Abstract

Abstract
Most optimization and decision problems in power systems include integer or binary variables, leading to combinatorial problems. In this paper, several approaches using metaheuristics and genetic algorithms are presented that deal with real problems of the power industry Most of these methodologies are now implemented in distribution management systems (DMS) used by several utilities.

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 proposes an integrated approach of genetic algorithms, Tabu search and simulated annealing for multi-stage (dynamic) transmission network expansion planning. The proposed algorithm integrates the most interesting and best features of the above individual algorithms. The efficiency and reliability of the proposed algorithm is proved with the modified Garver's six-bus network. Finally, a real-world application (Sri Lankan transmission network) of the integrated algorithm is presented for multi-stage transmission expansion planning.

Abstract
This paper reports the building of a system for predicting load curves at Low Voltage Substations supplying a set of consumers of different types (residential, industrial, etc.). The system is built by the aggregation of individual Fuzzy Inference Systems of the Takagi-Sugeno type. The paper describes how actual measurements formed a base of raw data and how test and training sets could be built from this base. Results produced by the prediction system and their comparison with actual load curves confirm the good performance of the model.

Abstract
In this paper we present a complete methodology to perform state estimation studies in distribution networks. Due to the peculiarities of these networks the traditional state estimation concept was enlarged in different ways. It includes a load allocation study, as a way to cope with the reduced number of real time measurements in SCADA database. The algorithm estimates binary values of topology variables, due to incomplete or erroneous topology information in the control center and it is able to include data modeled by fuzzy numbers as a way to include fuzzy results of the load allocation procedure or fuzzy assessments from experts. Finally, the paper describes a methodology developed to tune the weights to be used in the state estimation based on a Takagi-Sugeno fuzzy inference system. The paper includes a case study based in the IEEE 24 bus system to highlight and illustrate its application in a variety of situations.