Efficient scheduling is a key concern for the effectual execution of performance driven Grid applications, such as workflows. Many list heuristics have been developed for scheduling workflows in centralized Grid envir...
详细信息
In this paper, a reputation-based Grid workflow scheduling algorithm is proposed to counter the effect of inherent unreliability and temporal characteristics of computing resources in large scale, decentralized Grid o...
详细信息
Efficient scheduling is a key concern for the effectual execution of performance driven Grid applications, such as workflows. Many list heuristics have been developed for scheduling workflows in centralized Grid envir...
详细信息
Efficient scheduling is a key concern for the effectual execution of performance driven Grid applications, such as workflows. Many list heuristics have been developed for scheduling workflows in centralized Grid environment. However, in this paper, we present a distributed list heuristic for decentralized scheduling of workflow applications in global Grids. The simulation results show that the proposed scheduling approach is scalable with respect to increased workload on the system.
In this paper, a reputation-based Grid workflow scheduling algorithm is proposed to counter the effect of inherent unreliability and temporal characteristics of computing resources in large scale, decentralized Grid o...
详细信息
In this paper, a reputation-based Grid workflow scheduling algorithm is proposed to counter the effect of inherent unreliability and temporal characteristics of computing resources in large scale, decentralized Grid overlays. The proposed approach builds upon structured peer-to-peer indexing and overlay networking techniques to create a scalable wide-area networking of Grid sites for supporting dependable scheduling of applications. The scheduling algorithm considers reliability of a Grid resource as a statistical property, which is globally computed in the decentralized Grid overlay based on dynamic feedbacks or reputation scores assigned by individual service consumers (Grid Resource Brokers). The proposed algorithm can dynamically adapt to changing resource conditions and offer significant performance gains as compared to traditional approaches in the event of unsuccessful job execution or resource failure. We evaluate and demonstrate the feasibility of our approach through an extensive trace driven simulation. The results show that our scheduling technique can reduce the makespan up to 50% and successfully isolate the failure-prone resources from the system.
Our approach to the model-driven collaborative design of workflows for bioinformatic applications uses the jABC for model driven mediation and choreography to complement a Web service-based elementary service provisio...
详细信息
Our approach to the model-driven collaborative design of workflows for bioinformatic applications uses the jABC for model driven mediation and choreography to complement a Web service-based elementary service provision. jABC is a framework for service development based on lightweight process coordination. Users (product developers and system/software designers) develop services and applications by composing reusable building-blocks into (flow-)graph structures that can be animated, analyzed, simulated, verified, executed, and compiled. This way of handling the collaborative design of complex processes has proven to be effective and adequate for the cooperation of non-programmers (in this case biologists) and technical people, and it is now being rolled out in the operative practice
In this paper we present dETI, the next generation of the Electronic Tool Integration (ETI) platform, an open platform for the interactive experimentation with and coordination of heterogeneous software tools via the ...
详细信息
We propose an aggressive version of model-driven development (AMDD) 1, which moves most of the recurring problems of compatibility and consistency of software (mass-) construction and customization from the coding and...
详细信息
We propose an aggressive version of model-driven development (AMDD) 1, which moves most of the recurring problems of compatibility and consistency of software (mass-) construction and customization from the coding and integration level to the modelling level. AMDD requires a complex preparation of adequate settings, supporting the required automation. However, the effort to create these settings can be easily paid off by immense cost reductions in software mass-construction and maintenance. In fact, besides reducing the costs, AMDD will also lead towards a kind of normed software development, making software engineering a true engineering activity.
With MaTRICS, we describe an architecture for pervasive management of distributedsystems. It allows remotely connected users (e.g., system administrators) to modify the configuration of any service provided by a spec...
详细信息
With MaTRICS, we describe an architecture for pervasive management of distributedsystems. It allows remotely connected users (e.g., system administrators) to modify the configuration of any service provided by a specific (application) server, like email-, news- or Web-servers. Novel to our approach is that the system can manage configuration processes on heterogeneous software- and hardware- platforms, which are performed from a variety of peripherals unmatched in today's practice. In this sense, we realize a sort of pervasive system management, where devices like mobile phones, faxes, PDAs are enabled to be used by system managers as remote system configuration and management tools.
暂无评论