An Examination of the Backpropagation Method for Predicting the Amount of Demand for Power Installations in the North Sumatra UP2D Location Area

Authors

  • Afif Yasri Universitas Pembangunan Panca Budi
  • Zulham Sitorus Universitas Pembangunan Panca Budi

Keywords:

Forecasting, Backpropagation, Demand, UP2D North Sumatra

Abstract

This study examines the utilization of the Backpropagation method in artificial neural networks to predict the volume of electricity installation requests in the UP2D North Sumatra operational region. The demand for power installations fluctuates due to economic conditions, population expansion, and industrial development, necessitating an accurate forecasting model to enhance capacity planning and energy distribution. This study aims to evaluate the efficacy of the Backpropagation method in forecasting power installation requests using historical data and to determine the precision of the constructed model. The utilized data comprises power installation request records classified by time period (e.g., monthly) sourced from UP2D North Sumatra, and further segmented into training and testing datasets. The modeling process encompasses data preprocessing, specifying the network design (quantity of neurons in the hidden layer), training via the Backpropagation method, and assessing the model. The performance assessment is conducted utilizing error metrics, including Mean Absolute Percentage Error (MAPE) and Root Mean Square Error (RMSE). The research findings indicate that the Backpropagation approach can generate forecasting patterns that closely align with real data and serve as a decision-support tool for planning energy installation requirements at UP2D North Sumatra.

References

I. C. Saragih, D. Hartama, and A. Wanto, “Prediksi Perkembangan Jumlah Pelanggan Listrik Menurut Pelanggan Area Menggunakan Algoritma Backpropagation,” vol. 2, no. 1, pp. 48–54, 2020.

M. Noor and H. Siregar, “MODEL ARSITEKTUR ARTIFICIAL NEURAL NETWORK PADA PELANGGAN LISTRIK NEGARA ( PLN ),” pp. 1–5, 2015.

P. Listrik, B. Fachri, A. P. Windarto, and I. Parinduri, “Penerapan Backpropagation dan Analisis Sensitivitas pada Prediksi Indikator Terpenting,” vol. 5, no. 2, pp. 202–208, 2019.

T. Mikrohidro, D. Kabupaten, B. Bolango, and N. Doda, “Analisis Potensi Pengembangan Pembangkit Listrik,” pp. 1–10, 2002.

P. Windarto, P. Studi, M. Informatika, P. Studi, and S. Informasi, “MENDORONG LAJU PERTUMBUHAN EKONOMI,” vol. 04, no. 02, pp. 184–197, 2017.

S. Kasus, P. T. Pln, and R. Sumatera, “ARTIFICIAL NEURAL NETWORK UNTUK MEMPREDIKSI BEBAN LISTRIK DENGAN MENGGUNAKAN METODE BACKPROPAGATION,” vol. 5, no. 2, pp. 61–70, 2019.

D. Apriza, T. Sutabri, U. Bina, D. Palembang, and S. Selatan, “Prediksi Pemakaian Pulsa Listrik Kamar Kos Menggunakan Metode Jaringan Syaraf Tiruan Backpropagation ( Prediction of Electricity Consumption in Dormitory Rooms Using Backpropagation Neural Network,” vol. 2, no. 2, pp. 151–158, 2024.

P. Bengkulu, “No Title,” vol. 8, no. 1, 2012.

A. F. Suahati, A. A. Nurrahman, and O. Rukmana, “Penggunaan Jaringan Syaraf Tiruan – Backpropagation dalam Memprediksi Jumlah Mahasiswa Baru Predicting Number of New Student Using Artificial Neural Network - Backpropagation,” vol. 6, no. 1, pp. 21–29, 2022, doi: 10.35194/jmtsi.v6i1.1589.

R. T. Untari and M. Devegi, “Penerapan Algoritma Backpropagation untuk Memprediksi Jumlah Permintaan Buku dan Alat Tulis Application of Backpropagation Algorithm to Predict Number of Book and Stationery Requests,” vol. 2, no. 1, pp. 1–7, 2022, doi: 10.22202/jurteii.2022.6670.

Downloads

Published

2025-10-27

Issue

2025: Proceedings of International Conference on Islamic Community Studies

Section

Articles

License

Copyright (c) 2025 Afif Yasri, Zulham Sitorus

Creative Commons License

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