Time and cost trade-off management for scheduling parallel applications on Utility Grids

  • Authors:

  • Saurabh Kumar Garg;Rajkumar Buyya;Howard Jay Siegel

  • Affiliations:

  • Grid Computing and Distributed Systems Laboratory, Department of Computer Science and Software Engineering, The University of Melbourne, Victoria 3010, Australia;Grid Computing and Distributed Systems Laboratory, Department of Computer Science and Software Engineering, The University of Melbourne, Victoria 3010, Australia;Electrical and Computer Engineering Department, Colorado State University, Fort Collins, CO, USA and Computer Science Department, Colorado State University, Fort Collins, CO, USA

  • Venue:
  • Future Generation Computer Systems
  • Year:
  • 2010

Quantified Score

Hi-index 0.00

Visualization

Abstract

With the growth of Utility Grids and various Grid market infrastructures, the need for efficient and cost effective scheduling algorithms is also increasing rapidly, particularly in the area of meta-scheduling. In these environments, users not only may have conflicting requirements with other users, but also they have to manage the trade-off between time and cost such that their applications can be executed most economically in the minimum time. Thus, selection of the best Grid resources becomes a challenge in such a competitive environment. This paper presents three novel heuristics for scheduling parallel applications on Utility Grids that manage and optimize the trade-off between time and cost constraints. The performance of the heuristics is evaluated through extensive simulations of a real-world environment with real parallel workload models to demonstrate the practicality of our algorithms. We compare our scheduling algorithms against existing common meta-schedulers experimentally. The results show that our algorithms outperform existing algorithms by minimizing the time and cost of application execution on Utility Grids.