this paper presents Roboconf, an open-source distributed application orchestration framework for multi-cloud platforms, designed to solve challenges of current Autonomic computing Systems in the era of Cloud computing...
详细信息
this paper presents Roboconf, an open-source distributed application orchestration framework for multi-cloud platforms, designed to solve challenges of current Autonomic computing Systems in the era of Cloud computing. It provides a Domain Specific Language (DSL) which allows to describe applications and their execution environments (cloud platforms) in a hierarchical way in order to provide a fine-grained management. Roboconf implements an asynchronous and parallel deployment protocol which accelerates and makes resilient the deployment process. Intensive experiments with different type of applications over different cloud models (e.g. Private, hybrid, and multi-cloud) validate the genericity of Roboconf. these experiments also demonstrate its efficiency comparing to existing frameworks such as Right Scale, Scalr, and Cloudify.
Software-Defined networking (SDN) has emerged as a novel network architectural model that facilitates management of large-scale networks, enables efficient network virtualization and scalable network multi-tenancy. Ce...
详细信息
ISBN:
(纸本)9780769556970
Software-Defined networking (SDN) has emerged as a novel network architectural model that facilitates management of large-scale networks, enables efficient network virtualization and scalable network multi-tenancy. Centralized network controllers, an important component in the SDN paradigm, deploy on the data plane devices network policies from several independent sources, defined based on a global network view. While this approach allows to efficiently manage network connectivity and reduce the time and cost of deploying new configurations, it also increases the risk for errors -- either introduced by accident, through a combination with previous policies, or by a motivated adversary. In this position paper we review the state of the art for network policy verification for SDN deployments, identify existing challenges and outline a secure framework for network policy management in SDN deployments. Combined with existing work on cloud platform and storage security, this will contribute towards creating secure and trusted cloud deployments.
FELIX federates existing Future Internet (FI) experimental facilities across continents to build a test environment for large-scale SDN experiments. the management framework developed by FELIX allows the execution of ...
详细信息
ISBN:
(纸本)9780769556970
FELIX federates existing Future Internet (FI) experimental facilities across continents to build a test environment for large-scale SDN experiments. the management framework developed by FELIX allows the execution of experimental network services in a distributed environment comprised of heterogeneous resources. the demonstration described in this paper showcases the implementation of the FELIX architecture over the federated experimental facilities across Japan and Europe leveraging on boththe infrastructure resources and the FELIX management stack. the presented use-case also provides an important experimental scenario for data center operators who are developing Business Continuity Planning for IT services.
To solve the problem of data consistency in distributed database system based on Peer-to-Peer model, this paper designed a middleware-based database synchronization system. the system uses middleware to realize databa...
详细信息
ISBN:
(纸本)9781467376457
To solve the problem of data consistency in distributed database system based on Peer-to-Peer model, this paper designed a middleware-based database synchronization system. the system uses middleware to realize database synchronization, through the transaction management module, collision detection module, communication module, transaction execution module to complete the transaction capture, analysis, as well as matters of conflict detection and treatment. Experiment results show that the conflict be detected and treated at local, compared withthe two-phase locking (2PL), middleware-based database synchronization system reduces the response time of the transaction, reducing unnecessary traffic, improve the performance of the system.
Android app repackaging has become a serious problem currently. To protect apps from tampering, code obfuscation, watermarking and other techniques have been designed. However, most of these approaches could only prov...
详细信息
ISBN:
(纸本)9781467376457
Android app repackaging has become a serious problem currently. To protect apps from tampering, code obfuscation, watermarking and other techniques have been designed. However, most of these approaches could only provide inadequate protection. Meanwhile, it is possible to achieve remote tamper-resistance in recent, especially for networking apps, withthe development of cloud computing technology and the spread of networks. In this paper, we propose a novel remote protection mechanism for mobile apps in cloud computing environments. In the proposed mechanism, the app should download and execute some code from the cloud when some important function is called. Tamper proofing code which could check the app is tampered or not is embedded in the downloaded code. Furthermore, the code can only run correctly one time and is continuous changing, which makes it difficult for an adversary to analyze and modify.
Modern research and education networks need to solve two major tasks: (1) providing seamless access to their users, and (2) support new scientific and collaborative applications that are becoming increasingly complex ...
详细信息
ISBN:
(纸本)9780769556970
Modern research and education networks need to solve two major tasks: (1) providing seamless access to their users, and (2) support new scientific and collaborative applications that are becoming increasingly complex and dynamic in their scale, use of distributed resources, and required advanced networking services. Rapid deployment and automation of new network services provisioning is becoming difficult in large networks that incorporate different technologies and solutions. the task of providing seamless user experience in typically mobile and dynamically changing collaborative groups generates additional burdens for the configuration phases included in network provisioning. By introducing automation and enabling multipoint auto configuration of network devices, the Zero Touch Provisioning (ZTP) concept emerges as a possible alleviation of the complex network provisioning and infrastructure services deployment process. this paper investigates the characteristics of the ZTP model and discovers how ZTP can be used in order to enhance the services provided by the GEANT network and its associated National Research and Education Networks (NRENs) to the European research and education community. the future solution can be achieved by combining and enriching the existing provisioning models, solutions and practices available from different domains such as wireless networks, (complex) network management and operations services, and cloud based infrastructure services provisioning.
We present Mycocloud, a fully self-organized approach to service placement. Mycocloud supports service elasticity within a network of hosts with heterogeneous computational capacity. Mycocloud proposes a completely de...
详细信息
We present Mycocloud, a fully self-organized approach to service placement. Mycocloud supports service elasticity within a network of hosts with heterogeneous computational capacity. Mycocloud proposes a completely decentralized algorithm that continuously calculates the dynamic placement of different services on the host nodes, in response to the varying demand for each service, the churn and dynamism of the node set contributing resources to the system, and the changes in the overlay topology. Our simulation results show how Mycocloud provides good performance in terms of convergence rate, response time, system load and network traffic overhead.
Heterogeneous computing system is one of the focuses researched in the field of distributedcomputing nowadays. It is composed of various heterogeneous processors interconnected with high-speed networks. And it can ac...
详细信息
Heterogeneous computing system is one of the focuses researched in the field of distributedcomputing nowadays. It is composed of various heterogeneous processors interconnected with high-speed networks. And it can acquire rapid processing of computationally intensive applications to meet diverse computing needs. In heterogeneous computing system, it is a key issue for high performance computing to schedule tasks and allocate nodes properly. In this paper, first I introduce the problem of task scheduling and describe four kinds of task scheduling methods. Next I analyze the basic ideas of some representative task scheduling algorithms in heterogeneous computing system and describe their performance. then I compare these four methods and analyse their advantages and disadvantages. Finally I give a conclusion and the future work on heterogeneous computing system.
the emergence of blogs, and especially microblogs, has granted users the possibility of publishing and sharing ideas, news, opinions and any other kind of content withtheir audience. But this has also brought them th...
详细信息
DaaS (Data-as-a-Service) is an important model of the cloud. As DaaS provides clients withthe ability to view and download data from cloud providers, the service must ensure speed, reliability, and cost effectiveness...
详细信息
DaaS (Data-as-a-Service) is an important model of the cloud. As DaaS provides clients withthe ability to view and download data from cloud providers, the service must ensure speed, reliability, and cost effectiveness. An important research question pertaining to providing DaaS is how to improve the download time by using parallelism and efficient load balancing techniques. Other research focus on optimizing the storage consumed by the DaaS cloud providers. In this paper, we provide a solution to both issues by increasing the effectiveness of the dual direction load balancing technique using higher replication and optimizing the storage consumed by a smart self-controlled technique (ssCloud) for removing the redundant data from each cloud server. We elaborate on the design of this technique and how it can be applied on the cloud.
暂无评论