cover
Contact Name
Rudy Kurniawan
Contact Email
rudy14k@gmail.com
Phone
+6285267099660
Journal Mail Official
rudy14k@gmail.com
Editorial Address
Kampus Terpadu Balunijuk, Kecamatan Merawang, Kabupaten Bangka, Provinsi Kepulauan Bangka Belitung
Location
Kab. bangka,
Kepulauan bangka belitung
INDONESIA
Jurnal Ecotipe (Electronic, Control, Telecommunication, Information, and Power Engineering)
ISSN : 23555068     EISSN : 26224852     DOI : https://doi.org/10.33019/jurnalecotipe
This scientific journal is called Jurnal Ecotipe (Electronic, Control, Telcommunication, Information, and Power Engineering) with clusters of science in the field of Electrical Engineering covering the field of Electronics, Control, Telecommunications, Information/Informatics, and Power Electricity. The schedule of scientific journal publication is planned 2 times / volume in a year, ie April and October. The author can come from institutions outside the Department or from within the Department of Electrical Engineering University of Bangka Belitung. Aim and Scope : Electronics, Electronic Materials, Microelectronic System, Control System Engineering, Instrumentation and Control Engineering, Robotics, Telecommunication, Modulation and Signal Processing, Antenna and Wave Propagation, Information Technology, Information Theory and Coding, Computer Engineering and Informatics, Electrical and Power Engineering, Transmission and Distribution, Renewable Energy.
Articles 235 Documents
Comparing Deep Learning and Ensemble Models for Photovoltaic Power Forecasting Edris Shamsulhaq; Fikri Arif Wicaksana
Jurnal Ecotipe (Electronic, Control, Telecommunication, Information, and Power Engineering) Vol 13 No 2 (2026): Jurnal Ecotipe, October 2026
Publisher : Jurusan Teknik Elektro, Universitas Bangka Belitung

Show Abstract | Download Original | Original Source | Check in Google Scholar | DOI: 10.33019/jurnalecotipe.v13i2.4608

Abstract

Precise forecasting of photovoltaic (PV) power is crucial for maintaining grid stability and effectively incorporating solar energy. This study compares four forecasting models, LSTM, GRU, Random Forest, and XGBoost, using three years of real operational data (2023–2025) from the DKASC solar database. Fourteen input features were constructed from irradiance measurements, meteorological variables, rainfall, wind direction, and cyclical time features. A sliding window of 36 time steps captured temporal dependencies, while the dataset was chronologically split into training, validation, and testing subsets. Model performance was assessed using R², RMSE, MAE, and MAPE. Results show LSTM achieved the highest accuracy with R² of 0.9647 and RMSE of 88.40 W, whereas XGBoost obtained the lowest MAPE of 19.18%. SHAP analysis and an ablation study were conducted to identify influential features and evaluate their contributions to forecasting performance. SHAP analysis identified global horizontal radiation, global tilted radiation, and cyclical temporal features, particularly day_cos and hour_cos, as the most influential predictors, while wind speed and daily rainfall showed limited impact. The findings demonstrate that deep learning models can provide reliable PV power forecasts when combined with informative feature engineering and appropriate temporal window selection.
Fuzzy Expert System for Condition Assessment of Medium-Voltage Distribution Cable Insulation in Saline Environments Saepul Rahmat; Riyani Prima Dewi; Erna Alimudin
Jurnal Ecotipe (Electronic, Control, Telecommunication, Information, and Power Engineering) Vol 13 No 2 (2026): Jurnal Ecotipe, October 2026
Publisher : Jurusan Teknik Elektro, Universitas Bangka Belitung

Show Abstract | Download Original | Original Source | Check in Google Scholar | DOI: 10.33019/jurnalecotipe.v13i2.4609

Abstract

One cause of damage to medium-voltage cables is electrical treeing. This forms channels resembling tree branches in the cable insulation due to excessive electrical voltage. Electrical treeing can harm cable performance and cause short circuits between phase conductors. Short circuits in medium-voltage power networks increase fire risk and endanger electrical operators. This study aims to develop a non-destructive method for detecting defects in medium-voltage cables. The Arduino Mega and ESP32 microcontrollers were used because of the numerous parameters used to determine cable health and the need for a portable diagnostic tool that can be controlled from a safe distance for the user. This method enables faster damage identification, uses more accessible technology, and achieves greater accuracy through multi-parameter measurements. The research output is a prototype system that assesses the quality of medium-voltage cable insulation into six test parameters and six fuzzy rules based on mechanical and chemical data, resulting in a total of 216 unique rule combinations.  The tested cable samples are assessed by an expert system with an accuracy rate of 95% from actual conditions and show a decrease in insulation quality from mechanical and electrical perspectives, which affects the distribution cable's service life.
Design and Performance Evaluation of a Hybrid Photovoltaic System Integrated with Battery Storage and Utility Grid for Residential Applications Muhammad Reza Fahlevi; Syah Alam; Dianing Novita Nurmala Putri
Jurnal Ecotipe (Electronic, Control, Telecommunication, Information, and Power Engineering) Vol 13 No 2 (2026): Jurnal Ecotipe, October 2026
Publisher : Jurusan Teknik Elektro, Universitas Bangka Belitung

Show Abstract | Download Original | Original Source | Check in Google Scholar | DOI: 10.33019/jurnalecotipe.v13i2.4610

Abstract

The increasing demand for residential electricity requires a reliable and sustainable energy supply. However, photovoltaic (PV) systems are highly dependent on solar irradiance, resulting in fluctuating power generation. This study designs and evaluates a prototype hybrid PV system integrating a 160 Wp solar panel, a 12 V 100 Ah battery, a 1000 W hybrid inverter, and the utility grid (PLN). Performance was evaluated based on voltage, current, power, and irradiance. The results show that an average irradiance of 560.7 W/m² produced 15.91 V, 1.77 A, and 28.03 W, with a maximum power of 45.49 W at 754.9 W/m². The system maintained stable output voltage while current and power increased with irradiance, and it reliably supplied a daily load of 320 Wh using solar energy as the primary source, batteries for storage, and the grid as backup. These results demonstrate that the proposed hybrid PV system improves the reliability of residential electricity supply.
Voltage–Frequency Stability of a 300 W Portable Cross-Flow Pico-Hydropower System under Low-Flow Conditions Zulka Hendri; Akbar Abadi; Wiwik Wiharti; Yudia Seftiani
Jurnal Ecotipe (Electronic, Control, Telecommunication, Information, and Power Engineering) Vol 13 No 2 (2026): Jurnal Ecotipe, October 2026
Publisher : Jurusan Teknik Elektro, Universitas Bangka Belitung

Show Abstract | Download Original | Original Source | Check in Google Scholar | DOI: 10.33019/jurnalecotipe.v13i2.4611

Abstract

Pico-hydropower systems are widely recognized as a reliable solution for rural electrification; however, their performance is highly sensitive to hydraulic and load variations, particularly under low-flow conditions. This study presents an experimental investigation of voltage–frequency stability in a 300 W portable cross-flow pico-hydropower system. The system consists of a simple weir intake, a variable-diameter PVC penstock, a cross-flow turbine, and a directly coupled single-phase AC generator without a governing mechanism. Experimental tests were conducted by applying six resistive load levels ranging from 0 to 100 W to evaluate the output voltage, frequency, generator rotational speed, overall system efficiency, and voltage regulation. The results show a significant frequency drop from 77 Hz at no-load to 57 Hz at full-load, corresponding to a deviation of approximately 35%. The system also exhibits a low overall efficiency of 15.21% and a voltage regulation of 36.6%, indicating poor energy conversion and unstable voltage performance. These findings reveal that the absence of a speed control mechanism and turbine–generator mismatch significantly affect system stability. The study concludes that load variation alone is insufficient to maintain stable operation, highlighting the need for advanced control strategies such as ELC to improve the voltage and frequency stability.
Low-Cost AIS Vessel Tracking System for Real-Time Web Visualization Using Software Defined Radio and Leaflet.js Inka Trisna Dewi; Tri Budi Santoso; Rini Satiti; Fabria Alieftya Yusvianti; Nafilah Aqilatuz Zuhroh
Jurnal Ecotipe (Electronic, Control, Telecommunication, Information, and Power Engineering) Vol 13 No 2 (2026): Jurnal Ecotipe, October 2026
Publisher : Jurusan Teknik Elektro, Universitas Bangka Belitung

Show Abstract | Download Original | Original Source | Check in Google Scholar | DOI: 10.33019/jurnalecotipe.v13i2.4612

Abstract

A low-cost edge-based Automatic Identification System (AIS) monitoring platform was developed for real-time vessel surveillance, integrating AIS signal acquisition, decoding, data management, and geospatial visualization within a unified web-based architecture. The proposed platform was implemented using commercially available hardware components with a total hardware cost of approximately USD 189, providing a cost-effective alternative for real-time AIS monitoring. The system employs RTL-SDR for signal reception and a lightweight C-based processing pipeline incorporating GMSK demodulation, NRZI decoding, and CRC16 validation. Experimental deployment at Tanjung Perak Port under dense maritime traffic conditions demonstrated continuous end-to-end operation, achieving an average throughput of 3.71 messages per second and an end-to-end latency of 0–2 seconds. Decoded AIS records were stored in MariaDB and visualized through a Leaflet.js-based interface supporting real-time vessel tracking, historical trajectory reconstruction, and traffic analytics. Existing AIS studies commonly address signal reception, decoding, and visualization as separate processing stages. In contrast, the proposed platform consolidates the complete processing chain from radio-frequency AIS acquisition to web-based maritime information delivery within a single edge-computing environment. The results demonstrate the feasibility of employing resource-constrained edge devices for continuous AIS processing and provide an integrated framework for real-time maritime monitoring without reliance on high-performance computing infrastructure.
Design and Implementation of an IoT-Based Web Server System for Real-Time Vital Signs Monitoring Alamsyah; Tan Suryani Sollu; Catur Prasetyo; Mohammed Ikhlayel
Jurnal Ecotipe (Electronic, Control, Telecommunication, Information, and Power Engineering) Vol 13 No 2 (2026): Jurnal Ecotipe, October 2026
Publisher : Jurusan Teknik Elektro, Universitas Bangka Belitung

Show Abstract | Download Original | Original Source | Check in Google Scholar | DOI: 10.33019/jurnalecotipe.v13i2.4613

Abstract

The goal of this project is to develop and put into use a web server-based vital signs monitoring system for tracking health conditions in real time. The device is designed to enable medical personnel to remotely monitor blood pressure, body temperature, oxygen saturation (SpO₂), and heart rate. The system architecture integrates Internet of Things (IoT) physiological sensors, a microcontroller for data gathering, and a web server for data storage and visualization. Authorized users can view sensor data on a web-based dashboard after it is wirelessly delivered to the server. Requirements study, system design, implementation, and testing were all part of the prototype process used to create the system. Sensor accuracy, data transfer stability, and web interface responsiveness were assessed by system testing. The average measurement error for heart rate was 2.57%, with an accuracy of 97.43%; for oxygen saturation (SpO₂), it was 1.37%, with an accuracy of 98.63%; and for body temperature, it was 2.04%, with an accuracy of 97.96%, according to the test findings. The installation results show that the system is capable of low-latency, real-time monitoring and early notifications when critical metrics exceed normal limits.
Review on Resilience-Oriented Strategies Power Systems Facing Extreme Natural Disaster Arfita Y. Dewi; Adrianti; Muhammad Nasir; Asnal Effendi
Jurnal Ecotipe (Electronic, Control, Telecommunication, Information, and Power Engineering) Vol 13 No 2 (2026): Jurnal Ecotipe, October 2026
Publisher : Jurusan Teknik Elektro, Universitas Bangka Belitung

Show Abstract | Download Original | Original Source | Check in Google Scholar | DOI: 10.33019/jurnalecotipe.v13i2.4614

Abstract

Natural disasters significantly impact electricity services worldwide, making power grid resilience a crucial research topic. This article presents a literature review focusing on resilience-oriented strategies for electric power systems facing extreme natural disasters. Employing the Preferred Reporting items for Systematic Reviews and Meta-Analyses (PRISMA) methodology, fifty-eight relevant articles were selected and analyzed. The reviewed literature was categorized into three distinct operational stages of disasters: pre-disaster, during-disaster, and post-disaster. In the pre-disaster stage, the focus was placed on proactive infrastructure hardening and robust planning. During disasters, the priority shifted to real-time threat monitoring and active risk mitigation. Post-disaster recovery relied heavily on functional technologies, including distributed generation islanding, microgrid clustering, and optimal energy management coordinated with the deployment of emergency repair crews. The analysis revealed critical challenges, such as the lack of standardized metrics, limited transmission-distribution coordination studies, and a scarcity of multi-disaster modeling. Finally, future research directions were identified, emphasizing control stability in low-inertia microgrids and the integration of interconnected civil infrastructures to accelerate power system restoration.
Implementation of On-Device Convolutional Neural Network Inference for Indoor Occupancy Detection on the ESP32-S3 Ade Aditya Ramadha; Felix Corputty; Naufal Hanan Lutfianto
Jurnal Ecotipe (Electronic, Control, Telecommunication, Information, and Power Engineering) Vol 13 No 2 (2026): Jurnal Ecotipe, October 2026
Publisher : Jurusan Teknik Elektro, Universitas Bangka Belitung

Show Abstract | Download Original | Original Source | Check in Google Scholar | DOI: 10.33019/jurnalecotipe.v13i2.4616

Abstract

Indoor occupancy detection is a key enabling technology for energy-efficient smart building management, as heating, ventilation, air conditioning, and lighting systems waste significant energy when conditioned spaces are unoccupied. This paper implements a compact Convolutional Neural Network (CNN) trained on the UCI Occupancy Detection Dataset and deployed entirely on the ESP32-S3 microcontroller using TensorFlow Lite Micro with INT8 post-training quantization, eliminating any cloud dependency. Models are trained under a leakage-controlled protocol on the designated training file, selected on the first test file, and evaluated on the held-out second test file; the INT8 quantizer is calibrated from an evenly spaced spread of training windows to avoid class bias. Twelve configurations spanning four filter capacities, (F₁,F₂) ∈ {(4,8),(8,16),(16,32),(32,64)}, and three temporal window lengths, W ∈ {15,30,60} minutes, are quantized, flashed, and measured on the device for tensor arena, flash footprint, inference latency, and held-out F1. All twelve configurations execute successfully: the best compact model, CNN(8,16) at  fifteen-minute window, reaches a held-out F1 of 0.959 using 4.2 KB of tensor arena and 1.24 ms per inference, with more than 320 KB of heap remaining free; the tensor arena across the full grid stays between 2.6 and 30 KB; and INT8 quantization changes F1 by at most ±0.021 relative to the floating-point baseline. These results demonstrate that on-device CNN occupancy detection is practical on  low-cost microcontroller, that a compact two-block architecture is sufficient to reach near-optimal accuracy, and that the full pipeline from leak-free training through representative INT8 calibration to on-device measurement is reproducible.
Adaptive PLC Scan-Time Optimization in a Unified PLC–SCADA Architecture Yuda Bakti Zainal
Jurnal Ecotipe (Electronic, Control, Telecommunication, Information, and Power Engineering) Vol 13 No 2 (2026): Jurnal Ecotipe, October 2026
Publisher : Jurusan Teknik Elektro, Universitas Bangka Belitung

Show Abstract | Download Original | Original Source | Check in Google Scholar | DOI: 10.33019/jurnalecotipe.v13i2.4617

Abstract

Industrial automation systems require integrated intelligence to support Industry 4.0 manufacturing. However, PLC, IoT, predictive maintenance, and digital twin technologies are typically implemented independently, limiting system performance. This study proposes a unified adaptive PLC–SCADA architecture integrating adaptive PLC scan-time optimization, IoT monitoring, machine learning-based predictive maintenance, and digital twin synchronization within a cyber–physical framework. The proposed system was validated through a 14-day laboratory experiment using 40,320 time-stamped observations. Performance was evaluated in terms of energy consumption, PLC scan time, communication latency, and predictive maintenance accuracy. Compared with a conventional PLC architecture, the proposed framework reduced energy consumption by 25%, PLC scan time by 60.4%, and communication latency by 20.1%, while achieving 95.0% predictive maintenance accuracy. These results demonstrate the effectiveness of the proposed architecture for energy-efficient, intelligent, and data-driven industrial automation.
Single-Camera Flood Monitoring Using YOLOv5 for Water Level and Turbidity Detection Gamma Aditya Rahardi; Sherly Apta Maharani; Hasanur Mohammad Firdausi; Satryo Budi Utomo; Dani Hari Tunggal Prasetiyo
Jurnal Ecotipe (Electronic, Control, Telecommunication, Information, and Power Engineering) Vol 13 No 2 (2026): Jurnal Ecotipe, October 2026
Publisher : Jurusan Teknik Elektro, Universitas Bangka Belitung

Show Abstract | Download Original | Original Source | Check in Google Scholar | DOI: 10.33019/jurnalecotipe.v13i2.4618

Abstract

Floods are one of the most common natural disasters and require efficient early warning systems to mitigate their effects on infrastructure and communities. Conventional flood monitoring systems generally consist of many physical sensors, which may incur higher maintenance cost and reduce the system robustness in a severe river environment. The purpose of this study is to create a single-camera flood monitoring system that is capable of detecting water level and water turbidity in real-time using YOLOv5. An initial dataset containing 1,711 original images was collected and augmented to 4,104 images for model training and evaluation. Four YOLOv5 variants (YOLOv5s, YOLOv5m, YOLOv5l, and YOLOv5x) were trained for 50 and 150 epochs. Experimental results show that all models have high detection performance with precision, recall and mAP values above 0.98. YOLOv5s achieved the best real-time performance with 4.26 FPS and maintained competitive accuracy. Detection failures due to overexposure were observed at high illumination levels and illumination analysis indicated that detection can be reliably performed under lighting conditions below 25,000 lux. The proposed system provides a vision-based alternative for real-time inundation early warning applications.