Sistem Prediksi Biaya Bulanan Peralatan Elektronik di Rumah Berdasarkan Kebiasaan Pengguna Menggunakan Algoritma LSTM
DOI:
https://doi.org/10.65794/J.Electo.1.02.90-100Keywords:
konsumsi energi harian, LSTM, Node-RED, prediksi biaya listrik, smartplugAbstract
Konsumsi energi listrik rumah tangga yang tidak terpantau dapat menyebabkan pemborosan energi dan lonjakan biaya. Penelitian ini mengembangkan sistem prediksi biaya listrik bulanan berbasis algoritma Long Short-Term Memory (LSTM) menggunakan data real-time dari perangkat elektronik rumah tangga. Sistem memanfaatkan smartplug untuk merekam konsumsi daya per menit dan Node-RED sebagai platform visualisasi. Data melalui tahapan pre-processing, pembentukan time-series, pelatihan model, dan evaluasi menggunakan Mean Absolute Error (MAE) dan Root Mean Squared Error (RMSE). Hasil menunjukkan model LSTM mencapai akurasi 94,5% pada epoch ke-40 dengan RMSE 19.537,10 dan MAE 18.690,79. Sistem terintegrasi dalam dashboard Node-RED yang menyajikan visualisasi histori dan prediksi otomatis, membuktikan efektivitas pendekatan LSTM dalam membantu pengguna mengelola konsumsi energi rumah tangga.
References
[1] R. Abid, N. Javaid, U. Qasim, A. Ahmad, and Z. A. Khan, "A comprehensive review of energy management in smart homes," Journal of King Saud University - Computer and Information Sciences, vol. 34, no. 6, pp. 2500–2520, 2022.
[2] M. Susantok, F. Ahmad Po’ad, A. Joret, and M. Hilwa Salsabillah, “Natural smart home automation system using LSTM based on household behaviour,” Indonesian Journal of Electrical Engineering and Computer Science, vol. 37, no. 2, p. 758, Feb. 2025, doi: 10.11591/ijeecs.v37.i2.pp758-770.
[3] Y. Zhang, Q. Chen, and T. Gan, “Deep learning-based residential load forecasting: A review,” Renewable and Sustainable Energy Reviews, vol. 149, 2021.
[4] H. A. Rochman, R. Primananda, and H. Nurwasito, “Sistem kendali berbasis mikrokontroler menggunakan protokol MQTT pada smarthome,” Jurnal Teknologi Informasi dan Ilmu Komputer, vol. 1, no. 6, 2017.
[5] W. Kong, Z. Y. Dong, Y. Jia, D. J. Hill, Y. Xu, and Y. Zhang, "Short-term residential load forecasting based on LSTM recurrent neural network," IEEE Transactions on Smart Grid, vol. 10, no. 1, pp. 841–851, 2019.
[6] A. Gensler, J. Henze, B. Sick, and N. Raabe, "Deep learning for solar power forecasting—An approach using AutoEncoder and LSTM neural networks," in Proc. IEEE International Conference on Systems, Man, and Cybernetics (SMC), 2016, pp. 002858–002865.
[7] S. Hochreiter and J. Schmidhuber, "Long short-term memory," Neural Computation, vol. 9, no. 8, pp. 1735–1780, 1997.
[8] M. I. Maulana and M. A. Muslim, “Sistem prediksi tagihan listrik usaha jasa laundry menggunakan jaringan syaraf tiruan backpropagation,” UNNES Journal of Mathematics, vol. 4, no. 1, 2015. [Online]. Available: http://journal.unnes.ac.id/sju/index.php/ujm
[9] M. Rahman, “Prediksi pembayaran tagihan listrik menggunakan model artificial neural network,” Jurnal Mahasiswa Teknik Informatika, vol. 7, no. 5, 2023.
[10] S. Sutialisna, N. Sabrina, and H. Ashaury, “Prediksi tagihan listrik menggunakan metode weighted exponential moving average (WEMA),” Jurnal Mahasiswa Teknik Informatika, vol. 7, no. 5, 2023.
[11] I. Nyoman, K. Wardana, N. Jawas, I. Komang, and A. A. Aryanto, “Prediksi penggunaan energi listrik pada rumah hunian menggunakan long short-term memory,” TIERS Information Technology Journal, vol. 1, no. 1, 2020. [Online]. Available: http://journal.undiknas.ac.id/index.php/tiers
[12] C. Zhang, X. Tian, Y. Zhao, and J. Lu, “Automated machine learning-based building energy load prediction method,” Journal of Building Engineering, vol. 80, 2023. [Online]. Available: https://doi.org/10.1016/j.jobe.2023.108071
[13] J. Zheng, C. Xu, Z. Zhang, and X. Li, “Electric load forecasting in smart grids using long short-term memory networks,” IEEE PES General Meeting, 2017.
[14] A. Marino, L. Amarasinghe, and M. Manic, “Building energy load forecasting using deep neural networks,” IEEE Industrial Electronics Magazine, vol. 13, no. 3, pp. 34–43, 2019.
[15] J. Wang, Y. Wang, and X. Zhang, “Short-term electricity load forecasting using hybrid LSTM and CNN models,” Applied Energy, vol. 273, 2020.
[16] H. Eslava, L. A. Rojas, and R. Pereira, “Implementation of machine-to-machine solutions using MQTT protocol in internet of things (IoT) environment to improve automation process for electrical distribution substations in Colombia,” Journal of Power and Energy Engineering, vol. 3, no. 4, pp. 92–96, 2015. [Online]. Available: https://doi.org/10.4236/jpee.2015.34014
[17] S. Mulyono, M. Qomaruddin, and M. S. Anwar, “Penggunaan Node-RED pada sistem monitoring dan kontrol green house berbasis protokol MQTT,” Jurnal Transistor Elektro dan Informatika, vol. 3, no. 1, 2018.
[18] S. B. Taieb, G. Bontempi, A. F. Atiya, and A. Sorjamaa, "A review and comparison of strategies for multi-step ahead time series forecasting based on the NN5 forecasting competition," Expert Systems with Applications, vol. 39, no. 8, pp. 7067–7083, 2012.
[19] M. H. Rafiei and H. Adeli, “A novel machine learning model for electricity load forecasting,” Energy, vol. 198, 2020.
Downloads
Published
How to Cite
Issue
Section
License
Copyright (c) 2025 Muhammad Fajar, Mochamad Susantok
This work is licensed under a Creative Commons Attribution-NonCommercial 4.0 International License.
