AN ANALYSIS SYSTEM FOR PREDICTIVE POWER USAGE BY LEARNING OPERATION DATA AND METHOD THEREOF

摘要

An analysis system and method for predicting power consumption by learning operation data are provided. The method includes the steps of: generating, by a power data management server, standard operation data using operation data including operation power data corresponding to operation performance data; And generating, by the power data management server, predicted operating power data by analyzing power consumption for each process and power consumption for each item based on the standard operating data, including, but generating the predicted operating power data, Calculating a correlation coefficient by analyzing, by the power data management server, a correlation between variable data affecting the operating power data and the operating power data; Calculating, by the power data management server, a regression coefficient including an independent variable and a dependent variable using the variable data based on the correlation coefficient; Generating cluster data by standardizing and clustering data having similarity among the regression coefficients, by the power data management server; Generating, by the power data management server, power usage section data by cross-analyzing the operating power data and the cluster data; And generating, by the power data management server, the predicted operating power data by analyzing the power consumption section data for each process and the power consumption for each item.