Abstract
This paper reports new results in adopting entropy concepts to the training of mappers such as neural networks to perform wind power prediction as a function of wind characteristics (mainly speed and direction) in wind parks connected to a power grid. Renyi's Entropy is combined with a Parzen Windows estimation of the error pdf to form the basis of three criteria (MEE, MCC and MEEF) under which neural networks are trained. The results are favourably compared with the traditional minimum square error (MSE) criterion. Real case examples for two distinct wind parks are presented.

Abstract
Prediction models for generation from renewables are needed in the context of a power system with a diversified portfolio. The presentation will discuss a new criterion and procedure to develop prediction models based on Renyils Entropy combined with Parzen windows (an approach named Information Theoretic Learning) that is applied to wind prediction and suggested as a better training paradigm for fuzzy or neural systems.

Abstract

Abstract
This paper discusses some issues related with the growing importance of wind power and in modern power systems and some challenges raised by the emergence of distributed generation, and how computational intelligence and other modern techniques have been able to provide valuable results in solving the new problems. It presents some solutions obtained with a number of computational intelligence techniques and their application to real cases. © TÜBITAK.

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
Economic operation of medium-sized and large isolated power systems with a high penetration of renewables, namely wind power, is not well suited neither by the conventional unit commitment/dispatch arrangements for interconnected systems, nor by the simplified procedures used in small systems. In this paper, the economic scheduling functions developed within CARE are described. The main idea is to perform on-line unit commitment in the same cycle with the dispatch, using the most recent forecasts, as described by Hatziargyriou et al. (2000). The Unit Commitment module has two variants: one based on Genetic Algorithms, and one using a Combinatorial Approach. On the other hand, three alternative procedures were developed for the Economic Dispatch: a Linear Programming Optimal Power Flow, an Evolutionary approach and a Genetic Algorithms based procedure. The paper describes the main features of the five approaches, including test results when appropriate.Economic operation of medium-sized and large isolated power systems with a high penetration of renewables, namely wind power, is not well suited neither by the conventional unit commitment/dispatch arrangements for interconnected systems, nor by the simplified procedures used in small systems. In this paper, the economic scheduling functions developed within CARE are described. The main idea is to perform on-line unit commitment in the same cycle with the dispatch, using the most recent forecasts, as described by Hatziargyriou et al. (2000). The Unit Commitment module has two variants: one based on Genetic Algorithms, and one using a Combinatorial Approach. On the other hand, three alternative procedures were developed for the Economic Dispatch: a Linear Programming Optimal Power Flow, an Evolutionary approach and a Genetic Algorithms based procedure. The paper describes the main features of the five approaches, including test results when appropriate.