期刊名称：Journal of Theoretical and Applied Information Technology
印刷版ISSN：1992-8645
电子版ISSN：1817-3195
出版年度：2017
卷号：95
期号：5
出版社：Journal of Theoretical and Applied
摘要：One of the most important power quality problems in power system is harmonic distortion. Due to an increase of non-linear loads as harmonic sources, the identification of harmonic loads becomes important concern in the power system. Therefore, this paper proposes a Levenberg Marquardt Backpropagation (LMBP) Neural Network to identification of harmonic load. Data of harmonic load are gathered from a low cost microcontroller with Fast Fourier Transform (FFT) method as analysis of the input current waveform in the presence of multiple devices to obtain the harmonic value. LMBP is trained using harmonic as input with combination of 14 different types of load. The performance of LMBP is implemented with several of the different training and test data to validate the accuracy and efficiency of the proposed algorithm. The results show that the proposed algorithm has high accuracy to determine the presence of loads based on their harmonic signature.
