Mejora del perfil de voltaje en sistemas de transmisión mediante óptima ubicación de compensador en serie sincrónico estático (SSSC) a través de redes neuronales artificiales

Abstract

The objective of this paper is to optimally implement a static synchronous series compensator (SSSC), for which an algorithm based on artificial neural networks is used. The aim is to improve the voltage profile, thus obtaining reliability of electrical energy emitted in any IEEE busbar system. The training of the neural network is carried out in Matlab software, in which an algorithm capable of providing solutions to future variations in the model of 14 IEEE busbars is performed. The input data of the neural network is obtained by including loads, in all its transmission bars, which are in a range of 10 to 50. Each variation provides data of voltage profile, power flow in the transmission lines, active and reactive power in the busbars, as well as its corresponding power factor. The output data of the neural network is derived from the implementation of an exhaustive search, in which a 10 MVA SSSC compensator is incorporated to each load variation in the transmission lines. By implementing the 10 MVA SSSC compensator to the transmission line 13-14, the power flow present in the transmission line 9-14 and 13-14 is redistributed, improving the voltage profile in 3 bars of the system, such location provides the artificial neural network. The percentage of error presented by the analysis of the algorithm is in the range of -4% to 4%, which determines the efficiency and accuracy of the network, in the face of unknown data.