International Journal of Electrical, Energy and Power System Engineering

Enhanced Fault Detection in Solar Photovoltaic Modules Using VMD-LSTM Model

2024-11-02T14:22:33+07:00

Detection of solar PV faults in an Accurate and versatile technique are essential because the safety and efficiency of solar photovoltaic (PV) modules greatly depend on efficient fault identification. However, because it can be challenging to identify complex operating patterns and detect tiny faults, currently methods frequently have low accuracy. This may make it more difficult to validate the models, which would limit their usefulness in the actual world. This paper presents a new fault detection method that combines Empirical Mode Decomposition (EMD) with the power of Long Short-Term Memory (LSTM) networks. Critical features are efficiently extracted from the data by use of an adaptive decomposition of voltage and current signals into Intrinsic Mode Functions k(IMFs) through the use of EMD. An LSTM network that has been trained to recognize complex patterns and periodic connections then processes this information. Our model which has been validated using a PSCAD simulation model, shows notable improvements in accuracy and durability of more than 92% after undergoing thorough testing on a simulated PV system that allows for several fault types and their severities when compared to existing methods.

Optimization of Disk-Type External Rotor SRGs for Wind Power Generation

2024-11-01T14:06:12+07:00

In small-scale wind power generation, the disk-type external rotor switched reluctance generator (SRG) emerges as a promising innovation, offering distinct advantages. This comprehensive study, through rigorous steady-state and dynamic simulations, meticulously examines the performance of a carefully designed disk-type external rotor SRG using advanced finite element analysis tools such as Maxwell and Simplorer. The simulation results validate the excellence of this novel design, demonstrating its capability to achieve commendable power generation in both steady-state and dynamic scenarios. The simulations provide strong evidence of the generator’s ability to maintain stability under varying operational conditions while consistently delivering promising power generation. This research contributes to the validation and recognition of the disk-type external rotor SRG as a reliable and efficient solution in direct-drive wind power systems. By highlighting the generator's robustness and efficiency, this study paves the way for the adoption of this innovative SRG design in practical applications, advancing wind power generation technology.

Adaptive Security Solutions for NOMA Networks: The Role of DDPG and RIS-Equipped UAVs

2024-11-02T14:29:16+07:00

In this work, we apply the Deep Deterministic Policy Gradient (DDPG) technique to improve the security of a non-orthogonal multiple access (NOMA) downlink network by enabling use of a reconfigurable intelligent surface (RIS) equipped unmanned aerial vehicles (UAV). Our main objective is to prevent eavesdroppers from accessing the network while preserving seamless communication for authorized users. The system is made up of a UAV integrated with an RIS which is essential for optimizing signal paths, and a Base Station. Our work aims to maximize secrecy rates for all users under possible eavesdropping scenarios by dynamically adjusting the RIS’s phase shifts and power allocations. This method not only shows how flexible and successful the DDPG algorithm is at protecting wireless communications when used in conjunction with an RIS but it also highlights how much the algorithm has advanced secure communication systems.

Implementation of Solar Power Plant as a Backup Power Source in Apartment Buildings

2024-11-03T19:37:40+07:00

Indonesia has an average solar energy potential of 4.8 kWh/m²/day with a monthly variation of around 9%, providing opportunities for renewable energy utilization through Solar Power Plants to reduce dependence on fossil fuels and lower carbon emissions. This study is applied to The Lana Apartment, projected to have high electricity consumption. The main supply comes from PLN with a capacity of 2000 kVA, while backup power is provided by a generator with a capacity of 1250 kVA. To reduce reliance on the generator, this study aims to design and analyze Solar Power Plants as an environmentally friendly backup power system for the apartment. The Solar Power Plants design was created using HOMER software to model energy production potential, calculate power requirements, and evaluate system performance using the performance ratio. Simulation results show that the designed Solar Power Plants have a capacity of 2997.28 kWp, an inverter capacity of 3500 kW, and a battery capacity of 50160 Ah. This system can generate approximately 4,165,251.97 kWh per year with a performance ratio of 79.32%, indicating good operational efficiency in line with optimal Solar Power Plants standards. The implementation of these Solar Power Plants is expected to provide a more environmentally friendly backup power alternative and potentially reduce operational electricity costs in the apartment building.

Implementation of an Android-Based Attendance Application with Geofence Method for Employee Monitoring Efficiency

2024-11-03T13:37:42+07:00

This research aims to develop an Android-based employee attendance application using the Geofence method at PT Wahanakarsa Swandiri. The company's main issue is the manual attendance system, which is prone to manipulation and inefficient for monitoring employee attendance, especially for those working at project locations that frequently change. This application is designed to enhance the accuracy and efficiency of attendance data collection by utilizing Geofence technology, which ensures that employees can only record attendance when they are at the designated location. In addition to the Geofence feature, the app includes QR code validation to minimize the potential for fraud. The application development methodology follows a prototype approach, starting from the communication phase to identify company needs, followed by quick design, wireframe creation, and mockups. The prototype was developed using Android Studio, with Kotlin as the programming language and PostgreSQL as the database. Application testing was conducted based on the ISO 25010 standard, covering eight aspects: functionality, reliability, efficiency, portability, maintainability, compatibility, security, and usability. The test results indicate that this application performs well in all these aspects. This application is expected to address the issues of manual attendance, improve the effectiveness of attendance data, and support more accurate company decision-making.

Classification of Riau Batik Motifs Using the Convolutional Neural Network (CNN) Algorithm

2024-11-11T12:10:25+07:00

Riau Batik, a treasured cultural heritage, faces challenges in its preservation due to limited public awareness of its unique motifs. This research aims to bridge the knowledge gap by developing a website-based classification system that can identify and recognize Riau batik patterns, offering round-the-clock accessibility to users. By leveraging the Convolutional Neural Network (CNN) algorithm, the classification system was trained using a dataset of 1,440 images. The model was fine-tuned through optimization of batch size and epoch parameters to maximize classification accuracy. The training process culminated in a model with an accuracy of 89%, achieved using a batch size of 16 and 50 epochs. This system seeks to elevate public appreciation and knowledge of Riau Batik, thereby contributing to the preservation of its cultural and historical significance. The accessible classification tool presents a practical approach to ensuring the motifs and legacy of Riau Batik are preserved for future generations. The proposed CNN-based model demonstrates the potential to enhance digital engagement with traditional culture through modern technology, facilitating widespread recognition and appreciation of Riau's rich batik heritage.