We address the requirement for Energy Communities (ECs) to integrate efficient Energy Management Systems (EMSs) that optimize resource operation and maximize the benefits for participants. In this work, we implement an EMS that considers the supply and demand profiles of agents, fostering their engagement and ensuring their continued involvement within the community. We establish a mathematical model of an EC composed of prosumers with different types of distributed energy resources and pure consumers. The EMS integrates game theory and optimization techniques to coordinate and schedule energy transactions using welfare functions. Through the developed algorithm, the maximization of community welfare is ensured. This method is compared with the traditional Interior-Point Method (IPM). The results indicate a normalized error average of 0.23%. We simulate a community with six agents and analyze two case studies. The results show that the EMS promotes agent participation by optimizing their resources and achieving more competitive buy and sell prices compared to the main grid. Furthermore, the EMS prioritizes energy dispatch within the EC over transactions with the main grid and accounts for generation costs. The implementation of the EMS improves community welfare, thus contributing to the sustainability of the EC.
{"title":"Welfare Optimization in Energy Communities with P2P Markets","authors":"Sofía Chacón;Katerine Guerrero;Germán Obando;Andrés Pantoja","doi":"10.1109/TLA.2025.11072495","DOIUrl":"https://doi.org/10.1109/TLA.2025.11072495","url":null,"abstract":"We address the requirement for Energy Communities (ECs) to integrate efficient Energy Management Systems (EMSs) that optimize resource operation and maximize the benefits for participants. In this work, we implement an EMS that considers the supply and demand profiles of agents, fostering their engagement and ensuring their continued involvement within the community. We establish a mathematical model of an EC composed of prosumers with different types of distributed energy resources and pure consumers. The EMS integrates game theory and optimization techniques to coordinate and schedule energy transactions using welfare functions. Through the developed algorithm, the maximization of community welfare is ensured. This method is compared with the traditional Interior-Point Method (IPM). The results indicate a normalized error average of 0.23%. We simulate a community with six agents and analyze two case studies. The results show that the EMS promotes agent participation by optimizing their resources and achieving more competitive buy and sell prices compared to the main grid. Furthermore, the EMS prioritizes energy dispatch within the EC over transactions with the main grid and accounts for generation costs. The implementation of the EMS improves community welfare, thus contributing to the sustainability of the EC.","PeriodicalId":55024,"journal":{"name":"IEEE Latin America Transactions","volume":"23 8","pages":"687-695"},"PeriodicalIF":1.3,"publicationDate":"2025-07-08","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"https://ieeexplore.ieee.org/stamp/stamp.jsp?tp=&arnumber=11072495","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"144581450","PeriodicalName":null,"FirstCategoryId":null,"ListUrlMain":null,"RegionNum":4,"RegionCategory":"工程技术","ArticlePicture":[],"TitleCN":null,"AbstractTextCN":null,"PMCID":"OA","EPubDate":null,"PubModel":null,"JCR":null,"JCRName":null,"Score":null,"Total":0}
Accurate solar resource assessment is critical for the development of solar energy projects, especially in regions with complex climatic and geographic conditions. This study evaluates the performance of various satellite-based and reanalysis models in estimating global horizontal irradiance (GHI) in Northwestern Argentina, focusing on two locations characterized by different environmental conditions: La Quiaca and Salta. Five satellite-based models (CAMS Heliosat-4, NREL NSRDB, GOES DSR, LSA-SAF MDSSFTD, and GOES G-CIM) and two reanalysis datasets (MERRA-2 and ERA-5) were analysed and compared with high-quality ground-based measurements recorded between 2020 and 2023. The results show that the G-CIM and NSRDB models provide the most accurate irradiance estimates, effectivelyminimising errors even in challenging environments with extreme altitude or variable terrain reflectivity. At the 10-minute time scale in Salta, the G-CIM model yields a root mean squared deviation (RMSD) of 23.4% and a mean bias of 4.8%, whereas the NSRDB model records an RMSD of 26.6% and a mean bias of 4.2%. In La Quiaca, both models achieve RMSD values below 20% and mean biases under 1%. At the 60-minute scale, in Salta, G-CIM and NSRDB exhibit RMSDs of 20.7% and 19.7%, with corresponding mean biases of 5.4% and 3.6%, respectively, while in La Quiaca they maintain mean biases below 1% and RMSDs of 13.2% for G-CIM and 12.6% for NSRDB. Conversely, the MERRA-2 and ERA-5 reanalysis models showed higher uncertainties, particularly in areas with significant microclimatic variations. The study highlights the importance of using locally validated satellite data for accurate solar resource assessment and emphasises the need for site-specific adjustments when applying global irradiance models. These findings contribute to improved planning and decision-making for solar energy projects in Northwest Argentina and provide valuable insights for researchers, policy makers and industry professionals.
{"title":"Evaluation of Satellite and Reanalysis Models for Solar Irradiance Estimation in Northwest Argentina","authors":"Rubén Ledesma;Rodrigo Alonso-Suárez;Germán Salazar;Fernando Nollas;Olga Vilela","doi":"10.1109/TLA.2025.11072498","DOIUrl":"https://doi.org/10.1109/TLA.2025.11072498","url":null,"abstract":"Accurate solar resource assessment is critical for the development of solar energy projects, especially in regions with complex climatic and geographic conditions. This study evaluates the performance of various satellite-based and reanalysis models in estimating global horizontal irradiance (GHI) in Northwestern Argentina, focusing on two locations characterized by different environmental conditions: La Quiaca and Salta. Five satellite-based models (CAMS Heliosat-4, NREL NSRDB, GOES DSR, LSA-SAF MDSSFTD, and GOES G-CIM) and two reanalysis datasets (MERRA-2 and ERA-5) were analysed and compared with high-quality ground-based measurements recorded between 2020 and 2023. The results show that the G-CIM and NSRDB models provide the most accurate irradiance estimates, effectivelyminimising errors even in challenging environments with extreme altitude or variable terrain reflectivity. At the 10-minute time scale in Salta, the G-CIM model yields a root mean squared deviation (RMSD) of 23.4% and a mean bias of 4.8%, whereas the NSRDB model records an RMSD of 26.6% and a mean bias of 4.2%. In La Quiaca, both models achieve RMSD values below 20% and mean biases under 1%. At the 60-minute scale, in Salta, G-CIM and NSRDB exhibit RMSDs of 20.7% and 19.7%, with corresponding mean biases of 5.4% and 3.6%, respectively, while in La Quiaca they maintain mean biases below 1% and RMSDs of 13.2% for G-CIM and 12.6% for NSRDB. Conversely, the MERRA-2 and ERA-5 reanalysis models showed higher uncertainties, particularly in areas with significant microclimatic variations. The study highlights the importance of using locally validated satellite data for accurate solar resource assessment and emphasises the need for site-specific adjustments when applying global irradiance models. These findings contribute to improved planning and decision-making for solar energy projects in Northwest Argentina and provide valuable insights for researchers, policy makers and industry professionals.","PeriodicalId":55024,"journal":{"name":"IEEE Latin America Transactions","volume":"23 8","pages":"706-717"},"PeriodicalIF":1.3,"publicationDate":"2025-07-08","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"https://ieeexplore.ieee.org/stamp/stamp.jsp?tp=&arnumber=11072498","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"144581477","PeriodicalName":null,"FirstCategoryId":null,"ListUrlMain":null,"RegionNum":4,"RegionCategory":"工程技术","ArticlePicture":[],"TitleCN":null,"AbstractTextCN":null,"PMCID":"OA","EPubDate":null,"PubModel":null,"JCR":null,"JCRName":null,"Score":null,"Total":0}
Pub Date : 2025-07-08DOI: 10.1109/TLA.2025.11072501
Francisco Antonio Lloret Abrisqueta;Antonio Guerrero González;Roberto Zapata Martinez
This study presents an innovative implementation of Industry 5.0 principles in a window production line, integrating advanced robotics and artificial intelligence technologies to improve operational efficiency and worker well-being. A robotic cell was designed to automate the handling of heavy components in the final production stage, resulting in a 35% reduction in cycle times and a significant decrease in ergonomic risks. Additionally, an interactive voice assistant based on generative AI was implemented, allowing operators to access system data and technical information in real-time through cognitive interaction. The results show a substantial improvement in job satisfaction, with a 278% increase in the perception of occupational health. This approach not only optimizes productivity but also redefines workers' roles, aligning with the human-centered vision of Industry 5.0. The study demonstrates how the integration of advanced technologies can create safer, more efficient, and adaptable work environments in modern manufacturing.
{"title":"Redefining Human-Machine Collaboration: Industry 5.0 to Improve Safety and Efficiency","authors":"Francisco Antonio Lloret Abrisqueta;Antonio Guerrero González;Roberto Zapata Martinez","doi":"10.1109/TLA.2025.11072501","DOIUrl":"https://doi.org/10.1109/TLA.2025.11072501","url":null,"abstract":"This study presents an innovative implementation of Industry 5.0 principles in a window production line, integrating advanced robotics and artificial intelligence technologies to improve operational efficiency and worker well-being. A robotic cell was designed to automate the handling of heavy components in the final production stage, resulting in a 35% reduction in cycle times and a significant decrease in ergonomic risks. Additionally, an interactive voice assistant based on generative AI was implemented, allowing operators to access system data and technical information in real-time through cognitive interaction. The results show a substantial improvement in job satisfaction, with a 278% increase in the perception of occupational health. This approach not only optimizes productivity but also redefines workers' roles, aligning with the human-centered vision of Industry 5.0. The study demonstrates how the integration of advanced technologies can create safer, more efficient, and adaptable work environments in modern manufacturing.","PeriodicalId":55024,"journal":{"name":"IEEE Latin America Transactions","volume":"23 8","pages":"729-735"},"PeriodicalIF":1.3,"publicationDate":"2025-07-08","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"https://ieeexplore.ieee.org/stamp/stamp.jsp?tp=&arnumber=11072501","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"144581451","PeriodicalName":null,"FirstCategoryId":null,"ListUrlMain":null,"RegionNum":4,"RegionCategory":"工程技术","ArticlePicture":[],"TitleCN":null,"AbstractTextCN":null,"PMCID":"OA","EPubDate":null,"PubModel":null,"JCR":null,"JCRName":null,"Score":null,"Total":0}
Automated retinal disease diagnosis leveraging cutting-edge computer vision methodologies supports clinicians in the early identification of pathological conditions. This investigation delivers a novel framework, DeepRetinaNet for automating retinal disease diagnosis. The developed DeepRetinaNet model has two stages of novelties, including vessel extraction followed by disease identification. In the vessel extraction stage, the green channel, known for its heightened sensitivity to retinal vascular structures, is extracted from the source images. Subsequently, the vessel extraction network: RetiSegNet, processes these green channel images to extract retinal vessels, generating binary vessel maps. During the fusion phase, the original fundus images are combined with the extracted vessel maps to produce fused representations, encapsulating enriched spatial details from both sources. In the identification stage, these fused images are utilized to train the proposed classification framework: STDeepNet, which incorporates Modified Identity (MI), Modified Convolution (MCONV) blocks, and Long Short-Term Memory (LSTM) layers to effectively identify the diseases. The efficacy of the developed technique is corroborated using visual illustration and objective analysis. Also, the efficiency of the designed framework is verified on six benchmark datasets. The proposed framework demonstrates superior performance compared to 49 state-of-the-art methods, achieving notable accuracy in retinal disease diagnosis.
{"title":"DeepRetinaNet: An Automated AI-Based Framework for Retinal Disease Diagnosis","authors":"Akshya Kumar Sahoo;Priyadarsan Parida;Manoj Kumar Panda;Chittaranjan Nayak;N. Mohankumar","doi":"10.1109/TLA.2025.11072496","DOIUrl":"https://doi.org/10.1109/TLA.2025.11072496","url":null,"abstract":"Automated retinal disease diagnosis leveraging cutting-edge computer vision methodologies supports clinicians in the early identification of pathological conditions. This investigation delivers a novel framework, DeepRetinaNet for automating retinal disease diagnosis. The developed DeepRetinaNet model has two stages of novelties, including vessel extraction followed by disease identification. In the vessel extraction stage, the green channel, known for its heightened sensitivity to retinal vascular structures, is extracted from the source images. Subsequently, the vessel extraction network: RetiSegNet, processes these green channel images to extract retinal vessels, generating binary vessel maps. During the fusion phase, the original fundus images are combined with the extracted vessel maps to produce fused representations, encapsulating enriched spatial details from both sources. In the identification stage, these fused images are utilized to train the proposed classification framework: STDeepNet, which incorporates Modified Identity (MI), Modified Convolution (MCONV) blocks, and Long Short-Term Memory (LSTM) layers to effectively identify the diseases. The efficacy of the developed technique is corroborated using visual illustration and objective analysis. Also, the efficiency of the designed framework is verified on six benchmark datasets. The proposed framework demonstrates superior performance compared to 49 state-of-the-art methods, achieving notable accuracy in retinal disease diagnosis.","PeriodicalId":55024,"journal":{"name":"IEEE Latin America Transactions","volume":"23 8","pages":"718-728"},"PeriodicalIF":1.3,"publicationDate":"2025-07-08","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"https://ieeexplore.ieee.org/stamp/stamp.jsp?tp=&arnumber=11072496","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"144581628","PeriodicalName":null,"FirstCategoryId":null,"ListUrlMain":null,"RegionNum":4,"RegionCategory":"工程技术","ArticlePicture":[],"TitleCN":null,"AbstractTextCN":null,"PMCID":"OA","EPubDate":null,"PubModel":null,"JCR":null,"JCRName":null,"Score":null,"Total":0}
Pub Date : 2025-07-08DOI: 10.1109/TLA.2025.11072503
Miguel Gutierrez;Mario Chacon-Murguia;Juan Ramirez-Quintana
Image inpainting is a computer vision task that reconstructs missing image regions. Given its potential for various applications, it is an area of great interest. Despite advances in this field thanks to deep models such as autoencoders and generative adversarial networks, fundamental challenges persist, such as the causal interpretation of information loss and the risk of overfitting and lack of diversity in the features obtained with autoencoders. In this context, this article presents an innovative deep network model to solve occluded face inpainting. The model focuses on attributing the loss of information to the occlusion. The proposed model consists of two deep models: one for segmenting the object occluding the face, called SOCLNET, and another for reconstructing the face, IFACENET. SOCLNET is an improvement of the DeepLabv3 network by adding self-attention mechanisms. IFACENET is based on an autoencoder with an ensemble learning approach in the encoder to improve the diversity of the extracted features. SOCLNET was evaluated to demonstrate that the segmentation of occluding objects works adequately, even on out-of-distribution images. Its performance metrics were Pixel Accuracy = 0.93 and IoU = 0.788. The IFACENET model was compared against other state-of-the-art models using the Celeb-HQ database. The quantitative results of IFACENET show an average performance of SSIM = 0.95, PSNR = 26.813, and L1 = 0.261 with different mask values, being competitive with the state of the art. Additionally, qualitative results of IFACENET are shown to demonstrate the visual outcomes of face inpainting. Based on those results, it can be concluded that the proposed model effectively solves the reconstruction of occluded faces, opening new perspectives in the research of image reconstruction.
{"title":"De-Occlusion Face Model based on Deep Occlusor Segmentation and Deep Inpainting Models","authors":"Miguel Gutierrez;Mario Chacon-Murguia;Juan Ramirez-Quintana","doi":"10.1109/TLA.2025.11072503","DOIUrl":"https://doi.org/10.1109/TLA.2025.11072503","url":null,"abstract":"Image inpainting is a computer vision task that reconstructs missing image regions. Given its potential for various applications, it is an area of great interest. Despite advances in this field thanks to deep models such as autoencoders and generative adversarial networks, fundamental challenges persist, such as the causal interpretation of information loss and the risk of overfitting and lack of diversity in the features obtained with autoencoders. In this context, this article presents an innovative deep network model to solve occluded face inpainting. The model focuses on attributing the loss of information to the occlusion. The proposed model consists of two deep models: one for segmenting the object occluding the face, called SOCLNET, and another for reconstructing the face, IFACENET. SOCLNET is an improvement of the DeepLabv3 network by adding self-attention mechanisms. IFACENET is based on an autoencoder with an ensemble learning approach in the encoder to improve the diversity of the extracted features. SOCLNET was evaluated to demonstrate that the segmentation of occluding objects works adequately, even on out-of-distribution images. Its performance metrics were Pixel Accuracy = 0.93 and IoU = 0.788. The IFACENET model was compared against other state-of-the-art models using the Celeb-HQ database. The quantitative results of IFACENET show an average performance of SSIM = 0.95, PSNR = 26.813, and L1 = 0.261 with different mask values, being competitive with the state of the art. Additionally, qualitative results of IFACENET are shown to demonstrate the visual outcomes of face inpainting. Based on those results, it can be concluded that the proposed model effectively solves the reconstruction of occluded faces, opening new perspectives in the research of image reconstruction.","PeriodicalId":55024,"journal":{"name":"IEEE Latin America Transactions","volume":"23 8","pages":"662-674"},"PeriodicalIF":1.3,"publicationDate":"2025-07-08","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"https://ieeexplore.ieee.org/stamp/stamp.jsp?tp=&arnumber=11072503","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"144581452","PeriodicalName":null,"FirstCategoryId":null,"ListUrlMain":null,"RegionNum":4,"RegionCategory":"工程技术","ArticlePicture":[],"TitleCN":null,"AbstractTextCN":null,"PMCID":"OA","EPubDate":null,"PubModel":null,"JCR":null,"JCRName":null,"Score":null,"Total":0}
Pub Date : 2025-06-20DOI: 10.1109/TLA.2025.11045643
Daniela Bolaños-Flores;Tania Aglae Ramirez-delreal;Hamurabi Gamboa-Rosales;Guadalupe O. Gutierrez-Esparza
A variety of factors along the road can endanger the safety of drivers or pedestrians and lead to high-impact accidents while driving, which is why traffic signs are essential elements that provide information about the condition of the road during the trip. Traffic sign detection and classification is a research area in computer vision. Its applications are mainly in autonomous conduction or assistance driving. Convolutional neural networks (CNNs) have outstanding detection results compared to conventional methods. In this work, we employed machine learning techniques based on CNNs to categorize and detect Mexican traffic signs. A dataset focused on traffic signs was outlined for the Mexican territory within the main urban roads in eight different cities. The dataset contains 2,283 road elements divided into 37 classes for training and validation of algorithms; a novel methodology is proposed to apply data augmentation and obtain better performance in classification and detection models. The mean Average Precision (mAP) metric compares the performance in state-of-the-art detection methods, particularly YOLOv5, YOLOv8, and the Transformer DETR, obtaining better results with trained models incorporating data augmentation.
{"title":"Toward a new dataset: Mexican Traffic Signs ReWaIn-MTS for detection using deep learning","authors":"Daniela Bolaños-Flores;Tania Aglae Ramirez-delreal;Hamurabi Gamboa-Rosales;Guadalupe O. Gutierrez-Esparza","doi":"10.1109/TLA.2025.11045643","DOIUrl":"https://doi.org/10.1109/TLA.2025.11045643","url":null,"abstract":"A variety of factors along the road can endanger the safety of drivers or pedestrians and lead to high-impact accidents while driving, which is why traffic signs are essential elements that provide information about the condition of the road during the trip. Traffic sign detection and classification is a research area in computer vision. Its applications are mainly in autonomous conduction or assistance driving. Convolutional neural networks (CNNs) have outstanding detection results compared to conventional methods. In this work, we employed machine learning techniques based on CNNs to categorize and detect Mexican traffic signs. A dataset focused on traffic signs was outlined for the Mexican territory within the main urban roads in eight different cities. The dataset contains 2,283 road elements divided into 37 classes for training and validation of algorithms; a novel methodology is proposed to apply data augmentation and obtain better performance in classification and detection models. The mean Average Precision (mAP) metric compares the performance in state-of-the-art detection methods, particularly YOLOv5, YOLOv8, and the Transformer DETR, obtaining better results with trained models incorporating data augmentation.","PeriodicalId":55024,"journal":{"name":"IEEE Latin America Transactions","volume":"23 7","pages":"584-591"},"PeriodicalIF":1.3,"publicationDate":"2025-06-20","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"https://ieeexplore.ieee.org/stamp/stamp.jsp?tp=&arnumber=11045643","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"144331643","PeriodicalName":null,"FirstCategoryId":null,"ListUrlMain":null,"RegionNum":4,"RegionCategory":"工程技术","ArticlePicture":[],"TitleCN":null,"AbstractTextCN":null,"PMCID":"OA","EPubDate":null,"PubModel":null,"JCR":null,"JCRName":null,"Score":null,"Total":0}
Pub Date : 2025-06-20DOI: 10.1109/TLA.2025.11045645
Diego Dias Domingues;Sérgio José Melo Almeida;Eduardo Antonio César Costa
The electrical sector pursuit of technical and ecological alternatives makes it possible to integrate and cooperatively optimize dispersed energy resources, enhancing the stability, dependability, and resilience of contemporary energy systems. Microgrids and artificial intelligence are two ideas that could be included into contemporary power grids in an effort to lower costs and pollution emissions. This work proposes a new energy control and management strategy based on smart devices in this context. It explores machine-learning techniques for implementing supervised learning algorithms to perform automatic volt-var control adjustments and mitigate voltage fluctuations at the point of common coupling using smart inverters. The techniques explored and compared in this study include multilayer perceptron, SVM, and random forest. The results were consistent, with average accuracies above 90%, indicating the relevance of the analyzed models for this application. Thus, this research seeks to improve power quality in islanded microgrids with high penetration of distributed generation and explore the potential of artificial intelligence in decision-making processes.
{"title":"Local Volt-Var Control Applied in an Islanded Microgrid Using Supervised Learning Techniques","authors":"Diego Dias Domingues;Sérgio José Melo Almeida;Eduardo Antonio César Costa","doi":"10.1109/TLA.2025.11045645","DOIUrl":"https://doi.org/10.1109/TLA.2025.11045645","url":null,"abstract":"The electrical sector pursuit of technical and ecological alternatives makes it possible to integrate and cooperatively optimize dispersed energy resources, enhancing the stability, dependability, and resilience of contemporary energy systems. Microgrids and artificial intelligence are two ideas that could be included into contemporary power grids in an effort to lower costs and pollution emissions. This work proposes a new energy control and management strategy based on smart devices in this context. It explores machine-learning techniques for implementing supervised learning algorithms to perform automatic volt-var control adjustments and mitigate voltage fluctuations at the point of common coupling using smart inverters. The techniques explored and compared in this study include multilayer perceptron, SVM, and random forest. The results were consistent, with average accuracies above 90%, indicating the relevance of the analyzed models for this application. Thus, this research seeks to improve power quality in islanded microgrids with high penetration of distributed generation and explore the potential of artificial intelligence in decision-making processes.","PeriodicalId":55024,"journal":{"name":"IEEE Latin America Transactions","volume":"23 7","pages":"600-608"},"PeriodicalIF":1.3,"publicationDate":"2025-06-20","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"https://ieeexplore.ieee.org/stamp/stamp.jsp?tp=&arnumber=11045645","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"144331640","PeriodicalName":null,"FirstCategoryId":null,"ListUrlMain":null,"RegionNum":4,"RegionCategory":"工程技术","ArticlePicture":[],"TitleCN":null,"AbstractTextCN":null,"PMCID":"OA","EPubDate":null,"PubModel":null,"JCR":null,"JCRName":null,"Score":null,"Total":0}
Pub Date : 2025-06-20DOI: 10.1109/TLA.2025.11045647
Ravali Palakurthi;Kirubakaran Annamalai
This paper presents a Field Programmable Gate Array (FPGA) implementation for rapid prototyping of a new single-phase transformerless five-level inverter for PV applications. The inverter features a reduced device count, a common ground that eliminates the leakage current issue, and 100% DC utilization. It is capable of supplying both real and reactive power. A simple proportional-resonant (PR) controller is developed and uses a level-shifted pulse width modulation scheme to generate the firing pulses. Grid synchronization is achieved using a robust arc-tangent method-based phase-locked loop (PLL) strategy. To evaluate the open-loop performance, an experimental prototype is developed, and its responses are presented. Moreover, a hardware-in-the-loop (HIL) co-simulation is performed for grid interface to achieve real-time constraints on an Atlys Spartan 6 FPGA using Xilinx System Generator in the MATLAB/Simulink environment, and the results are reported. Finally, a detailed comparison of various five-level inverter topologies is presented to highlight the merits of the proposed topology.
本文提出了一种现场可编程门阵列（FPGA）实现，用于光伏应用的新型单相无变压器五电平逆变器的快速原型设计。该逆变器的特点是减少了器件数量，消除了漏电流问题的共地，并实现了100%的直流利用率。它能够提供实功率和无功功率。开发了一种简单的比例谐振（PR）控制器，并采用电平移位脉宽调制方案产生发射脉冲。电网同步采用基于鲁棒弧切法的锁相环（PLL）策略。为了评估该系统的开环性能，研制了实验样机，并给出了其响应。此外，在MATLAB/Simulink环境下，利用Xilinx System Generator在atlysspartan 6 FPGA上对网格接口实现实时约束进行了硬件在环（HIL）联合仿真，并给出了仿真结果。最后，对各种五电平逆变器拓扑进行了详细的比较，以突出所提出拓扑的优点。
{"title":"Rapid Prototyping of FPGA Controlled Common Ground Single-Phase Transformerless Five-Level Inverter using Xilinx System Generator","authors":"Ravali Palakurthi;Kirubakaran Annamalai","doi":"10.1109/TLA.2025.11045647","DOIUrl":"https://doi.org/10.1109/TLA.2025.11045647","url":null,"abstract":"This paper presents a Field Programmable Gate Array (FPGA) implementation for rapid prototyping of a new single-phase transformerless five-level inverter for PV applications. The inverter features a reduced device count, a common ground that eliminates the leakage current issue, and 100% DC utilization. It is capable of supplying both real and reactive power. A simple proportional-resonant (PR) controller is developed and uses a level-shifted pulse width modulation scheme to generate the firing pulses. Grid synchronization is achieved using a robust arc-tangent method-based phase-locked loop (PLL) strategy. To evaluate the open-loop performance, an experimental prototype is developed, and its responses are presented. Moreover, a hardware-in-the-loop (HIL) co-simulation is performed for grid interface to achieve real-time constraints on an Atlys Spartan 6 FPGA using Xilinx System Generator in the MATLAB/Simulink environment, and the results are reported. Finally, a detailed comparison of various five-level inverter topologies is presented to highlight the merits of the proposed topology.","PeriodicalId":55024,"journal":{"name":"IEEE Latin America Transactions","volume":"23 7","pages":"609-618"},"PeriodicalIF":1.3,"publicationDate":"2025-06-20","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"https://ieeexplore.ieee.org/stamp/stamp.jsp?tp=&arnumber=11045647","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"144331642","PeriodicalName":null,"FirstCategoryId":null,"ListUrlMain":null,"RegionNum":4,"RegionCategory":"工程技术","ArticlePicture":[],"TitleCN":null,"AbstractTextCN":null,"PMCID":"OA","EPubDate":null,"PubModel":null,"JCR":null,"JCRName":null,"Score":null,"Total":0}
Pub Date : 2025-06-20DOI: 10.1109/TLA.2025.11045671
Bianca S. de C. da Silva;Pedro H. C. de Souza;Luciano L. Mendes
This work proposes a new solution to reduce the PAPR in OFDM systems using NN. The NN leverages a training dataset generated by the MCSA, which fine-tunes the NN for attaining a similar PAPR reduction of the MCSA. Compared to traditional techniques such as the PTS, the proposed solution offers superior performance by achieving a PAPR reduction of up to 4 dB. Nevertheless, a significant advantage is that the trained NN presents a lower computational complexity compared to the MCSA, without compromising its PAPR reduction capabilities
{"title":"PAPR Reduction Technique for Mobile Communication Systems Using Neural Networks","authors":"Bianca S. de C. da Silva;Pedro H. C. de Souza;Luciano L. Mendes","doi":"10.1109/TLA.2025.11045671","DOIUrl":"https://doi.org/10.1109/TLA.2025.11045671","url":null,"abstract":"This work proposes a new solution to reduce the PAPR in OFDM systems using NN. The NN leverages a training dataset generated by the MCSA, which fine-tunes the NN for attaining a similar PAPR reduction of the MCSA. Compared to traditional techniques such as the PTS, the proposed solution offers superior performance by achieving a PAPR reduction of up to 4 dB. Nevertheless, a significant advantage is that the trained NN presents a lower computational complexity compared to the MCSA, without compromising its PAPR reduction capabilities","PeriodicalId":55024,"journal":{"name":"IEEE Latin America Transactions","volume":"23 7","pages":"556-564"},"PeriodicalIF":1.3,"publicationDate":"2025-06-20","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"https://ieeexplore.ieee.org/stamp/stamp.jsp?tp=&arnumber=11045671","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"144331818","PeriodicalName":null,"FirstCategoryId":null,"ListUrlMain":null,"RegionNum":4,"RegionCategory":"工程技术","ArticlePicture":[],"TitleCN":null,"AbstractTextCN":null,"PMCID":"OA","EPubDate":null,"PubModel":null,"JCR":null,"JCRName":null,"Score":null,"Total":0}
Pub Date : 2025-06-20DOI: 10.1109/TLA.2025.11045641
Igor Sales Bezerra Souza;Lucas Torres;André Murilo;Rafael Rodrigues da Silva
Automotive simulation tools have been employed in various areas of knowledge, especially in the production chain of the automotive industry. The main benefit of these tools consists of reducing the time and product development loops, which directly implies a reduced production cost and improved quality. Thus, the present study aims to use the VI-CarRealTime software widely used in the automotive industry to design and validate ABS and TCS automotive control systems using the ModelBased Design methodology. The simulation results show that the controllers meet the operating requirements well, showing a high correlation when compared to models of a complete vehicle for application in automotive simulators.
{"title":"Design and Validation of an ABS and TCS Control Strategy Applied in an Automotive Simulator Using Model-Based Design Methodology","authors":"Igor Sales Bezerra Souza;Lucas Torres;André Murilo;Rafael Rodrigues da Silva","doi":"10.1109/TLA.2025.11045641","DOIUrl":"https://doi.org/10.1109/TLA.2025.11045641","url":null,"abstract":"Automotive simulation tools have been employed in various areas of knowledge, especially in the production chain of the automotive industry. The main benefit of these tools consists of reducing the time and product development loops, which directly implies a reduced production cost and improved quality. Thus, the present study aims to use the VI-CarRealTime software widely used in the automotive industry to design and validate ABS and TCS automotive control systems using the ModelBased Design methodology. The simulation results show that the controllers meet the operating requirements well, showing a high correlation when compared to models of a complete vehicle for application in automotive simulators.","PeriodicalId":55024,"journal":{"name":"IEEE Latin America Transactions","volume":"23 7","pages":"565-571"},"PeriodicalIF":1.3,"publicationDate":"2025-06-20","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"https://ieeexplore.ieee.org/stamp/stamp.jsp?tp=&arnumber=11045641","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"144331641","PeriodicalName":null,"FirstCategoryId":null,"ListUrlMain":null,"RegionNum":4,"RegionCategory":"工程技术","ArticlePicture":[],"TitleCN":null,"AbstractTextCN":null,"PMCID":"OA","EPubDate":null,"PubModel":null,"JCR":null,"JCRName":null,"Score":null,"Total":0}
京公网安备 11010802042870号
京ICP备2023020795号-1
扫码关注我们
求助内容：
应助结果提醒方式：