Applying deep neural networks to HEP job classification

21st International Conference on Computing in High Energy and Nuclear Physics

物理学;计算机科学

Wang, L.^1 ; Shi, J.^1 ; Yan, X.^1

IHEP Computing Center, 19B Yuquan Road, Beijing

100049, China^1

关键词: Classification tasks;    Computing center;    Computing system;    Cross validation;    Job classification;    Linear modeling;    Pattern collections;    Training data sets;   

Others  :  https://iopscience.iop.org/article/10.1088/1742-6596/664/5/052042/pdf
DOI  :  10.1088/1742-6596/664/5/052042

学科分类：计算机科学（综合）

来源: IOP

【 摘 要 】

The cluster of IHEP computing center is a middle-sized computing system which provides 10 thousands CPU cores, 5 PB disk storage, and 40 GB/s IO throughput. Its 1000+ users come from a variety of HEP experiments. In such a system, job classification is an indispensable task. Although experienced administrator can classify a HEP job by its IO pattern, it is unpractical to classify millions of jobs manually. We present how to solve this problem with deep neural networks in a supervised learning way. Firstly, we built a training data set of 320K samples by an IO pattern collection agent and a semi-automatic process of sample labelling. Then we implemented and trained DNNs models with Torch. During the process of model training, several meta-parameters was tuned with cross-validations. Test results show that a 5- hidden-layer DNNs model achieves 96% precision on the classification task. By comparison, it outperforms a linear model by 8% precision.