Pemodelan Jaringan Saraf Tiruan untuk Prediksi Konsumsi Listrik Mesin Uji pada Laboratorium Otomotif

Teguh Iryanto, Mas'ud Adhi Saputra


Electric energy is becoming a major human need today. The biggest consumption is the use of electric energy in  factories, buildings, and residential dwellings. Energy management is needed for efficient use of electric energy. Electric energy prediction aims to find out how much load in the future so as to help providers of electric energy to prepare adequate sources. Artificial neural network (ANN) was used with a backpropagation learning algorithm to make intelligent system modeling to predict electricity usage during testing hourly. Retrieval of research data was limited to the use of automotive laboratories in Center for Material and Technical Product, Bandung City, West Java Province. ANN architecture used 6 neuron at input layer, 3 hidden layer with 12 neuron and 1 output layer. The logsig and purelin activation function was used to construct ANN modeling. The results of modeling showed that predictions using ANN got a mean square error (MSE) of 0,00043.

Energi listrik menjadi kebutuhan utama manusia saat ini. Konsumsi terbesar adalah penggunaan energi listrik pada bangunan baik pabrik, gedung, maupun hunian tinggal. Manajemen energi diperlukan untuk efisiensi penggunaan energi listrik. Prediksi penggunaan energi listrik bertujuan untuk mengetahui berapa beban di masa yang akan datang sehingga membantu penyedia energi listrik untuk mempersiapkan sumber energi listrik yang memadai. Jaringan saraf tiruan (JST) digunakan dengan algoritma pelatihan backpropagation untuk membuat pemodelan sistem cerdas yang mampu memprediksi penggunaan listrik pada saat pengujian dalam jangka waktu satu jam. Pengambilan data penelitian dibatasi pada penggunaan listrik laboratorium otomotif Balai Besar Bahan dan Barang Teknik, Kota Bandung, Propinsi Jawa Barat. Arsitektur JST menggunakan 6 neuron pada layer input, 3 layer tersembunyi dengan neuron 12 dan 1 layer output. Fungsi aktivasi logsig dan purelin digunakan untuk membangun pemodelan JST. Hasil pemodelan menunjukkan bahwa prediksi menggunakan JST menghasilkan nilai mean square error (MSE) 0,00043.



backpropagation; energi; jaringan syaraf tiruan; prediksi

Full Text:



C. Fan, Y. Sun, Y. Zhao, M. Song, and J. Wang, “Deep learning-based feature engineering methods for improved building energy prediction,” vol. 240, no. January, pp. 35–45, 2019.

I. Prediction, “The General Regression Neural Network Based on the Fruit Fly Optimization Algorithm and the Data Inconsistency Rate for Transmission Line Icing Prediction,” 2017.

S. Kusumadewi, Membangun Jaringan Saraf Tiruan Menggunakan MATLAB & EXCEL LINK, Pertama. Yogyakarta: Graha Ilmu, 2004.

Y. A. Lesnussa, S. Latuconsina, and E. R. Persulessy, “Aplikasi Jaringan Saraf Tiruan Backpropagation untuk Memprediksi Prestasi Siswa SMA ( Studi kasus: Prediksi Prestasi Siswa SMAN 4 Ambon ),” vol. 11, no. 2, pp. 149–160, 2015.

C. Hopmann, C. Augusto Santos Silva Eng Christian Luft, J. de Saldanha Gonçalves Matos Supervisor, and C. Augusto Santos Silva, “Machine Learning to improve indoor climate and building energy performance Energy Engineering and Management Examination Committee,” no. October, 2017.

N. M. Sukarno, P. W. Wirawan, and S. Adhy, “Perancangan dan implementasi jaringan saraf tiruan,” vol. 5, pp. 9–18.

A. Hasim, “Prakiraan Beban Listrik Kota Pontianak Dengan Jaringan Saraf Tiruan (Artificial Neural Network),” Cent. Libr. Bogor Agric. Univ., p. 1, 2008.

Arifah, N., T., A. Murnomo, and A. Suryanto, “Implementasi Neural Network pada Matlab untuk Prakiraan Konsumsi Beban Listrik Kabupaten Ponorogo Jawa Timur,” vol. 9, no. 1, 2017.

F. Rodrigues, C. Cardeira, and J. M. F. Calado, “The Daily and Hourly Energy Consumption and Load Forecasting Using Artificial Neural Network Method: A Case Study Using a Set of 93 Households in Portugal,” Energy Procedia, vol. 62, pp. 220–229, 2014.

S. A. Zagrebina, V. G. Mokhov, and V. I. Tsimbol, “ScienceDirect ScienceDirect ScienceDirect Electrical Energy Consumption Prediction is based Electrical Energy Consumption Prediction is based on the Recurrent Neural Network on the Recurrent Neural Network,” vol. 00, 2019.



  • There are currently no refbacks.

Creative Commons License
This work is licensed under a Creative Commons Attribution-NonCommercial-ShareAlike 4.0 International License.


Center for Material and Technical Product (B4T)

Jl. Sangkuriang No.14, Bandung, 40135, INDONESIA.

Email :

Telp : +62-22-2504088

This work is licensed under a Creative Commons Attribution-NonCommercial-ShareAlike 4.0 International License.

View My Stats