NON-INTRUSIVE LOAD MONITORING FOR LED LIGHT CLASSIFICATION: A DATA-DRIVEN MACHINE LEARNING APPROACH

Nguyễn Thành Công; Nguyễn Ngọc Sơn; Đào Ngọc Nam Hải; Nguyễn Huy Tình; Jonathan Andrew Ware; Nguyễn Ngọc An

doi:10.34238/tnu-jst.10115

NON-INTRUSIVE LOAD MONITORING FOR LED LIGHT CLASSIFICATION: A DATA-DRIVEN MACHINE LEARNING APPROACH

About this article

Received: 11/04/24 Revised: 10/06/24 Published: 10/06/24

Authors

1. Nguyen Thanh Cong, VNU University of Engineering and Technology
2. Nguyen Ngoc Son, VNU University of Engineering and Technology
3. Dao Ngoc Nam Hai, VNU Institute of Information Technology
4. Nguyen Huy Tinh, VNU University of Engineering and Technology
5. Jonathan Andrew Ware, University of South Wales, United Kingdom
6. Nguyen Ngoc An , VNU University of Engineering and Technology

Abstract

Monitoring the operational status of LED lights is important to achieve energy efficiency and protect user health. Recent studies employed machine learning and several parameters, such as the LED’s light output and electrical characteristics, to classify their operational status. However, under changing environmental conditions, these methods will no longer be effective, due to the compromise of the environmental noise to the input data of the models. In this study, we proposed a novel approach to identifying the operational status of household LED lights using non-intrusive load monitoring, machine learning models, confident learning, and the oscillation characteristic of the root-mean-square (RMS) current. By using the oscillation characteristics of the RMS current, we significantly reduced the number of inputs to the models and their computational hardware requirements compared to models using the RMS current. With the introduction of confident learning, we improved the prediction accuracy of the models by 2% on average. The models achieved prediction accuracy ranging from 94% to 97.5%. The proposed method shows potential in applying to different kinds of electrical devices.

Keywords

Non-intrusive load monitoring (NILM); LED operational state classification; Discrete Fourier transform; Confident Learning; Data-centric machine learning; Machine Learning

Full Text:

PDF

References

[1] M. M. A. S. Mahmoud, “Economic Applications for LED Lights in Industrial Sectors,” in Light-Emitting Diodes and Photodetectors, M. Casalino and J. Thirumalai, Eds., Rijeka: IntechOpen, 2021, doi: 10.5772/intechopen.95412.

[2] L. Ciabattoni et al., “A smart lighting system for industrial and domestic use,” in 2013 IEEE International Conference on Mechatronics, ICM 2013, Jan. 2013, pp. 126–131.

[3] N. Narendran and Y. Gu, “Life of LED-based white light sources,” Journal of Display Technology, vol. 1, pp. 167–171, Jan. 2005.

[4] K. Shahzad et al., “Comparative Life Cycle Analysis of Different Lighting Devices,” Chem Eng Trans, vol. 45, Jan. 2015, doi: 10.3303/CET1545106.

[5] M. Y. Soh, T. H. Teo, W. X. Ng, and K. S. Yeo, “Review of high efficiency integrated LED lighting,” in 2017 IEEE 12th International Conference on Power Electronics and Drive Systems (PEDS), 2017, pp. 93–97.

[6] M. M. Aman, G. B. Jasmon, H. Mokhlis, and A. H. A. Bakar, “Analysis of the performance of domestic lighting lamps,” Energy Policy, vol. 52, pp. 482–500, 2013.

[7] P. Mukherjee, “An Overview of Energy Efficient Lighting System Design for Indoor Applications of an Office Building,” Key Eng Mater, vol. 692, pp. 45–53, Jan. 2016.

[8] A. Jhunjhunwala et al., “Energy efficiency in lighting: AC vs DC LED lights,” 2016 First International Conference on Sustainable Green Buildings and Communities (SGBC), 2016, pp. 1–4.

[9] X. Zhan, W. Wang, and H. S. Chung, “A Novel Color Control Method for Multicolor LED Systems to Achieve High Color Rendering Indexes,” IEEE Trans Power Electron, vol. 33, pp. 8246–8258, 2018.

[10] C.-Y. Chen, M.-D. Ke, J.-H. Wu, and P.-J. Wu, “The Investigation on Physiological Influences and the Working Efficiencies of Several Lighting in Market,” in 2013 Ninth International Conference on Intelligent Information Hiding and Multimedia Signal Processing, 2013, pp. 96–99.

[11] T. Clark et al., “LED Luminaire Reliability: Impact of Color Shift,” Apr. 2017. [Online]. Available: https://www.energy.gov/sites/prod/files/2017/04/f34/lsrc_colorshift_apr2017.pdf [Accessed Apr. 09, 2024.]

[12] S. Uddin, H. Shareef, A. Mohamed, M. A. Hannan, and K. Mohamed, “LEDs as energy efficient lighting systems: A detail review,” in 2011 IEEE Student Conference on Research and Development, 2011, pp. 468–472.

[13] V. Gupta, B. Basak, and B. Roy, “A Fault-Detecting and Motion-Sensing Wireless Light Controller for LED Lighting System,” in 2020 IEEE Calcutta Conference (CALCON), 2020, pp. 462–466.

[14] C. Ding and T. Zhang, “Research on health monitoring of LED lighting system,” in 2016 Prognostics and System Health Management Conference (PHM-Chengdu), 2016, pp. 1–5.

[15] Y. Shang, F. Sun, Q. Fang, B. Chen, and J. Xie, “A novel fault diagnosis strategy for LED lamps via light output time-frequency characteristics analysis and machine learning,” Heliyon, vol. 9, no. 9, 2023, Art. no. e19737.

[16] A. Freddi, G. Ippoliti, M. Marcantonio, D. Marchei, A. Monteriu, and M. Pirro, “A Fault Diagnosis and prognosis LED lighting system for increasing reliability in energy efficient buildings,” in IET Conference on Control and Automation 2013: Uniting Problems and Solutions, 2013, pp. 1–6.

[17] H. Jiang, Q. Ma, F. Yang, and M. Shen, “LED device fault diagnosis base on neural network and SVM model analysis,” in 2017 14th China International Forum on Solid State Lighting: International Forum on Wide Bandgap Semiconductors China (SSLChina: IFWS), 2017, pp. 45–47.

[18] N. S. Nguyen, T. C. Nguyen, H. T. Nguyen, and N. A. Nguyen, “Determining the Operating Status of LEDs Using Non-Intrusive Load Monitoring and Machine Learning,” (in Vietnamese) in National Conference on Electronics, Communications Communications and Information Technology XXVI, REV-ECIT 2023, 2023, pp. 364–368.

[19] C. G. Northcutt, L. Jiang, and I. L. Chuang, “Confident Learning: Estimating Uncertainty in Dataset Labels,” Journal of Artificial Intelligence Research (JAIR) (2021), vol. 70, pp. 1373–1411, Oct. 2019.

[20] F. Pedregosa et al., “Scikit-learn: Machine Learning in Python,” Journal of Machine Learning Research, vol. 12, pp. 2825–2830, 2011.

[21] Y. Li, Y. Kong, M. Zhang, A. Yan, and Z. Liu, “Using Support Vector Machine (SVM) for Classification of Selectivity of H1N1 Neuraminidase Inhibitors,” Mol Inform, vol. 35, no. 3–4, pp. 116–124, Jan. 2016.

[22] L. Breiman, “Random Forests,” Mach Learn, vol. 45, no. 1, pp. 5–32, 2001.

[23] T. Chen and C. Guestrin, “XGBoost: A Scalable Tree Boosting System,” in Proceedings of the 22nd ACM SIGKDD International Conference on Knowledge Discovery and Data Mining, in KDD ’16. ACM, Aug. 2016, pp. 785–794.

[24] Z. C. Lipton, C. Elkan, and B. Naryanaswamy, “Optimal Thresholding of Classifiers to Maximize F1 Measure,” in Lecture Notes in Computer Science, Springer Berlin Heidelberg, 2014, pp. 225–239.

[25] C. E. Shannon, “Communication in the Presence of Noise,” Proceedings of the IRE, vol. 37, no. 1, pp. 10–21, 1949.

[26] I. Goodfellow, Y. Bengio, and A. Courville, Deep Learning. MIT Press, 2016.

DOI: https://doi.org/10.34238/tnu-jst.10115

Refbacks

There are currently no refbacks.



Remember me