Neural network based projection of electricity demand in Indonesia using repetitive training method
| Autor: | Emmilya Umma Aziza Gaffar, Ansar Rizal, Mohammad Zainuddin, Arbain |
|---|---|
| Rok vydání: | 2018 |
| Předmět: |
Environmental Engineering
Artificial neural network Computer science business.industry 020209 energy General Chemical Engineering General Engineering 02 engineering and technology Training methods Electricity demand Hardware and Architecture 0202 electrical engineering electronic engineering information engineering Computer Science (miscellaneous) Computer vision Artificial intelligence Projection (set theory) business Biotechnology |
| Zdroj: | International Journal of Engineering & Technology. 7:57 |
| ISSN: | 2227-524X |
| DOI: | 10.14419/ijet.v7i2.2.12733 |
| Popis: | Indonesia Energy Outlook (IEO) 2016 published by BPPT projected the electricity demand in 2025 significantly will increase more than twice to 513 TWh from 203 TWh in 2015. This projection is based on the target of 100% electrification ratio in 2025. Assuming an average population growth of 1.2% in 2025 and a nominal GDP growth of 5.02% in 2014 which are expected to increase to 8% in 2025.This study projected the total electricity demand for the period 2016-2025 based on GDP, population, and electricity sales per sector (household, commercial, and industry) from the period of 2000-2015. Time series data modeling using Auto Regressive (AR) model and Autoregressive model with exogenous input (ARX) implemented using Artificial Neural Network Back-Propagation (ANN-BP). The repetitive training method is used to achieve the specified target error. |
| Databáze: | OpenAIRE |
| Externí odkaz: |
|