Advances in Cloud computing attracted scientists to deploy their HPC applications to the cloud to benefit from the flexibility of the platform such as scalability and on-demand services. Nevertheless, HPC programs can...
详细信息
ISBN:
(纸本)9781467372879
Advances in Cloud computing attracted scientists to deploy their HPC applications to the cloud to benefit from the flexibility of the platform such as scalability and on-demand services. Nevertheless, HPC programs can face serious challenges in the cloud that could undermine the gained benefits. this paper first compares the performance of several HPC benchmarks on a commodity cluster and Amazon public cloud to illustrate the confronted challenges. To mitigate the problem, we have introduced a novel approach called ASETS, "A SDN Empowered Task Scheduling System", to schedule data-intensive High Performance computing (HPC) tasks in a Cloud environment. In this paper, we focus on the implementation and performance analysis of ASETS and its first algorithm called SETSA, (SDN Empowered Task Scheduling Algorithm). ASETS uses the "bandwidth awareness" capability of SDN to better utilize the bandwidths when assigning tasks to virtual machines. this approach aims to improve the performance of HPC programs and provides an efficient HPC-as-a-Service (HPCaaS) platform. the paper briefly describes the architecture and the algorithm, and then focuses on the details of the implementation and performance analysis of ASETS and SETSA. Preliminary results indicate that ASETS delivers substantial performance improvement for HPCaaS as the degree of multi-tenancy increases. this result is significant since it indicates boththe users and the cloud service providers can benefit from ASETS.
In this paper, authors present a framework on developing a comprehensive system to analyze border crossing transportation using an open-source meta-data acquisition and aggregation tool. It is a platform integration a...
详细信息
Open Cloud computing Interface (OCCI) proposes one of the first widely accepted, community-based, open standards for managing any kinds of cloud resources. But as it is specified in natural language, OCCI is imprecise...
详细信息
ISBN:
(纸本)9781467372879
Open Cloud computing Interface (OCCI) proposes one of the first widely accepted, community-based, open standards for managing any kinds of cloud resources. But as it is specified in natural language, OCCI is imprecise, ambiguous, incomplete, and needs a precise definition of its core concepts. Indeed, the OCCI Core Model has conceptual drawbacks: an imprecise semantics of its type classification system, a nonextensible data type system for OCCI attributes, a vague and limited extension concept and the absence of a configuration concept. To tackle these issues, this paper proposes a precise metamodel for OCCI. this metamodel defines rigourously the static semantics of the OCCI core concepts, of a precise type classification system, of an extensible data type system, and of both extension and configuration concepts. this metamodel is based on the Eclipse Modeling Framework (EMF), its structure is encoded with Ecore and its static semantics is rigourously defined with Object Constraint Language (OCL). As a consequence, this metamodel provides a concrete language to precisely define and exchange OCCI models. the validation of our metamodel is done on the first world-wide dataset of OCCI extensions already published in the literature, and addressing inter-cloud networking, infrastructure, platform, application, service management, cloud monitoring, and autonomic computing domains, respectively. this validation highlights simplicity, consistency, correctness, completeness, and usefulness of the proposed metamodel.
An open source private cloud architecture environment is described that supports tablet-class computer devices as clients. the cloud architecture employs a Metadata server, Data servers, and Compute servers. the priva...
详细信息
ISBN:
(纸本)9781467383615
An open source private cloud architecture environment is described that supports tablet-class computer devices as clients. the cloud architecture employs a Metadata server, Data servers, and Compute servers. the private cloud clients are treated as a limited resource device: limited in memory, view space and computing power. the client tablet makes requests to the Metadata server that maintains a dictionary of category specific information and services that reside on registered Data and Computeservers. the software architecture is a Java based Web server. In addition, support for interactive user apps are introduced by deploying a paired producer/consumer used to coordinating the data transfer between the client and server machines. the software architecture has been tested and the source is available for public access.
Nowadays, withthe rapid development of distributedcomputing, message distribution has been more and more important to distributed systems. Kafka was developed to collect and distribute massive messages for distribut...
详细信息
ISBN:
(纸本)9781467382212
Nowadays, withthe rapid development of distributedcomputing, message distribution has been more and more important to distributed systems. Kafka was developed to collect and distribute massive messages for distributed systems. It is a high-throughput distributed messaging system. Kafka can always keep stable performance even if it processes millions of messages per second. Messages are persistent in Kafka, and Kafka is able to scale out easily. Besides, it is suitable for both online and offline processing simultaneously. Existing messaging systems all have some disadvantages. In comparison withthese messaging systems, Kafka has superior performance. therefore, Kafka has already been successfully used in production by some companies for a certain time. though Kafka is still able to be improved in some aspects, it's expected to have broad development prospects.
Two of the prominent dimensions behind the development of cross-platform UIs are the UI distribution and UI migration. In UI distribution, since UI elements of a given application has to be distributed across more tha...
详细信息
In-memory computing aims to bring forward application data from the storage to the server's main memory. By locating the working set closer to its application, in memory, great performance gains can be achieved. M...
详细信息
the proceedings contain 327 papers. the topics discussed include: diabetes mellitus detection based on facial block texture features using the Gabor filter;classification of electrocardiogram signals with deep belief ...
ISBN:
(纸本)9781479979813
the proceedings contain 327 papers. the topics discussed include: diabetes mellitus detection based on facial block texture features using the Gabor filter;classification of electrocardiogram signals with deep belief networks;combining N-gram and dependency word pair for multi-document summarization;on utilizing stochastic non-linear fractional bin packing to resolve distributed web crawling;adaptive neural network position/force hybrid control for constrained reconfigurable manipulators;vehicle state estimation using cubature kalman filter;design and development of sypinge-type magnetorheological damper;an algorithm for fractional order system identification;semi-active spiral flow channel magnetorheological damper;attitude tracking control based on adaptive sliding mode technique with double closed loop for spacecraft near small body;and theory and substantiation of z0g1 controller conquering singularity problem of output tracking for a class of nonlinear system.
Withthe continuing growth of cloud computing services, power consumption has become one of the most challenging issues in data center environments. Withthe support of today's virtualization technology, the effic...
详细信息
ISBN:
(纸本)9781467372879
Withthe continuing growth of cloud computing services, power consumption has become one of the most challenging issues in data center environments. Withthe support of today's virtualization technology, the efficiency and flexibility of data center management can be greatly enhanced, creating great energy saving opportunities. However, effective energy aware design is a non-trivial task, considering the size of the data center, the dynamic fluctuation of workloads and the variation of computing resource requests. In this paper, we propose CoolCloud: a practical solution for managing the mappings of VMs to physical servers. this framework solves the problem of finding the most energy efficient way (least resource wastage and least power consumption) of placing the VMs considering their resource requirements. Experiment result demonstrates our design can effectively improve data center energy efficiency and scales well to large size data centers. Comparing with industry leading product VMware's distributed Resource Scheduler (DRS), our design offers better performance in both load balancing and power consumption.
E-mental health applications have gained popularity recently as a result of applying developing technologies to leverage advantages over traditional care. First, e-mental health applications are inherently scalable, w...
详细信息
ISBN:
(纸本)9781467394697
E-mental health applications have gained popularity recently as a result of applying developing technologies to leverage advantages over traditional care. First, e-mental health applications are inherently scalable, whereas traditional care involves one-to-one relations between patient and clinician. Second, electronic data formats can facilitate interoperability in a way that medical data on paper cannot. third, the flexibility of a web application warrants that improvements in the care program exposed through the application will immediately benefit all applicable users. For the specific domain of e-mental health, the primary source of medical data are online questionnaires, and most applications in this domain focus on viewing, filling out, and managing these questionnaires. Many distinct such applications have been developed in recent years, most of them starting from scratch and running in isolation. In this paper, we design and propose a generic architecture for e-mental health applications from two case studies. these case studies are two e-mental health applications called HowNutsAretheDutch and Leefplezier, and are used on a large scale with over 13,000 active users combined. By abstracting functionalities into reusable Service-Oriented Architecture interfaces, we can maximize data interoperability while minimizing application-specific code to facilitate rapid development of e-mental health applications.
暂无评论