Optimasi Bobot pada Extreme Learning Machine untuk Prediksi Beban Listrik menggunakan Algoritme Genetika (Studi Kasus: PT. PLN (Persero) APD Kalsel dan Kalteng)

Vina Meilia (Fakultas Ilmu Komputer, Universitas Brawijaya)
Budi Darma Setiawan (Fakultas Ilmu Komputer, Universitas Brawijaya)
Nurudin Santoso (Fakultas Ilmu Komputer, Universitas Brawijaya)

Jurnal Pengembangan Teknologi Informasi dan Ilmu Komputer
Vol 2 No 11 (2018): November 2018

The growth of electrical consumers in Indonesia continues to increases every year, but it is not matched by the provision of adequate infrastructure that available. This causes the available electrical capacity can't fulfill the demand for electricity. As an anticipation, beside to add more electrical capacities which will need a lot of costs. PLN also do operations management systems, which is electrical load forecasting. In this study, a smart computing system is build to solves the problem. Electrical load data per hour is being used as an input to do the electrical load forecasting with Extreme Learning Machine method. Extreme Learning Machine method uses random input weight within range -1 to 1. Before the electric load prediction process runs, genetic algorithms first optimizing the input weight. Mean Absolute Percentage Error (MAPE) is being used to calculate the accuration of prediction results. According to the test results with weight optimization, MAPE average error rate is 0.799% while without weight optimization the rate rise to 1.1807%. Thus this study implies that Extreme Learning Machine method with weight optimization using genetic algorithm can be used in electrical load forecasting problem and give better prediction result.