Abstract
Expansion planning of electric power or natural gas networks has become a consuming time engineering task due to the multiple factors that must be taken into account: technical, economic, environmental or social factors. This paper presents an advanced model of natural gas distribution networks based on Geographic Information Systems (GIS) methodologies, to evaluate the cost associated to the expansion of these networks in order to meet a demand imposed by the user in any location of a region. The experimental results show that this approach produces visual and useful information for planning the expansion of natural gas distribution networks.

Abstract

Abstract
This paper presents a method used to validate a spatial load forecasting model based on fuzzy systems implemented in a Geographical Information System. The validation process confirms the adequacy of the rule base, and also it is strictly necessary to define the confidence intervals associated to the predicted spatial demand.

Abstract
This text presents an overview of the basic concepts of a Neuro-Fuzzy inference system for spatial Offer-and-Demand forecasting of electric power on a geographical basis, over GIS (Geographical Information Systems).

Abstract
This paper presents a methodology developed within the SOLARGIS project - a Joule project - aiming at evaluating the potential of integrating renewable forms of energy for dispersed electricity production. With this project we also wanted to demonstrate the efficiency of GIS - Geographical Information Systems - as a tool to analyse the integration of renewable forms of energy. In this paper we present the methodologies developed to identify renewable resources in a given geographic region, to detect high potential areas for wind farm siting and to evaluate the efficiency and market of isolated systems to be used for dispersed rural electrification. In this last methodology we used fuzzy models to describe the uncertainties in demand and cost values.

Abstract
This paper presents the analysis of the importance of a set of explanatory (input) variables for the day-ahead price forecast in the Iberian Electricity Market (MIBEL). The available input variables include extensive hourly time series records of weather forecasts, previous prices, and regional aggregation of power generations and power demands. The paper presents the comparisons of the forecasting results achieved with a model which includes all these available input variables (EMPF model) with respect to those obtained by other forecasting models containing a reduced set of input variables. These comparisons identify the most important variables for forecasting purposes. In addition, a novel Reference Explanatory Model for Price Estimations (REMPE) that achieves hourly price estimations by using actual power generations and power demands of such day is described in the paper, which offers the lowest limit for the forecasting error of the EMPF model. All the models have been implemented using the same technique (artificial neural networks) and have been satisfactorily applied to the real-world case study of the Iberian Electricity Market (MIBEL). The relative importance of each explanatory variable is identified for the day-ahead price forecasts in the MIBEL. The comparisons also allow outlining guidelines of the value of the different types of input information.