Prediction of Peak Load Electricity Consumption in Apartment X Building Using Deep Learning with GRU Method
DOI:
https://doi.org/10.59097/jasae.v4i1.81Keywords:
RNN, GRU, Time Series, Electricity consumption, ForecastingAbstract
This study presents a predictive framework for daily electricity consumption forecasting in Apartment X using a Recurrent Neural Network (RNN) model with the Gated Recurrent Unit (GRU) method. The dataset consists of daily electricity log sheets containing two main variables: Peak Load Time (WBP) and Off-Peak Load Time (LWBP). The preprocessing stage includes data cleaning, normalization using Min–Max Scaling, and sequence formation through a sliding window approach. The GRU architecture comprises two hidden layers, a dropout layer, and optimization using the Adam optimizer. The model’s performance was evaluated using MAE, RMSE, and R². The results show that the GRU model achieved an R² value of 0.623, indicating a good capability in capturing consumption patterns. This study contributes to energy forecasting studies in developing countries, emphasizing smart building energy management applications
References
International Energy Agency (IEA), Global Status Report for Buildings and Construction: Towards a Zero-emission, Efficient and Resilient Buildings and Construction Sector, 2019.
A. Ahmad, M. R. Khan, and S. Rahman, “Short-term electricity load forecasting using Random Forest and Bi-LSTM: A hybrid approach,” Energies, vol. 14, no. 2, pp. 1–15, 2021.
Z. Chen, Y. Xu, and L. Wang, “Convolutional neural network–gated recurrent unit for household load forecasting,” IEEE Access, vol. 8, pp. 123–134, 2020.
H. Yang and J. Li, “Enhancing LSTM for short-term load forecasting with attention mechanism,” Applied Energy, vol. 268, pp. 114–124, 2020.
M. Ghofrani, “Comparison of RNN, LSTM, and GRU models for electricity load forecasting in Turkey,” International Journal of Electrical Power & Energy Systems, vol. 117, pp. 105–118, 2020.
H. Ibrahim, K. Ahmed, and A. Al-Samarraie, “Forecasting electricity outages using GRU and RNN models: A case study of Baghdad,” Energy Reports, vol. 7, pp. 567–576, 2021.
W. Ferdoush, T. Saha, and K. M. Rahman, “An ensemble deep learning model for building energy consumption forecasting,” Energy and Buildings, vol. 228, pp. 110–119, 2021.
J. Yu and X. Li, “A stacked ensemble learning framework for electricity demand forecasting using GRU, SVR, RF, and GBDT,” IEEE Transactions on Smart Grid, vol. 11, no. 4, pp. 3209–3219, 2020.
A. Kumar, P. Singh, and R. Jain, “Probabilistic load forecasting using CNN–GRU and Mixture Density Networks,” Electric Power Systems Research, vol. 190, pp. 106–118, 2021.
Y. Liu, Q. Zhang, and M. Zhou, “Electricity load forecasting by combining dynamic time warping and LSTM,” Energy, vol. 214, pp. 118–135, 2021.
Y. LeCun, Y. Bengio, and G. Hinton, “Deep learning,” Nature, vol. 521, no. 7553, pp. 436–444, 2015.
K. Cho et al., “Learning phrase representations using RNN encoder–decoder for statistical machine translation,” in Proc. EMNLP, 2014, pp. 1724–1734.
T. Akiba, S. Sano, T. Yanase, T. Ohta, and M. Koyama, “Optuna: A next-generation hyperparameter optimization framework,” in Proc. 25th ACM SIGKDD Int. Conf. Knowledge Discovery & Data Mining (KDD), 2019, pp. 2623–2631.
PLN, Peraturan Direksi PLN tentang Tarif Waktu Beban Puncak (WBP) dan Luar Waktu Beban Puncak (LWBP), 2019.
B. Lin, H. Xu, and Y. Zhou, “Smart building energy management with demand response and forecasting,” Energy Procedia, vol. 159, pp. 360–365, 2019.
Downloads
Published
How to Cite
Issue
Section
License
Copyright (c) 2026 Yusuf Yusuf, Ahmad Rofii, Jemie Muliadi
This work is licensed under a Creative Commons Attribution 4.0 International License.
