Prediksi Pemakaian Listrik Menggunakan Jaringan Syaraf Tiruan dan ARIMA Di Wilayah Sulluttenggo



Silviani E Rumagit(1*), Azhari SN(2)

(1) Mahasiswa Program Pascasarjana Ilmu Komputer, FMIPA, UGM
(2) Staf Pengajar Program Pascasarjana Ilmu Komputer, FMIPA UGM
(*) Corresponding Author

Abstract


Background this research was made where the increasing demand for electricity in each group. The meaning this group is social, the household, business, industry groups and the government fare. Prediction is an important requirement for electricity providers in making decisions related to the availability of electric energy. In doing predictions can be made by statistical methods and artificial intelligence.

ARIMA is a statistical method that is widely used to predict where the ARIMA modeled autoregressive (AR) moving average (MA). Terms of ARIMA is the data must be stationary, the data is not stationary should be stationary  use differencing. In addition to the statistical method, predictions can also be done by artificial intelligence techniques, which in this study selected Backpropagation neural network to predict. From the results of tests made the difference in MSE ARIMA, ANN and merging ARIMA, artificial neural networks are not significantly different

Keywords


ARIMA, neural network, tarif groups

Full Text:

Full Text PDF




Article Metrics

Abstract views : 877 | views : 1072

Refbacks

  • There are currently no refbacks.




ISSN 0215-9309 (Print)

Jumlah kunjungan : Web
Analytics View my Stat.