Power Quality
A. ِDeihimi; A. Rahmani
Abstract
An intelligent method based on wavelet neural network (WNN) is presented in this study to estimate voltage harmonic distortion waveforms at a non-monitored sensitive load. Voltage harmonics are considered as the main type of waveform distortion in the power quality approach. To detect and analyze voltage ...
Read More
An intelligent method based on wavelet neural network (WNN) is presented in this study to estimate voltage harmonic distortion waveforms at a non-monitored sensitive load. Voltage harmonics are considered as the main type of waveform distortion in the power quality approach. To detect and analyze voltage harmonics, it is not economical to install power quality monitors (PQMs) at all buses. The cost associated with the monitoring procedure can be reduced by optimizing the number of PQMs to be installed. The main aim of this paper is to further reduce the number of PQMs through recently proposed optimum allocation approaches. An estimator based on WNN is presented in this study to estimate voltage-harmonic waveforms at a non-monitored sensitive load using current and voltage at a monitored location. Since capacitors and distributed generations (DGs) have a special role in distribution networks, they are considered in this paper and their effects on the harmonic voltage waveform estimator are evaluated. The proposed technique is examined on the IEEE 37-bus network. Results indicate the acceptable high accuracy of the WNN estimator.
