Garuda - Garba Rujukan Digital

p-Index From 2021 - 2026

5.318

P-Index

This Author published in this journals

Giovanni Dimas Prenata

Program Studi Teknik Elektro, Universitas 17 Agustus 1945 Surabaya

Author-ID : 6457162

Agriculture, Biological Sciences & Forestry Computer Science & IT Control & Systems Engineering Decision Sciences, Operations Research & Management Economics, Econometrics & Finance Education Electrical & Electronics Engineering Energy Engineering Immunology & microbiology Industrial & Manufacturing Engineering Mathematics Mechanical Engineering Physics Public Health Social Sciences Other

Published : 37 Documents Claim Missing Document

Claim Missing Document

Articles

1 2 3 4

Thermal Behavior Clustering of High-Voltage Electrical Equipment Using K-Means and Fuzzy C-Means Giovanni Dimas Prenata; Ahmad Ridho’i
Elkom: Jurnal Elektronika dan Komputer Vol. 19 No. 1 (2026): Juli : Jurnal Elektronika dan Komputer
Publisher : STEKOM PRESS

Show Abstract | Download Original | Original Source | Check in Google Scholar | DOI: 10.51903/elkom.v19i1.3700

Thermal monitoring of high-voltage electrical equipment is an important aspect of maintaining the reliability and operational safety of electrical power systems. Conventional classification approaches generally require labeled data and are limited in representing transitional thermal conditions. Therefore, this study proposes an unsupervised learning approach using K-Means and Fuzzy C-Means (FCM) clustering methods to analyze thermal behavior patterns in high-voltage electrical equipment based on thermal image features. The proposed model utilizes two main features extracted from thermal images, namely the percentage of white regions (% white) and non-white regions (% non-white), where white regions represent high-temperature areas. A total of 12 thermal images were used in the clustering process. Experimental results showed that the K-Means algorithm converged after only 2 iterations, whereas FCM required 53 iterations to achieve convergence . Both methods successfully identified dominant thermal patterns corresponding to Normal, Warning, and Hazardous conditions. The most extreme thermal condition was observed in data sample 6, which had a white-region percentage of 83.2647% and was consistently classified as Hazardous by both K-Means and FCM . In addition, FCM demonstrated superior capability in representing transitional thermal conditions through membership values. Data sample 3, with a white-region percentage of 56.5476%, was classified as Hazardous by K-Means but categorized as Warning by FCM with a dominant membership value of 0.702543 . These results indicate that FCM provides more flexible thermal behavior representation compared with hard clustering approaches. Overall, the proposed clustering-based approach demonstrates significant potential for real-time thermal condition assessment and predictive maintenance applications in high-voltage electrical equipment.

Evaluasi Komparatif DFFNN, DFFNN yang Dioptimasi GA, DFFNN yang Dioptimasi GWO, dan LSTM untuk Prediksi Konsumsi Energi Listrik Menggunakan Sliding Window Cross-Validation Giovanni Dimas Prenata
Techné : Jurnal Ilmiah Elektroteknika Vol. 25 No. 1 (2026):
Publisher : Fakultas Teknik Elektronika dan Komputer Universitas Kristen Satya Wacana

Show Abstract | Download Original | Original Source | Check in Google Scholar | DOI: 10.31358/techne.v25i1.656

Prediksi konsumsi energi listrik yang akurat sangat penting untuk perencanaan jaringan dan efisiensi pasokan. Penelitian ini membandingkan empat pendekatan, yaitu Deep Feedforward Neural Network (DFFNN), DFFNN dengan Genetic Algorithm (GA), DFFNN dengan Grey Wolf Optimizer (GWO), serta Long Short-Term Memory (LSTM), menggunakan teknik Sliding Window Cross-Validation (SWCV). Tiga skenario evaluasi dilakukan: tanpa SWCV (2015-2018 latih, 2019 uji), SWCV mode 1 (2015-2017 latih, 2018 uji), dan SWCV mode 2 (2016-2018 latih, 2019 uji). Hasil menunjukkan bahwa DFFNN-GWO unggul dalam efisiensi, rata-rata hanya membutuhkan <1.000 iterasi untuk konvergen dengan MSE terbaik mencapai 6.0×10E-5 dan akurasi uji hingga 0,94-0,99. LSTM menunjukkan kestabilan temporal dengan akurasi uji konsisten di atas 0,90, meskipun MSE stagnan di kisaran 0,047. DFFNN-GA menghasilkan prediksi sangat akurat pada beberapa run (AE ? 0,00), tetapi performanya fluktuatif dengan iterasi tinggi hingga >50.000. Sementara itu, DFFNN standar berfungsi sebagai baseline dengan MSE rata-rata ~1.0×10??, namun membutuhkan iterasi 10.000-25.000 untuk stabil. Analisis ketiga skenario menegaskan bahwa kedekatan temporal data latih dengan data uji (seperti pada SWCV mode 2) meningkatkan generalisasi semua model. Secara keseluruhan, kombinasi optimisasi metaheuristik dan validasi temporal terbukti meningkatkan akurasi dan efisiensi prediksi konsumsi energi listrik, dengan GWO menonjol pada efisiensi dan LSTM pada kestabilan jangka panjang.

EVALUASI METODE KLASIFIKASI BERBASIS JARAK DAN PROBABILISTIK UNTUK DETEKSI GANGGUAN STATOR MOTOR INDUKSI Giovanni Dimas Prenata
Jurnal Elektro Kontrol (ELKON) Vol. 6 No. 1 (2026): Jurnal ELKON
Publisher : Teknik Elektro Fakultas Teknik Universitas Muria Kudus

Show Abstract | Download Original | Original Source | Check in Google Scholar | DOI: 10.24176/elkon.v6i1.17376

This study evaluates and compares the performance of three machine learning–based classification methods, namely Support Vector Machine (SVM), Gaussian Naive Bayes (GNB), and K-Nearest Neighbor (KNN), for diagnosing stator faults in induction motors using electrical and mechanical parameters, including phase voltage, phase current, power factor, rotational speed, torque, power, and temperature. The experimental results demonstrate that all three methods achieve an accuracy of 100% on the entire test dataset, while the KNN method maintains stable performance across all tested values of K. The consistency of results obtained from algorithms with fundamentally different principles margin-based, probabilistic, and distance-based indicates that classification performance is more strongly influenced by the quality and relevance of the selected features than by algorithmic complexity. Further analysis reveals that the primary differences among the methods lie in their computational characteristics and interpretability, where GNB offers superior efficiency, SVM provides robust decision boundaries, and KNN exhibits scalability limitations. These findings confirm that accurate and reliable induction motor stator fault diagnosis can be achieved using conventional classification algorithms when supported by appropriately selected and physically representative features.

Analisis Perbandingan Kinerja Jaringan Saraf Tiruan (JST) yang Dioptimalkan Metaheuristik dan Regresi Vektor Pendukung untuk Prediksi Konsumsi Energi Listrik Giovanni Dimas Prenata
CYCLOTRON Vol 9 No 02 (2026): CYCLOTRON
Publisher : Universitas Muhammadiyah Surabaya

Show Abstract | Download Original | Original Source | Check in Google Scholar | DOI: 10.30651/ct.v9i02.30809

This study analyzes the performance of electricity consumption prediction by comparing a metaheuristic optimization-based Artificial Neural Network (ANN) model from previous studies with a standalone Support Vector Regression (SVR) model. The SVR model uses an ε-insensitive linear regression approach with regularization, and feature normalization is performed to maintain training stability. Experimental results show that SVR is capable of producing very high prediction accuracy on training data with a relative accuracy per sample of 96.74%–99.90% and an average training accuracy of 99.09%, while maintaining generalization on test data with an accuracy of 92.56%. Compared to ANN with metaheuristic optimization (GA/PSO), which generally requires a more complex training process and relies on initialization, SVR offers the added value of more stable, deterministic, and easily reproducible training with lower model complexity. These findings confirm that SVR can be an effective and efficient alternative for electricity consumption prediction as well as a strong comparison to the ANN metaheuristic approach.

Predicting Breakdown Voltage of Transformer Oil under Copper/Iron Contamination: A Comparative Study of Gradient vs Metaheuristic Training Prenata, Giovanni Dimas
ELKHA Vol. 18 No.1 April 2026
Publisher : Faculty of Engineering, Universitas Tanjungpura

Show Abstract | Download Original | Original Source | Check in Google Scholar | DOI: 10.26418/elkha.v18i1.101026

Transformer oil functions as an insulating and cooling medium in high-voltage power systems, whose dielectric condition degrades over service life due to thermal aging, moisture ingress, and metallic contamination, leading to reduced Breakdown Voltage (BDV) and increased insulation failure risk that may necessitate oil regeneration, replacement, or indicate transformer end-of-life. Unlike Dissolved Gas Analysis (DGA), which evaluates transformer faults based on gas decomposition products, BDV directly reflects the dielectric strength of insulating oil and is more sensitive to particulate contamination such as Cu and Fe, making it more suitable for material-level insulation degradation assessment. This study investigates the influence of copper (Cu) and iron (Fe) particle contamination on BDV and compares three Artificial Neural Network (ANN) training strategies for BDV prediction: gradient-based training (DFFNN-Pure), Genetic Algorithm optimization (DFFNN-GA), and Grey Wolf Optimizer-based training (DFFNN-GWO), using experimental data from 36 transformer oil samples obtained in accordance with IEC 60156:2018. The comparison represents a before–after modeling perspective in terms of training strategy rather than repeated physical testing. The results show that DFFNN-Pure achieved the highest prediction accuracy (R² = 0.996, RMSE = 0.296 kV, MAE = 0.238 kV), while DFFNN-GWO demonstrated stable convergence with competitive accuracy (R² = 0.971, RMSE = 0.886 kV), whereas DFFNN-GA exhibited unstable convergence and poor generalization. Unlike previous studies that primarily focus on transformer remaining useful life estimation at the system level, this work emphasizes material-level BDV prediction of transformer oil under metallic contamination and provides a systematic comparison between gradient-based and metaheuristic training within the same DFFNN framework, supporting non-destructive condition monitoring and predictive maintenance.

Analisis Perbandingan Kinerja KNN Regression dan Support Vector Regression dalam Prediksi Kehandalan Sistem Tenaga Listrik Berdasarkan Indeks SAIDI–SAIFI Giovanni Dimas Prenata; Ahmad Ridhoi
Jurnal Teknik Elektro dan Komputasi (ELKOM) Vol. 8 No. 1 (2026): Jurnal Teknik Elektro dan Komputasi (ELKOM)
Publisher : Universitas Muhammadiyah Jember

Show Abstract | Download Original | Original Source | Check in Google Scholar | DOI: 10.32528/elkom.v8i1.5213

This study analyzes and compares the performance of K-Nearest Neighbor (KNN) Regression and Support Vector Regression (SVR) in predicting the reliability of electrical power distribution systems based on the SAIDI and SAIFI indices. The KNN Regression results indicate high sensitivity to the selection of parameter K; the optimal performance was achieved within the range of K = 2–5, while performance degradation occurred at K ≥ 6 due to the loss of locality effect. In contrast, the proposed SVR model (Model SVR), implemented with λ = 0.01 and ε = 0.03 and trained for 5000 epochs, demonstrated more stable and robust performance, achieving a training MAE of 0.126161, a training classification accuracy of 87.5% (7 out of 8 correctly classified samples), and a testing accuracy of 100% (2 out of 2 correctly classified samples). The resulting model coefficients, w0 = −1.038554 and w1 = 0.020590, indicate that SAIDI has a dominant and negative influence on the reliability score, which is physically consistent with the interpretation of outage duration. These findings suggest that, for small-sized datasets, the margin-based SVR approach provides greater robustness and stability compared to the distance-based KNN Regression method, thereby offering a more reliable framework for electrical distribution reliability prediction.

CLASSIFICATION OF RELIABILITY OF ELECTRIC POWER DISTRIBUTION SYSTEMS AT PT. PLN (PERSERO) UP3 SOUTH SURABAYA USING THE SINGLE PERCEPTRON METHOD Giovanni Dimas Prenata
Journal Renewable Energy, Electronics and Control Vol 3, No 2 (2023): JURNAL JREEC
Publisher : Department of Electrical Engineering, Institut Teknologi Adhi Tama Surabaya

Show Abstract | Download Original | Original Source | Check in Google Scholar | DOI: 10.31284/j.jreec.2023.v3i2.5091

The reliability of the electricity distribution system is very important for PLN. With a high level of reliability, PLN can ensure that electrical energy is distributed properly to customers. A high level of reliability is a guarantee for customers to get electrical energy. Some researchers measure reliability using the SAIDI (System Average Interruption Duration Index) and SAIFI (System Average Interruption Frequency Index) values. Apart from that, there are also those who use the FMEA (Failure Modes and Effects Analysis) method. In this study, researchers carried out reliability classification based on the SPLN 59-1985 standard using the artificial neuron network single perceptron method. Researchers used 3 neurons as input, namely the SAIDI value, SAIFI value and bias. The training data used is SAIDI value data and SAIFI value data for 10 months in 2021. The single perceptron neuron network application was created using C++ language with a learning rate of 0.1, and a sigmoid signal as the activation. So the weighting values obtained for 3 neurons, namely -3.95772 (W[0]), 1.15408 (W[1]) and 1.45799 (W[2]) in 6 training times to classify the level of reliability.

Co-Authors Adrianty Basyarach, Niken Ahmad Ridhoi Ahmad Ridho’i Ahmad Ridho’i Ahmad Ridho’i Andi Patriadi Aris Heri Andriawan, Aris Heri Aswanda Harja Baihaqi, Ahmad Basyarach, Niken Adriaty Eriko Ramadhani, Mohammad Fachrul Fauzan Fidhini Fidhini, Fachrul Fauzan Florentina Kuway Izzah Aula Wardah Junico Dwi Yussarianto Kukuh Setyadjit Labib Ubaidillah Iskhan Lutfi Agung Swarga Maulana Arief Mohammad Eriko Ramadhani Mohd Rizal Arshad Muhammad Alif Sofi Syariffudin Noufanda, Yudo Farrel Prasetyo, Arif Bayu Prayoga, Ageng Puji Slamet, Puji Rafli, Syah Achmad Amar Reza Sarwo Widagdo ridhoi, achmad Ridhoi, Ahmad Ridho’i, Ahmad Setiawan, Dani Agus Setiyawan, Ryan Agus Subekti Yuliananda, Subekti Subyakto, Doris Wardah, Izzah Aula

Title

Found 37 Documents
Search

Abstract

Abstract

Abstract

Abstract

Abstract

Abstract

Abstract

Title Search

Found 37 Documents Search

Abstract

Abstract

Abstract

Abstract

Abstract

Abstract

Abstract

Title

Found 37 Documents
Search