We consider the problem of task offloading and resource allocation in mobile edge computing (MEC). To maintain satisfactory quality of experience (QoE) of end-users, mobile devices (MDs) may offload their tasks to edge servers based on the allocated computation (e.g., CPU/GPU cycles and storage) and wireless resources (e.g., bandwidth). However, these resources could not be effectively utilized unless an encouraging resource allocation scheme can be proposed. What’s worse, task offloading incurs additional MEC energy consumption, which inevitably violate the long-term MEC energy budget. Considering these two challenges, we propose an online joint offloading and resource allocation (JORA) framework under the long-term MEC energy constraint, aiming at guaranteeing the end-users’ QoE. To achieve this, we leverage Lyapunov optimization to exploit the optimality of the long-term QoE maximization problem. By constructing an energy deficit queue to guide energy consumption, the problem can be solved in a real-time manner. On this basis, we propose online JORA methods in both centralized and distributed manners. Furthermore, we prove that our proposed methods enable the achievement of the close-to-optimal performance while satisfying the long-term MEC energy constraint. In addition, we conduct extensive simulations and the results show superiority in performance over other methods.

In connected autonomous vehicles (CAVs), the driving safety can be greatly deteriorated, in the presence of occlusions which are adverse to CAVs’ perception of region-of-interest (RoI). Collaborative perception on the basis the information sharing of occlusions among CAVs, in a real-time and accurate manner, provides a means of the occlusion-free RoI perception for safe driving. In this paper, we propose a novel framework of C ollaborative O cclusion- f ree P erception ( COFP ) in CAVs, to regain the real-time and accurate occlusion awareness. The innovative COFP targets two goals: well-balanced computation resource allocation, as well as fast and high-quality RoI information fusion. Specifically, the resource allocation problem, with the objective of minimizing CAVs’ completion delay, is formulated as a multi-player continuous potential game and solved by a better response dynamics (BRD) algorithm. The RoI information fusion, with the objective of maximizing the overall object depiction quality, is formulated as a combinatorial optimization problem, and solved by a modified discrete salp swarm (MDSSA) algorithm. Experimental results show that the proposed COFP with 5 GHz computing power can achieve full occlusion awareness for CAVs with 69.61% completion time reduction and 19.03% fusion quality improvement, compared to the existing methods.

For years, vehicle trajectory data have increasingly been important for a wide range of applications, from driver behavior investigation/classification, travel time/distance estimation, routing in vehicular networks, to vehicle energy/emission evaluation. This paper presents TrajData, the first systematic solution to reliable vehicle trajectory data collection, with only reliance on Commercial-Off-The-Shelf (COTS) On-Board Unit (OBU) devices which utilize lightweight GPS modules and low-cost On-Board Diagnostics (OBD) readers. In the practical use of trajectory collection, GPS outages inevitably occur in urban environments thereby leading to large trajectory errors as well as missing vehicle location data. To resolve this, we propose a novel data-fusion enabled deep learning approach with the purpose on achieving reliable vehicle trajectory collection in various urban road conditions. Specifically, we leverage motion information retrieved from OBD readers in TrajData to help reconstruct the trajectory data during GPS outages. By investigating the changes of direction angle from the OBD readings, we can identify different types of road sections. Furthermore, we integrate the Neural Arithmetic Logic Units (NALU) into our trajectory reconstruction model to tame the challenges when GPS outages take place in various road sections. Experimental results from realistic data have demonstrated the effectiveness and reliability of the proposed method. In the road test, TrajData achieves an average position error below 15 meters around a 60-second GPS outage, even in complex road sections, i.e., continuous turns and driving with accelerations/decelerations resulting in frequent changes of direction and speed.

Currently, an increasing number of private cars drive on roads and produce a massive volume of trajectory data. These data provide a new opportunity for understanding people's travel behavior. In this paper, we conduct an in-depth empirical study of people's travel behavior using private car trajectory data. First, we conduct the study in terms of four metrics, namely, number of trips, average velocity, trip distance, and entropy, and compare the data with those from taxi and ridesharing. Through experiments, we find that the number of trips, average velocity, and trip distance of private cars are more in line with people's travel habits, and the entropy values of private cars are lower. Therefore, we consider private car trajectory data capable of well characterizing people's travel behavior, even better than that from floating cars (such as taxis and buses) or ridesharing services. Moreover, we reveal that a unique metric (so-called dwell time) from the private car trajectory data helps to further understand people's travel behavior. Finally, we propose a fine-grained destination prediction algorithm as a case study, enhancing the state-of-the-art SubSyn algorithm, and show a good understanding of people's travel behavior facilitate a more personalized prediction of final destinations for private cars.

Service composition has emerged as a fundamental technique for developing Web applications. Multiple services, often from different organizations or trust domains, may be dynamically composed to satisfy a user's request. Access control in the presence of service compositions is a challenging security problem. In this paper, we present an access control model and techniques for specifying and enforcing access control rules on Web service compositions. A key advantage of our approach is that past histories of service invocations can be used to make access control decisions. Our approach allows role hierarchies and separation of duty constraints. Access controls rules may be parameterized by one or more arguments. We have implemented our access control model via a declarative policy specification language which uses pure-past linear temporal logic (PPLTL). We describe an implementation of our approach using a supply chain management (SCM) application. Our experiments show that our approach can enforce expressive and flexible access control policies while incurring reasonable performance overhead on the application.