Caching and sharing the content files are critical and fundamental for various future vehicular applications. However, how to satisfy the content demands in a timely manner with limited storage is an open issue owing to the high mobility of vehicles and the unpredictable distribution of dynamic requests. To better serve the requests from the vehicles, a cache-enabled multi-layer architecture, consisting of a Micro Base Station (MBS) and several Small Base Stations (SBSs), is proposed in this paper. Considering that vehicles usually travel through the coverage of multiple SBSs in a short time period, the cooperative caching and sharing strategy is introduced, which can provide comprehensive and stable cache services to vehicles. In addition, since the content popularity profile is unknown, we model the content caching problems in a Multi-Armed Bandit (MAB) perspective to minimize the total delay while gradually estimating the popularity of content files. The reinforcement learning-based algorithms with a novel Q-value updating module are employed to update the caching files in different timescales for MBS and SBSs, respectively. Simulation results show the proposed algorithm outperforms benchmark algorithms with static or varying content popularity. In the high-speed environment, the cooperation between SBSs effectively improves the cache hit rate and further improves service performance.

During real-time production in industrial Internet of Things systems, equipment changes its operating speed due to changing operating conditions. And dynamic speed changes of rotating machinery under fluctuating workloads often lead to domain changes of vibration signals, which will directly lead to degradation of fault diagnostic model performance. Furthermore, the acquisition of data from multiple domains in real industrial scenarios is challenging due to the expense of collecting data from all possible working conditions. Consequently, applying diagnostic models trained using a single-source domain directly to an unknown target domain is a very challenging single domain generalization problem. Therefore, a generic single-source domain generalization framework via wavelet packet augmentation and pseudo-domain generation for fault diagnosis under unknown operating conditions is proposed in this paper. Pseudo-domain generation involves augmenting single-source domain by integrating data generetion model, thereby enhancing prediction accuracy. Furthermore, a wavelet packet augmentation method is proposed. Initially, the original signal is decomposed to obtain high and low frequency information. Subsequently, the high and low frequency information within the batch are linearly interpolated, respectively. Consequently, the interpolated high and low frequency information is then reconstructed to yield enhanced samples. The experimental results on four datasets show that the proposed framework can effectively improve the robustness of the generalization ability of fault diagnosis under unknown operating environments.

Resource allocation is the foundation of Internet of Vehicles in the edge cloud system. Based on that, a joint optimization problem is considered in a multi-layer vehicular architecture. To model the interaction between the vehicles and the edge servers, a framework of the Stackelberg game is introduced. The vehicles, which are viewed as distributed intelligent bodies, act as the followers and the edge server acts as the leader. However, due to the unlimited authorities, followers ignore the existence of the system, leading the excessive game. Therefore, to strengthen the authorities of the leader, a new offloading strategy matrix is proposed to replace the original offloading vector. Then, with the cooperation of the Chaos game, an improved Stackelberg game-based distributed optimization algorithm (ISGDOA) is proposed. Simulation verifies the efficient performances of ISGDOA and shows that besides the prevention of the excessive game, it still achieves an effective solution regardless of the performances of other sub-problems.

The recent development of advanced trackers, which use nighttime image enhancement technology, has led to marked advances in the performance of visual tracking at night. However, the images recovered by currently available enhancement methods still have some weaknesses, such as blurred target details and obvious image noise. To this end, we propose a novel method for learning multidimensional spatial attention for robust nighttime visual tracking, which is developed over a spatial channel transformer based low light enhancer (SCT), named MSA-SCT. First, a novel multidimensional spatial attention (MSA) is designed. Additional reliable feature responses are generated by aggregating channel and multi-scale spatial information, thus making the model more adaptable to illumination conditions and noise levels in different regions of the image. Second, with optimized skip connections, the effects of redundant information and noise can be limited, which is more useful for the propagation of fine detail features in nighttime images from low to high level features and improves the enhancement effect. Finally, the tracker with enhancers was tested on multiple tracking benchmarks to fully demonstrate the effectiveness and superiority of MSA-SCT.

In vehicular ad hoc networks (VANETs), beacon broadcasting plays a critical role in improving road safety and avoiding hazardous situations. How to ensure reliability and scalability of beacon broadcasting is a difficult and open problem, due to high mobility, dynamic network topology, hidden terminal, and varying density in both the time and location domains. In this paper, wireless resources are divided into basic resource units in the time and frequency domains, and a distributed and adaptive reservation based MAC protocol (DARP) is proposed to solve the above problem. For decentralized control in VANETs, each vehicle's channel access is coordinated with its neighbors to solve the hidden terminal problem. To ensure the reliability of beacon broadcasting, different kinds of preambles are applied in DARP to support distributed reservation, detect beacon collisions, and resolve collisions. Once a vehicle reserves a resource unit successfully, it will not release it until collision occurs due to topology change. The protocol performance in terms of access collision probability and access delay are analyzed. Based on the analysis, protocol parameters, including transmission power and time slots duration, can be adjusted to reduce collision probability and enhance reliability and scalability. Using NS-3 with vehicle traces generated by simulation of urban mobility (SUMO), simulation results show that the proposed DARP protocol can achieve the design goals of reliability and scalability, and it substantially outperforms the existing standard solutions.

Reliable and scalable wireless transmissions for Internet of Vehicles (IoV) are technically challenging. Each vehicle, from driver-assisted to automated one, will generate a flood of information, up to thousands of times of that by a person. Vehicle density may change drastically over time and location. Emergency messages and real-time cooperative control messages have stringent delay constraints while infotainment applications may tolerate a certain degree of latency. On a congested road, thousands of vehicles need to exchange information badly, only to find that service is limited due to the scarcity of wireless spectrum. Considering the service requirements of heterogeneous IoV applications, service guarantee relies on an in-depth understanding of network performance and innovations in wireless resource management leveraging the mobility of vehicles, which are addressed in this article. For single-hop transmissions, we study and compare the performance of vehicle-to-vehicle (V2V) beacon broadcasting using random access-based (IEEE 802.11p) and resource allocation-based (cellular vehicle-to-everything) protocols, and the enhancement strategies using distributed congestion control. For messages propagated in IoV using multihop V2V relay transmissions, the fundamental network connectivity property of 1-D and 2-D roads is given. To have a message delivered farther away in a sparse, disconnected V2V network, vehicles can carry and forward the message, with the help of infrastructure if possible. The optimal locations to deploy different types of roadside infrastructures, including storage-only devices and roadside units with Internet connections, are analyzed.

Internet of Vehicles (IoV) is a promising Internet of Things application, where roadside unit (RSU) plays an important role for network service provisioning. How to select the number and locations of RSUs to deploy and allocate the traffic load to them is a critical and practical open problem. Most of the existing work focused on 1-D scenarios assuming unlimited RSU capacity, while a more practical 2-D case with limited RSU capacity has not been fully considered yet. In this paper, we investigate an RSU deployment problem for 2-D IoV networks considering the expected delivery delay requirements and task assignment. We formulate a novel utility-based maximization problem to solve the RSU deployment problem, where the utility function indicates the total benefit from the RSU deployment. We observe that each RSU has an irregular service area, which makes the problem much more difficult than the traditional facility location problem. Then, we design a utility-based RSU deployment algorithm (URDA), a linear programming-based clustering algorithm, to solve the problem. The gap between URDA and the optimal solution has been analyzed, which proved that the proposed URDA is near optimal if the deployment cost is low. Extensive simulations have been conducted to demonstrate the effectiveness and superiority of the proposed solution for IoV network service guarantee over other approaches.

For vehicular networks, dropboxes are very useful for assisting the data dissemination, as they can greatly increase the contact probabilities between vehicles and reduce the data delivery delay. However, due to the costly deployment of dropboxes, it is impractical to deploy dropboxes in a dense manner. In this paper, we investigate how to deploy the dropboxes optimally by considering the tradeoff between the delivery delay and the cost of dropbox deployment. This is a very challenging issue due to the difficulty of accurate delay estimation and the complexity of solving the optimization problem. To address this issue, we first provide a theoretical framework to estimate the delivery delay accurately. Then, based on the idea of dimension enlargement and dynamic programming, we design a novel optimal dropbox deployment algorithm (ODDA) to obtain the optimal deployment strategy. We prove that ODDA has a fast convergence speed, which is less than κ (κ <; n) iterations for convergence. We also prove that the computational complexity of ODDA is O(nkm logm), i.e., ODDA has a polynomial computational complexity for a given m, the number of dropboxes for deployment. Performance evaluation by simulation demonstrates the superior performance of the proposed strategies compared with the benchmark methods.

Data dissemination is a fundamental yet challenging issue in vehicular networks. Due to high mobility, the vehicular network topology is random and fast- changing in both the time and spatial domains. How to fully utilize limited wireless resources for supporting heterogeneous safety and multimedia services in vehicular networks is a pressing, open issue. In this article, we leverage the software- defined network architecture for hybrid vehicular networks, using both vehicle-to-vehicle (V2V) and vehicle-to-infrastructure (V2I) wireless communication technologies to ensure network performance and quality of services (QoS). The architecture of the software-defined vehicular network (SDVN) is introduced. A simulation study on how to take advantage of the SDVN framework for efficient and effective data dissemination has been given. Further research problems and opportunities are discussed.

Future hybrid vehicle networks can use both Vehicle-to- Infrastructure (V2I) and Vehicle-to-Vehicle (V2V) communications to provide reliable, timely, scalable, and media-rich services. In this paper, we investigate the problem that how to disseminate the data to the Road Side Unit (RSU) considering bidirectional transmissions, using vehicles to store-carry-and-forward the messages if possible, in hybrid V2I/V2V networks. We focus on the delay modeling and dissemination strategy design, aiming to minimize the delivery delay. Considering a one-dimensional vehicle network with multiple road segments, we model the process of uploading a message to an RSU either in front of or behind the source. Furthermore, based on the delay analysis, we obtain the desirable message dissemination direction, and further design the message uploading algorithm to minimize the expected deliver delay. Simulations have been conducted to verify the correctness of the analysis and illustrate the efficiency of the proposed algorithm. The analytical model can also provide important insights and guideline for the deployment of RSUs.