Abstract
The service-oriented distributed systems such as Gr ids and Clouds are unified computing platform that connect and share heterogeneous resources including computation resource, storage resource, informatio n resource and knowledge resource. While these systems provide a vast amount of computing power their reliability are often hard to be guaranteed. It is due to the increased complexity of processing (e.g. , overhead, latency) that can indirectly affect the s ystem performance. In this study, we addressed the problem of dynamic control for resource management in distributed computing environment. Our dynamic resource control mechanism is designed based on rep utation-based scheduling that aims for sustainable resource sharing. Particularly, each computational resource in the environment has its own reputation value that calculated online by considering the computing capacity and availability. The degree of resource reputation significantly helps in scheduling decisi ons in terms of successful execution while adaptive ly monitoring resource availability. Results demonstra te that our resource control mechanism significantl y increases successful execution, while leading to ro bust resource management.
Highlights
The service-oriented distributed systems such as Grids and Clouds are unified computing platform that connect and share heterogeneous resources including computation resource, storage resource, information resource and knowledge resource
Their mapping decisions are according to fitness value that calculated as the product of reputation value rrepj and deadline factor dfJC
We address the dynamic resource control in the context of resource sharing
Summary
Xingshe, 2011; Zunjare and Sahoo, 2012) made the evaluation of the resource behaviour varies. Each administrative domain in the distributed systems has its own resource usage pattern (Hussin et al, 2011; Ping issue is because their behaviors change more rapidly than a controller can adapt that made the resource information for the controller (scheduler) delayed and potentially inaccurate. Such unpredictable and imprecise resource behaviour inherently results in unreliable task execution. With the reputation value of scheduler it helps to dynamically monitor a trust interaction between service providers and users that improves task successful execution This is realized based on three aspects.
Sign-in/Register to view highlights & summary Sign-in/Register to access full text options 
Free) 
Talk to us
Join us for a 30 min session where you can share your feedback and ask us any queries you have
Schedule a call
