TS-Decompression-based data center high-frequency fault time domain early warning method and system

TS-Decompression-based data center high-frequency fault time domain early warning method and system

The invention discloses a TS-Decompression-based data center high-frequency fault time domain early warning method and system, and the method comprises the steps of obtaining the time sequence monitoring data in a data center scene, carrying out data cleaning, and obtaining a monitoring value of the...

Ausführliche Beschreibung

Gespeichert in:
Bibliographische Detailangaben
Hauptverfasser: ZHANG JIANBO, WU ZIHANG, YAO MENGLONG, WANG HONGPING, DONG JUNDUO, TIAN HAO, WANG TONG
Format: Patent
Sprache:chi ; eng
Schlagworte:
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
Online-Zugang:Volltext bestellen
Tags: Tag hinzufügen
Keine Tags, Fügen Sie den ersten Tag hinzu!
Beschreibung
Zusammenfassung:The invention discloses a TS-Decompression-based data center high-frequency fault time domain early warning method and system, and the method comprises the steps of obtaining the time sequence monitoring data in a data center scene, carrying out data cleaning, and obtaining a monitoring value of the historical time sequence data; analyzing the numerical influence factors of the time series data, performing time series decomposition on the time series data based on a TS-Decomposition algorithm, and performing numerical influence factor calculation according to the monitoring value of historical time series data; establishing a time sequence prediction model according to a numerical influence factor calculation result, and performing time sequence data trend prediction to obtain a predicted value of the future time sequence data; performing hybrid calculation according to the monitoring value of the historical time series data and the predicted value of the future time series data, and judging the fault time do