Abstract: Heterogeneous computing (HC) is the coordinated use of different types of machines, networks, and interfaces to maximize the combined performance and/or cost effectiveness of the system. Heuristics for allocating resources in an HC system have different optimization criteria. In the environments considered in this thesis, the optimization criteria was based on robustness. For each different environment, a robustness metric was derived and resource allocation heuristics were designed to maximize the robustness. The environments studies are: a weather data-processing system, a massive multi-player online gaming system, and a distributed massive satellite image processing system. Also, the performance of a few greedy heuristics working iteratively on smaller subsets of the total machine/task data (at the end of each iteration the makespan machine and tasks assigned to it are removed) is studied.

Adviser: H. J. Siegel
Co-Adviser: Anthony Maciejewski
Non-ECE Member: Wim Bohm
Member 3: Computer Science
Addional Members: NA

Publications:

Program of Study: