The client assignment problem is known to be NP-complete and heuristics play an important role in finding near optimal solutions. We propose two distributed heuristic algorithms to the online client assignment problem in a dynamic DIA system. We utilized real-time Internet latency data on the Planet Lab platform and performed extensive experiments using geographically distributed Planet Lab nodes where nodes can arbitrarily join/leave the system. The experimental results demonstrate that our proposed algorithms can reduce the maximum interaction time among clients up to 45% compared to an existing baseline technique.

Clustering is an effective mechanism to handle the fast changes in the topology of vehicular ad hoc networks (VANET) by using local coordination. Constructing stable clusters by determining the vehicles sharing similar mobility pattern is essential in reducing the overhead of clustering algorithms. In this paper, we introduce VMaSC: Vehicular Multi-hop algorithm for Stable Clustering. VMaSC is a novel clustering technique based on choosing the node with the least mobility calculated as a function of the speed difference between neighboring nodes as the cluster head through multiple hops. Extensive simulation experiments performed using ns-3 with the vehicle mobility input from the Simulation of Urban Mobility (SUMO) demonstrate that novel metric used in the evaluation of the least mobile node and multi-hop clustering increases cluster head duration by 25% while decreasing the number of cluster head changes by 10%.