The decision behavior of the leading vehicle driver significantly impacts the safety of the connected mixed platoon, especially on the longitudinal decision during emergency braking events. However, driving abilities vary among leading vehicle drivers. Predictive-forward-collision-warning (PFCW) is an emerging technology that enhances driving safety by providing traffic information beyond the driver’s line of sight. But the influence of PFCW on their decision behavior remains unclear. Therefore, it is necessary to investigate the leading driving competence of heterogeneous driver groups under the influence of PFCW. This study established a test platform for the connected mixed platoon using driving simulation technology. Subsequently, it developed a connected human–machine interface incorporating PFCW functionality and recruited 36 participants to experiment. The experiment aimed to analyze decision behaviors during the emergency braking event involving preceding vehicles. The latent profile analysis model was employed to identify heterogeneous driver groups. Moreover, the cumulative prospect theory was used to characterize drivers’ decision behaviors. The results indicated that PFCW encouraged drivers to maintain a larger distance from the preceding vehicle and to exhibit smoother braking behavior. However, the group of older, skilled drivers who were subjectively concerned about the driving status of following vehicles exhibited higher driving risk as the leading vehicle driver when PFCW was absent. Overall, this study enhances the understanding of longitudinal decision behavioral performance among heterogeneous driver groups in the presence of PFCW. It offers insights for subsequent customization of the selection criteria for leading vehicle drivers, and the tailored design of PFCW based on the characteristics and behavioral preferences of these heterogeneous driver groups.

Serverless computing are invented to free developers of analytic services from the management of cloud resources. Developers only need to submit their code to a serverless edge cloud (SEC) and the cloud platform matches the submitted code to itsserverless functions, enabled by the paradigm of Function as a Service (FaaS). However, serverless functions usually are short-lived with limited resources. In this paper, we aim to address the challenge of how to fully utilize the short-lived serverless functions to enable continuous analysis of the most freshly-generated big data. We first formulate an optimization problem of age-aware big data query evaluation in an SEC network so that theage of datais minimized, where the age of data is the duration between the generation time of the data and the current time. We then propose approximation algorithms for the age-aware big data query evaluation problem of a single query, by proposing a parameterized virtualization technique that smartly handles the large resource demands of big data queries in short-lived and resource-constraint serverless functions. We further consider the scenario where big data queries arrive into the system one-by-one and their resource demands are uncertain. To this end, we devise an online learning algorithm with bounded regret by leveraging a memory repacking mechanism to improve resource utilization, for the problem of online age-aware big data query evaluation. We evaluate the performance of the proposed algorithms through extensive simulations to testify their performances in large scales. We also validate the effectiveness of the proposed mechanism in a real test-bed built on Kubernetes and OpenWhisk with TPC-DS benchmarks. Experimental results show that the proposed algorithms outperform the state-of-the-arts, by reducing the age of data by$8.82\%$on average.

Unsupervised domain adaptation (UDA) has been widely studied with the goal of transferring knowledge from a label-rich source domain to a related but unlabeled target domain. Most UDA techniques achieve this by reducing the feature discrepancies between the two domains to learn domain-invariant feature representations. While domain-invariant feature representations can reduce the differences between the source and target domains, excessively simplifying these differences may cause the model to overlook important domain-specific features, resulting in a decline in transfer learning effectiveness. To address this issue, this paper proposes a novel Gaussian Mixture Model for graph domain adaptation (GMM). This model effectively reduces the distributional bias between the source and target domains by modeling the distribution differences on a graph structure. GMM leverages the local structural information of the graph and the clustering capability of the Gaussian mixture model to automatically learn the latent mapping relationships between the source and target domains. To the best of our knowledge, this is the first work to introduce a Gaussian mixture model into UDA. Extensive experimental results on three standard benchmarks demonstrate that the proposed GMM algorithm outperforms state-of-the-art unsupervised domain adaptation methods in terms of performance.

Pretrained Foundation Models (PFMs) are regarded as a promising accelerator for the development of various Artificial Intelligence (AI) applications, and have recently been widely fine-tuned to satisfy users' personalized inference demands. As many users are attracted to PFM-based AI applications, remote data centers are increasingly unable to solely bear the enormous computational demands and meet the delay requirements of inference requests. Mobile edge computing (MEC) offers a viable solution for delivering low-latency inference services by pulling fine-tuned PFMs from the remote data center to cloudlets in the proximity of users. However, a fine-tuned PFM typically comprises billions of model parameters, which are highly resource-intensive, time-consuming, and cost-prohibitive to execute at the edge. To address this, we investigate a novel joint large model selection and pulling problem in MEC networks. The novelty of our study lies in exploring parameter sharing among fine-tuned PFMs based on their common knowledge. Specifically, we first formulate a Non-Linear Integer Programming (NLIP) for the problem to minimize the total delay of implementing all inference requests. We then transform the NLIP into an equivalent Integer Linear Program (ILP) that is much simpler to solve. We further propose a randomized algorithm with a provable approximation ratio for the problem. We also consider the online version of the problem with uncertain request demand, and develop an online learning algorithm with a bounded regret. The crux of the online algorithm is the adoption of the multi-armed bandit technique with restricted context for dynamic admissions of inference requests. We finally conduct extensive experiments based on real datasets. Experimental results demonstrate that our algorithms reduce at least 38% in total delays and average costs, while achieving a 5% improvement in average accuracies.

Serverless computing is emerging as an enabling technology for elastic and low-cost AI applications in the edge of core networks. It allows AI developers to decompose a complex training and time-sensitive inference task into multiple functions with dependency, and upload the task to a Multi-access Edge Computing platform (MEC) for execution. Serverless computing adopts a popular design principle: the disaggregation of storage and computation, making the functions ‘stateless’. However, most AI applications are ‘stateful’ and rely on an external storage service to manage their states (ephemeral data). This will incur a prohibitively long delay for delay-sensitive AI applications if external services storing the states are far from the serverless functions. Motivated by this critical issue, in this paper we investigate a fundamental problem in serverless computing – the stateful serverless application placement problem, for which, we first propose an efficient heuristic algorithm, and then devise an approximation algorithm with a provable approximation ratio for one of its special cases. We also consider the online version of the problem, and develop an online learning-driven algorithm with a bounded regret. The crux of the online algorithm is the adoption of the multi-armed bandits technique for dynamic admissions of inference requests, under the uncertainty of both data volumes of requests and network delays. We finally evaluate the performance of the proposed algorithms through experimental simulations. Simulation results show that the proposed algorithms outperform their counterparts, reducing at least 32% in the total cost and 27% of the average delay.

The age of data (AoD) is identified as one of the most novel and important metrics to measure the quality of big data analytics for Internet-of-Things (IoT) applications. Meanwhile, mobile edge computing (MEC) is envisioned as an enabling technology to minimize the AoD of IoT applications by processing the data in edge servers close to IoT devices. In this paper, we study the AoD minimization problem for IoT big data processing in MEC networks. We first propose an exact solution for the problem by formulating it as an Integer Linear Program (ILP). We then propose an efficient heuristic for the offline AoD minimization problem. We also devise an approximation algorithm with a provable approximation ratio for a special case of the problem, by leveraging the parametric rounding technique. We thirdly develop an online learning algorithm with a bounded regret for the online AoD minimization problem under dynamic arrivals of IoT requests and uncertain network delay assumptions, by adopting the Multi-Armed Bandit (MAB) technique. We finally evaluate the performance of the proposed algorithms by extensive simulations and implementations in a real test-bed. Results show that the proposed algorithms outperform existing approaches by reducing the AoD around 10%.

More and more artificial intelligence (AI) applications, such as virtual reality (VR) and video analytics, are rapidly progressing towards enterprise and end-users with the promise of bringing immersive experience. Driven by the desire to improve users’ experience and promote business scenarios, such AI applications have unprecedented requirements for ultra-low latency as well as abundant computing resource in networks. Data centers in the core network can meet these demands by deploying various AI services and providing abundant resources. However, data transmission delay from data centers to end-users is too time-consuming because of traffic congestion in the core network, which compromises the performance of the AI applications. 5G and edge computing are emerging technologies to guarantee the timeliness for the delay-sensitive applications. The delay experienced by AI users can be significantly reduced, by ‘caching’ various services that are initially deployed at data centers to cloudlets in edge networks. Although ubiquitous edge service caching is always preferable for improving user experiences, it is impractical to cache all services from data centers to edge cloudlets, due to often limited caching budget of service providers and resource capacity constraints of cloudlets. Therefore, a service provider has to cautiously decide how many instances of a service can be cached, and where to cache the service instances. In this article, we investigate a fundamental problem ofservice cachingfrom remote data centers to edge cloudlets in a multi-tiered edge cloud network. We first develop two approximation algorithms with approximation ratios to solve the problem for users demanding a single type of service. We then devise an efficient heuristic to solve the problem that users require different types of services. We finally conduct extensive experiments on a real test-bed to evaluate the performance of the proposed algorithms, and experimental results demonstrate that our algorithms can outperform some existing algorithms significantly.

Machine learning (ML) has been penetrating into our daily life by facilitating many daily applications, e.g., self-driving, cloud gaming, product fault detection and drones. Meanwhile, there is an emerging trend that adopts ML methods into network optimization problems, such as flow classification, traffic engineering, routing, and etc. Conventional ML methods need careful training for a specific application of a given network structure, and the trained model normally cannot be applied to other applications and network structures. In this paper, we aim to design adaptive ML methods for network optimization problems, with the trained models having the ability of being deployed to any similar problems. In particular, we consider the virtualized network function (VNF) provisioning problem as our target optimization problem. We first propose a deep Q-learning-based optimization framework for VNF provisioning in a mobile edge network with network capacity constraints, by devising an adaptive graph feature embedding method. We then propose a series of deep Q-learning based learning algorithms for the problems of service chaining and the throughput maximization, based on the proposed learning-based optimization framework. We also propose a novel design of master-slave dual neural network that enables the decisions on both cloudlet selections and routing path finding. To stabilize and accelerate the convergence of the proposed methods, we devise a novel environment generation and termination strategy and a new structure for the replay buffer. We also evaluate the performance of the proposed framework and algorithms by extensive simulations. Results show that the proposed algorithms outperform existing methods by around 12%, and the trained model in a network can be directly adapted to other network structures and settings.