High-Accuracy Real-Time Soft Failure Detection in Optical Access Networks Using Hybrid Isolation Forest and One-Class SVM

Egi Rangga Maulana
Uranus: Jurnal Ilmiah Teknik Elektro, Sains dan In... 📅 2025 Vol 3, No 4 🔗 DOI: 10.61132/uranus.v3i4.1267
Abstract
This study presents a high-accuracy real-time soft failure detection framework for large-scale fiber-to-the-home(FTTH) optical access network using a hybrid ensemble of Isolation Forest and One-Class Support Vector Machine (OCVSM). The proposed model was trainde and validated on a real-word multivariate performance dataset comprising more than 1.8 million samples collected at 5-minute intervals from 50 Optical Line Terminal (OLTs) and over 3,000 Optical Network Terminals (ONTs) across a five-month periode(June-October 2025). Ground-truth validation was performed using 111 confirmed network incidents in October 2025 affecting 12,990 customer. The hybrid ensemble achieved Precision 0.940, Recall 0.982, with an average detection delay of only 7.8 minutes-representing an 87.7% reduction compared to conventional manual response (63.5 minutes). The framework significantly outperforms traditional threesholding and recent ML-based methods while demonstrating practical deployability in live operational enviroments.
Keywords
Ensemble Learning; FTTH; Isolation Forest; One-Class SVM; Optical Access Network
How to Cite

Egi Rangga Maulana (2025). High-Accuracy Real-Time Soft Failure Detection in Optical Access Networks Using Hybrid Isolation Forest and One-Class SVM. Uranus: Jurnal Ilmiah Teknik Elektro, Sains dan Informatika, 3(4). https://doi.org/10.61132/uranus.v3i4.1267

Egi Rangga Maulana, "High-Accuracy Real-Time Soft Failure Detection in Optical Access Networks Using Hybrid Isolation Forest and One-Class SVM," Uranus: Jurnal Ilmiah Teknik Elektro, Sains dan Informatika, vol. 3, no. 4, 2025.

Egi Rangga Maulana. "High-Accuracy Real-Time Soft Failure Detection in Optical Access Networks Using Hybrid Isolation Forest and One-Class SVM." Uranus: Jurnal Ilmiah Teknik Elektro, Sains dan Informatika, vol. 3, no. 4, 2025.

Egi Rangga Maulana. "High-Accuracy Real-Time Soft Failure Detection in Optical Access Networks Using Hybrid Isolation Forest and One-Class SVM." Uranus: Jurnal Ilmiah Teknik Elektro, Sains dan Informatika 3, no. 4 (2025).

Egi Rangga Maulana (2025) 'High-Accuracy Real-Time Soft Failure Detection in Optical Access Networks Using Hybrid Isolation Forest and One-Class SVM', Uranus: Jurnal Ilmiah Teknik Elektro, Sains dan Informatika, 3(4). doi: 10.61132/uranus.v3i4.1267.

Egi Rangga Maulana. High-Accuracy Real-Time Soft Failure Detection in Optical Access Networks Using Hybrid Isolation Forest and One-Class SVM. Uranus: Jurnal Ilmiah Teknik Elektro, Sains dan Informatika. 2025;3(4).

Artikel Terkait

Perancangan Alat Penerjemah Bahasa Isyarat Ke Suara Berbasis Sensor Flex, Sensor Mpu6050, dan Raspberry Pi

Zauqy Launu Hayya; Farady Alif Fiolana; Diah Arie Widhining

Digitalisasi Profil Usaha Siomay Batagor Bogarasa Melalui Perancangan Website Berbasis Odoo

Erika Fitriyani; Sri Bekti Handayani

Apliksi E-Absensi Berbasis Web untuk Efisiensi Rekapitulasi Data Kehadiran di PLN ULP Tanjug Balai

Rahmadani Fitri Panjaitan

Penggunaan Transfer Learning untuk Peningkatan Akurasi Deteksi Penyakit Tanaman Bunga

Enteng Hardiansyah; Lailan Sofinah Haharap; Muhammad Farros Atiqi

Digitalisasi Sistem Simpan Pinjam Bagi Anggota Kopdit Cu Mera Ndi Ate Berbasis Web

Ningsiana Dappa; Andreas Ariyanto Rangga; Paulus Mikku Ate

Analisis Dampak AI terhadap Keterlibatan Politik Digital Pemuda Menggunakan SEM

Ruspandi Ruspandi
Tren Sitasi Jurnal