深度学习驱动下IaaS云运维异常检测算法的研究进展  

Research Progress of Anomaly Detection in IaaS Cloud Operation Driven by Deep Learning

作　　者：司佳 梁建峰[1] 谢硕 邓英俊 SI Jia;LIANG Jianfeng;XIE Shuo;DENG Yingjun(National Marine Data and Information Service,Tianjin 300171,China;Center for Applied Mathematics,Tianjin University,Tianjin 300072,China)

机构地区：[1]国家海洋信息中心,天津300171 [2]天津大学应用数学中心,天津300072

出　　处：《计算机科学》2024年第S01期718-725,共8页Computer Science

基　　金：国家海洋信息中心青年基金项目(202102006);南海海洋资源利用国家重点实验室开放基金(MRUKF2021035)。

摘　　要：异常检测是IaaS云系统运维中的一个关键任务,通过早期预警和提前干预,可有效避免系统崩溃等严重事故的发生。但相较于传统数据中心,IaaS云系统具有较大规模的计算节点,节点拓扑复杂、监测数据量大、缺少标注信息等特点,为IaaS云运维异常检测带来新的挑战。从深度学习的技术框架出发,分析了异常检测问题面临的难点,调研总结了IaaS云系统下常见异常检测算法和相关技术。面向节点异常和系统异常两类典型问题,对深度学习驱动的解决方法进行调研:面向节点级别异常,重点调研了时间依赖的运维数据下由时序数据驱动的检测算法;面向系统级别异常,重点调研了网络拓扑建模下由图数据驱动的检测算法。最后,提出了数据驱动下IaaS云运维数据异常检测中的新问题与新挑战。Anomaly detection is an important task in the operation and maintenance of IaaS cloud systems.Through early warning and intervention,serious accidents such as system crashes can be effectively avoided.However,compared to traditional data centers,IaaS cloud systemshave the characteristics of large-scale computing nodes,complex node topology,large monitoring data vo-lume,and lack of data labels,which bring new challenges for IaaS cloud anomaly detection.Starting from the technical framework of deep learning,this paper analyzes the difficulties faced by anomaly detection problems,and summarizes common anomaly detection algorithms and related technologies in IaaS cloud systems.This paper investigates deep learning driven solutions for two typical problems:node anomalies and system anomalies.For node anomalies,detection algorithms driven by temporal data are studied for time-dependent data.For system anomalies,detection algorithms driven by graph data in network topology modeling are investigated.Finally,new issues and challenges in data-driven anomaly detection in IaaS cloud systems are proposed.

关 键 词：异常检测 IaaS云平台 时序数据 图数据 深度学习 机器学习 

分 类 号：TP311.1[自动化与计算机技术—计算机软件与理论]