Load estimation of power transformers using an artificial neural network

Abstract

This paper presents a methodology for load estimation of power transformers by means of an artificial neural network. To implement the proposed methodology the data of two power transformers, located in different places and with different operational conditions, were considered. Real data from a data base was provided by utility Interconexión Eléctrica S.A. (ISA). To forecast the load curves a neural network was trained using MATLAB, being able to fit a load curve with daily and weekly prediction times. The proposed method allows the estimation of load curve values in power transformers with an average percentage of relative error around 10%. The method described in this paper can be applied to other equipment with similar operating characteristics.