Prediksi Intensitas Cahaya Berbasis Interpolasi Newton pada Edge IoT ESP32
Abstract
Intensitas cahaya merupakan parameter penting pada sistem monitoring berbasis Internet of Things (IoT) yang memerlukan estimasi cepat dan stabil di sisi edge. Penelitian ini mengembangkan sistem prediksi intensitas cahaya berbasis ESP32 dengan menerapkan interpolasi polinomial Newton lokal pada data sensor LDR, dengan BH1750 sebagai pembanding. Data ADC diproses menggunakan median filter dan moving average, kemudian dikonversi ke intensitas cahaya melalui empat titik kalibrasi terdekat dari 16 titik kalibrasi. Hasil pengolahan ditampilkan pada dashboard web responsif yang dapat diakses melalui perangkat seluler. Pengujian menunjukkan bahwa keluaran LDR Newton mengikuti pembacaan BH1750 pada kondisi intensitas rendah, menengah, dan tinggi. Evaluasi error yang dihitung langsung pada ESP32 menghasilkan MAE 0.04 lux, RMSE 0.05 lux, dan MAPE 0.93%. Hasil ini menunjukkan bahwa interpolasi Newton lokal layak digunakan sebagai metode numerik ringan untuk prediksi intensitas cahaya secara real-time pada sistem edge IoT berbasis ESP32.
Downloads
References
[2] M. Syahril and H. Sulistiani, “Implementation of the GY-302 BH1750 Sensor for Adjusting Light Intensity in Hydroponic Lettuce and Mustard Plants Implementasi Sensor GY-302 BH1750 untuk Penyesuaian Intensitas Cahaya pada Tanaman Selada dan Sawi Hidroponik,” vol. 5, no. October, pp. 1490–1497, 2025.
[3] J. Khairina and M. Fikry, “Development of an IoT-Based Smart Greenhouse with Fuzzy Logic for Chrysanthemum Cultivation,” vol. 9, no. 5, pp. 2220–2229, 2025.
[4] A. M. Hugo et al., “IoT-Based Monitoring System Applied to Aeroponics Greenhouse,” 2022.
[5] W. Nramat, E. Songkroh, P. Boonma, W. Traiphat, and E. Martwong, “Implementation of a Wireless Sensor Network for Agro-Environmental Monitoring and Growing Degree Day-Based Rice Growth Assessment,” pp. 1–18, 2026.
[6] J. A. Nava-pintor et al., “Development and Evaluation of Solar Radiation Sensor Using Cost-Effective Light Sensors and Machine Learning Techniques,” pp. 1–31, 2025.
[7] L.-M. Shih, H.-L. Tsai, and C.-Y. Tsai, “Design and Evaluation of Wireless DYU Air Box for Environment-Monitoring IoT System on Da-Yeh University Campus,” Appl. Sci., vol. 14, no. 5, p. 2201, 2024.
[8] T. S. Kalaivani, T. Kamireddy, and S. Govindakumar, “IoT-Enabled Soil and Crop Monitoring System Using Low-Cost Smart Sensors for Precision Agriculture,” Eng. Proc., vol. 118, no. 1, p. 77, 2025.
[9] J. A. Nava-Pintor, “Development and Evaluation of Solar Radiation Sensor Using Cost-Effective Light Sensors and Machine Learning Techniques,” Technologies, vol. 13, no. 5, p. 182, 2025.
[10] U. Guloglu, S. Baghaee, E. Uysal, and E. Engineering, “Evaluation of Age Control Protocol ( ACP ) and ACP + on ESP32”.
[11] J. Palomeque-gonzalez, “A Modular , Low-Cost IoT System for Environmental and Behavioural Monitoring in Cultural Heritage Sites,” 1895.
[12] M. Hutagalung, Y. Gamaliel, N. P. Manullang, T. A. Nugroho, and D. Angela, “Development of Low-Power IOT Devices with Edge Machine Learning on ESP32-S3-Cam for Early Detection of Rice Diseases : Supporting Agricultural Efficiency,” vol. 5, no. 03, pp. 454–464, 2026.
[13] I. M. A. Journal et al., “Multivariate Newton interpolation in downward closed spaces reaches the optimal Bernstein – Walsh approximation rate,” pp. 1–30, 2026.
[14] Y. Cheng, H. Zhang, J. Xing, and Z. Xiao, “An improved two-beat deadbeat synchronous predictive current control strategy for MMC based on Newton interpolation method,” no. April, pp. 1–14, 2024, doi: 10.3389/fenrg.2024.1385029.
[15] J. Bieber and M. Beitelschmidt, “Computationally efficient implementation of the Gauss – Newton method for solving the forward kinematics of redundant cable-driven parallel robots,” no. August, pp. 1–8, 2023, doi: 10.1002/pamm.202300231.
An author who publishes in the Jurnal Teknik Elektro (JTE) agrees to the following terms:
Author retains the copyright and grants the journal the right of first publication of the work simultaneously licensed under the Creative Commons Attribution-ShareAlike 4.0 License that allows others to share the work with an acknowledgement of the work's authorship and initial publication in this journal.
Submission of a manuscript implies that the submitted work has not been published before (except as part of a thesis, report, or abstract); that it is not under consideration for publication elsewhere; that its publication has been approved by all co-authors. If and when the manuscript is accepted for publication, the author(s) still hold the copyright and retain publishing rights without restrictions. For the new invention, authors are suggested to manage its patent before publication. The license type is CC-BY-SA 4.0.
Jurnal Teknik Elektro (JTE)is licensed under a Creative Commons Attribution-ShareAlike 4.0 International License.
.jpg)
