Data center load prediction method based on ensemble learning

• Main Authors: ZHANG LIXIA, WANG JIE, SUN JUNLIAN, LONG HUI, CHEN YUNFANG, HAN ZIBO, LI NA, HAO JIAFEI
• Format: Patent
• Language: Chinese; English
• Published: 22.12.2023
• Subjects: CALCULATING; CIRCUIT ARRANGEMENTS OR SYSTEMS FOR SUPPLYING OR DISTRIBUTINGELECTRIC POWER; COMPUTER SYSTEMS BASED ON SPECIFIC COMPUTATIONAL MODELS; COMPUTING; CONVERSION OR DISTRIBUTION OF ELECTRIC POWER; COUNTING; DATA PROCESSING SYSTEMS OR METHODS, SPECIALLY ADAPTED FORADMINISTRATIVE, COMMERCIAL, FINANCIAL, MANAGERIAL, SUPERVISORYOR FORECASTING PURPOSES; ELECTRIC DIGITAL DATA PROCESSING; ELECTRICITY; GENERATION; PHYSICS; SYSTEMS FOR STORING ELECTRIC ENERGY; SYSTEMS OR METHODS SPECIALLY ADAPTED FOR ADMINISTRATIVE,COMMERCIAL, FINANCIAL, MANAGERIAL, SUPERVISORY OR FORECASTINGPURPOSES, NOT OTHERWISE PROVIDED FOR

The invention discloses a data center load prediction method based on ensemble learning, and belongs to the field of data center load prediction, and the method comprises the steps: S1, collecting the historical operation data of a data center electric load and an influence factor thereof, and building a feature database; s2, constructing an SARIMA prediction model based on the feature database, and estimating parameters of the SARIMA prediction model according to information criteria AIC and BIC; s3, constructing an LSTM (Long Short Term Memory) prediction model; s4, constructing an integrated learning neural network data set based on the SARIMA prediction model and the LSTM prediction model; s5, training an integrated learning neural network data set, and generating an FC network of summation weight; and S6, obtaining a final prediction result by the SARIMA prediction model and the LSTM prediction model through the FC network of the summation weight. The method can improve the accuracy of data center load p