Server operation and maintenance fault identification method and positioning method based on fingerprints

• Main Authors: JI XUECHUN, KONG YANRU, PENG CHENG, ZHANG KEHENG, ZHAI MINGYU, HUANG XINJIAN, XU LIYAN, CHEN ZIYUN, LI HAO, GAO SHANG
• Format: Patent
• Language: Chinese; English
• Published: 23.06.2023
• Subjects: CALCULATING; COMPUTER SYSTEMS BASED ON SPECIFIC COMPUTATIONAL MODELS; COMPUTING; COUNTING; DATA PROCESSING SYSTEMS OR METHODS, SPECIALLY ADAPTED FORADMINISTRATIVE, COMMERCIAL, FINANCIAL, MANAGERIAL, SUPERVISORYOR FORECASTING PURPOSES; ELECTRIC DIGITAL DATA PROCESSING; PHYSICS; SYSTEMS OR METHODS SPECIALLY ADAPTED FOR ADMINISTRATIVE,COMMERCIAL, FINANCIAL, MANAGERIAL, SUPERVISORY OR FORECASTINGPURPOSES, NOT OTHERWISE PROVIDED FOR

The invention discloses a fingerprint-based server operation and maintenance fault identification method and positioning method, and the method comprises the steps: carrying out the collection, screening, processing and conversion of operation and maintenance indexes, forming a fingerprint which can reflect the performance state of a server, and learning a fault fingerprint rule through employing a convolutional neural network, therefore, abnormality of the power grid dispatching control system server can be found in real time, fault nodes can be quickly positioned, fault types can be intelligently identified, operation and maintenance personnel can be assisted to isolate the fault nodes, and safe and stable operation of the power grid dispatching control system is guaranteed. 本发明公开了一种基于指纹的服务器运维故障识别方法、定位方法，通过对运维指标的采集、筛选、加工和转化，形成能反映服务器性能状态的"指纹"，并利用卷积神经网络学习故障指纹规律，从而实现实时发现电网调度控制系统服务器异常、快速定位故障节点、智能识别故障类型，辅助运维人员隔离故障节点，保障电网调度控制系统安全稳定运行。