Penerapan Algoritma Support Vector Machine (SVM) Dalam Prediksi Konsumsi Energi

Valentine, Ivani and Triloka, Joko (2026) Penerapan Algoritma Support Vector Machine (SVM) Dalam Prediksi Konsumsi Energi. Penerapan Algoritma Support Vector Machine (SVM) dalam Prediksi Konsumsi Energi, x (x). xx-xx. ISSN 2548-6861 (Submitted)

[img] Text
cover.pdf
Download (106kB)
[img] Text
Daftar Isi.pdf
Download (143kB)
[img] Text
pernyataan.pdf
Download (405kB)
[img] Text
Pengesahan Publikasi Ivani Valentine _20260206_144846_0000.pdf
Download (402kB)
[img] Text
Jurnal.pdf
Download (646kB)
[img] Text
lampiran LOA.pdf
Download (276kB)
[img] Text
SK Pembimbing MTI genap 2425.pdf
Download (2MB)

Abstract

ABSTRACT Global energy consumption continues to increase, driven by population growth, urbanization, and rapid technological advancement. This trend presents significant challenges for effective energy management. This study proposes a prediction model for energy consumption using a Support Vector Machine (SVM), capable of capturing complex, non-linear relationships influenced by temperature, time, and human activity. The data preprocessing stage employs StandardScaler for normalization and SMOTE to address class imbalance and ensure a balanced feature distribution. Experimental results indicate that the SVM with a radial basis function (RBF) kernel (C = 10, Gamma = 0.1) delivers the best performance. The model achieves an average accuracy of 88.15%, precision of 91.08%, recall of 88.16%, and an F1-score of 87.54%. These findings demonstrate the effectiveness of machine learning in enhancing the accuracy of energy consumption forecasts, contributing to improved demand management, optimal resource allocation, and long-term sustainability initiatives. Keyword: Energy Consumption, Energy Efficiency, SMOTE, SVM Kernel.

Item Type: Article
Subjects: Ilmu Komputer
eTheses
Divisions: Pasca Sarjana > Magister Teknik Informatika
Depositing User: ivani valentine
Date Deposited: 09 Feb 2026 07:47
Last Modified: 09 Feb 2026 07:47
URI: http://repo.darmajaya.ac.id/id/eprint/23652

Actions (login required)

View Item View Item