Resource management is one of the basic and key aspects in grid computing, especially in resource allocation and scheduling, which need to be adaptive to handle dynamic changes in availability of resources and user requirements. At the same time, they need to provide scalable, controllable, measurable, and easily enforceable policies for management of resources. In the different types of requirements that users are concerned about, cost and time become two primary factors. So the cost-time tradeoff problem for allocating resources and scheduling tasks becomes challenging with the goal of cost-time optimization. To address these requirements in this paper, we take both the grid userspsila QoS requirements of deadline and budget into consideration and propose an universal flexible utility function based on the principle of universal logics, which contains all function forms by using an adaptive family of parameterized operators and realizes the flexibilities of integrations of time and cost. And then, detailed analysis on the properties and operation models of the proposed utility function is described. This will make a steady foundation for future use in grid economy.
[1]
Ian Foster,et al.
The Grid 2 - Blueprint for a New Computing Infrastructure, Second Edition
,
1998,
The Grid 2, 2nd Edition.
[2]
David Abramson,et al.
A case for economy grid architecture for service oriented grid computing
,
2001,
Proceedings 15th International Parallel and Distributed Processing Symposium. IPDPS 2001.
[3]
Ami Marowka,et al.
The GRID: Blueprint for a New Computing Infrastructure
,
2000,
Parallel Distributed Comput. Pract..
[4]
Ramin Yahyapour,et al.
Economic Scheduling in Grid Computing
,
2002,
JSSPP.
[5]
Daniel P. Siewiorek,et al.
A scalable solution to the multi-resource QoS problem
,
1999,
Proceedings 20th IEEE Real-Time Systems Symposium (Cat. No.99CB37054).
[6]
David Abramson,et al.
Economic models for resource management and scheduling in Grid computing
,
2002,
Concurr. Comput. Pract. Exp..