No abstract

This paper presents an assessment of the potential behind the BiGRU-CNN artificial neural network to be used as an electric power theft detection tool. The network is based on different architecture layers of the bidirectional gated recurrent unit and convolutional neural network. The use of such a tool with this classification model can help energy sector companies to make decisions regarding theft detection. The BiGRU-CNN artificial neural network singles out consumer units suspected of fraud for later manual inspections. The proposed artificial neural network was programmed in python, using the keras package. The best detection model was that of the BiGRU-CNN artificial neural network when compared to multilayer perceptron, recurrent neural network, gated recurrent unit, and long short-term memory networks. Several tests were carried out using data of an actual electricity supplier, showing the effectiveness of the proposed approach. The metric values assigned to their classifications were 0.929 for accuracy, 0.885 for precision, 0.801 for recall, 0.841 for F1-Score, and 0.966 for area under the receiver operating characteristic curve.

No abstract

RESUMENEl azufre (S) es un nutriente esencial para los cultivos, y recientemente se han registrado deficiencias en algunos suelos. El índice de fertilidad de S se basa en la disponibilidad de sulfato medido a través de turbidimetría (TB), que es un método fácil y rápido de aplicar. Este método es muy variable e impreciso, especialmente en Andisoles, por lo que la evaluación de la fertilidad de S en estos suelos no es confiable. El objetivo de este estudio fue evaluar la aplicabilidad del método de cromatografía iónica (IC) para medir con más exactitud y precisión el S disponible en suelos volcánicos de Chile. Se evaluó el contenido de sulfato disponible en dos sitios con suelos y climas contrastantes, a través de TB e IC. Se probó la exactitud y precisión del método IC calculando la curva de calibración y comparando la concentración de sulfato en extractos de suelo (n = 10) con la adición de concentraciones conocidas en los mismos extractos. El S disponible en el Andisol no obtuvo el mismo valor de acuerdo a la metodología empleada (P < 0,05), y no se observaron diferencias en el Inceptisol (P > 0,05). El método IC mostró linealidad (R 2 = 0,9998) y precisión, sin diferencias significativas entre el valor de sulfato medido y el modelado (P > 0,05). Un amplio rango de S disponible fue medido en otros suelos usando IC (7-37 mg SO 4 -2 kg suelo -1 ), demostrando los diferentes suministros de S en Andisoles y la importancia de aplicar un método apropiado para la interpretación del balance de S en estos suelos.Palabras claves: sulfato, Andisol, turbidimetría, cromatografía iónica ABSTRACT Sulphur (S) is an essential crop nutrient, and its deficiency in the soil has been reported in recent years. The index of S fertility is based on the sulphate availability measured by the turbidimetry method (TB), because it is easily and quickly applied. However, this method has shown a large variability, and lack of precision to determine sulphate, particularly in Andisols, so S fertility assessment in this type of soil is not certain. The objective of this study was to evaluate the applicability of the ion-chromatography method (IC) to obtain more accurate and precise results of the available S in volcanic soils of Chile. Two sites contrasting soil and climate conditions were ISSN 0719-3882 print ISSN 0719-3890 online Chilean J. Agric. Anim. Sci., ex Agro-Ciencia (2017) 33(2): 118 assessed in their available sulphate content by the TB and IC methods The IC method was tested for accuracy and precision by calculating the curve of calibration and by comparing sulphate in the soil extracts (n=10) with the addition of standard concentrations to the same extracts. Values of available S in the Andisol varied depending on the methodology used (P < 0.05), whilst no differences were observed in the Inceptisol (P > 0.05). The IC showed linearity (R 2 = 0.9998) and precision, with no significant differences between the measured and modelled value of sulphate (P > 0.05). A wide range of available S was found in others sites (7-37 mg SO 4 -2 k...

In this work, the state estimation problem of electric power systems is represented through a mathematical programming approach. Initially, a non-linear mathematical model based on the classical method of weighted least squares is proposed to solve the state estimation problem for comparative purposes. Due to the inherent limitations that this classical model presents when dealing with errors in the set of measurements, a new mathematical model is proposed that can be used within an iterative procedure to reduce the impact of measurement errors on the estimated results. Several tests on a didactic 5-bus power system and IEEE benchmark power test systems showed the effectiveness of the proposed approach which achieved better results than the proposed classical state estimation model. The non-linear programming models proposed in this paper are implemented in the mathematical modeling language AMPL. Additionally, to validate the results of the proposed methodologies, the power system operation points are compared with the results obtained using the Matpower simulation package. The results allowed concluding that the proposed mathematical models can be successfully applied to perform state estimation studies in power systems.