Penerapan Jaringan Saraf Tiruan Metode Backpropogation Dalam Memprediksi Distribusi Air Pada PDAM Tirtauli Kota Pematangsiantar

Lestari Sinaga, Eka Irawan, Widodo Saputra, Irfan Sudahri Damanik, Ilham Syahputra Saragih

Abstract


PDAM Tirtauli, Pematangsiantar City is one of the companies responsible for water supply requests. The problem arises is the amount of water produced is less or does not meet the needs of consumers to eat will cause water can not flow which will cause losses for customers and if the amount of water produced is greater than the demand for water then there will be a problem of waste. PDAM Tirtauli needs a long-term plan to supply clean water for the following year. The criteria used in this study are installed production capacity, real production capacity, production volume, production loss, unused capacity and distribution volume as targets from 2017-2019. This study aims to predict the results of water distribution in PDAM Tirtauli, Pematang Siantar City for 2020 by using Artificial Neural Networks with Backpropogation algorithm. Artificial Neural Network is a process to solve problems based on information received by predicting models that will occur in the future. In the artificial neural network there are several algorithms, one of which is Backpropogotion. This algorithm can minimize errors in the results obtained by finding the best architecture. The best architecture that is obtained is 4-2-5-1 with an accuracy rate of 100%, MSE 0.00654398. Thus, this model is good enough to predict the volume of water distribution for the following years.

Full Text:

PDF

References


A. Ahmad, P. M. Putri, W. Alifah, and I. Gunawan, “Analisis jaringan syaraf tiruan metode backpropogation dalam memprediksi ketersediaan komoditas beras berdasarkan provinsi di indonesia,” vol. 2, no. 1, pp. 4–16, 2019.

Solikhun, “Jaringan Saraf Tiruan Untuk Memprediksi Tingkat Pemahaman Siswa Terhadap Mata Pelajaran Dengan Menggunakan Algoritma Backpropogation,” no. 1, pp. 24–36, 2017.

D. Jauhari, “PREDIKSI DISTRIBUSI AIR PDAM MENGGUNAKAN METODE JARINGAN,” vol. 3, no. 2, 2016.

A. P. Windarto et al., “MODEL ARSITEKTUR NEURAL NETWORK DENGAN BACKPROPOGATION PADA PREDIKSI TOTAL LABA,” vol. 05, no. 02, pp. 147–158, 2018.

R. N. Putri and D. Setiawan, “PROTOTIPE PAKAN AYAMOTOMATIS MENGGUNAKAN METODE,” vol. 2, no. 1, 2018.

H. Pratiwi and K. et al Harianto, “Perbandingan Algoritma ELM Dan Backpropagation Terhadap Prestasi Akademik Mahasiswa,” vol. 3, no. September, pp. 282–294, 2019.

B. Satria, “Prediksi Volume Penggunaan Air PDAM Menggunakan Metode Jaringan Syaraf Tiruan Backpropogation,” vol. 2, no. 3, pp. 674–684, 2018.

A. Wanto, “PREDIKSI PRODUKTIVITAS JAGUNG INDONESIA TAHUN 2019-2020 SEBAGAI UPAYA ANTISIPASI IMPOR MENGGUNAKAN JARINGAN SARAF,” vol. 1, no. 1, pp. 53–62, 2019.

A. D. & M. Arhami, “Konsep Kecerdasar Buatan.” 2006.

M. ko. T. Sutojo, S.Si., M.Kom, Edy Mulyanto, S.si., “Jaringan Saraf Tiruan.” 2011.

W. Saputra, T. Tulus, M. Zarlis, R. W. Sembiring, and D. Hartama, “Analysis Resilient Algorithm on Artificial Neural Network Backpropagation,” J. Phys. Conf. Ser., vol. 930, no. 1, 2017.

L. M. Rokky Septian Suharto, Candra Dewi, “Implementasi Jaringan Syaraf Tiruan Backpropagation untuk Mendiagnosis Penyakit Kulit pada Anak,” vol. 1, no. 7, pp. 555–562, 2017.




DOI: http://dx.doi.org/10.30645/senaris.v2i0.157

Refbacks

  • There are currently no refbacks.


&nbsp