FP-STE: A Novel Node Failure Prediction Method Based on Spatio-Temporal Feature Extraction in Data Centers

作     者：Yang Yang Jing Dong Chao Fang Ping Xie Na An 

作者机构：State Key Laboratory of Networking and Switching TechnologyBeijing University of Posts and TelecommunicationsBeijingChina Beijing Smartchip Microelectronics Technology Company LimitedBeijingChina The 54th Research Institute of CETCShijiazhuangChina 

出 版 物：《Computer Modeling in Engineering & Sciences》 (工程与科学中的计算机建模（英文）)

年 卷 期：2020年第123卷第6期

页      面：1015-1031页

核心收录：

学科分类：08[工学] 0812[工学-计算机科学与技术（可授工学、理学学位）] 

基　　金：supported in part by National Key Research and Development Program of China(2019YFB2103200) NSFC(61672108),Open Subject Funds of Science and Technology on Information Transmission and Dissemination in Communication Networks Laboratory(SKX182010049) the Fundamental Research Funds for the Central Universities(5004193192019PTB-019) the Industrial Internet Innovation and Development Project 2018 of China 

主　　题：Failure prediction data center features extraction XGBoost service availability 

摘      要：The development of cloud computing and virtualization technology has brought great challenges to the reliability of data center *** centers typically contain a large number of compute and storage nodes which may fail and affect the quality of *** prediction is an important means of ensuring service *** node failure in cloud-based data centers is challenging because the failure symptoms reflected have complex characteristics,and the distribution imbalance between the failure sample and the normal sample is widespread,resulting in inaccurate failure *** these challenges,this paper proposes a novel failure prediction method FP-STE(Failure Prediction based on Spatio-temporal Feature Extraction).Firstly,an improved recurrent neural network HW-GRU(Improved GRU based on HighWay network)and a convolutional neural network CNN are used to extract the temporal features and spatial features of multivariate data respectively to increase the discrimination of different types of failure symptoms which improves the accuracy of *** the intermediate results of the two models are added as features into SCSXGBoost to predict the possibility and the precise type of node failure in the ***-XGBoost is an ensemble learning model that is improved by the integrated strategy of oversampling and cost-sensitive *** results based on real data sets confirm the effectiveness and superiority of FP-STE.