Tinjauan Sistematis Peramalan Beban Listrik Menggunakan Deep Learning dan Hybrid

Halim Prasetyo Rieno; Desti Mualfah

doi:10.31004/riggs.v5i2.11178

Authors

Halim Prasetyo Rieno Universitas Muhammadiyah Riau
Desti Mualfah Universitas Muhammadiyah Riau

DOI:

https://doi.org/10.31004/riggs.v5i2.11178

Keywords:

Peramalan Beban Listrik, Deep Learning, Transformer, Smart Grid, Systematic Literature Review

Abstract

Peramalan beban listrik memiliki peran yang sangat penting dalam pengelolaan sistem tenaga modern karena hasil prediksi yang akurat berpengaruh langsung terhadap efisiensi operasi, keandalan sistem, perencanaan energi, pengalokasian sumber daya, serta stabilitas smart grid. Seiring meningkatnya kebutuhan listrik dan kompleksitas pola konsumsi energi, metode peramalan berbasis kecerdasan buatan, khususnya deep learning dan hybrid, semakin banyak dikembangkan untuk meningkatkan akurasi prediksi dibandingkan metode konvensional. Penelitian ini bertujuan untuk mengkaji perkembangan metode deep learning dan hybrid dalam peramalan beban listrik dengan fokus pada algoritma yang digunakan, variabel input, serta metrik evaluasi yang diterapkan. Metode penelitian menggunakan Systematic Literature Review (SLR) dengan mengacu pada kerangka PRISMA. Sebanyak 18 artikel ilmiah yang diterbitkan pada periode 2022–2026 dipilih melalui proses identifikasi, penyaringan, dan seleksi dari basis data Google Scholar, MDPI, Frontiers, dan arXiv. Hasil kajian menunjukkan bahwa beban historis, fitur waktu, dan variabel cuaca merupakan variabel input yang paling sering digunakan karena memiliki pengaruh signifikan terhadap pola konsumsi listrik. Dari sisi algoritma, penelitian terbaru menunjukkan pergeseran dari model deep learning tunggal menuju model Transformer dan pendekatan hybrid, seperti CNN-GRU, CNN-LSTM, serta BiLSTM-Transformer, yang terbukti lebih mampu menangkap karakteristik data deret waktu yang kompleks, nonlinier, dan dinamis. Sementara itu, metrik evaluasi yang paling banyak digunakan untuk mengukur performa model adalah Root Mean Square Error (RMSE), Mean Absolute Percentage Error (MAPE), dan Mean Absolute Error (MAE). Temuan penelitian ini menunjukkan bahwa integrasi data multivariat dengan model deep learning hybrid berpotensi meningkatkan akurasi peramalan beban listrik serta menjadi arah pengembangan yang menjanjikan dalam mendukung implementasi sistem smart grid yang lebih efisien, adaptif, dan berkelanjutan.

Downloads

Download data is not yet available.

References

[1] M. Abumohsen, A. Y. Owda, and M. Owda, “Electrical load forecasting using LSTM, GRU, and RNN algorithms,” Energies, vol. 16, no. 5, Art. no. 2283, 2023. doi: https://doi.org/10.3390/en16052283

[2] J. Cui, W. Kuang, K. Geng, A. Bi, F. Bi, X. Zheng, and C. Lin, “Advanced short-term load forecasting with XGBoost-RF feature selection and CNN-GRU,” Processes, vol. 12, no. 11, Art. no. 2466, 2024. doi: https://doi.org/10.3390/pr12112466

[3] F. Dakheel and M. Çevik, “Optimizing smart grid load forecasting via a hybrid long short-term memory-XGBoost framework: Enhancing accuracy, robustness, and energy management,” Energies, vol. 18, no. 11, Art. no. 2842, 2025. doi: https://doi.org/10.3390/en18112842

[4] S. Ding, D. He, and G. Liu, “Improving short-term load forecasting with multi-scale convolutional neural networks and transformer-based multi-head attention mechanisms,” Electronics, vol. 13, no. 24, Art. no. 5023, 2024. doi: https://doi.org/10.3390/electronics13245023

[5] Q. Dong, R. Huang, L. Zhou, D. Towey, J. Tian, and J. Wang, “Short-term electricity load forecasting with multi-frequency reconstruction diffusion,” arXiv, 2026. doi: https://arxiv.org/abs/2601.06533

[6] G. Dudek, “A comprehensive study of random forest for short-term load forecasting,” Energies, vol. 15, no. 20, Art. no. 7547, 2022. doi: https://doi.org/10.3390/en15207547

[7] Q. Hong, F. Meng, and F. Maldonado, “Advancing long-term multi-energy load forecasting with Patchformer: A patch and transformer-based approach,” arXiv, 2024. doi: https://arxiv.org/abs/2404.10458

[8] B. Ibrahim, L. Rabelo, E. Gutierrez-Franco, and N. Clavijo-Buritica, “Machine learning for short-term load forecasting in smart grids,” Energies, vol. 15, no. 21, Art. no. 8079, 2022. doi: https://doi.org/10.3390/en15218079

[9] V. Y. Kondaiah and B. Saravanan, “A modified deep residual network for short-term load forecasting,” Front. Energy Res., vol. 10, Art. no. 1038819, 2022. doi: https://doi.org/10.3389/fenrg.2022.1038819

[10] A. L’heureux, K. Grolinger, and M. A. M. Capretz, “Transformer-based model for electrical load forecasting,” Energies, vol. 15, no. 14, Art. no. 4993, 2022. doi: https://doi.org/10.3390/en15144993

[11] Z. Li and Z. Chen, “Short-term load forecasting based on CEEMDAN-FE-ISSA-LightGBM model,” Front. Energy Res., vol. 11, Art. no. 1111786, 2023. doi: https://doi.org/10.3389/fenrg.2023.1111786

[12] F. Liu, T. Dong, and Y. Liu, “An improved informer model for short-term load forecasting by considering periodic property of load profiles,” Front. Energy Res., vol. 10, Art. no. 950912, 2022. doi: https://doi.org/10.3389/fenrg.2022.950912

[13] L. Moosbrugger, V. Seiler, P. Wohlgenannt, S. Hegenbart, S. Ristov, E. Eder, and P. Kepplinger, “Load forecasting for households and energy communities: Are deep learning models worth the effort?” arXiv, 2025. doi: https://arxiv.org/abs/2501.05000

[14] P. Tao, H. Ma, C. Li, and L. Liu, “Intelligent grid load forecasting based on BERT network model in low-carbon economy,” Front. Energy Res., vol. 11, Art. no. 1197024, 2023. doi: https://doi.org/10.3389/fenrg.2023.1197024

[15] M. Wu, W. Feng, X. Li, Y. Liu, and C. Cao, “Short-term power load forecasting using an improved model integrating GCN and transformer,” Appl. Sci., vol. 15, no. 13, Art. no. 7003, 2025. doi: https://doi.org/10.3390/app15137003

[16] X. Xiong, Z. Huang, Y. Chen, and J. Sun, “Load forecasting for commercial buildings using BiLSTM–Transformer network and cyber–physical cognitive control systems,” Symmetry, vol. 16, no. 12, Art. no. 1601, 2024. doi: https://doi.org/10.3390/sym16121601

[17] L. Zeng, K. Zheng, G. Lin, J. Yang, M. Wu, G. Chen, and H. Jiang, “Enhanced short-term load forecasting based on adaptive residual fusion of Autoformer and Transformer,” Energies, vol. 18, no. 24, Art. no. 6496, 2025. doi: https://doi.org/10.3390/en18246496

[18] Q. Zheng, J. Zheng, F. Mei, A. Gao, X. Zhang, and Y. Xie, “TCN-GAT multivariate load forecasting model based on SHAP value selection strategy in integrated energy system,” Front. Energy Res., vol. 11, Art. no. 1208501, 2023. doi: https://doi.org/10.3389/fenrg.2023.1208501