Abstract

Abstract

Abstract
En este documento se presenta una evaluación experimental del estado del aislamiento de un transformador trifásico de 50 kVA sumergido en aceite a través de la aplicación de impulsos atmosféricos estándar de alto voltaje y su respuesta en frecuencia realizando un Análisis de la Respuesta en Frecuencia al Impulso (IFRA). La evaluación se basa en tener dos estados representativos del aislamiento, por ejemplo, cuando el transformador usa aceite dieléctrico deteriorado y luego este aceite es reemplazado por uno nuevo, por lo que se realiza el cambio del aceite dieléctrico. Se lleva a cabo una valoración general del estado del transformador en ambos estados representativos mediante la ejecución de pruebas de rutina. El análisis de la respuesta en frecuencia se desarrolla mediante la obtención de la respuesta del transformador en los dos estados representativos del aislamiento y bajo diferentes configuraciones de medición. Posteriormente se evalúa a través de una comparación gráfica entre las respuestas en frecuencia, valorando cualitativamente y cuantitativamente las figuras obtenidas; y relacionándolas con el estado del aislamiento. Por ello, se proporciona una metodología experimental como una opción al uso de equipo especializado para análisis de respuesta en frecuencia por medio de la acción de impulsos atmosféricos estándar de alto voltaje, usando el equipo disponible en el Laboratorio de Alto Voltaje de la Escuela Politécnica Nacional destinado para pruebas de impulso.

Abstract
This paper presents qualitative and quantitative analysis of the traveling waves induced by faults on direct current (DC) transmission lines of line-commutated converter high-voltage direct current (LCC HVDC) systems for detecting the wavefront arrival times using the boundary wavelet coefficients from real-time stationary wavelet transform (RT-SWT). The qualitative analysis takes into account the steady-state operation and the detection of the inception times of both first and second wavefronts at the converter stations. The behavior of the boundary wavelet coefficients in DC transmission lines is examined considering the effects of the main parameters that influence the detection of the traveling waves, such as mother wavelets, sampling frequency, DC transmission line terminations, electrical noises, as well as fault resistance and distance. An algorithm designed to run in real-time and able to minimize the factors that hamper the performance of traveling wave-based protection (TWP) methods is proposed to detect the first and second surge arrival times. Quantitative results are achieved based on the accuracy of one- and two-terminal fault location estimation methods, and indicate the proper operation of the presented algorithm.

Abstract
This paper presents a new method to identify classes of events, by processing phasor measurement units (PMU) frequency data through deep neural networks. Deep tapered Multi-layer Perceptrons of the half-autoencoder type, Deep Belief Networks and Convolutional Neural Networks (CNN) are compared, using real data from Brazil. A sound success is obtained by a transformation of time-domain signals, from dynamic events recorded, into 2D images; these images wee processed with a CNN, taking advantage of the strong dependency existing among neighboring pixels in images. The training, computing and processing was achieved with a GPU (Graphics Processing Unit), allowing speeding-up of the process up to 30 times and rendering the process suitable to increase the online situational awareness of network operators.

Abstract
This paper presents a data-driven spatial net-load forecasting model that is applied to the distribution network expansion problem. The model uses population census data with Information Theory-based Feature Selection to predict spatial adoption patterns of residential electric vehicle chargers and photovoltaic modules. Results are high-resolution maps (0.02 km(2)) that allow distribution network planners to forecast asymmetric changes in load patterns and assess resulting impacts on installed HV/MV substation transformers in distribution systems. A risk analysis routine identifies the investment that minimizes the maximum regret function for a 15-year planning horizon. One of the outcomes from this study shows that traditional approaches to allocate distributed energy resources in distribution networks underestimate the impact of adopting EV and PV on the grid. The comparison of different allocation methods with the presented diffusion model suggests that using conventional approaches might result in strong underinvestment in capacity expansion during early uptake and overinvestment in later diffusion stages.