No abstract

ResumenSe propone un modelo para el pronóstico del precio de la energía eléctrica en Colombia mediante el uso de redes neuro-difusas. Se utilizan dos estructuras de redes incluyendo como entradas la serie de precios diarios en la primera y la serie de precios más el nivel medio de los embalses en la segunda. Los resultados son comparados con dos estructuras de redes neuronales y con un modelo Autoregresivo Condicional Heterocedástico Generalizado (GARCH). Los datos históricos fueron obtenidos de la Compañía XM del Grupo ISA; datos para 120 días son usados para entrenamiento y los 31 días siguientes para verificar la capacidad predictiva del modelo. Se encontró ventajas en este último dentro del periodo de muestreo para una variable de entrada, pero un mejor desempeño de las redes neuro-difusas en el periodo fuera de la muestra tanto para una como para dos variables de entrada. Palabras clave: precio de la electricidad, redes neuronales artificiales, redes neuro-difusas, modelos de series de tiempo Electricity Price Forecasting using Neurofuzzy Networks AbstractA forecasting model for the price of electricity in Colombia using neurofuzzy networks is proposed. Two network structures including the price series in the first and the price series plus the reserve water levels in the latter are used. The results are compared with two neural networks structures and a Generalized Autoregressive Conditional Heteroscedasticity model (GARCH). Historical data were supplied by the Company XM of the ISA Group; data for 120 days were used as for training the network and the following 31 days were used for testing the predictive capabilities of the model. The GARCH model shows better adjustment within the training period for the prices series as input, but the neurofuzzy networks have better forecasting performance for one and for two input variables.

Results of a review of the literature on asset management in the electricity sector is presented, as well as a glance at some progress on it in Colombia. Such results can serve as a reference for the development of tools that strengthen the implementation of asset management systems in the electricity industry, as well as help to identify shortcomings in the methodologies in use today in Colombia. A proper management of power assets is of paramount importance, especially since such assets are characterized by high capital costs and also by the high economic losses that are faced when assets fail. The review focuses on the power transformer given the characteristics which make it a strategic asset in the management of the power system. It is concluded that the adoption of policies and techniques of asset management is of strategic importance for the electricity sector, and that there are general and specific guidelines provided by worldwide acknowledged organizations and they are being assimilated and implemented by large electric power companies in Colombia.

No abstract

No abstract