Reputation-Aware Scheduling for Storage Systems in Data Grids

Data grids provide such data-intensive applications with a large virtual storage framework with unlimited power. However, conventional scheduling algorithms for data grids are unable to meet the reputation service requirements of data-intensive applications. In this paper we address the problem of scheduling data-intensive jobs on data grids subject to reputation service constraints. Using the reputation-aware technique, the dynamic scheduling strategy is proposed to improve the capability of predicting the reliability and credibility for data-intensive applications. To incorporate reputation service into job scheduling, we introduce a new performance metric, degree of reputation sufficiency, to quantitatively measure quality of reputation service provided by data grids. Experimental results based on a simulated grid show that the proposed scheduling strategy significantly is capable of significantly satisfying the reputation service requirements and guaranteeing the desired response times .