WEBREVIEW

Artificial Neural Network for Real Time Load Flow Calculation:Application to a Micro Grid with Wind Generators .

Francois B., Hadj Abdallah H., Krichen L. — 2011-03-14T09:35:01Z

This work presents a method for solving the problem of load flow in electric power
systems including a wind power station with asynchronous generators. For this type
of power station, the generated active power is only known and consequently the
absorbed reactive power must be determined. So we have used the circular diagram
at each iteration and by considering this node as a consuming node in the load flow
program. Since the wind speed is not constant, the generated power is neither (...)

- Volume 01 issue 03 / Artificial neural networks, Electrical supply networks, Load flow, Microgrid, Circular power diagram, Wind generator

Modélisation, commande et interaction de deux éoliennes à vitesse variable

Francois B., Krichen L. , Ouali A. — 2008-02-10T10:11:05Z

Dans ce papier, on s'intéresse à la modélisation, la commande et l'interaction de deux aérogénérateurs à base de machine asynchrone à cage couplés au réseau au travers de convertisseurs statiques. Tout d'abord, nous avons simulé la chaîne de conversion d'une seule éolienne en adoptant le modèle continu équivalent des convertisseurs. Pour contrôler la tension du bus continu et les échanges de puissances active et réactive, nous avons implanté des correcteurs de type proportionnel intégral. Ensuite, nous avons (...)

- Numéro 02 / Aérogénérateur, Convertisseur mli, Interaction, Contrôle, Transfert de puissances

Solving Harmonics Elimination Problem in Voltage-controlled Three Phase Inverter using Artificial Neural Networks

Berkouk M., Bouhali O., Francois B. — 2007-01-31T13:51:43Z

A novel concept of application of Artificial Neural Networks ( ANN) for generating the optimum switching functions for the voltage and harmonic control of DC-to-AC bridge inverters is presented. In many research, the neural network is trained off line using the desired switching angles given by the classic harmonic elimination strategy to any value of the modulation index. This limits the
utilisability and the precision in other modulation index values. In order to avoid this problem, a new training algorithm is developed without using the desired switching angles but it uses the desired solution of the elimination harmonic equation, i.e. first harmonics are equal to zero. Theoretical analysis of the proposed solving algorithm with neural networks is provided, and simulation results are given to show the high performance and technical advantages of the developed modulator.