In this paper, we investigate the diffusion containment problem through a novel hyperparametric influence minimization model. This model integrates a hyperparametric diffusion framework into the classical influence minimization paradigm, enabling practical, flexible, and fine-grained control over diffusion dynamics via feature interventions on nodes. The objective is to minimize the diffusion from initial seeds, by optimizing the interventions on node feature values. We analyze the challenges and intrinsic properties of hyperparametric influence minimization and derive an upper-bound on the spread, which quantifies the total uncertainty of nodes remaining inactive during the diffusion process. We prove that it exhibits supermodularity in the context of the node selection problem. Based on that, we further design greedy-based algorithms to solve the problem, which outperform the state-of-the-art methods.

In this paper, we study cascading failures in power grids through the lens of information diffusion models. Similar to the spread of rumors or influence in an online social network, it has been observed that failures (outages) in a power grid can spread contagiously, driven by viral spread mechanisms. We employ a stochastic diffusion model that is Markovian (memoryless) and local (the activation of one node, i.e., transmission line, can only be caused by its neighbors). Our model integrates viral diffusion principles with physics-based concepts, by correlating the diffusion weights (contagion probabilities between transmission lines) with the hyperparametric Information Cascades (IC) model. We show that this diffusion model can be learned from traces of cascading failures, enabling accurate modeling and prediction of failure propagation. This approach facilitates actionable information through well-understood and efficient graph analysis methods and graph diffusion simulations. Furthermore, by leveraging the hyperparametric model, we can predict diffusion and mitigate the risks of cascading failures even in unseen grid configurations, whereas existing methods falter due to a lack of training data. Extensive experiments based on a benchmark power grid and simulations therein show that our approach effectively captures the failure diffusion phenomena and guides decisions to strengthen the grid, reducing the risk of large-scale cascading failures. Additionally, we characterize our model's sample complexity, improving upon the existing bound.

One of the main DevOps practices is the automation of resource provisioning and deployment of complex software. This automation is enabled by the explicit definition of Infrastructure-as-Code (IaC), i.e., a set of scripts, often written in different modeling languages, which defines the infrastructure to be provisioned and applications to be deployed. We introduce the DevOps Modeling Language (DOML), a new Cloud modeling language for infrastructure deployments. DOML is a modeling approach that can be mapped into multiple IaC languages, addressing infrastructure provisioning, application deployment and configuration. The idea behind DOML is to use a single modeling paradigm which can help to reduce the need of deep technical expertise in using different specialized IaC languages. We present the DOML’s principles and discuss the related work on IaC languages. Furthermore, the advantages of the DOML for the end-user are demonstrated in comparison with some state-of-the-art IaC languages such as Ansible, Terraform, and Cloudify, and an evaluation of its effectiveness through several examples and a case study is provided.

Abstract One of the main DevOps practices is the automation of resource provisioning and deployment of complex software. This automation is enabled by the explicit definition of Infrastructure-as-Code (IaC), i.e., a set of scripts, often written in different modelling languages, which defines the infrastructure and applications to be deployed. We introduce the DevOps Modelling Language (DOML), a new Cloud modelling language for infrastructure deployments. DOML is a modelling approach that can be mapped into multiple IaC languages, addressing infrastructure provisioning, application deployment and configuration at once. The idea behind DOML is to use a single modelling paradigm which can help to reduce the need of deep technical expertise in using different specialised IaC languages. We present the DOML’s principles and discuss the related work on IaC languages. We demonstrate the DOML advantages for the end-user in comparison with state-of-the-art IaC languages such as Ansible, Terraform, and Cloudify, and show its effectiveness through an example.

Technological advances have now made it possible to simultaneously profile the changes of epigenomic, transcriptomic and proteomic at the single cell level, allowing a more unified view of cellular phenotypes and heterogeneities. However, current computational tools for single-cell multi-omics data integration are mainly tailored for bi-modality data, so new tools are urgently needed to integrate tri-modality data with complex associations. To this end, we develop scMHNN to integrate single-cell multi-omics data based on hypergraph neural network. After modeling the complex data associations among various modalities, scMHNN performs message passing process on the multi-omics hypergraph, which can capture the high-order data relationships and integrate the multiple heterogeneous features. Followingly, scMHNN learns discriminative cell representation via a dual-contrastive loss in self-supervised manner. Based on the pretrained hypergraph encoder, we further introduce the pre-training and fine-tuning paradigm, which allows more accurate cell-type annotation with only a small number of labeled cells as reference. Benchmarking results on real and simulated single-cell tri-modality datasets indicate that scMHNN outperforms other competing methods on both cell clustering and cell-type annotation tasks. In addition, we also demonstrate scMHNN facilitates various downstream tasks, such as cell marker detection and enrichment analysis.

Multi-access Edge Computing (MEC) facilitates the deployment of critical applications with stringent QoS requirements, latency in particular. This article considers the problem of jointly planning the availability of computational resources at the edge, the slicing of mobile network and edge computation resources, and the routing of heterogeneous traffic types to the various slices. These aspects are intertwined and must be addressed together to provide the desired QoS to all mobile users and traffic types still keeping costs under control. We formulate our problem as a mixed-integer nonlinear program (MINLP) and we define a heuristic, named Neighbor Exploration and Sequential Fixing (NESF), to facilitate the solution of the problem. The approach allows network operators to fine tune the network operation cost and the total latency experienced by users. We evaluate the performance of the proposed model and heuristic against two natural greedy approaches. We show the impact of the variation of all the considered parameters (viz., different types of traffic, tolerable latency, network topology and bandwidth, computation and link capacity) on the defined model. Numerical results demonstrate that NESF is very effective, achieving near-optimal planning and resource allocation solutions in a very short computing time even for large-scale network scenarios.

Comparison Lift is an experimentation-as-a-service (EaaS) application for testing online advertising audiences and creatives at JD.com. Unlike many other EaaS tools that focus primarily on fixed sample A/B testing, Comparison Lift deploys a custom bandit-based experimentation algorithm. The advantages of the bandit-based approach are two-fold. First, it aligns the randomization induced in the test with the advertiser’s goals from testing. Second, by adapting experimental design to information acquired during the test, it reduces substantially the cost of experimentation to the advertiser. Since launch in May 2019, Comparison Lift has been utilized in over 1,500 experiments. We estimate that utilization of the product has helped increase click-through rates of participating advertising campaigns by 46% on average. We estimate that the adaptive design in the product has generated 27% more clicks on average during testing compared to a fixed sample A/B design. Both suggest significant value generation and cost savings to advertisers from the product.

Mobile Edge Computing (MEC) is a key technology for the deployment of next generation (5G and beyond) mobile networks, specifically for reducing the latency experienced by mobile users which require ultra-low latency, high bandwidth, as well as real-time access to the radio network. In this paper, we propose an optimization framework that considers several key aspects of the resource allocation problem for MEC, by carefully modeling and optimizing the allocation of network resources including computation and storage capacity available on network nodes as well as link capacity. Specifically, both an exact optimization model and an effective heuristic are provided, jointly optimizing (1) the connections admission decision (2) their scheduling, also called calendaring (3) and routing as well as (4) the decision of which nodes will serve such connections and (5) the amount of processing and storage capacity reserved on the chosen nodes. Numerical experiments are conducted in several real-size network scenarios, which demonstrate that the heuristic performs close to the optimum in all the considered network scenarios, while exhibiting a low computing time.

The omnidirectional application is immersive and highly interactive. In industrial scenarios, it can be used to improve the efficiency of remote collaborative work between workers. The transmission of omnidirectional video (OV) is a key step. Compared with ordinary video transmission, OV transmission requires more bandwidth, which is still a huge burden even in 5G networks. The tile-based scheme can reduce bandwidth consumption, but it cannot accurately obtain the user's field of view (FOV) area. In this paper, we propose an edge-assisted viewport adaptive scheme (EVAS-OV) to reduce bandwidth consumption. First, EVAS-OV uses a Gated Recurrent Unit (GRU) model to predict the user's viewport. Then, the users are divided into multicast clusters according to their viewports. EVAS-OV reprojects the OV frame to accurately obtain the user's FOV area from the pixel level. At the same time, a redundancy strategy is adopted to reduce the influence of viewport prediction errors and improve the robustness of the system. All computing tasks are transferred to the edge server to reduce transmission delay and improve bandwidth utilization. Experimental results show that compared to the viewport adaptive two-layer scheme, EVAS-OV can save 30% of bandwidth.

With the merit of containing full panoramic content in one camera, Virtual Reality (VR) and 360° videos have arisen in the field of industrial cloud manufacturing and training. Industrial Internet of Things (IoT), where many VR terminals needed to be online at the same time, can hardly guarantee VR's bandwidth requirement. However, by making use of users' quality of experience (QoE) awareness factors, including the relative moving speed and depth difference between the viewpoint and other content, bandwidth consumption can be reduced. In this paper, we propose Optical Flow Based VR(OFB-VR), an interactive method of VR streaming that can make use of VR users' QoE awareness to ease the bandwidth pressure. The Just-Noticeable Difference through Optical Flow Estimation (JND-OFE) is explored to quantify users' awareness of quality distortion in 360° videos. Accordingly, a novel 360° videos QoE metric based on Peak Signal-to-Noise Ratio and JND-OFE (PSNR-OF) is proposed. With the help of PSNR-OF, OFB-VR proposes a versatile-size tiling scheme to lessen the tiling overhead. A Reinforcement Learning (RL) method is implemented to make use of historical data to perform Adaptive BitRate (ABR). For evaluation, we take two prior VR streaming schemes, Pano and Plato, as baselines. Vast evaluations show that our system can increase the mean PSNR-OF score by 9.5-15.8% while maintaining the same rebuffer ratio compared with Pano and Plato in a fluctuate LTE bandwidth dataset. Evaluation results show that OFB-VR is a promising prototype for actual interactive industrial VR. A prototype of OFB-VR can be found in https://github.com/buptexplorers/OFB-VR.

Mobile traffic generated by a variety of services is rapidly increasing in volume. Both network and computation resources in a single edge network are therefore often too limited to provide the desired Quality of Service (QoS) to mobile users. In this paper, we propose a mathematical model, called JSNC, to perform an efficient joint slicing of mobile network and edge computation resources. JSNC aims at minimizing the total latency of transmitting, outsourcing and processing user traffic, under the constraint of user tolerable latency for multiple classes of traffic. The constraints of network, link and server capacities are considered as well. The optimization model results in a mixed-integer nonlinear programming (MINLP) problem. To tackle it efficiently, we perform an equivalent reformulation, and based on that, we further propose two effective heuristics: Sequential Fixing (SF), which can achieve near-optimal solutions, and a greedy approach which obtains suboptimal results with respect to SF. Both of them can solve the optimization problem in a very short computing time. We evaluate the performance of the proposed model and heuristics, showing the impact of all the considered parameters (viz. different types of traffic, tolerable latency, network topology and bandwidth, computation and link capacity) on the optimal and approximate solutions. Numerical results demonstrate that JSNC and the heuristics can provide efficient resource allocation solutions.