ANALISIS ALGORITMA PREDIKSI UNTUK MENGHASILKAN PREDIKSI BEBAN LISTRIK JANGKA PENDEK
Abstract: Electricity is the
lifeblood for human life, both for household and industrial world. In the power
supply industry, it is important to determine the power requirements for the
future as soon as possible (at the earliest). Short-term electric load
prediction is one way that can be used to generate and distribute electrical
energy economically, so that the power provider can know the load and demand
for power for the next month, previous short-term power prediction studies,
generally using the Neural method Network. Neural Network is an information
processing system that has characteristics similar to biological neural
networks but, deficiencies in Neural Network often overfitting due to
overtrained. In a short-term electrical load prediction study, using the
Support Vector Machine (SVM) method, Support Vector Machines (SVM) is a
technique for predicting both classification and regression. This research
begins by processing daily load system load data with a time span of 30
minutes, with data input used is data in January 2017. The results show that
the SVM method can be one of the reference methods for the prediction of
short-term electrical load with RMSE 0.034.
Penulis: Veti Apriana, Rani
Irma Handayani
Kode Jurnal: jptkomputerdd170277