Dynamic Resource Management Heuristics for Minimizing Makespan while Maintaining an Acceptable Level of Robustness in an Uncertain Environment

Heterogeneous parallel and distributed computing sys-tems may operate in an environment where certain system performance features degrade due to unpredictable circum-stances. Robustness can be defined as the degree to which a system can function correctly in the presence of parameter values different from those assumed. This paper presents a mathematical model for quantifying robustness in a dy-namic environment where task execution times estimates are known to contain errors. This research proposes, evaluates, and compares ten different dynamic heuristics for their abil-ity to maintain or maximize the proposed dynamic robust-ness metric in an uncertain environment. In addition, the makespan results of the proposed heuristics are compared to a lower bound. 1