Electrical Load Prediction Model for the SG 06 Feeder of ULP Meureudu Using a Gated Recurrent Unit Architecture

Mahdi Syukri, Analdi Muttaqin, Khairun Saddami, Ramdhan Halid Siregar, Mohd Syaryadhi


Abstract


The increasing electricity demand and the growing complexity of distribution networks require PLN to employ accurate load forecasting to ensure system reliability. This challenge is evident in the SG 06 Feeder of ULP Meureudu, which exhibits highly fluctuating load patterns, significant disparities between average and peak loads, and a relatively low load factor. These characteristics reduce the effectiveness of conventional forecasting methods and highlight the need for a model capable of accurately capturing temporal patterns. This study develops a short-term load forecasting model based on a Gated Recurrent Unit (GRU) architecture, utilizing time-based features as the sole input variables. The research process includes historical data collection, preprocessing, time-series windowing, model training, and performance evaluation using RMSE, MAE, and MAPE. The results show that the GRU model is able to generate stable and accurate predictions for both daily and weekly load patterns of the SG 06 Feeder, outperforming the simple statistical and time-based reference models used for comparison. The proposed model provides a reliable solution to support operational decision-making and enhance the reliability of the 20 kV distribution network managed by ULP Meureudu.

Keywords


GRU, Short-Term Load Forecasting, Jaringan distribusi 20 kV, Penyulang SG

Full Text:

PDF

References


PT. PLN. (Persero), 2024, Statistik PLN 2024 Data Operasional.

L. Assaffat, 2017, Prediksi Energi Industri Menggunakan Support Vector Machine dan Kernel, Prosiding Seminar Nasional Teknologi dan Informatika, pp. 140–145.

PLN Wilayah Banda Aceh, 2015, Kajian Kelayakan Proyek.

R. Syahputra, 2012, Prakiraan Beban Listrik Jangka Pendek Kota Banda Aceh Berbasis Logika Fuzzy, Jurnal Rekayasa Elektrika, vol. 4, no. 2, pp. 72–78.

M. Silfiani, 2023, Model Gabungan SARIMA dan ANN untuk Peramalan Beban Listrik, Variance: Jurnal Ilmiah Matematika dan Statistik, vol. 5, no. 1, pp. 49–57.

H. K. Asshiddiq, 2022, Prediksi Beban pada Transformator 150kV Menggunakan Algoritma Machine Learning, Universitas Muhammadiyah Yogyakarta, Tesis.

M. Syukri, 2022, Monitoring dan Identifikasi Pemakaian Beban Listrik Secara Real-Time Berbasis Artificial Neural Network, Universitas Hasanuddin, Tesis.

M. Binoto and Y. Kristiawan, 2015, Peramalan Energi Listrik Terjual dan Daya Listrik Tersambung di Solo Menggunakan Model Jaringan Syaraf Tiruan, Prosiding Seminar Nasional Teknologi dan Informatika, pp. 230–236.

H. Wibowo, Y. Mulyadi, and A. G. Abdullah, 2012, Prediksi Beban Terklasifikasi dengan Metode ARIMA, Electrans, vol. 10, no. 1, pp. 15–22.

A. T. Rahman, A. Riza, and A. Pambudi, 2014, Prediksi Beban Listrik pada Hari Libur Menggunakan Kombinasi Fuzzy Subtractive Clustering dan MLP, Reka Elkomika, vol. 2, no. 2, pp. 44–51.

A. Susanti, 2015, Implementasi Algoritma Hybrid Firefly dan MLP untuk Prediksi Konsumsi Listrik, Universitas Airlangga, Tesis.

D. P. Ardyansyah and U. T. Kartini, 2020, Peramalan Beban Listrik Konsumen Menggunakan Metode CBL dan Backpropagation Neural Network, Jurnal Teknik Elektro, vol. 9, no. 1, pp. 37–44.

N. Sugiarto, U. T. Kartini, and S. I. Haryudo, 2021, Prediksi Beban Listrik Menggunakan C-BPNN (Combined-Backpropagation Neural Network), Jurnal Teknik Elektro, vol. 10, no. 2, pp. 71–78.

A. A. Ningrum, I. Syarif, and A. I. Gunawan, 2021, Prediksi Umur Transformator Menggunakan Deep Learning-LSTM, Jurnal Ilmu Informasi dan Teknologi, vol. 5, no. 1, pp. 31–37.

R. Saputra and S. Sunardiyo, 2023, Analisis Arsitektur JST-MLP untuk Estimasi Beban Energi Listrik Area Pelayanan PLN Salatiga, Elkomika: Jurnal Teknik Energi Elektrik, Teknik Telekomunikasi, & Teknik Elektronika, vol. 11, no. 1, pp. 102–109.

N. P. Sakinah, I. Cholissodin, and A. W. Widodo, 2018, Prediksi Permintaan Menggunakan Jaringan Syaraf Tiruan Backpropagation, J-PTIIK, vol. 4, no. 2, pp. 90–96.

H. Dermawan and S. I. Alkadri, 2025, Prediksi Beban Listrik Harian Menggunakan ANN Backpropagation, Journal of Engineering and Science, vol. 6, no. 1, pp. 44–50.

B. A. Septian and U. T. Kartini, 2023, Pemodelan Prediksi Beban Listrik Menggunakan LSTM Neural Network, Jurnal Teknik Elektro, vol. 11, no. 1, pp. 18–25.

Z. Liu and H. Bao, 2018, Short-term load forecasting with multi-source data using GRU, in 2018 13th IEEE Conference on Industrial Electronics and Applications (ICIEA), Wuhan, China, May, pp. 2787–2792.

A. Hasanat, A. Anwar, M. Aslam, and M. A. Khan, 2024, Enhancing short-term load forecasting with a CNN-GRU hybrid model: Insights from single-step and multi-step forecasting on the AEP dataset, Energy Reports, vol. 12, pp. 111–124, Jan. 2024

Y. Hua, Y. Gao, and X. Wang, 2024, A short-term power load forecasting method using CNN-GRU with an attention mechanism, Sustainability, vol. 16, no. 5, p. 2064, Feb.

X. Xia, Y. Zhou, J. Li, and Y. Liang, 2023, A stacked GRU-RNN-based approach for predicting renewable energy and electricity load, Sustainability, vol. 15, no. 3, p. 2705, Feb.

N. Nurmahaludin, 2014, Perbandingan Metode PSO dan Regresi Linear untuk Prediksi Beban Puncak Listrik, Poros Teknik, vol. 6, no. 2, pp. 75-83.

Single Line Diagram PLN ULP Meureudu, 2025.

H. K. Ramadhan, 2021,Simulasi Prediksi Beban Energi Listrik Area Pelayanan Jaringan Kendal dengan Algoritma MLP,” Universitas Semarang, Tesis.

M. Haddin and A. Marwanto, 2022, Peramalan Potensi PLTS dan PLTB Menggunakan Jaringan Syaraf Tiruan MLP, Jurnal ELKOM, vol 14, no. 2, pp. 22–29.

M. P. Damayanti, 2022, Klasifikasi Beban Listrik Berdasarkan Citra CT-scan Menggunakan K-Means Clustering, Skripsi, UIN Walisongo Semarang.

V. Apriana and R. I. Handayani, 2017, Analisis Algoritma Prediksi untuk Beban Listrik Jangka Pendek Menggunakan Backpropagation Neural Network, Jurnal Ilmiah Teknologi Informasi, vol. 3, no. 2, pp. 104–109, 2017.




DOI: https://doi.org/10.30743/jet.v11i3.14301

Refbacks

  • There are currently no refbacks.


Copyright (c) 2026 Mahdi Syukri, Analdi Muttaqin, Khairun Saddami, Ramdhan Halid Siregar, Mohd Syaryadhi

Creative Commons License
This work is licensed under a Creative Commons Attribution-ShareAlike 4.0 International License.