Modeling Disk Arrays Using Genetic Programming

Kirshenbaum, Evan

HP Development Company

关键词: genetic programming;    machine learning;    storage systems;   

RP-ID  :  HPL-2002-20

学科分类：计算机科学（综合）

美国|英语

来源: HP Labs

【 摘 要 】

This paper describes the results of using genetic programming to evolve models that predict the throughput in disk arrays. The results are compared to previous hand-crafted analytical and automatically- generated interpolation-based device models. An analysis is performed to investigate the optimality of the run parameters chosen as well as to discover whether the approach has the tendency to overfit its training data. The process is shown to find models that outperform both recently published and currently used models and to be sensitive to population size but not run length. 8 Pages