Article Per Year (5 Year)
p-Index From 2019 - 2024
0
P-Index
This Author published in this journals
All Journal Jurnal Pengembangan Teknologi Informasi dan Ilmu Komputer
Novi Nur Putriwijaya
Fakultas Ilmu Komputer, Universitas Brawijaya
Computer Science & IT Control & Systems Engineering Education Electrical & Electronics Engineering Engineering

Published : 1 Documents Claim Missing Document
Claim Missing Document
Check
Articles

Found 1 Documents
Search

 1 
Peramalan Jumlah Pemakaian Air Di PT. Pembangkitan Jawa Bali Unit Pembangkit Gresik Menggunakan Support Vector Regression Novi Nur Putriwijaya; Wayan Firdaus Mahmudy
Jurnal Pengembangan Teknologi Informasi dan Ilmu Komputer Vol 2 No 10 (2018): Oktober 2018
Publisher : Fakultas Ilmu Komputer (FILKOM), Universitas Brawijaya

Show Abstract | Download Original | Original Source | Check in Google Scholar | Full PDF (514.868 KB)

Abstract

There are several kinds of resources that are often used in daily activities, one of which is water. PT. PJB UP Gresik utilizes water as a catalyst in producing electricity and other operational needs. This leads to a large reduction in the quantity of water, thus allowing a lack of water supply in PT.PJB UP Gresik. To anticipate the problem, it is necessary to forecast the amount of water usage. Support Vector Regression (SVR) is used to forecast the amount of water usage. The data used is taken from history of water usage for 7 months. Testing data used is 49, which is taken randomly from the whole data. To determine the best parameters in forming regression model, testing will be done by calculating Mean Average Percentage Error (MAPE). From the testing results that have been done, the optimal parameters obtained are the amount of training data is 110 with average MAPE value 26.104, number of iterations is 650 with average MAPE value 20.222, value of lambda is 6 with average MAPE value 19.058, value of epsilon is 0.001 with average MAPE value 19.049, value of cLr is 0.00001 with average MAPE value 19.676, value of C is 0.00006 with average MAPE value 20.018, and value of sigma is 0.75 with average MAPE value 19.455. The final result accuracy of forecasting conducted using MAPE with average MAPE value 19.051 that is included in the good category.
Co-Authors Wayan Firdaus Mahmudy