Abstract
Classifying consumers, namely LV consumers, in order to assign them typical load diagrams, was always a concern of the electric utilities, which used this kind of information to better manage their distribution networks. Now, with the transition to a completely open market, the need for settlement between distribution operators and traders requires hourly consumption records that are not generally available, so deriving load diagrams for LV consumers is a mandatory task. This paper presents a new methodology for this purpose that uses typical diagrams obtained in measurement campaigns to create classes defined in the commercial information space that maximize the compactness of the diagrams in each class. The methodology was developed in a project with EDP (the Portuguese distribution operator) and the result will probably be adopted by the regulatory authority. © 2005 ISAP.

Abstract
An artificial neural network concept has been developed for transformer fault diagnosis using dissolved gas-in-oil analysis (DGA). A new methodology for mapping the neural network into a rule-based inference system is described. This mapping makes explicit the knowledge implicitly captured by the neural network during the learning stage, by transforming it into a Fuzzy Inference System. Some studies are reported, illustrating the good results obtained.

Abstract
This paper provides evidence that Evolutionary Particle Swarm Algorithms outperform Genetic Algorithms in deriving optimal strategic decisions for an Energy Retailer, in the framework of a complex simulation of a multiple energy market, based on an Intelligent Agent FIPA-compliant open source platform.

Abstract
This paper describes a system for estimating load curves at low-voltage (LV) substations. The system is built by the aggregation of individual fuzzy inference systems of the Takagi-Sugeno type. The model was developed from actual measurements forming a base of raw data of consumer behavior. This database allowed one to build large test and,training sets of simulated LV substations, which led to the development of the fuzzy system. The results are compared in terms of accuracy with the ones obtained with a previous artificial neural network approach, with better performance.

Abstract
The development of techniques under geographical information system (GIS) platforms, such as geocomputational modeling, which increase the capabilities of GIS, allowing the systems to adapt to optimal distributed generation (DG) planning studies, is discussed. Using adequate software under the GIS platform, users can obtain useful information on the economic or technical viability of any distributed power generation facilities. GIS offers a variety of structured data models suitable for the storage, manipulation, and analysis of the information needed in DG planning. GIS can also be used in DG planning to study negotiation processes among different energy actors to look for geographical planning solutions.

Abstract
This paper presents an overview of a simulation platform for studying the behavior of energy retail markets where multiple energies enter in competition. This platform is based on autonomous agent techniques. The simulations include agents representing Residential, Commercial and Industrial Consumer Groups, Electricity, Gas, Heat Retail Suppliers and Energy Deliverers, Regulators, Market Operators, Economy and Information Environment. Each pursues its own interests and from their interaction a complex collective behavior emerges. Agents formulate their strategies namely by inner complex simulation process that try to guess other agent move s and define optimum decisions in energy purchasing, price fixing, market share wining, investing and capturing new consumers, among other. The process works on a FIPA complying platform being able to run in a parallel cluster machines.