In vehicular networks (VNets), vehicular federated learning (VFL) is a new learning paradigm that can protect data privacy of vehicle nodes (VNs) while training models. In VFL, the importance of data ...(IoD) is a key factor that affects model training accuracy. However, due to the heterogeneity of data in the VFL, it is a challenge to evaluate the quality of data owned by different VNs and design an efficient federated learning scheme to enable the VNs to complete learning tasks collaboratively. In this paper, we consider the IoD and propose a redundancy-aware collaborative federated learning (RCFL) scheme for the VFL. In the scheme, by jointly considering the data quality and the cooperation among VNs, we first design a redundancy-aware federated learning architecture to efficiently provide learning services in VNets. Then, we develop a data importance model that integrates the non-independent and identically distributed (non-IID) degree and the redundancy of data (RoD) to evaluate the data quality and formulate the cooperation of the VNs as a coalition game to improve their data importance, where the equilibrium of the coalition game is obtained by designing a coalition formation algorithm. After that, by considering the diversified characteristics of data and the available resources of different VNs in each coalition, a coalition-based federated learning algorithm is designed to enable the distributed coalitions to complete the learning task cooperatively with the target of improving the learning accuracy. The simulation results show that the proposed scheme outperforms the benchmark schemes in terms of the IoD obtained by the VNs and the training accuracy.
The 5G heterogeneous networks (HetNets) are capable of providing real-time computing services for autonomous vehicles (AVs) by deploying edge computing devices (ECDs) at macro cell base stations ...(MCBSs) and small cell base stations (SCBSs). With the imbalanced distribution and fast moving AVs contending intensely for computing services, how to efficiently exploit cooperations among participants in 5G HetNets to improve the service performance is therefore challenging. In this paper, we develop a game theoretic scheme for collaborative vehicular task offloading to facilitate the computing services in 5G HetNets. Specifically, we propose a two-stage vehicular task offloading mechanism to promote the cooperation among participants with the target of improving the task completion rate and the utilities of the participants, where the mechanism jointly considers the network architecture of the HetNets, the imbalanced distribution of AVs and the reuse of task results. In the first stage, an auction model is designed to help the MCBS select the optimal SCBS to execute the offloaded task based on the requirement of the task and the available computing resources of SCBSs. According to the task execution cost declared by the selected SCBS, the MCBS then bargains with the AV for the agreement of the task offloading service to maximize their utilities in the second stage. Using simulations, we show that the proposed collaborative task offloading scheme can achieve a higher task completion rate for the task offloading service and bring higher utilities to all participants than conventional schemes.
Sixth-generation (6G) space-air-ground integrated vehicular networks (SAGIVNs) are expected to provide customized edge computing services for moving vehicles (MVs). In this article, by integrating 6G ...SAGIVNs and edge computing, we propose a secure and personalized vehicular edge computing framework in 6G to satisfy the diversified requirements of MVs. In the framework, we first develop a collaborative edge computing mechanism, where each 6G infrastructure (e.g., satellite, drone, and base station) cooperates with parked vehicles to provide services for MVs in order to improve the efficiency of the edge computing services. Then, considering the security issues, a smart-contract-based secure collaboration mechanism is designed to establish a reliable transaction environment for edge computing in 6G. Next, based on the personalized service requirements of MVs and the available resources in 6G SAGIVNs, the resource allocation strategy of each infrastructure and the competitiveness of different infrastructures are discussed to provide MVs with the optimal personalized service. After that, compared with the conventional schemes, a case is studied to evaluate the effectiveness of the proposed framework. Finally, we outline open research topics to identify future research opportunities and directions.
Collaborative driving can significantly reduce the computation offloading from autonomous vehicles (AVs) to edge computing devices (ECDs) and the computation cost of each AV. However, the frequent ...information exchanges between AVs for determining the members in each collaborative group will consume a lot of time and resources. In addition, since AVs have different computing capabilities and costs, the collaboration types of the AVs in each group and the distribution of the AVs in different collaborative groups directly affect the performance of the cooperative driving. Therefore, how to develop an efficient collaborative autonomous driving scheme to minimize the cost for completing the driving process becomes a new challenge. To this end, we regard collaboration as a service and propose a digital twins (DT)-based scheme to facilitate the collaborative and distributed autonomous driving. Specifically, we first design the DT for each AV and develop a DT-enabled architecture to help AVs make the collaborative driving decisions in the virtual networks. With this architecture, an auction game-based collaborative driving mechanism (AG-CDM) is then designed to decide the head DT and the tail DT of each group. After that, by considering the computation cost and the transmission cost of each group, a coalition game-based distributed driving mechanism (CG-DDM) is developed to decide the optimal group distribution for minimizing the driving cost of each DT. Simulation results show that the proposed scheme can converge to a Nash stable collaborative and distributed structure and can minimize the autonomous driving cost of each AV.
The rapid growth of connected and autonomous vehicles (CAVs) shows an urgent demand for driving and transportation-related data, which gives rise to vehicular crowdsensing systems (VCSs). ...Nevertheless, the existing centralized VCS framework mainly faces the system reliability problem while the decentralized one cannot satisfy the management flexibility. In addition, when the privacy preservation scheme that prevents information leakage encounters the user selection scheme that desires detailed information of participants, how to balance this seemingly irreconcilable contradiction is inevitable for VCS. To remedy that, we take the first research attempt and explore the balance point between the system management, privacy preservation, and quality of experience (QoE) of participants. By fully exploiting the characters of participating entities, a blockchain-enabled conditional decentralized VCS is proposed in this paper. Firstly, we propose a privacy-preserving scheme where the zk-SNARK proof combines with the mixed-task smart contract to guarantee the interaction process will not reveal any private information of participants. Secondly, we propose an efficient reputation management mechanism that renders certain the participants can get a satisfactory QoE even under the condition that the private information of users is secured. And also, the malicious operations in the system will be effectively supervised. Theoretical analysis and extensive simulations demonstrate the security and efficiency properties of privacy preservation and indicate the effectiveness of reputation management.
Recently, mobile charging stations (MCSs) have attracted more attentions compared with fixed charging stations (FCSs). Electric vehicles (EVs) can be easily provided with charging service through ...MCSs. However, most of existing approaches cannot be properly used to design the optimal pricing strategy for MCSs, leading to the inefficiency of power in MCSs. Thus, it is necessary to study new incentive mechanisms to improve MCSs’ profits. In this paper, we propose a contract-based scheme to maximize MCSs’ profits in the heterogeneous networks. Considering the power trading between EV users and MCSs, we develop the utility function with EV users’ types. Aiming to maximize MCSs’ profits, we formulate this problem as an optimization problem under the complete and incomplete information of EV users, respectively. Through the theoretical analysis, we prove the existence of optimal contract items, which also ensure the feasibility of EV users. Then optimal solutions can be achieved based on our proposed algorithm. Numerical and simulation results validate the effectiveness of our proposal.
The integration of the massive multiple-input multiple-output (MIMO) and millimeter-wave (mmWave) communication can increase the throughput of 5G networks. As an attractive technique in the MIMO ...systems, hybrid beamforming (HBF) can improve the 5G capacity by employing spatial domain resources. However, with the increase of the number of antennas, the traditional beamforming algorithms fail to efficiently keep a balance between the hardware complexity and beamforming gains. In this paper, with the aid of bidirectional location information, a bidirectional positioning assisted HBF (BPA-HBF) scheme is proposed. Specifically, we first propose a new scheme to decouple the optimal problem of traditional HBF as two phases. In the analog beamforming (ABF) phase, the dominated path among the multi-path components is determined by the transmitter and receiver. In addition, the codebook-based beamforming weight vectors are bidirectionally and synchronously determined according to the angle parameters of the dominated path. In the second phase, based on the ABF matrices, the digital beamformers are designed to maximize the energy efficiency. Simulation results indicate that the proposed BPA-HBF scheme can lead to a lower convergence time and complexity than the conventional schemes. In addition, the results show that the algorithm convergence time can be significantly reduced by increasing the positioning precision.
With the widespread application of wireless networks, the importance of intelligent analysis of network behaviors is becoming increasingly prominent. In the analysis of networks behaviors, learning ...and reasoning about the connectivity of unknown networks is a fundamental problem. To obtain the topology information of a noncooperative wireless network that could not be accessed by the monitoring sensors, we propose a topology inference algorithm based on the network two-dimensional spatiotemporal features (TDSTFs). Specifically, the monitoring sensor network monitors the power of the noncooperative network and locates the nodes of the noncooperative network exploiting the neural network (NN)-based method. Then, the communication time and distance between the noncooperative nodes are used as characteristics to infer the topology of the noncooperative network based on Formula Omitted-nearest neighbors (KNNs). Simulation results validate that the proposed TDSTF topology inference algorithm outperforms other topology inference algorithms that do not consider both spatial and temporal features and can greatly improve the inference accuracy.
With the rapid development of autonomous driving and heterogeneous vehicular networks (HetVNets), vehicles can collect data and generate valuable information to obtain profits, thus forming a new ...vehicular self-media paradigm. However, with potential security risks, the current data trading schemes in the HetVNets lack the comprehensive consideration of the requirements of the participants including media data producers (MDPs), media data sellers (MDSs), and media data buyers (MDBs) to design a trading framework that integrates data caching services and data selling services. To this end, we propose an on-demand self-media data trading scheme in HetVNets. Specifically, based on blockchain and smart contracts, we first design an on-demand self-media trading architecture that jointly considers the data caching services and the data selling services to provide the participants with a secure transaction environment. In the data caching phase, by considering the value of media data generated by the MDPs and the sales capabilities of different MDSs, we model the requirements of the MDPs and the MDSs as utility functions and formulate the interactions between them as a Stackelberg game, where an iterative algorithm is designed for the MDPs and the MDSs to obtain their optimal strategies. In the data selling phase, we consider the diversified requirements of the MDBs and propose an iteration-based mechanism to help the MDSs dynamically determine the data selling strategies. Compared with the traditional schemes, the simulation results show that our scheme can obtain the optimal strategies for the MDPs and the MDSs and bring them the highest utilities.
In the heterogeneous vehicular networks (HetVNets), the roadside units (RUs) 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 request their model training tasks in the HetVNets. In this paper, we consider the scenario of multi-TR and multi-RU and propose a digital twins (DT) enabled on-demand matching scheme for multi-task federated learning to address the two-way selection problem between TRs and RUs. Specifically, by jointly considering the diversified requirements of the TRs and the differentiated training capabilities of the RUs, we first design a DT enabled on-demand matching architecture to facilitate the multi-task federated learning in the HetVNets. Then, based on the personalized requirement of the DT of each TR (DT-TR), a marginal utility based vehicle selection mechanism is proposed to enable the DT of each RU (DT-RU) to determine the customized model training strategy. With the determined strategies, the two-way selection problem between the DT-TRs and the DT-RUs is formulated as an on-demand matching game in DT networks, where a matching algorithm is designed to obtain their optimal strategies. Simulation results demonstrate that the proposed scheme outperforms the conventional schemes in terms of training accuracy, performance-cost ratio (PCR), and task completion rate (TCR).