Claim Missing Document
Check
Articles

Found 1 Documents
Search

APPLICATION OF ARTIFICIAL NEURAL NETWORK BACKPROPAGATION TO PREDICT HOUSEHOLD CONSUMPTION OF ELECTRICITY IN AMBON S. H. Saija; Y. A. Lesnussa; F. Kondolembang
Pattimura Proceeding 2017: Proceedings of the 3rd International Seminar of Basic Science
Publisher : Pattimura University

Show Abstract | Download Original | Original Source | Check in Google Scholar | Full PDF (510.174 KB) | DOI: 10.30598/PattimuraSci.2017.ICBS3.131-138

Abstract

Electricity is one of the energy most widely used in the universe. Electric power demand in Ambon city tends to increase due to the growing of population in Ambon. The necessary of electricity power in Ambon City by utilizing two systems are interconnected such as: PLTD Poka and PLTD Hative Kecil (Galala). In this research forecast the demand for household electricity consumption in 2016 based on validation data from 2011-2015 using Application of Neural Networks Backpropagation method. The validation data are using in JST-Backpropagation training, with the best network architecture that is 20 10 5 1 neurons and 0.8 learning rate, can produce the best pattern with the accuracy is 75% and the value of Mean Square Error is 0.298335.