Resource requirement prediction techniques for near miss clone jobs
P. Datta, M. Sarkar, Sarbani Roy, Nandini Mukherjee · 2013
Resource requirement prediction of jobs prior to their submission in the dynamic and heterogeneous natured modern distributed systems is a difficult task. A feedback-based job modelling scheme based on clone detection technique was proposed in [1, 2] and an extended taxonomy of clones to facilitate prediction was proposed in [3]. In this paper, we propose the resource requirement prediction scheme for different Near Miss clones. The Near Miss clone jobs differ only in some aspects like data type of input data, input data size and operations performed in job. So, resource requirement prediction of a new job from traits of its Near Miss clones previously executed in the system can provide a good estimate. This paper focuses on the issue of resource requirement prediction of different types of Near Miss clone jobs.