Keywords
Forecasting
Load
Abstract
The increase in electricity demand in Indonesia, triggered by rapid population growth, necessitates efficient planning to ensure all citizens can meet their energy needs. PT. PLN (Persero) ULP Panakkukang responds to this challenge by forecasting electricity load using Artificial Neural Network (ANN) method through the Matlab application. Daily electricity load data from the Pengayoman substation in March, April, May, and June 2023 served as the basis for calculations. The research results indicate that the forecasting process using ANN successfully provides values close to the actual load of PT. PLN (Persero) ULP Panakkukang, with low average errors of 0.022%, 0.03%, and 0.018% for May to July, respectively. These efforts are expected to help optimize electricity capacity in the future, considering the uncertainty in predicting electricity demand preciselyReferences
H. Wibowo, Y. Mulyadi, and A. G. Abdullah, "Peramalan beban listrik jangka pendek terklasifikasi berbasis metode autoregressive integrated moving average," Electrans, vol. 11, no. 2, pp. 44-50, 2012.
J. A. Perdana, A. Soeprijanto, and R. S. Wibowo, "Peramalan Beban Listrik Jangka Pendek Menggunakan Optimally Pruned Extreme Learning Machine (OPELM) pada Sistem Kelistrikan Jawa Timur," Jurnal Teknik ITS, vol. 1, no. 1, pp. B176-B181, 2012.
K. A. Hamidie, "Metode Koefisien Energi Untuk Peramalan Beban Jangka Pendek Pada Jaringan Jawa Madura Bali," Jurnal Electrical Engineering of Universitas Indonesia, 2009.
S. R. Aida Putri, S. Fuady, and D. Tessal, "Perbandingan Peramalan Beban Listrik Jangka Pendek di Kota Sungai Penuh Menggunakan Metode Koefisien dan Jaringan Syaraf Tiruan," UNIVERSITAS JAMBI, 2022.