International Journal of Electrical and Computer Engineering Systems

Comparative Study of the Grid Current Harmonic Attenuation in a Photovoltaic Generator Due to the Influence of the Synchronization Strategy

2024-11-08T09:40:42+01:00

The present paper studies the current harmonic attenuation for four synchronization strategies commonly used in inverters for photovoltaic power generation. In a model of a 6kWp photovoltaic generator, the four synchronization strategies are implemented in the inverter controller. Real-time simulations are performed, for this purpose, the models of the photovoltaic generator and the utility grid were embedded in an OPAL-RT OP5707XG simulator. The distortion of the grid current for each synchronization strategy is analyzed using its corresponding frequency spectrum and a comparison is made with the IEEE Std. 519-2022 standard. The purpose of this test is to observe the effect of the synchronization strategy on the harmonic attenuation of the grid currents. The results show that one of the synchronization strategies evaluated in this work may be sufficient for the system to comply with the harmonic standard for photovoltaic generators without the use of harmonic compensation structures or active harmonic filters. The evaluation of the harmonic distortion behavior of photovoltaic generators as a function of the synchronization strategy used in the inverter controller is the principal work contribution.

Hyperparameter Optimization for Deep Learning Modeling in Short-Term Load Forecasting

2025-01-23T13:27:38+01:00

The evolution of new technologies has made short-term power load forecasting an essential part of the streamlining process in the management of power grid systems. Machine learning algorithms have been applied widely in this area but with little success towards achieving better accuracy rates. These gaps point out the necessity for better forecasting methods . This study is about the power grid system from Ho Chi Minh city in Vietnam. Ho Chi Minh operates as a metropolitan area on the rise with economic activity and seasonal factors greatly influencing electricity consumption. Due to its intricate fluctuations in consumption pattern, the city is known for having a high level of energy. This makes the city suitable for an in-depth investigation regarding a case study on short-term load forecasting approaches. In this study, the goal is to evaluate the effectiveness of three hyperparameter optimization methods: Random Search, Grid Search, and Bayes Search. All these methods optimize the performance of Convolutional Neural Network (CNN) models for short-term electricity load forecasting in Ho Chi Minh City. The results obtained through this work can also be used as a basis for introducing the methods to other locations in Vietnam. The assessment of the techniques is performed using fundamental error measures such as Mean Absolute Error (MAE) and Mean Absolute Percentage Error (MAPE). Mean Absolute Error (MAE), Mean Absolute Percentage Error (MAPE), Mean Squared Error (MSE), and Root Mean Squared Error (RMSE). Bayes Search completed with an MAE of 77.93, MAPE of 2.94%, MSE of 10,376.7, and RMSE of 101.9. These results indicate a noticeable enhancement in prediction accuracy when compared with the outcomes from Grid Search and Random Search. Grid Search provided an MAE of 106.23, MAPE of 3.95%, MSE of 17,033.7, and RMSE of 130.5. Random Search produces results of an MAE of 96.8, MAPE of 3.57%, MSE of 14,951.0, RMSE of 122.3. These results are evidence that Bayes Search is better for short-term electricity load forecasting in Ho Chi Minh City. The study also proposes an evaluation framework, which is meant for load forecasting in Vietnam. It is designed for Ho Chi Minh City predicting purposes, thus, integrating innovative concepts with actual forecasting functions. The framework is also applicable to other areas in Vietnam, both rural and urban, having different power consumption patterns. The reduction in forecasting inaccuracies through the use of Bayes Search is found to be promising as observed in the research. This automation supports better decision-making in energy management. It helps reduce costs in dynamic and complex power grid environments. These findings have practical value. They support efforts to build more flexible and efficient energy grids in Vietnam.

Highly Miniaturized Octa-band Antenna Using Concentric Circular Split Ring Structures

2025-01-24T07:05:43+01:00

The proposed antenna design represents a systematic evolution from a simple ring-shaped structure to a highly efficient and versatile multi-band configuration tailored for next-generation wireless communication systems. Through the integration of rectangular slots, circular-shaped split ring resonators (CSRRs), and optimized geometries, the antenna achieves octa-band operation with superior impedance matching, enhanced bandwidth, and improved performance over a wide frequency range. The antenna is designed to support communication bands, including 4G/3G/2G, Wi-Fi, WLAN, WiMAX, and sub-6 GHz 5G connectivity. It resonates at 1.22, 2.12, 3.00, 4.76, 5.40, 5.94, 6.70, and 7.44 GHz, with a compact electrical size of 0.08 λ0 × 0.08 λ0. The inclusion of CSRRs and slots significantly expands the operational frequency bands while achieving a radiation efficiency of 84% and a peak gain of 4.1 dBi, making it well-suited for modern wireless applications. Moreover, the antenna design simplifies manufacturing and reduces the costs. Its compact and efficient structure ensures seamless integration into portable devices such as tablets and laptops, addressing the challenges of system complexity, size, and cost. This antenna provides a practical and scalable solution to meet the demands of diverse frequency bands in modern communication systems.

DCT-based Robust Reversible Watermarking Technique based on histogram Modification

2025-02-21T14:26:34+01:00

In this paper, a strong, reversible image watermarking technique based on discrete cosine transform (DCT) and histogram shifting is proposed, where it overcomes the following concerns: (i) Reversing the cover object to its starting appearance is the primary goal of the reversible watermarking system. (ii) Military, medical, and standard law enforcement images are the main types of images that require distortion and reinstatement of the cover object following the watermark extraction. (iii) Lack of robustness and cover image-dependent embedding capacity are the primary concerns about reversible watermarking. Decompose the cover object into blocks that don't overlap in the first stage to insert a binary watermark bit into every block that is converted. These binary bits of watermark are embedded by altering a single set of middle substantial AC coefficients. To restore the cover image, subsequently using the histogram bin shifting method, a location map is created and integrated within the cover image. On the extracting side, at first, a location map is extracted from the image using the histogram bin shifting technique. In the following step, the image's watermark is recovered, and a reversed image has been generated using a location map. To verify the robustness property, several image processing attacks are tested with the suggested reversible watermarking approach, and favorable results are attained. The proposed scheme using the Lena image achieved 46.62 imperceptibility for 4096 embedding capacities. To methodically evaluate the proposed approach, it is compared with two current reversible watermarking systems, where they achieved 39.10 and 37.90 imperceptibility with 4.4 × 103 and 256 embedding capacities, respectively. The experimental results affirmed that the suggested method exhibits superior performance relative to these existing techniques.

Customer In-Store Behavior Analysis Using Beacon Data at a Home Improvement Retailer

2025-03-28T13:09:10+01:00

In this study, we aimed to analyze the in-store behavior of customers at a home improvement retail company using data collected from Bluetooth Low Energy beacon devices installed on shelves and shopping carts within a selected store. The beacons were strategically placed on store shelves to ensure complete coverage, leaving no blind spots. To cover 18 departments spanning a total area of approximately 4,800 square meters, 99 beacons were deployed. The duration of stay in each department, the order of visits, and the absolute visit date and time were recorded in the database. To investigate the relationship between in-store behavior and purchase data, we combined customers' behavioral data with their purchase information. Correlation analysis revealed a positive relationship between visit duration and purchase amount, particularly in the Floor Deco, Paint, and Taps departments. Additionally, we visualized store-wide data using a network diagram, highlighting key shopping areas, customer flow patterns, and high-revenue departments. The problem was also formulated as a multi-class classification task, and LSTM and XGBoost algorithms were applied for comparative analysis. Experiments were conducted on both the original dataset and a cleaned version, utilizing two distinct data modeling approaches: one based solely on sequential department visits and another incorporating visit duration. The results showed that both models performed similarly on the noisy dataset, indicating that adding duration information did not improve learning. However, when trained on the cleaned dataset where short- duration visits were removed, LSTM models outperformed XGBoost, demonstrating a stronger ability to capture meaningful sequential patterns. These findings highlight the potential of BLE beacon technology in retail analytics, offering deeper insights into customer behavior and informing data-driven decision-making for store optimization and personalized marketing. Future work will focus on expanding the dataset and refining predictive models to further enhance the accuracy and applicability of in-store behavior analysis.

Bibliometric Analysis of Scientific Production of Intelligent Video Surveillance

2025-01-07T12:53:41+01:00

This article offers a bibliometric analysis of academic research in intelligent video surveillance, evaluating its evolution between 2000 and 2024. 1,343 documents were collected from the Scopus database and the PRISMA methodology was applied to organize the search and selection of relevant publications. The findings show a notable increase in the number of studies, reaching its highest point in 2022, driven by advances in artificial intelligence, the Internet of Things (IoT) and deep learning. China leads scientific production in this field, followed by India and the United States. Main research areas include real-time surveillance using deep learning methods, sequential and transfer learning techniques, as well as the use of advanced YOLO, Faster-RCNN and RFCN algorithms in controlled environments; however, detecting unusual behavior is a latent challenge.