Identifikasi dan Klasifikasi Gangguan Kualitas Daya Berbasis Transformasi Wavelet dan Radial Basis Function Neural Network (RBFNN)
DOI:
https://doi.org/10.65794/J.Electo.1.01.23-33Keywords:
Kualitas Daya, Transformator Wavelet, Jaringan Syaraf TiruanAbstract
Kualitas daya listrik merupakan aspek krusial dalam sistem tenaga listrik modern, dimana gangguan seperti voltage sag, swell, harmonisa, flicker, dan interupsi dapat berdampak negatif pada peralatan elektronik dan efisiensi sistem. Penelitian ini bertujuan untuk mengembangkan metode identifikasi dan klasifikasi gangguan kualitas daya, khususnya voltage sag dan swell, secara otomatis dan akurat menggunakan kombinasi transformasi wavelet dan Radial Basis Function Neural Network (RBFNN). Sinyal gangguan kualitas daya disimulasikan menggunakan perangkat lunak MATLAB dengan parameter yang telah ditentukan. Fitur-fitur penting dari sinyal gangguan, berupa energi pada setiap level dekomposisi, diekstraksi melalui transformasi wavelet tipe Daubechies 4 (db4). Data energi hasil ekstraksi fitur ini kemudian digunakan sebagai masukan untuk melatih dan menguji jaringan RBFNN. Hasil pengujian menunjukkan bahwa model RBFNN yang diusulkan mampu mengklasifikasikan gangguan voltage sag dan swell dengan tingkat akurasi yang tinggi. Performa klasifikasi ini ditunjukkan dengan nilai Mean Squared Error (MSE) pada data pengujian yang sangat rendah, yaitu 0.000287131 untuk sag dan 0.00028714 untuk swell. Keberhasilan ini mengindikasikan bahwa pendekatan transformasi wavelet dan RBFNN merupakan metode yang efektif dan menjanjikan untuk identifikasi dan klasifikasi gangguan kualitas daya, dengan potensi aplikasi secara real-time.
References
[1] M. M. Azizan, “Introductory Chapter: Power Quality,” Jun. 2024. doi: 10.5772/intechopen.110259.
[2] P. R. Kumar, C. Shravani, M. Rajitha, and C. L. Reddy, “A Review of Emerging Techniques for Power Quality Improvement in Renewable Energy Integration,” in E3S Web of Conferences, EDP Sciences, Feb. 2025. doi: 10.1051/e3sconf/202561603029.
[3] M. Kumar, M. A. Uqaili, Z. A. Memon, and B. Das, “Experimental Harmonics Analysis of UPS (Uninterrupted Power Supply) System and Mitigation Using Single-Phase Half-Bridge HAPF (Hybrid Active Power Filter) Based on Novel Fuzzy Logic Current Controller (FLCC) for Reference Current Extraction (RCE),” Advances in Fuzzy Systems, vol. 2022, pp. 1–18, May 2022, doi: 10.1155/2022/5466268.
[4] Y. Liu et al., “Research on Power Quality Evaluation Method for High Energy-consuming Enterprises,” in Journal of Physics: Conference Series, IOP Publishing Ltd, Mar. 2021. doi: 10.1088/1742-6596/1820/1/012005.
[5] S. Wei, D. Wenjuan, and C. Xia, “Power quality disturbances categorization using Identity Feature Vector and Extreme Learning Machine,” Intelligent Systems with Applications, vol. 24, p. 200446, Dec. 2024, doi: 10.1016/j.iswa.2024.200446.
[6] D. Prasad and C. Dhanamjayulu, “Solar PV integrated dynamic voltage restorer for enhancing the power quality under distorted grid conditions,” Electric Power Systems Research, vol. 213, p. 108746, Dec. 2022, doi: 10.1016/j.epsr.2022.108746.
[7] S. R. Das et al., “A Comprehensive Survey on Different Control Strategies and Applications of Active Power Filters for Power Quality Improvement,” Energies (Basel), vol. 14, no. 15, p. 4589, Jul. 2021, doi: 10.3390/en14154589.
[8] S. Cen, D. O. Kim, and C. G. Lim, “A fused CNN‐LSTM model using FFT with application to real‐time power quality disturbances recognition,” Energy Sci Eng, vol. 11, no. 7, pp. 2267–2280, Jul. 2023, doi: 10.1002/ese3.1450.
[9] M. S. Priyadarshini, M. Bajaj, L. Prokop, and M. Berhanu, “Perception of power quality disturbances using Fourier, Short-Time Fourier, continuous and discrete wavelet transforms,” Sci Rep, vol. 14, no. 1, p. 3443, Feb. 2024, doi: 10.1038/s41598-024-53792-9.
[10] Mayyadah Sahib Ibrahim and Ali Sachit Kaittan, “Efficient Classification of Power Quality Using Long Short-Term Memory Network Technique,” Proceedings of Engineering and Technology Innovation, vol. 29, pp. 26–46, Feb. 2025, doi: 10.46604/peti.2024.13831.
[11] N. Singh, M. A. Ansari, M. Tripathy, and V. P. Singh, “Feature Extraction and Classification Techniques for Power Quality Disturbances in Distributed Generation: A Review,” IETE J Res, vol. 69, no. 6, pp. 3836–3851, Aug. 2023, doi: 10.1080/03772063.2021.1920849.
[12] R. S. Salles and P. F. Ribeiro, “The use of deep learning and 2-D wavelet scalograms for power quality disturbances classification,” Electric Power Systems Research, vol. 214, p. 108834, Jan. 2023, doi: 10.1016/j.epsr.2022.108834.
[13] P. Ghelasi and F. Ziel, “From day-ahead to mid and long-term horizons with econometric electricity price forecasting models,” Renewable and Sustainable Energy Reviews, vol. 217, p. 115684, Jul. 2025, doi: 10.1016/j.rser.2025.115684.
[14] V. Wahyuningrum, “Penerapan radial basis function neural network dalam pengklasifikasian daerah tertinggal di indonesia,” Jurnal Aplikasi Statistika & Komputasi Statistik, vol. 12, no. 1, p. 37, Jun. 2020, doi: 10.34123/jurnalasks.v12i1.250.
[15] Q. Wang, X. Liang, and S. Qin, “Research on power quality disturbance analysis and identification based on LSTM,” Energy Reports, vol. 8, pp. 709–718, Nov. 2022, doi: 10.1016/j.egyr.2022.09.170
Downloads
Published
How to Cite
Issue
Section
License
Copyright (c) 2025 Nurhalim Dani Ali, Fera Gustia Handayani, Antonius Rajagukguk, Iswadi Hasyim Rosma, Edy Ervianto
This work is licensed under a Creative Commons Attribution-NonCommercial 4.0 International License.
