F.J. Marin

Genetic Algorithms on LAN-message Passing Architectures using PVM: Application to the Routing Problem

In this work we address the Genetic Algorithm parallelization problem, over a LAN-based message passing computer architectures, using PVM 3.1 (Parallel Virtual Machine — Public Domain software) as a software integration tool. The strategy used has been to split the problem into independent functions, most of them running in server processors which perform the work, and report periodically their partial results to a master node which redistributes the information in order to improve the work in each server. The strategy we present here handles all data communications through sockets via PVM calls, in such a way that the communication latency and the overall data-passing load are significantly reduced. In addition, a dynamic load balancing and fault tolerant capabilities are achieved. As an application, we study the Routing problem, which is a classical optimization problem with combinatorial complexity.

Optimal phasor measurement unit placement using genetic algorithms

Many methods to codify Artificial Neural Networks have been developed to avoid the defects of direct encoding schema, improving the search into the solutions space. A method to estimate how the search space is covered and how are the movements along search process applying genetic operators is needed in order to evaluate the different encoding strategies for Feedforward Neural Networks. A first step of this method is considered with two encoding strategies, a direct encoding method and an indirect encoding scheme based on graph grammars: generative capacity, how many different architectures the method is able to generate.

Self-organizing maps for contingency analysis: visual classification and temporal evolution

In this paper an analysis of the applicability of Kohonens self-organizing maps (SOMs) to contingency analysis in power systems is presented. We show the applicability of this artificial neural paradigm for both visualization and graphic monitoring of contingency severity, and the prediction of the system evolution to a future possible dangerous state. Both bidimensional and linear SOMs have been studied using as reference standard IEEE-14 and IEEE-118 electrical networks. Among the advantages of linear SOMs with respect to bidimensional SOMs and other classical methods we highlight the following ones: (1) a greater number of contingencies may be represented in one only screen and they may be more easily analyzed by a human operator; (2) the architecture and training process complexity of the SOM does not significantly increase with the power system size; and (3) the operation model is carried out in real time.

Neural Networks for Contingency Evaluation and Monitoring in Power Systems

In this paper an analysis of the applicability of different neural paradigms to contingency analysis in power systems is presented. On one hand, unsupervised Self-Organizing Maps by Kohonen have been implemented for visualization and graphic monitoring of contingency severity. On the other hand, supervised feed-forward neural paradigms such as Multilayer Perceptron and Radial Basis Function, are implemented for severity numerical evaluation and contingency ranking. Experiments have been performed with successfully result in the case of Kohonen and Multilayer Perceptron paradigms.

Improving Biological Sequence Property Distances by Using a Genetic Algorithm

In this work we present a genetic-algorithm-based approach to optimise weighted distance measurements from compositional and physical-chemical properties of biological sequences that allow a significant reduction of the computational cost associated to the distance evaluation, while maintaining a high accuracy when comparing with traditional methodologies. The strategy has a generic and parametric formulation and exhaustive tests have been performed to shown its adaptability to optimise the weights over different compositions of sequence characteristics. These fast-evaluation distances can be used to deal with large set of sequences as is nowadays imperative, and appear as an important alternative to the traditional and expensive pairwise sequence similarity criterions.

Hopfield neural networks for state estimation: parameters, efficient implementation and results

State estimation processes measurements and other information to find the network state vector. In this paper, state estimation is considered as an optimization problem to be solved with a Hopfield neural network. Several activation models for this network are simulated and compared. A new method is proposed that calculates the integration step parameter for this network in an autonomous way, eliminating the need for determining it in a manual way for each particular problem. This algorithm has been successfully tested for a wide range of electrical nets. Neural and classic analytical methods are compared.ZusammenfassungDie Zustandsschätzung verarbeitet Messungen und andere Informationen, um den Netzzustandsvektor zu finden. Dieser Beitrag betrachtet die Zustandsschätzung als Optimierungsproblem, das mit einem neuronalen Hopfield-Netzwerk gelöst wird. Verschiedene Aktivierungsmodelle für dieses Netzwerk werden simuliert und verglichen. Eine neue Methode, die den Integrationsschrittparameter für dieses Netz autonom berechnet, und die es erübrigt, ihn für jedes einzelne Problem manuell zu bestimmen, wird vorgeschlagen. Dieser Algorithmus ist für einen großen Bereich von elektrischen Netzen erfolgreich getestet worden. Neuronale und klassische analytische Methoden werden verglichen.

Weighting and Feature Selection on Gene-Expression data by the use of Genetic Algorithms

One of the most promising approaches for gaining insight into the biological activity of genes is to study their expression patterns in a variety of experimental conditions and contexts. In this work we present a genetic- algorithm-based approach for optimizing weighting schemes of variables used to improve clustering solutions. The same technique is used for feature selection and the detection of marker components in large datasets. An original string representation based on real numbers is used to encode the variable weight, and a modified silhouette value is used as fitness function. The strategy has a generic and parametric formulation, and effectiveness is demonstrated on gene-expression data.