APPLICATION OF METHODOLOGY FOR DATA COMPRESSION AND REDUCTION OF BIG DATA GENERATED IN MONITORING SYSTEMS
Keywords:
Discrete Wavelet Transform, zero crossings, electrical signalsAbstract
DOI: https://doi.org/10.46296/ig.v8i15.0252
The exponential growth of Big Data in electrical monitoring systems has created the need to develop efficient methodologies for data compression and storage optimization. In this study, the Discrete Wavelet Transform (DWT) is implemented to reduce the redundancy of electrical signals while preserving relevant information for fault analysis. The results show that DWT-based compression achieves a 60% reduction in data size without compromising signal quality, with a Normalized Mean Squared Error (NMSE) below 0.05 and a Correlation Coefficient (CORR) above 0.98. Additionally, combining DWT with sparse representation improves computational efficiency by 45%, significantly reducing processing times in LSTM neural networks used for fault prediction. The analysis of zero crossings and noise removal using adaptive filters optimizes transient detection, enhancing fault localization accuracy in electrical systems. These findings demonstrate that integrating advanced compression techniques enables more efficient storage, allowing for faster analysis in real-time monitoring environments and optimizing resource utilization in power networks.
Keywords: Discrete Wavelet Transform, zero crossings, electrical signals.
References
Bhavik R. Bakshi. (2020). Wiley Encyclopedia of Electrical and Electronics Engineering. 13, 1–12. https://www.researchgate.net/publication/2816208_Multiscale_Analysis_And_Modeling_Using_Wavelets
Cruz, L., Carrión, D., & Riofrio, A. (2017). Localización de Fallas Mediante la Transformada Wavelet en Líneas de Transmisión. Revista Técnica “Energía”, 13(1). https://doi.org/10.37116/REVISTAENERGIA.V13.N1.2017.10
Daubechies, I. (1992). Ten Lectures on Wavelets. Ten Lectures on Wavelets. https://doi.org/10.1137/1.9781611970104
Dr. Sergio M. Ramírez Campos, M. Cj. G. F. C. Ing. M. I. A. G. Ing. J. F. M. M. A. A. L. R. J. (2024). Diseño y Aplicación de un Algoritmo Colonia de Hormigas en un Caso Real de Balanceo de Líneas de Ensamble con Subprocesos Mutuamente Excluyentes. 18, 1–15. https://static1.squarespace.com/static/55564587e4b0d1d3fb1eda6b/t/65eb698dcc28f63adafd960d/1709926797326/Ramirez_Campos+--+II2024+--+1-15.pdf
Emmanuel J. Espejo, & Marcelo Gustavo Molina. (2016). Modelado y Evaluación de Sistemas Eléctricos Híbridos Que Combinan Sistemas Fotovoltaicos y Eólicos Conectados a la Red. World Energy Perspective Renewable Intergration, september 2016, 140. https://www.researchgate.net/publication/317193562_MODELADO_Y_EVALUACION_DE_SISTEMAS_ELECTRICOS_HIBRIDOS_QUE_COMBINAN_SISTEMAS_FOTOVOLTAICOS_Y_EOLICOS_CONECTADOS_A_LA_RED
Faheem Mushtaq, M., Akram, U., Aamir, M., Ali, H., & Zulqarnain, M. (2019). Neural Network Techniques for Time Series Prediction: A Review. 3, 2–10. https://www.researchgate.net/publication/335107160_Neural_Network_Techniques_for_Time_Series_Prediction_A_Review/fulltext/5da2398245851553ff8c23b8/Neural-Network-Techniques-for-Time-Series-Prediction-A-Review.pdf
José de Jesús, R., José Alberto, H.-A., Francisco Jacob, Á.-C., Juan Manuel, S.-C., & Adolfo, M.-R. (2016). Neuronales Sensor System Based in Neural Networks for the Environmental Monitoring. 17, 211–222. https://www.redalyc.org/pdf/404/40445803006.pdf
L. Cruz, D. Carrión, & A. Riofrio. (2016). Vista de Localización de Fallas Mediante la Transformada Wavelet en Líneas de Transmisión. 13, 79–89. https://revistaenergia.cenace.gob.ec/index.php/cenace/article/view/10/9
Learnig Statis. (2024). ¿Qué es el cruce por cero? Comprender el comportamiento de las señales. https://es.statisticseasily.com/glossario/what-is-zero-crossing-in-signal-analysis/?utm_source=chatgpt.com
Li, T., Zhao, Z., Sun, C., Cheng, L., Chen, X., Yan, R., & Gao, R. X. (2022). WaveletKernelNet: An Interpretable Deep Neural Network for Industrial Intelligent Diagnosis. IEEE Transactions on Systems, Man, and Cybernetics: Systems, 52(4), 10–15. https://doi.org/10.1109/TSMC.2020.3048950
Luis Rubén Cruz Andaluz. (2016). Aplicación de la Transformada de Wavelet Para Ubicación de Fallas En Sistemas Eléctricos de Potencia [Ivestigación, Universidad Politecnica Saleciana]. https://dspace.ups.edu.ec/bitstream/123456789/12873/3/UPS-KT01292.pdf
LUNA, M., STALLER, A., HARNISTH, K., ECHEVERRÍA, D., CASTRO, R., & PORTILLA, Ó. (2019). Análisis de la serie temporal de la estción de monitoreo continuo CUEC - REGME. Revista Geoespacial, 15(2), 127. https://doi.org/10.24133/GEOESPACIAL.V15I2.1281
Mercado Polo, D., Pedraza Caballero, L., & Martínez Gómez, E. (2015). Comparación de Redes Neuronales aplicadas a la predicción de Series de Tiempo. Prospectiva, 13(2), 88. https://doi.org/10.15665/rp.v13i2.491
Morales-Oñate, V., Moreta, L., Morales-Oñate, B., Morales-Oñate, V., Moreta, L., & Morales-Oñate, B. (2020). ALGORITMO DE BALANCEO DE DATOS MIXTOS PARA BIG DATA EN R. Perfiles, 1(24), 20–26. https://doi.org/10.47187/PERF.V1I24.75
Wang, Z., & Bovik, A. C. (2002). A universal image quality index. IEEE Signal Processing Letters, 9(3), 81–84. https://doi.org/10.1109/97.995823
Published
How to Cite
Issue
Section
License
Copyright (c) 2025 Scientific Journal INGENIAR: Engineering, Technology and Research
This work is licensed under a Creative Commons Attribution-NonCommercial-ShareAlike 4.0 International License.
