cover
Article Per Year (5 Year)
All
Home Page
OAI Link
Editorial Team
Contact
Reviewer
Google Scholar
Contact Name
Al Mahdali
Contact Email
almahdali@atim.ac.id
Phone
+6281340032063
Journal Mail Official
redaksijjeee@ung.ac.id
Editorial Address
Electrical Engineering Department Faculty of Engineering State University of Gorontalo Jenderal Sudirman Street No.6, Gorontalo City, Gorontalo Province, Indonesia
Location
Kota gorontalo,
Gorontalo
INDONESIA
Jambura Journal of Electrical and Electronics Engineering
Published by Universitas Negeri Gorontalo
ISSN : 26547813     EISSN : 27150887     DOI : 10.37905/jjeee
Core Subject : Science, Engineering,
Computer Science & IT Control & Systems Engineering Electrical & Electronics Engineering Energy Engineering
Jambura Journal of Electrical and Electronics Engineering (JJEEE) is a peer-reviewed journal published by Electrical Engineering Department Faculty of Engineering, State University of Gorontalo. JJEEE provides open access to the principle that research published in this journal is freely available to the public to support the exchange of knowledge globally. JJEEE published two issue articles per year namely January and July. JJEEE provides a place for academics, researchers, and practitioners to publish scientific articles. Each text sent to the JJEEE editor is reviewed by peer review. Starting from Vol. 1 No. 1 (January 2019), all manuscripts sent to the JJEEE editor are accepted in Bahasa Indonesia or English. The scope of the articles listed in this journal relates to various topics, including: Control System, Optimization, Information System, Decision Support System, Computer Science, Artificial Intelligence, Power System, High Voltage, Informatics Engineering, Electronics, Renewable Energy. This journal is available in online and highly respects the ethics of publication and avoids all types of plagiarism.
Arjuna Subject : Teknik (semua kategori) - Teknik Listrik dan Elektro
Articles 21 Documents
 1   2   3 
Search results for , issue "Vol 7, No 2 (2025): Juli - Desember 2025" : 21 Documents clear
Effectiveness of Gradient Boosting Stacking Model in Predicting Electricity Costs: Residential Building Data Nadifa, Ulfatun; H, Haeriani; Abdussamad, Syahrir; Tolago, Ade Irawaty; Dako, Rahmat Deddy Rianto; Bonok, Zainudin; Asmara, Bambang Panji
Jambura Journal of Electrical and Electronics Engineering Vol 7, No 2 (2025): Juli - Desember 2025
Publisher : Electrical Engineering Department Faculty of Engineering State University of Gorontalo

Show Abstract | Download Original | Original Source | Check in Google Scholar | DOI: 10.37905/jjeee.v7i2.33158

Abstract

Accurate electricity cost prediction is essential to support energy efficiency and resource management, particularly in residential and commercial buildings. This study aims to evaluate the effectiveness of the Gradient Boosting model in predicting monthly electricity costs. The model is built using the Stacking Ensemble method, a technique that combines multiple Gradient Boosting algorithms in a layered manner to improve prediction accuracy. To enhance the model’s performance, automatic selection of the best parameter values (Hyperparameter Optimization) is conducted using Optuna. The initial phase involves developing a tree-based preprocessing pipeline to address data variability and complexity. The model is evaluated using the K-Fold Cross Validation method, which divides the data into several subsets for more representative testing. The performance is assessed using the Root Mean Squared Logarithmic Error (RMSLE) metric to measure prediction accuracy. The evaluation results show that the model achieves an RMSLE score of 0.22, with an average prediction time of 0.00029 seconds. These findings suggest that although Gradient Boosting models are typically used on high-dimensional datasets, this approach remains effective for low-dimensional data. The combination of ensemble techniques and hyperparameter optimization yields accurate and efficient predictions. Therefore, this approach can be applied in real-world scenarios, such as urban energy management.Prediksi biaya listrik yang akurat penting untuk mendukung efisiensi energi dan pengelolaan sumber daya, terutama pada bangunan residensial maupun komersial. Penelitian ini bertujuan untuk menguji efektivitas model Gradient Boosting dalam memprediksi biaya listrik bulanan. Model dibangun dengan menggunakan metode Stacking Ensemble, yaitu teknik penggabungan beberapa algoritma Gradient Boosting secara bertingkat untuk meningkatkan akurasi prediksi. untuk meningkatkan kinerja model, digunakan pemilihan nilai parameter terbaik secara otomatis (Optimasi Hyperparameter) dengan bantuan Optuna. Tahapan awal dimulai dengan membangun pipeline preprocessing berbasis Tree Model untuk menangani variasi dan kompleksitas data. Model dievaluasi dengan menggunakan metode K-Fold Cross Validation, yaitu pembagian data menjadi beberapa bagian untuk pengujian yang lebih representatif, dan hasilnya diukur menggunakan metrik Root Mean Squared Logarithmic Error (RMSLE) untuk menilai ketepatan prediksi. Hasil evaluasi menunjukkan bahwa model mampu mencapai nilai RMSLE sebesar 0.22. Selain itu, waktu prediksi rata-rata adalah 0.00029 detik. Temuan ini menunjukkan bahwa meskipun model Gradient Boosting umumnya digunakan pada dataset berdimensi besar, pendekatan ini tetap efektif pada data berdimensi kecil. Kombinasi teknik ensemble dan Optimasi Hyperparameter mampu menghasilkan prediksi yang akurat dan efisien. Oleh karena itu, pendekatan ini dapat diterapkan dalam skenario nyata, seperti manajemen energi di kawasan perkotaan. 

Page 3 of 3 | Total Record : 21

 1   2   3 

Filter by Year

2025 2025


Reset
Filter By Issues
All Issue Vol 7, No 2 (2025): Juli - Desember 2025 Vol 7, No 1 (2025): Januari - Juni 2025 Vol 6, No 2 (2024): Juli - Desember 2024 Vol 6, No 1 (2024): Januari-Juni 2024 Vol 5, No 2 (2023): Juli - Desember 2023 Vol 5, No 1 (2023): Januari - Juni 2023 Vol 4, No 2 (2022): Juli - Desember 2022 Vol 4, No 1 (2022): Januari - Juni 2022 Vol 3, No 2 (2021): Juli - Desember 2021 Vol 3, No 1 (2021): Januari - Juni 2021 Vol 2, No 2 (2020): Juli - Desember 2020 Vol 2, No 1 (2020): Januari - Juni 2020 Vol 1, No 2 (2019): Juli - Desember 2019 Vol 1, No 1 (2019): Januari - Juni 2019 More Issue