Date of Award
Master of Science
Cloud computing enables the delivery of computing services, software, storage, and data access through web browsers as a metered service. In addition to commercial applications, large scale scientific workflows are being executed and supported by cloud environments. However, in order to meet the ever increasing and dynamic demands from scientific users, the cloud service provider needs to adopt efficient resource mapping and job scheduling algorithms to guarantee a certain quality of services as well as maximize the resource utilization rate of the cloud's physical resources. This bi-objective optimization problem has been proven to be NP-complete. We hereby proposed a two-step heuristic approach to minimize the cloud overhead within an execution time bound specified by the user namely minimized End-to-End delay workflow mapping and cost reduced remapping. The simulation results compared with other representative approaches illustrate that our approach consistently achieves lower cost within the user required execution time bound. On the other hand, our algorithm can significantly reduce the total execution time by strategically selecting the mapping nodes for prioritized modules using a dynamic programming technique.
This thesis is only available for download to the SIUC community. Others should
contact the interlibrary loan department of your local library.