Empirical Voltage-current Signatures for Individual Household Consumers Obtained by
Non-linear Regression^*

Dadiana-Valeria CĂIMAN^*, Toma-Leonida DRAGOMIR
Politehnica University Timișoara, Automation and Applied Informatics, 2 Vasile Pârva, Timișoara, Romania
dadiana.grando@aut.upt.ro (^*Corresponding author), toma.dragomir@upt.ro

ABSTRACT: The article is part of the approach of finding the signatures for the individual household consumers using the voltage-current trajectories. Four classes of signatures are presented, known as: discontinuous tangent, tangent, ellipse, and hybrid. The functions describing the signatures are defined using a method based on non-linear regression and genetic algorithms. The method is implemented, with concrete results, on consumers from each of the four classes, starting with pairs of voltage-current values measured at low frequency, of approximately 20 Hz. This represents an important aspect from a practical point of view. There are four examples of signatures determined for: a laptop, a vacuum cleaner, a TV, and a fridge.

KEYWORDS: Voltage-current signature, Household consumers, Non-linear regression, Genetic algorithms.

>>FULL TEXT: PDF

CITE THIS PAPER AS:
Dadiana-Valeria CĂIMAN, Toma-Leonida DRAGOMIR, Empirical Voltage-current Signatures for Individual Household Consumers Obtained by Non-linear Regression, Studies in Informatics and Control, ISSN 1220-1766, vol. 28(2), pp. 201-212, 2019. https://doi.org/10.24846/v28i2y201908

________________________________________________

^* This paper is based on two previous presentations in: “Journal of Economic Computation and Economic Cybernetics Studies and Research” and “The 14th International Conference on Informatics in Economy” (see references 3 and 4). This work presents new data from our research about the evaluation of the system ontology, and implementation of the developed solution.