Influence of Grid Economic Factors on Scheduling and Migration

• Published in: High Performance Computing for Computational Science - VECPAR 2004 pp. 274 - 287
• Main Authors: Moreno-Vozmediano, Rafael, Alonso-Conde, Ana B.
• Format: Book Chapter Conference Proceeding
• Language: English
• Published: Berlin, Heidelberg Springer Berlin Heidelberg 2005; Springer
• Series: Lecture Notes in Computer Science
• Subjects: Applied sciences; Computer science; control theory; systems; Computer systems and distributed systems. User interface; Exact sciences and technology; Grid Environment; Migration Policy; Monte Carlo; Optimization Criterion; Rank Function; Software; Availability; Economics; High performance; Monte Carlo method; Finance; Deadline; Grid; Task scheduling; Scheduling; Distributed system; Distributed computing; Modeling; Adaptive method; Optimization; Economy; User requirement; Budget; Economic information; Portfolio management; User need
• ISBN: 9783540254249; 3540254242
• ISSN: 0302-9743; 1611-3349
• DOI: 10.1007/11403937_22

Grid resource brokers need to provide adaptive scheduling and migration mechanisms to handle different user requirements and changing grid conditions, in terms of resource availability, performance degradation, and resource cost. However, most of the resource brokers dealing with job migration do not allow for economic information about the cost of the grid resources. In this work, we have adapted the scheduling and migration policies of our resource broker to deal with different user optimization criteria (time or cost), and different user constraints (deadline and budget). The application benchmark used in this work has been taken from the finance field, in particular a Monte Carlo simulation for computing the value-at-risk of a financial portfolio.