The biggest overhead for the instantiation of a virtual machine in a cloud infrastructure is the time spent in transferring the image of the virtual machine into the physical node that executes it. This overhead becomes larger for requests composed of several virtual machines to be started concurrently, and the illusion of flexibility and elasticity usually associated with the cloud computing model may vanish. This poses a problem for both the resource providers and the software developers, since tackling those overheads is not a trivial issue.
In this work we implement and evaluate several improvements for virtual machine image distribution problem in a cloud infrastructure and propose a method based on BitTorrent and local caching of the virtual machine images that reduces the transfer time when large requests are made
In this article, the authors introduce the main ideas around the governance of cross-Cloud application deployment and their related concepts. It is argued that, due to the increasing complexity and nature of the Cloud market, an intermediary specialized in brokering the deployment of different components of a same application onto different Cloud products could both facilitate said deployment and in some cases improve its quality in terms of cost, security & reliability and QoS. In order to fulfill these objectives, the authors propose a high level architecture that relies on their previous wo…
The paper illustrates how we built a federated cloud computing platform dedicated to the Italian research community. Building a cloud platform is a daunting task, that requires coordinating the deployment of many services, interrelated and dependent on each other. Provisioning, servicing and maintaining the platform must be automated. For our deployment, we chose a declarative modeling tool, that allows describing the parts that compose the system and their relations of supplier/consumer of specific interfaces. The tool arranges the steps to bring the deployment to convergence by transforming …
Recently, cloud systems composed of heterogeneous hardware have been increased to utilize progressed hardware power. However, to program applications for heterogeneous hardware to achieve high performance needs much technical skill and is difficult for users. Therefore, to achieve high performance easily, this paper proposes a PaaS which analyzes application logics and offloads computations to GPU and FPGA automatically when users deploy applications to clouds.
In a virtualized environment, contextualization is the process of configuring a VM instance for the needs of various deployment use cases. Contextualization in CernVM can be done by passing a handwritten context to the user data field of cloud APIs, when running CernVM on the cloud, or by using CernVM web interface when running the VM locally. CernVM Online is a publicly accessible web interface that unifies these two procedures. A user is able to define, store and share CernVM contexts using CernVM Online and then apply them either in a cloud by using CernVM Cloud Gateway or on a local VM wit…
This is a survey paper that explores six Cloud-based deployment archetypes for Cloud applications and the tradeoffs between them to achieve high availability, low end-user latency, and acceptable costs. These are (1) Zonal, (2) Regional, (3) Multi-Regional, (4) Global, (5) Hybrid, and (6) Multi-Cloud deployment archetypes. The goal is to classify cloud applications into a set of deployment archetypes and deployment models that tradeoff their needs around availability, latency, and geographical constraints with a focus on serving applications. This enables application owners to better examine t…
Institute for Architecture of Application Systems（应用系统架构研究所）；University of Stuttgart（斯图加特大学）
Cloud providers are facing a complex problem in configuring software applications ready for deployment on their infrastructures. Hierarchical Task Network (HTN) planning can provide effective means to solve such deployment problems. We present an HTN planning domain that models deployment problems as found in realistic Cloud environments.
When orchestrating highly distributed and data-intensive Web service workflows the geographical placement of the orchestration engine can greatly affect the overall performance of a workflow. We present CloudForecast: a Web service framework and analysis tool which, given a workflow specification, computes the optimal Amazon EC2 Cloud region to automatically deploy the orchestration engine and execute the workflow. We use geographical distance of the workflow, network latency and HTTP round-trip time between Amazon Cloud regions and the workflow nodes to find a ranking of Cloud regions. This o…
The IP Multimedia Subsystem (IMS) defined by the 3GPP has been mainly developed and deployed by telephony vendors on vendor-specific hardware. Recent advances in Network Function Virtualisation (NFV) technology paved the way for virtualized hardware and telephony function elasticity. As such, Telecom vendors have started to embrace the cloud as a deployment platform, usually selecting a privileged virtualization platform. Operators would like to deploy telecom functionality on their already existing IT cloud platforms. Achieving such flexibility would require the telecom vendors to adopt a sof…
When orchestrating Web service workflows, the geographical placement of the orchestration engine(s) can greatly affect workflow performance. Data may have to be transferred across long geographical distances, which in turn increases execution time and degrades the overall performance of a workflow. In this paper, we present a framework that, given a DAG-based workflow specification, computes the op- timal Amazon EC2 cloud regions to deploy the orchestration engines and execute a workflow. The framework incorporates a constraint model that solves the workflow deployment problem, which is genera…
Various Cloud layers have to work in concert in order to manage and deploy complex multi-cloud applications, executing sophisticated workflows for Cloud resource deployment, activation, adjustment, interaction, and monitoring. While there are ample solutions for managing individual Cloud aspects (e.g. network controllers, deployment tools, and application security software), there are no well-integrated suites for managing an entire multi cloud environment with multiple providers and deployment models. This paper presents the CYCLONE architecture that integrates a number of existing solutions …
In Mobile Cloud Computing (MCC), Virtual Machine (VM) migration based process offloading is a dominant approach to enhance Smart Mobile Devices (SMDs). A challenging aspect of VM deployment is the additional computing resources usage in the deployment and management of VM which obliges computing resources for VM creation and configuration. The management of VM comprises computing resources exploitation in the monitoring of VM in entire lifecycle and physical resources management for VM on SMDs. Therefore, VM migration based application offloading requires additional computing resource. Consequ…
Workflow management systems (WMS) support the composition and deployment of workflow-oriented applications in distributed computing environments. They hide the complexity of managing large-scale applications, which includes the controlling data pipelining between tasks, ensuring the application's execution, and orchestrating the distributed computational resources to get a reasonable processing time. With the increasing trends of scientific workflow adoption, the demand to deploy them using a third-party service begins to increase. Workflow-as-a-service (WaaS) is a term representing the platfo…
The hybrid cloud idea is increasingly gaining momentum because it brings distinct advantages as a hosting platform for complex software systems. However, there are several challenges that need to be surmounted before hybrid hosting can become pervasive and penetrative. One main problem is to architecturally partition workloads across permutations of feasible cloud and non-cloud deployment choices to yield the best-fit hosting combination. Another is to predict the effort estimate to deliver such an advantageous hybrid deployment. In this paper, we describe a heuristic solution to address the s…
Virtual clusters are widely used computing platforms than can be deployed in multiple cloud platforms. The ability to dynamically grow and shrink the number of nodes has paved the way for customised elastic computing both for High Performance Computing and High Throughput Computing workloads. However, elasticity is typically restricted to a single cloud site, thus hindering the ability to provision computational resources from multiple geographically distributed cloud sites. To this aim, this paper introduces an architecture of open-source components that coherently deploy a virtual elastic cl…
Distributing agent-based simulators reveals many challenges while deploying them on a hybrid cloud infrastructure. In fact, a researcher's main motivations by running simulations on hybrid clouds, are reaching more scalable systems as well as reducing monetary costs. Indeed, hybrid cloud environment, despite providing scalability and effective control over proper data, requires an efficient deployment strategy combining both an efficient partitioning mechanism and cost savings. In this paper, we propose a cost deployment model dedicated to distributed agent-based simulation systems. This cost …
Due to the limited and varying availability of cheap infrastructure and resources, cloud network systems and applications are tested in simulation and emulation environments prior to physical deployments, at different stages of development. Configuration management tools manage deployments and migrations across different cloud platforms, mitigating tedious system administration efforts. However, currently a cloud networking simulation cannot be migrated as an emulation, or vice versa, without rewriting and manually re-deploying the simulated application. This paper presents SENDIM (Sendim is a…
The recent past has seen the adoption of multi-cloud deployments by enterprises due to availability, features, and regulatory requirements. A typical deployment involves parts of an application/workloads running inside a private cloud with the other parts spread across multiple on-prem/public clouds. Typical cluster-to-cluster networking in such deployments involve the establishment of site-to-site encrypted tunnels to connect the workloads. In this report, we benchmark the performance of various tunneling and encryption technologies to provide directions on their use in multi-cloud deployment…
This project aims to explore the process of deploying Machine learning models on Kubernetes using an open-source tool called Kubeflow [1] - an end-to-end ML Stack orchestration toolkit. We create end-to-end Machine Learning models on Kubeflow in the form of pipelines and analyze various points including the ease of setup, deployment models, performance, limitations and features of the tool. We hope that our project acts almost like a seminar/introductory report that can help vanilla cloud/Kubernetes users with zero knowledge on Kubeflow use Kubeflow to deploy ML models. From setup on different…
Whilst computational resources at the cloud edge can be leveraged to improve latency and reduce the costs of cloud services for a wide variety mobile, web, and IoT applications; such resources are naturally constrained. For distributed stream processing applications, there are clear advantages to offloading some processing work to the cloud edge. Many state of the art stream processing applications such as Flink and Spark Streaming, being designed to run exclusively in the cloud, are a poor fit for such hybrid edge/cloud deployment settings, not least because their schedulers take limited cons…
Compute infrastructure hosted by a cloud provider allows an application to scale without limit. The application developer no longer needs to worry about the up-front investment in a server farm provisioned for a worst-case load scenario. However, managing cloud deployments requires a sophisticated framework that can autoscale the infrastructure and guarantee the up-time of running container images. This paper surveys existing research addressing the management and orchestration of cloud deployments as well as the modelling framework to abstract away the low-level details of the host infrastruc…
OpenStack is an open-source private cloud used to run VMs and its related cloud services. OpenStack deployment, management, and upgradation require lots of efforts and manual troubleshooting. Also, workloads and services offered by OpenStack cannot self-heal itself on failures. We present KupenStack, a Cloud-Native OpenStack as Code model built on top of Kubernetes stack as Custom Resources. KupenStack is a controller that interacts between Kubernetes and OpenStack and automates complex operations like scaling, LCM, zero-downtime, self-healing, version upgrades, configuration management, and o…
Orchestrating service-oriented workflows is typically based on a design model that routes both data and control through a single point - the centralised workflow engine. This causes scalability problems that include the unnecessary consumption of the network bandwidth, high latency in transmitting data between the services, and performance bottlenecks. These problems are highly prominent when orchestrating workflows that are composed from services dispersed across distant geographical locations. This paper presents a novel workflow partitioning approach, which attempts to improve the scalabili…
CPU is undoubtedly the most important resource of the computer system. Recent advances in software and system architecture have increased processing complexity, as computing is now distributed and parallel. CloudSim represents the complexity of an application in terms of its computational requirements. CloudSim [9] is a complete solution for simulating Cloud Computing environments and building test beds for provisioning algorithms. This paper analyzes and evaluates the performance of cloud environment modeling using CloudSim. We describe the CloudSim architecture and then investigate the new m…
Deep Learning Model Deployment in Multiple Cloud Providers: an Exploratory Study Using Low Computing Power Environments
Cloud Plarform Engineering, Wildlife Studios（云平台工程，野生动物工作室）；Technology, State University of Feira de Santana（技术，费亚尔德萨桑塔纳州立大学）；Computer Engineering, Federal University of Vale do São Francisco（计算机工程，巴伊亚州联邦大学）
Recent advancements in the cloud computing domain have resulted in huge strides toward simplifying the procurement of hardware and software for diverse needs. By moving enterprise workloads to managed cloud offerings (private, public, hybrid), customers are delegating mundane tasks and labor-intensive maintenance activities related to network connectivity, procurement of cloud resource, application deployment, software patches, and upgrades, etc., This often translates to benefits such as high availability and reduced cost. The popularity of container and micro-services-based deployment has ma…
In the cloud computing environment, cloud virtual machine (VM) will be more and more the number of virtual machine security and management faced giant Challenge. In order to address security issues cloud computing virtualization environment, this paper presents a virtual machine based on efficient and dynamic deployment VM security management model state migration and scheduling, study of which virtual machine security architecture, based on AHP (Analytic Hierarchy Process) virtual machine deployment and scheduling method, based on CUSUM (Cumulative Sum) DDoS attack detection algorithm, and th…
Cloud computing datacenters provide millions of virtual machines in actual cloud markets. In this context, Virtual Machine Placement (VMP) is one of the most challenging problems in cloud infrastructure management, considering the large number of possible optimization criteria and different formulations that could be studied. Considering the on-demand model of cloud computing, the VMP problem should be optimized dynamically to efficiently attend typical workload of modern applications. This work proposes several dynamic environments for solving the VMP from the providers' perspective based on …
Cloud Computing is a new trend emerging in IT environment with huge requirements of infrastructure and resources. Load Balancing is an important aspect of cloud computing environment. Efficient load balancing scheme ensures efficient resource utilization by provisioning of resources to cloud users on demand basis in pay as you say manner. Load Balancing may even support prioritizing users by applying appropriate scheduling criteria. This paper presents various load balancing schemes in different cloud environment based on requirements specified in Service Level Agreement (SLA).
Cloud environment is very different from traditional computing environment and therefore tracking the performance of cloud leverages additional requirements. The movement of data in cloud is very fast. Hence, it requires that resources and infrastructure available at disposal must be equally competent. Infrastructure level performance in cloud involves the performance of servers, network and storage which act as the heart and soul for driving the entire cloud business. Thus a constant improvement and enhancement of infrastructure level performance is an important task that needs to be taken in…
Currently, due to the advantages of light weight, simple deployment, multi-environment support, short startup time, scalability, and easy migration, container technology has been widely used in both cloud and edge/fog computing, and addresses the problem of device heterogeneity in different computing environments. On this basis, as one of the most popular container orchestration and management systems, Kubernetes almost dominates the cloud environment. However, since it is primarily designed for centralized resource management scenarios where computing resources are sufficient, the system is u…
Transilvania University of Brasov（布拉索夫特兰西瓦尼亚大学）；Elektrobit Automotive（易特驰汽车）；University of Southampton（南安普顿大学）
Self-driving cars and autonomous vehicles are revolutionizing the automotive sector, shaping the future of mobility altogether. Although the integration of novel technologies such as Artificial Intelligence (AI) and Cloud/Edge computing provides golden opportunities to improve autonomous driving applications, there is the need to modernize accordingly the whole prototyping and deployment cycle of AI components. This paper proposes a novel framework for developing so-called AI Inference Engines for autonomous driving applications based on deep learning modules, where training tasks are deployed…
The increasing availability of cloud computing services for science has changed the way scientific code can be developed, deployed, and run. Many modern scientific workflows are capable of running on cloud computing resources. Consequently, there is an increasing interest in the scientific computing community in methods, tools, and implementations that enable moving an application to the cloud and simplifying the process, and decreasing the time to meaningful scientific results. In this paper, we have applied the concepts of containerization for portability and multi-cloud automated deployment…
Cloud Computing is emerging as a new computational paradigm shift. Hadoop-MapReduce has become a powerful Computation Model for processing large data on distributed commodity hardware clusters such as Clouds. In all Hadoop implementations, the default FIFO scheduler is available where jobs are scheduled in FIFO order with support for other priority based schedulers also. In this paper we study various scheduler improvements possible with Hadoop and also provided some guidelines on how to improve the scheduling in Hadoop in Cloud Environments.
Heterogeneous systems consisting of general-purpose processors and different types of hardware accelerators are becoming more and more common in HPC systems. Especially FPGAs provide a promising opportunity to improve both performance and energy efficiency of such systems. Adding FPGAs to clouds or data centers allows easy access to such reconfigurable resources. In this paper we present our cloud service models and cloud hypervisor called RC3E, which integrates virtualized FPGA-based hardware accelerators into a cloud environment. With our hardware and software framework, multiple (virtual) u…
Algorithms, policies, and methodologies are necessary to achieve high user satisfaction and practical utilization in cloud computing by ensuring the efficient and fair allocation of every computing resource. Whenever a new job arrives in cloud environments, the service broker is responsible for selecting the data center that will execute that job. Selecting data centers serves an important function in enhancing the performance of a cloud environment. This study proposes a new service broker policy for large-scale cloud applications based on the round-robin algorithm. The proposed policy is imp…
Catalyzed by the popularity of blockchain technology, there has recently been a renewed interest in the design, implementation and evaluation of decentralized systems. Most of these systems are intended to be deployed at scale and in heterogeneous environments with real users and unpredictable workloads. Nevertheless, most research in this field evaluates such systems in controlled environments that poorly reflect the complex conditions of real-world environments. In this work, we argue that deployment is crucial to understanding decentralized mechanisms in a real-world environment and an enab…
With recent developments in cloud computing, a paradigm shift from rather static deployment of resources to more dynamic, on-demand practices means more flexibility and better utilization of resources. This demands new ways to efficiently configure networks. In this paper, we will characterize a class of competitive cloud services that telecom operators could provide based on the characteristics of telecom infrastructure through an applicable streaming service architecture. Then, we will model this architecture as a cost-based mathematic model. This model provides a tool to evaluate and compar…
Internet-enabled things and devices operating in the physical world are increasingly integrated in modern distributed systems, supporting functionalities that require assurances that certain critical requirements are satisfied by the overall system. We focus here on spatially-distributed Internet-of-Things systems such as smart environments, where the dynamics of spatial distribution of entities in the system is crucial to requirements satisfaction. Analysis techniques need to be in place while systems operate to ensure that requirements are fulfilled. This may be achieved by keeping a model o…
RoboECC: Multi-Factor-Aware Edge-Cloud Collaborative Deployment for VLA Models
School of Computer Science, Peking University, Beijing, China（北京大学计算机科学学院）；School of Computer Science, South China University of Technology, Guangzhou, China（华南理工大学计算机科学学院）；School of Artificial Intelligence, Beijing Normal University, Beijing, China（北京师范大学人工智能学院）；School of EECS, Peking University, Beijing, China（北京大学电子工程与科学学院）
Cloud computing offers a variable-cost payment scheme that allows cloud customers to specify the price they are willing to pay for renting spot instances to run their applications at much lower costs than fixed payment schemes, and depending on the varying demand from cloud customers, cloud platforms could revoke spot instances at any time. To alleviate the effect of spot instance revocations, applications often employ different fault-tolerance mechanisms to minimize or even eliminate the lost work for each spot instance revocation. However, these fault-tolerance mechanisms incur additional ov…
