Long-term electrical consumption forecasting using Artificial Neural Network (ANN)
Authors:
- R AdhiswaraRAR Adhiswara
- A G AbdullahAAA G Abdullah
- Y MulyadiYMY Mulyadi
Open Access
- 1 December 2019
- conference paper
- Published by IOP Publishing in Journal of Physics: Conference Series
- Vol. 1402 (3)
Abstract
Long-term forecasting of electricity energy consumption has become one of the main fields in the electricity sector in each country. This study aims to compare the accuracy of the results of the method used in this study with research conducted by the government to estimate electricity consumption in Indonesia. Many methods can be used to estimate electrical energy consumption such as statistic methods (Exponential Smoothing, ARIMA, Regression), fuzzy logic and artificial neural network algorithms. The method used in RUPTL is Simple E (Simple Econometric) and method used in this study is the Artificial Neural Network algorithm. The results of this research are data on estimates of electricity consumption in Indonesia for 2019-2025. This research is expected to prove the accuracy of the Artificial Neural Network (ANN) method to estimate electricity consumption in Indonesia.Keywords
This publication has 11 references indexed in Scilit:
- An evaluation of conventional and computational intelligence methods for medium and long-term load forecasting in Algeria2015
- The Optimization Selection of Correlative Factors for Long-Term Power Load Forecasting2013
- Short-Term Power Load Forecasting Based on Self-Adapting PSO-BP Neural Network Model2012
- Long-term electric power load forecasting using fuzzy linear regression technique2011
- The study of long-term load forecasting based on method combination innovation2011
- Applications of optimization combination model for medium-long term load forecasting2010
- Linear low-density polyethylene/silica micro- and nanocomposites: dynamic rheological measurements and modellingExpress Polymer Letters, 2010
- Study on long-term load forecasting of MIXSVM based on principal component analysis2009
- Application of relevance vector regression model based on sparse bayesian learning to long-term electricity demand forecasting2009
- Medium to Long-term Peak Load Forecasting for Riyadh City Using Artificial Neural NetworksJournal of King Saud University – Engineering Sciences, 2000