METHOD FOR ESTIMATING CUSTOMER BASELINE LOAD USING DATA MANING AND APPARATUS THEREOF

摘要

The present invention relates to a method for estimating a customer baseline load by using a data mining technique and a device thereof. The method comprises the steps of: receiving load profile data as analysis target data for a predetermined period of time to set a value in a parameter for determining similarity of a power usage pattern; and sequentially applying a self-organizing map technique and a K-means clustering technique as data mining techniques to extract at least one of a date when a demand response signal is received and a candidate date to which the power usage pattern is similar. Therefore, the method can estimate a customer baseline load value with a low error rate.