This paper contains a proposal to determine the kind of nonlinear load when are connected to the solar or conventional generation system. A database was built with sampled signals extracted from the photovoltaic system of the National Learning Service (SENA) in Bogota, Colombia. The used methodology has an acquisition system of voltage signals, and then, information from harmonic distortion was employed to identify the nonlinear loads. An artificial neural network was implemented to discriminate appliances with supervised learning. Two proposals were implemented. First one was based on energy information and second one was worked with wave peaks information. Results show that a classification rate of 95percent-flag-change could be reached in a problem with eight classes.
