The heterogeneous vehicular networks (HetVNets) can accelerate the deployment of Internet of vehicles (IoV) and enrich the content distribution methods. However, the diverse requirements of vehicular ...users (VUs), the limited cache resources of roadside units (RUs), and the frequent interactions between VUs and RUs pose great challenges to efficiently distribute contents. To address these challenges, we propose an on-demand content delivery scheme in digital twin enabled HetVNets (DT-HetVNets). Specifically, we first design an on-demand content delivery architecture in DT-HetVNets which uses DT communication mode to simplify the frequent interactions between VUs and RUs. With this architecture, by jointly considering the popularity of each content and the relevance between different contents, the personal content requirement of each DT of VU (DT-VU) can be perceived and the VUs within the coverage of the same RU can collaboratively request contents in groups. Then, we formulate the interaction between each group and the DT of the RU (DT-RU) as a double auction game to determine the transaction price of the perceived content, where the request information of the contents which are accepted by the groups can be shared between different DT-RUs based on the path of each group, enabling collaborative content recommendation between the RUs. After that, by jointly considering the contents recommended by different DT-RUs and the content popularity, the content caching model of each DT-RU is formulated as a knapsack problem, where a collaborative content caching algorithm is designed to obtain the optimal caching strategy with the target of making full use of the limited cache resources. Compared with the conventional schemes, the simulation results show that our scheme can not only bring the highest utility to the RUs, but also lead to the highest hit ratio and the lowest delay.
The autonomous vehicles (AVs), as intelligent mobile robots, can undertake tasks to facilitate various computation-intensive services in intelligent transportation systems (ITS). Due to hardware ...device failures or environmental identification errors, the AVs controlled by intelligent algorithms may cause accidents during driving. However, the existing studies in post-accident stage lack the analysis of the impact degree of the accidents and the computing tasks undertaken by the AVs to determine the optimal maintenance strategy. In this paper, we consider the accidents in a continuous period of time and design a digital twins (DT)-enabled post-accident maintenance scheme. Specifically, by considering the computing tasks undertaken by the AVs and the impact degree of the accidents, we first design a DT-enabled post-accident maintenance architecture. With the designed architecture, an optimal maintenance method under incomplete information scenario is then proposed to help each accident AV decide its optimal maintenance strategy. Besides, based on the maintenance strategies of the AVs and the capacities of the maintenance service providers (MSPs), the two-way selection problem between the AVs and the MSPs in the continuous period of time is modeled as a dynamic matching game to obtain the optimal AV-MSP pairs. Simulation results demonstrate that the proposed scheme outperforms the benchmark schemes in terms of the maintenance rate of the accident AVs, the average utility of the MSPs, and the average social welfare.
The rapid development of Internet of Things (IoT) technology can significantly promote the development and deployment of smart roads, enabling efficient and reliable road information sensing and ...analysis. As an important part of smart roads, timely and accurate detection of road cracks can improve service life of roads and reduce road management and operating costs. In this paper, we propose a vibration-sensor-based crack detection scheme for smart roads. In this scheme, by deploying the vibration sensor on the roadside, the changes in the vibration signals caused by the vehicle passing through the range of the sensor can be collected in real time. Then, considering that the seismic waves caused by vehicle driving are mostly distributed in the low-frequency range, we perform low-pass filtering on the collected vibration signals to retain the low-frequency vibration signals. After that, in order to distinguish the crack state of the road, we extract the vibration signal features of the normal road and the cracked road in the time domain, frequency domain and time-frequency domain, respectively. Based on the extracted features, we use logistic regression (LR), support vector machine (SVM) and random forest classification (RFC) machine learning algorithms to realize road crack detection. Finally, we conduct experiments to evaluate the performance of the proposed road crack detection scheme. The experimental results verify the high accuracy of the proposed scheme, and the accuracy of LR, SVM and RFC are 93.3%, 93.3% and 96.7%, respectively.
In digital twins enabled space-air-ground integrated networks (DT-SAGINs), the DT of a vehicle (DT-V) needs to constantly migrate between the infrastructures deployed on the path of the vehicle as ...the vehicle moves to provide stable and continuous driving services for the vehicle. However, each DT-V has differentiated migration requirements and the heterogeneous network infrastructures have various migration performances. Therefore, how to design a scheme that jointly considers the above factors to determine the optimal migration strategy for each DT-V becomes a challenge. In this paper, we propose a game-based migration scheme for the DT-Vs in DT-SAGINs. In this scheme, we first design a two-layer DT migration architecture, where each vehicle has two DTs and each network infrastructure only has one DT. The two DTs of the vehicle are respectively deployed in the cloud layer (Primary DT-V) and the edge layer (Second DT-V). In contrast, the DT of each network infrastructure is deployed in the cloud layer (DT-I). Based on the designed architecture, the interaction of the Primary DT-Vs and the DT-Is deployed in the cloud layer is formulated as a matching game, where an integrated algorithm that couples bilateral matching and dynamic programming is designed to obtain the optimal migration strategy for each Second DT-V deployed in the edge layer to maximize its average utility. The simulation results show that the proposed scheme can lead to a higher utility for each Second DT-V than the conventional schemes.
With the development of communication technology and virtual reality (VR) technology, virtual Metaverse services are gradually entering people's lives to provide immersive experience. As one of the ...important travel tools for people, vehicles have the opportunity to become the carrier of Metaverse, thereby enhancing the driving experience and entertainment experience of vehicle users (VUs). However, due to the high-speed movement of vehicles, how to dynamically adapt to environmental changes to allocate transmission and computing resources so that VUs can better experience VR services in the Metaverse has become a challenge. To this end, in this paper, we propose an environment-aware dynamic resource allocation scheme for VR video services in vehicle Metaverse, aiming to efficiently allocate computing and communication resources to maximize the quality of experience (QoE) of VUs when requesting VR video services. Specifically, we first establish the system model which includes network model, communication model, and VR video model. Then, considering the dynamic changes in the driving environment, we design a QoE model for each VU based on its VR video buffer. After that, we design a deep deterministic policy gradient (DDPG) algorithm to optimally allocate communication and computing resources to maximize the QoE of each VU. The simulation results show that our scheme can bring the highest reward to the VUs compared with the benchmark schemes.
Vehicular location information plays a crucial role in intelligent transportation systems. A particular focus is on developing an internet of things (IoT)-based sensing system for smart roads to ...enable high-precision vehicle localization that does not rely on global navigation satellite system (GNSS) and improve traffic safety and efficiency. As a passive low-power IoT technology, radio frequency identification (RFID) has been proposed as an alternative localization approach in GNSS-denied scenarios. However, limited by the licensed narrow bandwidth, the localization accuracy of commercial off-the-shelf (COTS) RFID readers is quite low. To achieve the RFID-based high-precision localization, we develop an RFID localization reader on a universal software radio peripheral (USRP) platform, which realizes virtual broadband multi-frequency continuous-wave (MFCW) transmission and phase extraction of the received backscattered signals. The genetic algorithm (GA) is applied to choose the optimal frequency set to minimize the range difference estimating error. By calculating the phase difference of arrival (PDOA), the localization problem can be modeled as hyperbolic equations and solved. Experimental results validate that our developed RFID-based vehicle localization system could achieve an accuracy less than 5 cm.
The combination of digital twins (DT) and heterogeneous vehicular networks (HetVNets) can significantly enhance the resource integration capability and performance of the network. In DT-HetVNets, ...vehicles need to selectively synchronize the data to be updated or cached to their DTs deployed in the cloud for data interaction and decision-making. However, considering that vehicles have diversified data synchronization requirements and network infrastructures have differentiated access capabilities, how to formulate optimal network access strategies and resource pricing strategies for vehicles and network infrastructures becomes a key challenge in the data synchronization process. To this end, we propose a utility-based on-demand data synchronization scheme in DT-HetVNets. In this scheme, we first establish the DT model and communication model in DT-HetVNets. Then, we design the utility functions of the DTs of vehicles and infrastructures by comprehensively considering their requirements. According to the utility functions, we model the decision-making process between the DTs of vehicles and the DTs of infrastructures as a Stackelberg game, where an iterative algorithm is proposed to obtain the Stackelberg equilibrium. The simulation results show that our scheme can bring them the highest utilities compared with the traditional schemes.
Smart roads can achieve a comprehensive, real-time and accurate perception of road environment, which is of great significance for intelligent transportation systems (ITS). However, due to massive ...data needed to be computed, cloud computing usually imposes pressure on backhaul and produces high delay. In this context, mobile edge computing (MEC) provides a promising solution. Meanwhile, current researches of the task offloading based on MEC lack global considerations and ignore IoT devices along the roadside, so optimization on three-side is very necessary and worth researching. To this end, we consider a scenario of smart roads including vehicular terminals (VTs), IoT devices and MEC servers. And we formulate an optimization problem aiming at minimizing a weighted sum of the costs of energy consumption and time delay for users side and cost for MEC servers. On this basis, we propose a three-side dynamic joint task offloading and resource allocation (TDJORA) scheme. Moreover, considering that the optimization problem is a multi-objective optimization problem, we utilize a combination of the particle swarm optimization (PSO) algorithm and Pareto optimality to obtain the optimal solution. Simulation results show that our proposed TDJORA can realize reasonable task offloading and optimal resource allocation for three sides.
In the heterogeneous vehicular networks (HetVNets), the base stations (BSs) can exploit the massive amounts of valuable data collected by vehicles to complete federated learning tasks. However, most ...of the existing studies consider the scenario of one task requester (TR) and ignore the fact that multiple TRs may concurrently generate their model training requests in the HetVNets. In this paper, we consider the scenario of multi-TR and multi-BS and propose a digital twin enabled scheme for multitask federated learning to address the two-way selection problem between the TRs and the BSs. We first analyze the diversified requirements of the TRs in the HetVNets. Then, we develop a novel model that jointly considers the available training data, the declared price, and the training experience to evaluate the differentiated training capabilities of the BSs. After that, based on the requirements of the TRs and the training capabilities of the BSs, the two-way selection problem between the TRs and the BSs is formulated as a matching game in the digital twin networks, where a matching algorithm is designed to obtain their optimal strategies. The simulation results demonstrate that the proposed scheme can obtain the highest model accuracy and bring the highest utility to the TRs compared with the conventional schemes.
The customization of edge computing services is one of the key research fields in sixth-generation (6G) heterogeneous vehicular networks (HetVNETs). With various personalized requirements of vehicles ...on computation-intensive applications, how to explore the heterogeneous computing resources in the 6G HetVNETs to guarantee vehicles with the customized Quality of Experience (QoE), therefore, becomes a challenge. In this article, we develop a novel secure scheme to provide personalized edge computing services for moving vehicles (MVs) in 6G HetVNETs. In the scheme, a smart-contract-based secure edge computing architecture is designed by jointly considering the attack models and the characteristics of the 6G network infrastructures (e.g., satellites, drones, base stations, and roadside units), where each network infrastructure manages a number of parking vehicles to complete computing services collaboratively. With this architecture, based on the available computing resources owned by different network infrastructures, the collaborative computing resource allocation algorithm is designed to help each network infrastructure decide a customized service strategy (CSS) to satisfy the QoE of MVs. After deciding the CSSs, a model based on the second price-sealed auction is formulated to describe the competition among the network infrastructures, where the Nash equilibrium of the game is obtained to guide their optimal bidding strategies to obtain the chance for completing the services. The security analysis and the simulation results show that the proposed scheme can defend against the attacks and lead to a lower cost for completing the services than the conventional schemes.