Articles

Access the latest knowledge in applied science, electrical engineering, computer science and information technology, education, and health.

Advanced Search
Filter Icon

Filters article

Years

FAQ Arrow
Single Year
Range Year
0
0

Source Title

FAQ Arrow

Authors

FAQ Arrow

31,377 Article Results

Artificial neural network-enhanced solid-state DC breaker for ultra-fast protection in LVDC microgrids

10.11591/ijeecs.v43.i3.pp709-717
Eswaraiah Giddalur , Askani Jaya Laxmi
Low voltage direct current (LVDC) microgrids are increasingly adopted due to their efficiency in integrating distributed energy resources (DERs) and DC loads without multiple conversion stages. However, the presence of high amplitude fault currents and the vulnerability of electronic devices pose significant challenges to reliable protection. Conventional electromechanical switches suffer from slow response times, making them unsuitable for modern LVDC systems. Solid-state circuit breakers (SSCBs), with their millisecond-level interruption capability, offer a promising alternative. This paper introduces an artificial neural network (ANN)-based protection strategy integrated with a bi-directional SSCB for DC bus fault mitigation. The ANN is designed to optimize fault detection and clearing time, achieving rapid isolation within 0.25 ms. A feedforward two-layer neural network with 20 hidden neurons and a sigmoid activation function is trained using multiple algorithms, including Levenberg-Marquardt, Bayesian Regularization, and Scaled Conjugate Gradient. Simulation results demonstrate superior performance compared to conventional differential protection, with the LM algorithm providing the most accurate and efficient fault clearing. The proposed ANN-SSCB approach enhances system reliability, equipment safety, and overall resilience of LVDC microgrids.
Volume: 43
Issue: 3
Page: 709-717
Publish at: 2026-09-01

Graph-guided contrastive transformer architecture for robust and explainable network intrusion detection

10.11591/ijra.v15i3.pp698-708
Archana Jayapal , Kamalakkannan Somasundaram , Arun Kumar Ramamoorthy
Intrusion detection systems (IDS) are very instrumental in protecting contemporary network infrastructures against the ever-advancing cyberattacks. Conventional signature-based and machine learning-enabled IDS solutions frequently have difficulty when it comes to high false-positive rates, inability to flexibly adapt to novel attacks, and the lack of support for complex traffic dynamics. New deep learning architectures have better detection properties, yet are limited by feature overlap, temporality, and lack of extensiveness to generalization in changing network conditions. To overcome these issues, this paper presents a new graph-guided contrastive transformer-based intrusion detection system (GCT-IDS) which aims at improving detection accuracy and robustness and preserving real-time feasibility. The framework combines feature interaction by graph modeling, contrastive representation learning, and a sparse self-attention transformer to effectively learn global traffic relationships and behavioral variations. The CSE-CIC-IDS2018 data is used to test the proposed method in real network conditions.
Volume: 15
Issue: 3
Page: 698-708
Publish at: 2026-09-01

Design of a portable IoT robot with azure machine learning for monitoring mine workers’ health

10.11591/ijra.v15i3.pp577-588
Shanthi Natarajan , Vijayaraja Loganathan , Dhanasekar Ravikumar , Diwakar Venkat Nalini , Harish Elangovan , Balaji Arikrishnan
The mining environment exposes workers to physical, environmental, and health risks. The lack of effective real-time health monitoring systems leads to delayed medical responses. Hence, this paper discusses developing a portable Internet of Things (IoT) robot with advanced machine learning and cloud computing to monitor mine workers’ health and send out alerts. The system is equipped with IoT sensors that monitor parameters continuously, such as heart rate, body temperature, blood pressure, and environmental factors (gas concentrations, air quality). Data collected in real-time is transmitted to a cloud-based platform for analysis using advanced machine learning algorithms. MQ-135 detects harmful gases, and DHT11 measures humidity and transmits data to the Arduino UNO. The HC-SR04 sensor measures object distances by emitting ultrasonic waves and detecting their echoes, aiding in obstacle detection. The NEO-6M GPS with GSM SIM900 modules transmit location data and emergency alerts via the GSM network, enabling responses to potential dangers. Simulation via Proteus validates the robot’s transceiver connectivity, mobility, and sensing functions. To enhance monitoring precision, the system adopts XGBoost, which classifies mine conditions, and the training model achieves 96.77% accuracy with high precision and recall. The system with Azure Machine Learning improves detection accuracy, raising temperature, CO, NH₄, and NO₂ precision by 7.25%, 15%, 17%, and 18%, respectively. Thus, the system features an intelligent alert mechanism to notify users of emergencies, enhancing worker safety and minimizing health-related risks in mining operations.
Volume: 15
Issue: 3
Page: 577-588
Publish at: 2026-09-01

Social media resonance on destination dispersion to predict tourist behavior and travel distance using geospatial analysis

10.11591/ijaas.v15.i3.pp883-893
Nindyo Cahyo Kresnanto , Wika Harisa Putri , Muhamad Willdan
This study investigates the influence of social media popularity on tourist destination preferences in Gunungkidul Regency, Yogyakarta, Indonesia, using an integrated big data and geographic information system (GIS) approach. Field surveys involving 504 respondents were combined with sentiment analysis of 30,432 cleaned tweets collected from X (formerly Twitter). Spatial analysis was applied to identify tourist origin patterns and destination attractiveness. The results show that neutral sentiment dominates online discussions, indicating generally positive but moderate tourist experiences. Destinations with higher popularity on social media, particularly Heha Sky View, Drini Beach, and Indrayanti Beach, attracted visitors from broader and more diverse origins. Spatial analysis also indicates stronger preferences for coastal and highland destinations. The integration of big data and GIS enhances understanding of tourism behavior and spatial destination patterns. Future studies are recommended to integrate multiple social media platforms and comparative spatial analyses to improve tourism planning and destination management.
Volume: 15
Issue: 3
Page: 883-893
Publish at: 2026-09-01

One-day analysis of natural sound via very low frequency signal from Malaysian ionosphere

10.11591/ijaas.v15.i3.pp902-910
Suryadi Suryadi , Mariyam Jamilah Homam , Rohaida Mat Akir , Mardina Abdullah
This paper presents findings on the impact of lightning discharges on very low frequency (VLF) signal, which falls from 30 Hz up to 50 kHz has been used effectively for space parameter detection of the lower ionosphere signal propagation over Malaysia. Using a VLF line receiver installed at Universiti Kebangsaan Malaysia (Latitude 2° 55' N, Longitude 101° 46' E), observations conducted on 22 July 2009 revealed distinct diurnal variations. During the daytime, broadband and narrowband data were analyzed to investigate natural radio signals from transmitters in neighboring countries such as India, Japan, China, and Australia. The results reveal significant perturbations in VLF signal propagation caused by lightning discharges, leading to the detection of natural sferics, tweeks, and ionospheric disturbances. These phenomena, originating from radiated lightning discharge activity, were found to average 44 occurrences per hour during the afternoon and evening. The study highlights how these natural electromagnetic events contribute to amplitude and phase variations in VLF signals, offering deeper insights into ionospheric interactions with lightning activity. Additionally, the findings emphasize the presence of natural radio emissions such as sferics and their components, which further illustrate the effect of lightning discharges on the lower ionosphere above Malaysia.
Volume: 15
Issue: 3
Page: 902-910
Publish at: 2026-09-01

THD reduction in a 13-level multilevel inverter using the angle control technique

10.11591/ijpeds.v17.i3.pp1982-1993
Dewan Ashikur Rahaman , Aive Alamgir , Md Ashraf Hossain , Tapan Kumar Chakraborty , Raisul Islam Rafi , Raiyan Rahman Zihad , Md. Abdullah Al Mahmud , Samia Sarkar
When compared to a traditional multilevel inverter, multilevel inverters can produce switched waveforms with lower amounts of harmonic distortion. Due to their capacity to provide excellent output waveforms at lower switching frequencies and without distortion, multilevel inverters have recently attracted more attention. The dynamic voltage restorer's multilevel topology reduces the output waveform's harmonic distortion without causing inverter power output losses. This study examines the most widely used topologies to determine how the sinusoidal switching angle affects total harmonic distortion (THD%). Among the crucial multilevel topologies, the cascaded H-bridge was selected. Because it needed fewer parts than the others. Asymmetric was selected for observation and simulations of output voltages up to Fifteen levels for equal and sinusoidal angles using PSIM software after a review of the literature. Appropriate switching angles were maintained in this research. With fewer H-bridges, higher-level multilevel inverters have been manufactured.
Volume: 17
Issue: 3
Page: 1982-1993
Publish at: 2026-09-01

Real-time selective harmonic elimination in multilevel inverters using embedded metaheuristic optimization on PYNQ-Z2

10.11591/ijpeds.v17.i3.pp1914-1925
Taha Ahmad Hussein , Dahaman Ishak
This paper offers a structured methodology for regulating optimal control switching angles in multilevel inverters to achieve selective harmonic elimination (SHE) using embedded optimization algorithms on the PYNQ‑Z2 FPGA operating base. The proposed approach employs metaheuristic techniques including particle swarm optimization (PSO), genetic algorithm (GA), gray wolf optimization (GWO), slime mould algorithm (SMA), and whale optimization algorithm (WOA) to generate candidate switching angles across a wide range of modulation indices. For each modulation index, the most effective solution towards harmonic reduction and waveform quality is selected and implemented on the FPGA controller, enabling reliable real‑time operation with very low delay. Experimental validation of a 31‑level single‑phase inverter confirms the effectiveness of the method in eliminating selected harmonics and refining the fundamental output. Combining comparative algorithmic selection with FPGA‑based control demonstrates a systematic and efficient strategy for advanced inverter systems. A MATLAB/Simulink model is constructed to represent the 31-level inverter to enhance the practical aspect and study the frequency spectrum, where many harmonics that contribute to obtaining THD within the IEEE standards are eliminated. Also, the different types of losses are calculated based on the governing mathematical rates.
Volume: 17
Issue: 3
Page: 1914-1925
Publish at: 2026-09-01

Digital twin driven federated multi-agent intelligence for autonomous renewable forecasting and smart grid optimization

10.11591/ijpeds.v17.i3.pp2029-2038
Pushpa Sreenivasan , K. Gattaiah , N. Hemalatha , Radhey Shyam Meena , Mallareddy Adudhodla , V. S. Bhagavan
The rapid growth of renewable energy integration has increased the complexity of smart grid operation due to the intermittent nature of distributed energy resources and continuously varying load demand. Existing approaches often rely on centralized control or combine only selected intelligent technologies, limiting scalability, data privacy, and autonomous decision-making. This paper proposes a digital twin-driven federated multi-agent intelligence (DT-FMAI) framework that integrates virtual system synchronization, privacy-preserving distributed learning, and cooperative multi-agent control within a unified architecture. Digital twins continuously mirror physical grid assets, federated learning enables collaborative forecasting without sharing raw data, and intelligent agents coordinate energy management in real time. The framework was implemented in MATLAB/Simulink with TensorFlow Federated and evaluated using renewable generation, weather, battery, and load datasets. Results demonstrate a 15-25% reduction in forecasting error, 10-18% improvement in voltage regulation, 92-96% load-matching efficiency, and 12-20% higher energy efficiency. These outcomes demonstrate the potential of the proposed framework for scalable, secure, and intelligent renewable-integrated smart grid operation.
Volume: 17
Issue: 3
Page: 2029-2038
Publish at: 2026-09-01

Comparison of acrylic and zinc blade materials on the performance of Darrieus vertical axis wind turbine

10.11591/ijpeds.v17.i3.pp2162-2171
Dina Maizana , Andreas Tiopan Togatorop , Indri Dayana , Habib Satria , Muhammad Irwanto Misrun , Yanawati Yahya
The performance of vertical axis wind turbine is strongly influenced by blade characteristics, yet the effect of blade material on turbine performance remains relatively underexplored, particularly for small scale Darrieus type turbines. This study experimentally investigated the influence of acrylic and zinc blade materials on the aerodynamics and energy conversion performance of a three bladed Darrieus vertical axis wind Turbine. A laboratory-scale experimental setup was employed to evaluated turbine rotational speed, torque, and electrical power under a controlled wind speed of 4.3 m/s. The results demonstrate the blade material significantly affects the turbine’s ability to extract and convert wind energy. The acrylic blade turbine achieved a power coefficient (Cp) of 0.293 and an overall conversion efficiency 62.81%, compared with 0.208 and 47.11%, respectively, for the zinc bladed turbine. The acrylic configuration therefore provided approximately 25% higher overall performance than zinc configuration. These findings experimentally validate the importance of blade material selection in the design of small scale Darrieus wind turbines and indicate that acrylic can provide a more effective alternative to zinc for improving wind energy conversion under low speed operating conditions. The results provide practical guidance for material selection in the development of lightweight, low speed vertical axis turbines for decentralized and small scale renewable energy applications.
Volume: 17
Issue: 3
Page: 2162-2171
Publish at: 2026-09-01

Design of a novel single-source 15-level inverter with self-balancing capacitors and sensorless PWM control

10.11591/ijpeds.v17.i3.pp1950-1961
Taoufiq El Ansari , Ayoub El Gadari , Youssef Ounejjar
Multilevel inverters (MLIs) are widely used in energy-conversion systems because they generate high-quality AC voltages with reduced harmonic distortion. However, existing MLIs often require numerous power devices, multiple DC sources, voltage sensors, or dedicated capacitor-balancing controllers, which increases both hardware cost and control complexity. This paper proposes a single-phase 15-level inverter derived from the Packed U-Cell structure. It employs a single DC source, three capacitors, and a reduced number of power switches. Based on the number of power switches, gate drivers, diodes, capacitors, DC sources, output levels, and total standing voltage per unit (TSVpu), the proposed topology achieves a lower cost function than the compared topologies reported in the literature. The proposed topology achieves a relatively low total standing voltage per unit (TSVpu) of 4.43. Sensorless open-loop SPWM offers inherent capacitor-voltage self-balancing, eliminating the need for voltage sensors or additional balancing loops. MATLAB/Simulink validation at 2 kHz and a modulation index of 1 covers steady-state operation, load transients, nonlinear loading, and DC-source voltage fluctuations. For a 50 Ω–20 mH load, the current THD is 2.20% without an output filter, confirming suitability for energy-conversion systems.
Volume: 17
Issue: 3
Page: 1950-1961
Publish at: 2026-09-01

Implementation of filter-clamped topology for transformerless three-phase PV inverters with reduced leakage current

10.11591/ijpeds.v17.i3.pp1553-1563
Mohammed Abdullah , S. Venkata Padmavathi
The growing prevalence of grid-connected photovoltaic (PV) systems has intensified the demand for efficient, reliable, and compact power conversion technologies. Transformerless photovoltaic (TLPV) systems provide improved efficiency and reduced size and costs compared to those using line-frequency or high-frequency isolation transformers. However, these inverters commonly exhibit leakage current because they lack galvanic isolation. Conventional topologies address this issue by adding extra semiconductor devices or employing complex control methods. This paper examines how a filter-clamped inverter (FCI) operates in grid-connected three-phase transformerless photovoltaic (TLPV) applications. However, the proposed inverter successfully reduces leakage current without additional components or control modifications. This makes it a compact and simplified alternative for transformerless PV applications. Additionally, the traditional full-bridge (FB) inverter with three phases, when compared to the FC inverter, has very high leakage current. Simulation results validate the FC inverter’s ability to minimize leakage current.
Volume: 17
Issue: 3
Page: 1553-1563
Publish at: 2026-09-01

Spatiotemporal digital twin for city-scale EV charging infrastructure using LSTM-GNN fusion and resilience-driven optimization

10.11591/ijpeds.v17.i3.pp2271-2280
Deepa Somasundaram , B. Ravisankar , Chavvakula Janaki Devi , Ajay Babu Bathula , Sabarimuthu Muthusamy , K. Vinoth
The rapid growth of electric vehicles (EVs) requires intelligent and resilient planning of charging infrastructure under dynamic urban conditions. This paper proposes a city-scale spatiotemporal digital twin (SDT) that integrates LSTM-GNN fusion with resilience-driven hybrid optimization (GA-PSO-deep reinforcement learning) for adaptive EV infrastructure management. The LSTM model captures temporal variations in charging demand, while the graph neural network (GNN) learns spatial dependencies across charging stations, mobility networks, and grid components. Unlike existing approaches, the proposed framework incorporates power electronics-aware modeling, including charger power conversion system (PCS) efficiency, switching losses, and harmonic distortion constraints, ensuring realistic grid interaction. The digital twin also considers energy system metrics such as transformer loading, voltage deviation, and renewable energy variability, along with EV drive-cycle characteristics like fast charging and battery limits. Simulation results show that the proposed model improves demand prediction accuracy by 14-22%, reduces grid overload probability by 35%, lowers operational cost by 18%, and achieves improved power quality performance compared to conventional methods. The system maintains a high resilience index (>0.92) under stress scenarios. Overall, this work presents a holistic AI-driven digital twin framework that enhances grid stability, supports sustainable EV integration, and enables scalable deployment of future smart charging infrastructure.
Volume: 17
Issue: 3
Page: 2271-2280
Publish at: 2026-09-01

Transformer fault diagnosis using dissolved gas analysis: a hybrid ensemble model with data preprocessing

10.11591/ijpeds.v17.i3.pp1780-1793
Fatima Zohra Boudjella , Souhila Boudjella , Nasiru Yahaya Ahmed , Hazlee Azil Illias , Smail Latifa , Reriballah Hafidha
Failures and guaranteed dependability of the electrical grid, early fault diagnosis in power transformers is essential. By examining gas ratios suggestive of faults, dissolved gas analysis (DGA) continues to be a vital component for transformer health monitoring. Using four preprocessing techniques raw data, min-max normalization, logarithmic transformation, and square root transformation; this study suggests a machine learning method for fault detection using DGA gas ratios (such as CH₄/H₂, C₂H₂/C₂H₄). Random forest (RF), support vector machines (SVM), gradient boosted trees (GBT), and a hybrid RF-GBT model that uses prediction fusion were the four supervised classifiers assessed. Performance was assessed using accuracy, precision, recall, f1-score, and Cohen's kappa. Experimental results show that the hybrid RF-GBT model with logarithmic transformation achieves the highest performance, with 94.93% accuracy and 92.37% Cohen's kappa, significantly outperforming individual classifiers. Data preprocessing, particularly logarithmic and square root transformations, enhances diagnostic robustness by mitigating feature skewness. This study underscores the importance of tailored preprocessing and ensemble methods for reliable transformer fault diagnosis.
Volume: 17
Issue: 3
Page: 1780-1793
Publish at: 2026-09-01

Deep learning-based intelligent islanding detection for grid-connected photovoltaic systems using convolutional neural networks

10.11591/ijpeds.v17.i3.pp1755-1767
Dondapati Ravi Kishore , T. Vijay Muni , K. Venkata Kishore , V. Suresh , S. Saahithi , Thandava Krishna Sai Pandraju , S. N. Chaitra , B. Logeshwary
The increasing integration of photovoltaic (PV) systems into smart grids requires fast and reliable islanding detection to maintain grid stability and operational safety. Conventional detection methods often face challenges such as delayed response, reduced accuracy, and large non-detection zones under varying operating conditions. This paper proposes an intelligent islanding detection method for grid-connected PV systems using advanced artificial intelligence and deep learning techniques. Electrical parameters including voltage, current, frequency, and power signals are analyzed using signal processing methods and classified through a convolutional neural network (CNN) model developed in MATLAB/Simulink. Simulation results demonstrate that the proposed AI-based approach achieves rapid and accurate detection of islanding events with improved sensitivity and reduced false detections compared to conventional techniques. The proposed framework enhances the reliability, safety, and protection performance of modern photovoltaic power systems integrated with smart grids.
Volume: 17
Issue: 3
Page: 1755-1767
Publish at: 2026-09-01

Short-circuit analysis and protection coordination of a 33 kV phosphate plant distribution network

10.11591/ijpeds.v17.i3.pp1768-1779
Cheikhani Abdel Kader , Bamba El Heiba , Mohamed El Mamy Mohamed Mahmoud , Beibah Gleigume , Abdel Kader Mahmoud
This study presents a short-circuit and protection coordination analysis of a 33 kV/0.4 kV industrial distribution network supplying a phosphate processing plant in Mauritania. Using ETAP software, the system was modeled to evaluate fault behaviors based on IEC 60909 and IEC 60255-151 standards. The study assesses the existing protection architecture and proposes an optimized digital protection framework. Simulation results indicate that the initial symmetrical short-circuit current at the 0.4 kV busbar reaches 96.5 kA, exceeding the 25-36 kA breaking capacity of the legacy equipment by nearly 300%. The analysis also investigates single-line-to-ground faults, revealing a fault current inversion phenomenon driven by the solid grounding configuration. To address these vulnerabilities, the study proposes upgrading to 150 kA-rated high-breaking-capacity switchgear and implementing advanced negative-sequence protection (ANSI 46) and transformer differential protection (ANSI 87T). This work provides a practical diagnostic framework for mitigating asymmetrical faults and optimizing protection coordination in heavy-duty industrial clusters.
Volume: 17
Issue: 3
Page: 1768-1779
Publish at: 2026-09-01
1 2 3
...
2091 2092
Show 34 of 2092

Discover Our Library

Embark on a journey through our expansive collection of articles and let curiosity lead your path to innovation.

Explore Now
Library 3D Ilustration