Prediksi Beban Listrik Jangka Pendek Menggunakan Algoritma Feed Forward Back Propagation dengan Mempertimbangkan Variasi Tipe Hari

Ramadani Dwisatya, M.Ramdlan Kirom


The development of computing technology that has lead to soft computing technologies prompted researchers to try for finding an alternative method to predict the power load-based artificial intelligence (which is a popular and widely used: Adaptive Neural Network / Neural Network). Short term load forecasting has a very important role for the efficiency of electrical energy. For it will be done prediction electrical load short term for the 3 types of days, weekdays, weekends and national holidays by the method of Artificial Neural Network (ANN) algorithm using feedforward backpropagation, and the data used is real data throughout 2013 and 2014. The software for designing programs to use is Matlab from Mathwork Corps. Based on test results obtained average value error for all three types of day best is 2.89% and the forecasting from PLN gained 8.84% on the type of national holidays, so we get electrical energy efficiency on a national holiday the average 6% in each hour.

Full Text:



Abdullah AG. Short Term Load Forecasting (STLF) Melalui Pendekatan Logika Fuzzy. Electrans. 2008;7:1-6.

Mulyadi Y, Farida L, Abdullah AG, Rohmah KA. Anomalous STLF for Indonesia power system usingg Artificial Neural Network. InScience and Technology (TICST), 2015 International Conference on 2015 Nov 4 (pp. 1-4). IEEE.

Ade Gafar Abdullah, Galura Muhammad Suranegara, Dadang Lukman Hakim, 2014, Hybrid PSO-ANN Application for Improved Accuracy of Short Term Load Forecasting, WSEAS Transactions on Power Systems, Volume 9, 2014, pp. 446-451.

Hakim, Lukmanul, M. Syafruddin & Dikpride Despa. Metode Regresi Linier untuk Prediksi Kebutuhan Energi Listrik Jangka Panjang. 2008

Siang, Jong Jek (2009). Jaringan Syaraf Tiruan & Pemrogramannya menggunakan MATLAB.Yogyakarta: Penerbit Andi Offset.


  • There are currently no refbacks.