Papers by Gustavo Alejandro Schweickardt
LATAM Revista Latinoamericana de Ciencias Sociales y Humanidades, Jul 25, 2023
El presente trabajo propone un modelo de ecuaciones estructurales basado en la estructura de la v... more El presente trabajo propone un modelo de ecuaciones estructurales basado en la estructura de la varianza-covarianza (CB-SEM), para medir la calidad de servicio técnico percibida por los usuarios residenciales en un sistema de distribución eléctrica. El enfoque adoptado establece un correlato entre los indicadores objetivos, utilizados normativamente, y la percepción que los usuarios tienen de sus efectos. Se incorpora, además, un factor no controlado regulatoriamente: la atención recibida por los usuarios ante reclamos por interrupciones no programadas del suministro eléctrico. Son evaluados diferentes modelos que sirvan a las relaciones estructurales identificadas, para finalmente definir el de mayor validez y mejor ajuste, conforme los indicadores que se emplean para esta técnica. Los resultados permiten observar que cada constructo representa adecuadamente un índice objetivo, y que la atención ante reclamos tiene un impacto sustancial en la calidad medida. El sistema de distribución analizado pertenece a la ciudad de Bariloche, Argentina, y los datos utilizados corresponden a una encuesta realizada durante el año 2021.
Lámpsakos, Jun 29, 2014
This work presents a model to Low Voltage (LV) Unbalance Degree Optimization in a Three-phase Ele... more This work presents a model to Low Voltage (LV) Unbalance Degree Optimization in a Three-phase Electric Distribution Network (EDN). The combination of two new Fuzzy-MultiObjective MetaHeuristics FEPSO GIST (Fuzzy Particles Swarm Optimization with Global/Individual Stochastic Topology) proposed by the author and, FAFS (Fuzzy Artificial Fish Shool) extended to MultiObjective domain by the author, using Fuzzy Sets, are presented. Of multiple problems resulting from such unbalance degree, are considered the technical losses and the voltage drops. Both aspects are fundamentals in the rational use of energy, when this objective is focused from the offer side, and are observed for Regulatory Authority. In addition, a MatHeuristic approach composed for the classical approach based in Mixed-Interger Linear Programming and FEPSO GIST-FAFS Meta-Heuristics, is introduced. In this Part I of the work, the framework and theoretical developments, required for the Models application, are presented.
Revista de la Escuela de Perfeccionamiento en Investigación Operativa XXVII(45), 5-24. (2019), May 1, 2019
2021 XIX Workshop on Information Processing and Control (RPIC), 2021
In this work, a neural model is proposed, which solves two limitations of artificial neural netwo... more In this work, a neural model is proposed, which solves two limitations of artificial neural networks. The first refers to the ability to extrapolate outside the domain of the training data. The second arises when only a small sample is available for training. On the other hand, there is a need to characterize a complex system, and the dynamics of its components is partially known. The proposed model is based on the construction of a regressor from a feasible space, using Homotopy Analysis. In this way, a functional neural network is obtained.
2020 IEEE Congreso Bienal de Argentina (ARGENCON), 2020
En este trabajo se expone un método que permite el cálculo de los parámetros de regresores no lin... more En este trabajo se expone un método que permite el cálculo de los parámetros de regresores no lineales, de sistemas dinámicos con intervalos. El método propuesto, es un método contractivo aplicable a transformaciones homeomorfas. Este requisito lo cumplen muchos regresores usados para modelar sistemas dinámicos no lineales. Permite aplicar un modelo que puede establecer y compatibilizar cuatro aspectos: horizonte de predicción, incertidumbre, datos requeridos para el ajuste y dominio de validez. Es decir captar la tendencia con un dominio de validez mayor del obtenido con un ajuste de mayor cantidad de parámetros y menor incerteza. Tiene carácter robusto de su convergencia. Como contraparte es un método costoso en términos computacionales, pero tal circunstancia se salva por su característica de algoritmo paralelizables. Así hace posible su aplicación en sistema de control, con hardware de paralización masiva.
2020 IEEE Congreso Bienal de Argentina (ARGENCON), 2020
In this work, a method is exposed that allows the calculation of the parameters of non-linear reg... more In this work, a method is exposed that allows the calculation of the parameters of non-linear regressors, of dynamic systems with intervals. The proposed method is a contractive method applicable to homeomorphic transformations. This requirement is met by many regressors used to model nonlinear dynamic systems. It allows to apply a model that can establish and make compatible four aspects: prediction horizon, uncertainty, data required for adjustment and validity domain. In other words, capturing the trend with a validity domain greater than that obtained with an adjustment of a greater number of parameters and less uncertainty. It has a robust character of its convergence. As a counterpart, it is a costly method in computational terms, but this circumstance is saved by its characteristic of parallelizable algorithms. In this way, it can be applied in a control system, with massive shutdown hardware.
2018 Congreso Argentino de Ciencias de la Informática y Desarrollos de Investigación (CACIDI), 2018
Sensors play a critical role monitoring processes and control of infrastructure. These together w... more Sensors play a critical role monitoring processes and control of infrastructure. These together with the adaptation, calibration and signal transmission devices conform measurement devices that operate in a control and monitoring loop, are essential for the correct operation of various industrial production systems. A disarrangement of such devices as a whole and eventual failure, are expressed in deviated measurements of expected values that an operator can detect. Therefore, it is necessary to have algorithms that can offer an early warning when the dynamics of a system does not correspond to the measured values. In this sense, this document proposes two approaches. A forecasting technique based on series of past temporary data, which uses an autoregressive model of integrated moving average (ARIMA) and another based on a neuronal network of the multilayer Perceptron type. For both cases, a 95% prediction interval was established to set a criterion to detect anomalies and issue a warning of failure of the measuring device. Both methods were compared to issue an alert, in industrial temperature measurement systems.
2006 IEEE PES Transmission and Distribution Conference and Exposition: Latin America, TDC'06, 2006
... Analytical Hierarchy Process G. Schweickardt, V. Miranda, Fellow Member, IEEE, and E. Muela, ... more ... Analytical Hierarchy Process G. Schweickardt, V. Miranda, Fellow Member, IEEE, and E. Muela, Student Member, IEEE ... Therefore, if its form is changed to Yager's [9], by normalizing and multiplying it by the order of the judgment matrix, it will be Yage ...
Neural Computing and Applications, 2014
This paper presents a statistical learning-based method for security assessment of microgrids (MG... more This paper presents a statistical learning-based method for security assessment of microgrids (MGs) in case of isolation from the main grid. Based on the stability criteria, the MG pre-islanding conditions are divided into secure and insecure regions. Critical system variables regarding the MG dynamic security are first selected via a feature selection procedure, known as minimum redundancy maximum relevance. An unsupervised learning method called pattern discovery method is then performed on the space of the critical features to extract the organization (patterns) among samples. Geometrically, the patterns are hyper-rectangles in the features space representing the system dynamic secure/insecure regions and can be effectively used for online MG security monitoring before islanding condition. Simulation results are carried out in the time domain, by using MATLAB, which demonstrate the effectiveness and accuracy of the proposed method in the MG security assessment.
Energy Policy, 2007
The aim of this paper is to apply a fuzzy possibilistic model to the power generation planning th... more The aim of this paper is to apply a fuzzy possibilistic model to the power generation planning that includes environmental criteria. Since it is not always meaningful to relate uncertainty to frequency, the proposed approach analyzes the imprecision and ambiguity into the decision making, especially when the system involves human subjectivity. This paper highlights the subjacent differences between fuzzy and possibilistic entities. Additionally, it illustrates the use of fuzzy sets theory and possibility theory for modeling flexibility, and nonprobablistic uncertainty, respectively. The necessity of a new direction for the environmental problem in a power system is outlined, an approach that attempts a greater integral quality of planning instead of searching for a simple optimal solution. This process must be consistent with a wider and more suitable interpretation about both the problem as such and the concept of solution in uncertain situations.
Energy Economics, 2008
The main objective of this paper is to present a model developed to evaluate the Dynamic Adaptati... more The main objective of this paper is to present a model developed to evaluate the Dynamic Adaptation of an Electric Energy Distribution System respecting its planning for a given period of Tariff Control. The model is based on a two-stage strategy that deals with the mid/short-term and long term planning, respectively. The starting point for modeling is brought about by the results from a multi-attribute method based on Fuzzy Dynamic Programming and on Analytic Hierarchy Processes for a mid/short-term horizon. Such a method produces a set of possible evolution trajectories which can be defined as satisfactory when they evolve above a given risk threshold that the planner is willing to accept. Then, the decision-making activities within the framework of the Analytic Hierarchy Processes are those tasks that allow defining a Vector for Dynamic Adaptation of the System, which is directly associated to an eventual series of imbalances that take place during its evolution.
Energy policy is an essential part of the economy and the society. In some countries, there is a ... more Energy policy is an essential part of the economy and the society. In some countries, there is a lack of a regulatory framework, which must be clear and practicable to allow new technologies to compete with the conventional way of generation. This is the problem in Argentine, the lack of a regulatory framework that can regulate the insertion of wind energy into the Argentine power system (SADI). In this paper, a review of typical incentives for the installation of wind farms in the world, and a review of some laws and policies in Argentine are presented. Also financial and economic issues that are related to the installation of wind farms are analyzed, and some recommendations related to the topics are presented in this paper.
Pollution problems such as the greenhouse effect as well as the high value and volatility of fuel... more Pollution problems such as the greenhouse effect as well as the high value and volatility of fuel prices have forced and accelerated the development and use of renewable energy sources. In this paper, a revision of wind generation is presented. In the first part, a brief history of wind energy developments is detailed. Next, some commentaries related to the present and future state are made. Then, a revision of the modern structures of wind generation is realized. In fourth place a brief comparison between small and big size turbines is presented. Then, different types of energy storage are mentioned. Finally, some regulatory aspects are discussed.
DYNA
This work analyzes the problem of non-technical losses in a low-voltage electrical power distribu... more This work analyzes the problem of non-technical losses in a low-voltage electrical power distribution system with an artificial intelligence model. The problem focuses on the use of a backpropagation multilayer perceptron neural network, which will quantitatively determine these losses from the manipulation of the current profile and the voltage drop expressed as percentages of their nominal values. These two magnitudes considered, will allow obtaining from the identification of patterns with large variations a technical assessment or quantification to approach the analysis from a different perspective, differing in the methodological determination of non-technical losses currently considered as a percentage of total losses. The results obtained will allow to form a basis for the correct determination of the non-supplied energy, its influence on distribution costs and energy efficiency for the future insertion of distributed generation.
En el presente trabajo se desarrolla un modelo de optimización para identificar subsidios intríns... more En el presente trabajo se desarrolla un modelo de optimización para identificar subsidios intrínsecos entre grupos de usuarios que exhiben características de consumo y distributivas diferentes, definiendo su costo de acceso a las redes de distribución eléctrica. Las características de consumo son traducidas por la elasticidad demanda-precio del servicio de acceso a redes. Las características distributivas se presentan desde un desarrollo auxiliar al modelo, que conduce a una variante de los denominados precios Ramsey, incorporando en su estructura un parámetro que traduce el impacto distributivo. La solución es tomada de forma indicativa para plantear el apartamiento ?óptimo? del vector de precios en cada segmento del mercado residencial, respecto del costo propio de distribución (CPD). Al contrario de lo adoptado en la práctica regulatoria, un CPD constante, el modelo propuesto arrojará un Vector CPD, cuyos componentes difieren en los segmentos identificados, permitiendo subsidios ...
En el presente trabajo se aplica la Hiperheurística HY X-FPSO CBR soportando a la Optimización Di... more En el presente trabajo se aplica la Hiperheurística HY X-FPSO CBR soportando a la Optimización Dinámica Posibilística que se corresponde con la Planificación de Mediano/Corto Plazo de un Sistema de Distribución de Energía Eléctrica (SDEE). El problema a resolver, específicamente, es la definición/identificación del Espacio de Estados por los que el SDEE debe evolucionar, conociendo el número de etapas. Las mismas se corresponden con cada año del Período de Control Regulatorio. Se procede al Diseño y Entrenamiento de la Red Neuronal Artificial de Retropropagación, en la que se basa el mecanismo de Aprendizaje/Selección mediante el cual son aplicadas las formas X-FPSO, para cierta instancia de decisión, identificadas como dominio de la Hiperheurística propuesta. Se integran los resultados al Modelo de Optimización Posibilística y se procede a la simulación completa en un Estudio de Caso sobre un SDEE real. Se comparan los resultados que arroja la Hiperheurística propuesta, con el Espa...
Revista de la Escuela de Perfeccionamiento en Investigación Operativa XXI(34): 8-29 (2013)., Nov 1, 2013
In this work the Hyperheuristic HY X-PSO CBR, supporting a Possibilistc Dynamic Optimization corr... more In this work the Hyperheuristic HY X-PSO CBR, supporting a Possibilistc Dynamic Optimization corresponding to the Electric Distribution System (EDS) Planning in the Mid/Short Term, is applied. The problem to solve is the definition/identification of States Space for the evolution of EDS, knowing the number of stages, corresponding with each of years of Regulatory Control Period. The Artificial Backpropagation Neural Network, that support the Selection/Learning Method to choice, in certain decision instance, the X-FPSO form in Metaheuristics domain of proposed Hyperheuristic, is Designed an Trained. The results are used in the Dynamic Possibilistic Model and a simulation on a real EDS, as Study Case, is performed. The Hyperheuristic results and States Space defined by mean inspection for optimizations performed on the same real EDS, are compared.
Uploads
Papers by Gustavo Alejandro Schweickardt