Long Short-Term Memory untuk Prediksi Beban Listrik Jangka Pendek pada Lini Produksi Manufaktur
DOI:
https://doi.org/10.31294/imtechno.v7i2.13268Keywords:
peramalan beban listrik, LSTM, lini produksi, deep learning, manajemen energiAbstract
Pengelolaan energi listrik pada lini produksi merupakan faktor penting dalam efisiensi biaya operasional dan keberlanjutan industri manufaktur. Beban listrik lini produksi bersifat nonlinier dan fluktuatif karena dipengaruhi pola operasi sif, jadwal produksi, dan perilaku mesin, sehingga sulit diprediksi menggunakan metode statistik konvensional. Penelitian ini menerapkan model deep learning Long Short-Term Memory (LSTM) untuk peramalan beban listrik jangka pendek satu jam ke depan. Data yang digunakan adalah dataset publik ElectricityLoadDiagrams (Trindade, 2015) dari UCI Machine Learning Repository versi agregasi per jam yang memuat 321 pelanggan selama 2012-2014; satu pelanggan dengan profil industri dan autokorelasi harian tinggi (0,984) dipilih sebagai representasi beban lini produksi. Data diproses melalui pembersihan, standardisasi Z-score, penambahan fitur kalender, dan pembentukan sliding window 24 jam. Model LSTM dilatih menggunakan algoritma Adam dan dibandingkan dengan ARIMA serta Multilayer Perceptron (MLP). Hasil pengujian pada 3.946 titik data menunjukkan model LSTM memberikan akurasi terbaik dengan MAPE 6,83%, lebih rendah dibanding ARIMA (7,31%) dan MLP (10,07%), serta koefisien korelasi 0,99 terhadap data aktual. Temuan ini menunjukkan LSTM mampu menangkap ketergantungan temporal beban listrik sehingga dapat mendukung perencanaan produksi, penjadwalan beban, dan efisiensi energi dalam manajemen industri.
References
Bouktif, S., Fiaz, A., Ouni, A., & Serhani, M. A. (2018). Optimal deep learning LSTM model for electric load forecasting using feature selection and genetic algorithm: Comparison with machine learning approaches. Energies, 11(7), 1636. https://doi.org/10.3390/en11071636
Box, G. E. P., Jenkins, G. M., Reinsel, G. C., & Ljung, G. M. (2015). Time series analysis: Forecasting and control (5th ed.). Hoboken, NJ: John Wiley & Sons.
Gers, F. A., Schmidhuber, J., & Cummins, F. (2000). Learning to forget: Continual prediction with LSTM. Neural Computation, 12(10), 2451-2471. https://doi.org/10.1162/089976600300015015
Goodfellow, I., Bengio, Y., & Courville, A. (2016). Deep learning. Cambridge, MA: MIT Press.
Hochreiter, S., & Schmidhuber, J. (1997). Long short-term memory. Neural Computation, 9(8), 1735-1780. https://doi.org/10.1162/neco.1997.9.8.1735
Hyndman, R. J., & Athanasopoulos, G. (2018). Forecasting: Principles and practice (2nd ed.). Melbourne: OTexts.
Kingma, D. P., & Ba, J. (2015). Adam: A method for stochastic optimization. In Proceedings of the 3rd International Conference on Learning Representations (ICLR). https://doi.org/10.48550/arXiv.1412.6980
Kong, W., Dong, Z. Y., Jia, Y., Hill, D. J., Xu, Y., & Zhang, Y. (2019). Short-term residential load forecasting based on LSTM recurrent neural network. IEEE Transactions on Smart Grid, 10(1), 841-851. https://doi.org/10.1109/TSG.2017.2753802
LeCun, Y., Bengio, Y., & Hinton, G. (2015). Deep learning. Nature, 521(7553), 436-444. https://doi.org/10.1038/nature14539
Marino, D. L., Amarasinghe, K., & Manic, M. (2016). Building energy load forecasting using deep neural networks. In Proceedings of the 42nd Annual Conference of the IEEE Industrial Electronics Society (IECON) (pp. 7046-7051). https://doi.org/10.1109/IECON.2016.7793413
Rumelhart, D. E., Hinton, G. E., & Williams, R. J. (1986). Learning representations by back-propagating errors. Nature, 323(6088), 533-536. https://doi.org/10.1038/323533a0
Siami-Namini, S., Tavakoli, N., & Siami Namin, A. (2018). A comparison of ARIMA and LSTM in forecasting time series. In Proceedings of the 17th IEEE International Conference on Machine Learning and Applications (ICMLA) (pp. 1394-1401). https://doi.org/10.1109/ICMLA.2018.00227
Trindade, A. (2015). ElectricityLoadDiagrams20112014 [Data set]. UCI Machine Learning Repository. https://doi.org/10.24432/C58C86
Wang, Y., Chen, J., Chen, X., Zeng, X., Kong, Y., Sun, S., Guo, Y., & Liu, Y. (2021). Short-term load forecasting for industrial customers based on TCN-LightGBM. IEEE Transactions on Power Systems, 36(3), 1984-1997. https://doi.org/10.1109/TPWRS.2020.
Han, J., & Kamber, M. (2006). Data Mining: Concepts and Techniques. Soft Computing (Vol. 54). https://doi.org/10.1007/978-3-642-
19721-5
Liza, Y., & Yupinti. (2012). Sistem Informasi persediaan barang pada PT.Surya Nusa Bhaktindo Bengkulu. Media Infotama, 8(1), 90–117.
Marcoulides, G. a. (2005). Discovering Knowledge in Data: an Introduction to Data Mining:Discovering Knowledge in Data: An Introduction to Data Mining. Journal of the American Statistical Association (Vol. 100). https://doi.org/10.1198/jasa.2005.s61
Downloads
Published
Issue
Section
License
Copyright (c) 2026 Martias Martias, sri watmah, Rian Septian Anwar (Author)
This work is licensed under a Creative Commons Attribution-ShareAlike 4.0 International License.
