Penerapan Long Short Term Memory untuk Peramalan Beban Listrik pada Gedung Bertingkat
Application of Long Short-Term Memory for Electric Load Forecasting in Buildings
DOI:
https://doi.org/10.37338/elti.v7i2.540Keywords:
Long – Short Term Memory , Peramalan Beban , Jaringan Syaraf Tiruan, Manajemen EnergiAbstract
In electric power operations, the use of energy often leads to decreased energy efficiency. Some of the main causes of power load instability are due to sudden changes or shifts, which cause the fluctuation of electrical energy to become imbalanced. If this instability persists over a long period, it poses a risk to the electrical system and can damage components. To prevent this, a load forecasting method is employed to determine the loading for a specific period. Electric energy forecasting is frequently used to determine the loading parameters that will occur in the future. This is done to maintain the quality of the electric power and ensure adequate energy supply. To provide accurate electric energy forecasting, several methods are often used, one of which is the artificial neural network (ANN). An ANN can use parameters not only derived from electrical measurements and main loading but also allows for non-linear computations. There are several ANN methods, one of which is Long Short-Term Memory (LSTM). Long Short-Term Memory is used when the input parameters are non-linear or uncorrelated. Therefore, to obtain maximum forecasting results, electric energy forecasting using Long Short-Term Memory was employed for a high-rise building. The research results then showed that a learning rate of 0.1 yielded an MAPE (Mean Absolute Percentage Error) of 6.41% and an RMSE (Root Mean Square Error) of 9.4.
References
N. Abu-Shikhah and F. Elkarmi, “Medium-term electric load forecasting using singular value decomposition,” Energy, vol. 36, no. 7, pp. 4259–4271, Jul. 2011, doi: 10.1016/j.energy.2011.04.017.
A. Carlon, L. Espath, and R. Tempone, “Efficient Stochastic BFGS methods Inspired by Bayesian Principles,” Jul. 10, 2025, arXiv: arXiv:2507.07729. doi: 10.48550/arXiv.2507.07729.
G. A. Bahadirov, A. B. Gulmatov, B. T. Umarov, and O. T. Mirzayev, “Eco-efficient conveyer belt loading methods. A classification approach for minimizing energy consumption,” E3S Web Conf., vol. 614, p. 01004, 2025, doi: 10.1051/e3sconf/202561401004.
R. V. Klyuev et al., “Methods of Forecasting Electric Energy Consumption: A Literature Review,” Energies, vol. 15, no. 23, p. 8919, Nov. 2022, doi: 10.3390/en15238919.
M. Ghiassi, D. K. Zimbra, and H. Saidane, “Medium term system load forecasting with a dynamic artificial neural network model,” Electric Power Systems Research, vol. 76, no. 5, pp. 302–316, Mar. 2006, doi: 10.1016/j.epsr.2005.06.010.
P. Bunnoon, K. Chalermyanont, and C. Limsakul, “Mid-Term Load Forecasting: Level Suitably of Wavelet and Neural Network based on Factor Selection,” Energy Procedia, vol. 14, pp. 438–444, 2012, doi: 10.1016/j.egypro.2011.12.955.
M. Massaoudi et al., “An Effective Hybrid NARX-LSTM Model for Point and Interval PV Power Forecasting,” IEEE Access, vol. 9, pp. 36571–36588, 2021, doi: 10.1109/ACCESS.2021.3062776.
N. AL-Rousan and H. Al-Najjar, “A Comparative Assessment of Time Series Forecasting Using NARX and SARIMA to Predict Hourly, Daily, and Monthly Global Solar Radiation Based on Short-Term Dataset,” Arab J Sci Eng, vol. 46, no. 9, pp. 8827–8848, Sep. 2021, doi: 10.1007/s13369-021-05669-6.
M. A. Elhamid, C. Yacine, and B. Tahar, “Two improved nonlinear conjugate gradient methods with application in conditional model regression function,” JIMO, vol. 21, no. 1, pp. 658–675, 2025, doi: 10.3934/jimo.2024098.
S. Abdal, T. Taha, N. A. Shah, and S.-J. Yook, “Novel investigation of burger fluid with gyrotactic microorganisms over a sheet using levenberg marquardt back propagations (LMBP),” Alexandria Engineering Journal, vol. 117, pp. 403–417, Apr. 2025, doi: 10.1016/j.aej.2025.01.014.
C. Chen et al., “Forecast of rainfall distribution based on fixed sliding window long short-term memory,” Engineering Applications of Computational Fluid Mechanics, vol. 16, no. 1, pp. 248–261, Dec. 2022, doi: 10.1080/19942060.2021.2009374.
J. Moon, Y. Kim, M. Son, and E. Hwang, “Hybrid Short-Term Load Forecasting Scheme Using Random Forest and Multilayer Perceptron,” Energies, vol. 11, no. 12, p. 3283, Nov. 2018, doi: 10.3390/en11123283.
L. Zhang, L. Yang, C. Gu, and D. Li, “LSTM-based Short-term Electrical Load Forecasting and Anomaly Correction,” E3S Web Conf., vol. 182, p. 01004, 2020, doi: 10.1051/e3sconf/202018201004.
Downloads
Published
Issue
Section
License
Copyright (c) 2025 Ony Ramadhan Armanto, Masyitah, Aulidina Dwi Nur Andriyanti
This work is licensed under a Creative Commons Attribution-NonCommercial 4.0 International License.
