One of the greatest challenges facing photovoltaic (PV) power generation systems today is maintaining their operation at the desired power generation efficiency. To achieve this goal, the anomaly detection of the output power of PV arrays is crucial for ensuring reliability and safety. This article proposes an anomaly detection for the output power of PV arrays based on temporal Kolmogorov–Arnold networks (TKANs). First, a dataset of PV array parameters is constructed by selecting the time series of output power, ambient temperature, component temperature, and irradiance of the PV array as input features. Second, the PV array parameter dataset undergoes feature normalization by obtaining the boundary values of environmental information and operating parameters, and scaling them to the range of 0–1. Then, the processed dataset is trained using the TKAN neural network to obtain the anomaly detection model of the output power of the PV array. Finally, the proposed method is compared and analyzed with three other methods, such as Isolation Forest, $K$-means, and long short-term memory, verifying its reliability and superiority. In addition, the effectiveness of the proposed method is validated in a self-built PV power plant.
{"title":"An Anomaly Detection Method for the Output Power of Photovoltaic Arrays Based on TKAN","authors":"Tingting Pei;Lei Jiang;Wei Chen;Haiyan Zhang;Jian Zhang;Lihan Xin","doi":"10.1109/JPHOTOV.2025.3596688","DOIUrl":"https://doi.org/10.1109/JPHOTOV.2025.3596688","url":null,"abstract":"One of the greatest challenges facing photovoltaic (PV) power generation systems today is maintaining their operation at the desired power generation efficiency. To achieve this goal, the anomaly detection of the output power of PV arrays is crucial for ensuring reliability and safety. This article proposes an anomaly detection for the output power of PV arrays based on temporal Kolmogorov–Arnold networks (TKANs). First, a dataset of PV array parameters is constructed by selecting the time series of output power, ambient temperature, component temperature, and irradiance of the PV array as input features. Second, the PV array parameter dataset undergoes feature normalization by obtaining the boundary values of environmental information and operating parameters, and scaling them to the range of 0–1. Then, the processed dataset is trained using the TKAN neural network to obtain the anomaly detection model of the output power of the PV array. Finally, the proposed method is compared and analyzed with three other methods, such as Isolation Forest, <inline-formula><tex-math>$K$</tex-math></inline-formula>-means, and long short-term memory, verifying its reliability and superiority. In addition, the effectiveness of the proposed method is validated in a self-built PV power plant.","PeriodicalId":445,"journal":{"name":"IEEE Journal of Photovoltaics","volume":"15 6","pages":"965-976"},"PeriodicalIF":2.6,"publicationDate":"2025-08-25","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"145341071","PeriodicalName":null,"FirstCategoryId":null,"ListUrlMain":null,"RegionNum":3,"RegionCategory":"工程技术","ArticlePicture":[],"TitleCN":null,"AbstractTextCN":null,"PMCID":"","EPubDate":null,"PubModel":null,"JCR":null,"JCRName":null,"Score":null,"Total":0}
Pub Date : 2025-08-21DOI: 10.1109/JPHOTOV.2025.3597182
{"title":"Call for Papers for a Special Issue of IEEE Transactions on Electron Devices on “Ultrawide Band Gap Semiconductor Device for RF, Power and Optoelectronic Applications”","authors":"","doi":"10.1109/JPHOTOV.2025.3597182","DOIUrl":"https://doi.org/10.1109/JPHOTOV.2025.3597182","url":null,"abstract":"","PeriodicalId":445,"journal":{"name":"IEEE Journal of Photovoltaics","volume":"15 5","pages":"734-735"},"PeriodicalIF":2.6,"publicationDate":"2025-08-21","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"https://ieeexplore.ieee.org/stamp/stamp.jsp?tp=&arnumber=11133609","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"144887706","PeriodicalName":null,"FirstCategoryId":null,"ListUrlMain":null,"RegionNum":3,"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 : 2025-08-21DOI: 10.1109/JPHOTOV.2025.3597184
{"title":"Call for Papers for a Special Issue of IEEE Transactions on Electron Devices on “Reliability of Advanced Nodes”","authors":"","doi":"10.1109/JPHOTOV.2025.3597184","DOIUrl":"https://doi.org/10.1109/JPHOTOV.2025.3597184","url":null,"abstract":"","PeriodicalId":445,"journal":{"name":"IEEE Journal of Photovoltaics","volume":"15 5","pages":"736-737"},"PeriodicalIF":2.6,"publicationDate":"2025-08-21","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"https://ieeexplore.ieee.org/stamp/stamp.jsp?tp=&arnumber=11133596","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"144887705","PeriodicalName":null,"FirstCategoryId":null,"ListUrlMain":null,"RegionNum":3,"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 : 2025-08-21DOI: 10.1109/JPHOTOV.2025.3597178
{"title":"IEEE Journal of Photovoltaics Information for Authors","authors":"","doi":"10.1109/JPHOTOV.2025.3597178","DOIUrl":"https://doi.org/10.1109/JPHOTOV.2025.3597178","url":null,"abstract":"","PeriodicalId":445,"journal":{"name":"IEEE Journal of Photovoltaics","volume":"15 5","pages":"C3-C3"},"PeriodicalIF":2.6,"publicationDate":"2025-08-21","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"https://ieeexplore.ieee.org/stamp/stamp.jsp?tp=&arnumber=11133598","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"144887639","PeriodicalName":null,"FirstCategoryId":null,"ListUrlMain":null,"RegionNum":3,"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 : 2025-08-21DOI: 10.1109/JPHOTOV.2025.3597180
{"title":"Call for Papers for a Special Issue of IEEE Transactions on Electron Devices on “Wide Band Semiconductors for Automotive Applications”","authors":"","doi":"10.1109/JPHOTOV.2025.3597180","DOIUrl":"https://doi.org/10.1109/JPHOTOV.2025.3597180","url":null,"abstract":"","PeriodicalId":445,"journal":{"name":"IEEE Journal of Photovoltaics","volume":"15 5","pages":"732-733"},"PeriodicalIF":2.6,"publicationDate":"2025-08-21","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"https://ieeexplore.ieee.org/stamp/stamp.jsp?tp=&arnumber=11133594","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"144887740","PeriodicalName":null,"FirstCategoryId":null,"ListUrlMain":null,"RegionNum":3,"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 : 2025-08-08DOI: 10.1109/JPHOTOV.2025.3583031
Sophie Pelland;Stefan Riechelmann
Full-resolution spectral irradiance data can comprise upwards of 2000–3000 data points at a single time step. Given that photovoltaic (PV) modeling is regularly performed with subhourly time resolutions over multiyear periods, incorporating spectral effects can become challenging both in terms of file sizes and computational burden. For this reason, spectral irradiances are sometimes aggregated into a limited number of wavelength bands (or wavebands), such as the 32-band grouping known as Kato bands that is used in the IEC 61853 series of standards on “PV module performance testing and energy rating.” To test the impact of such aggregation, measured, and modeled spectral irradiance data from two sites in the United States—Tempe, Arizona and Golden, Colorado—are used to assess the impact on PV spectral effect estimates of aggregating spectral irradiances into Kato bands and into two other sets of wavebands known as PV-bands. Calculations using the aggregated spectra are compared with those using the full-resolution spectra, for crystalline silicon and cadmium telluride modules. Each of the three sets of wavebands yields negligible errors of less than 0.1% in the spectral derate factor, which characterizes long-term spectral effects. This indicates that both Kato bands and PV-bands should be sufficient for the purposes of PV energy rating. Meanwhile, a recent version of PV-bands performs best for evaluating the instantaneous spectral mismatch factor, leading to errors of less than 0.2% across all time steps for both sites and PV module technologies, while instantaneous errors for Kato bands reach magnitudes of up to 1.4%.
{"title":"The Impact of Spectral Irradiance Aggregation Into Kato Bands and PV-Bands on Estimates of Photovoltaic Spectral Effects","authors":"Sophie Pelland;Stefan Riechelmann","doi":"10.1109/JPHOTOV.2025.3583031","DOIUrl":"https://doi.org/10.1109/JPHOTOV.2025.3583031","url":null,"abstract":"Full-resolution spectral irradiance data can comprise upwards of 2000–3000 data points at a single time step. Given that photovoltaic (PV) modeling is regularly performed with subhourly time resolutions over multiyear periods, incorporating spectral effects can become challenging both in terms of file sizes and computational burden. For this reason, spectral irradiances are sometimes aggregated into a limited number of wavelength bands (or wavebands), such as the 32-band grouping known as Kato bands that is used in the IEC 61853 series of standards on “PV module performance testing and energy rating.” To test the impact of such aggregation, measured, and modeled spectral irradiance data from two sites in the United States—Tempe, Arizona and Golden, Colorado—are used to assess the impact on PV spectral effect estimates of aggregating spectral irradiances into Kato bands and into two other sets of wavebands known as PV-bands. Calculations using the aggregated spectra are compared with those using the full-resolution spectra, for crystalline silicon and cadmium telluride modules. Each of the three sets of wavebands yields negligible errors of less than 0.1% in the spectral derate factor, which characterizes long-term spectral effects. This indicates that both Kato bands and PV-bands should be sufficient for the purposes of PV energy rating. Meanwhile, a recent version of PV-bands performs best for evaluating the instantaneous spectral mismatch factor, leading to errors of less than 0.2% across all time steps for both sites and PV module technologies, while instantaneous errors for Kato bands reach magnitudes of up to 1.4%.","PeriodicalId":445,"journal":{"name":"IEEE Journal of Photovoltaics","volume":"15 5","pages":"657-661"},"PeriodicalIF":2.6,"publicationDate":"2025-08-08","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"144887789","PeriodicalName":null,"FirstCategoryId":null,"ListUrlMain":null,"RegionNum":3,"RegionCategory":"工程技术","ArticlePicture":[],"TitleCN":null,"AbstractTextCN":null,"PMCID":"","EPubDate":null,"PubModel":null,"JCR":null,"JCRName":null,"Score":null,"Total":0}
Pub Date : 2025-07-25DOI: 10.1109/JPHOTOV.2025.3587887
Marco Nicoletto;Davide Panizzon;Alessandro Caria;Nicola Trivellin;Carlo De Santi;Matteo Buffolo;Gaudenzio Meneghesso;Enrico Zanoni;Matteo Meneghini
This work investigates the impact of cracks on silicon heterojunction photovoltaic (PV) modules by analyzing their electrical and thermal behavior under low and high current conditions. The analysis was conducted on PV modules affected by a severe hailstorm, which produced hailstones up to 16 cm in diameter, far exceeding the standard test sizes (IEC 61215). A combination of electroluminescence (EL) and infrared (IR) thermography, along with dark and light current–voltage characterization, was employed to examine both hail and operator-induced cracks. The findings revealed that these cracks, which are latent damages not visible to the naked eye but only with EL and IR investigations, lead to localized temperature increase near open circuit voltage, and to a more uniform distributed temperature increase near short circuit conditions. A Simulink/Matlab model was developed to reproduce the thermal behavior of cracked cells in series with intact ones, to reproduce what happens in a real-world scenario. The results emphasize the importance of identifying latent defects in PV modules to ensure long-term reliability, safety, and efficiency, offering insights into their electrical and thermal behavior in low and high current regime.
{"title":"Modeling Cracks in Silicon-Heterojunction Photovoltaic Modules: A Real-World Case Study","authors":"Marco Nicoletto;Davide Panizzon;Alessandro Caria;Nicola Trivellin;Carlo De Santi;Matteo Buffolo;Gaudenzio Meneghesso;Enrico Zanoni;Matteo Meneghini","doi":"10.1109/JPHOTOV.2025.3587887","DOIUrl":"https://doi.org/10.1109/JPHOTOV.2025.3587887","url":null,"abstract":"This work investigates the impact of cracks on silicon heterojunction photovoltaic (PV) modules by analyzing their electrical and thermal behavior under low and high current conditions. The analysis was conducted on PV modules affected by a severe hailstorm, which produced hailstones up to 16 cm in diameter, far exceeding the standard test sizes (IEC 61215). A combination of electroluminescence (EL) and infrared (IR) thermography, along with dark and light current–voltage characterization, was employed to examine both hail and operator-induced cracks. The findings revealed that these cracks, which are latent damages not visible to the naked eye but only with EL and IR investigations, lead to localized temperature increase near open circuit voltage, and to a more uniform distributed temperature increase near short circuit conditions. A Simulink/Matlab model was developed to reproduce the thermal behavior of cracked cells in series with intact ones, to reproduce what happens in a real-world scenario. The results emphasize the importance of identifying latent defects in PV modules to ensure long-term reliability, safety, and efficiency, offering insights into their electrical and thermal behavior in low and high current regime.","PeriodicalId":445,"journal":{"name":"IEEE Journal of Photovoltaics","volume":"15 5","pages":"639-644"},"PeriodicalIF":2.6,"publicationDate":"2025-07-25","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"144887704","PeriodicalName":null,"FirstCategoryId":null,"ListUrlMain":null,"RegionNum":3,"RegionCategory":"工程技术","ArticlePicture":[],"TitleCN":null,"AbstractTextCN":null,"PMCID":"","EPubDate":null,"PubModel":null,"JCR":null,"JCRName":null,"Score":null,"Total":0}
Pub Date : 2025-07-23DOI: 10.1109/JPHOTOV.2025.3587297
Victoria Lofstad-Lie;Aleksander Simonsen;Tønnes Frostad Nygaard;Erik Stensrud Marstein
As the installed capacity of photovoltaic power plants continues its near exponential growth, cost-efficient operation and maintenance strategies become increasingly crucial. Aerial infrared thermography has enabled fast and robust fault detection in utility-scale PV plants. In this article, we explore two key approaches to improve inspection efficiency: increase the flight altitude and deploy swarms of unmanned aerial vehicles. A larger imaging distance expands the field of view but reduces fault detectability and georeferencing accuracy. In this work, we study the tradeoff between inspection efficiency and data quality for automatic fault detection and localization. The YOLO11 machine learning model was trained to detect defects in thermal images, and its performance was evaluated to vary imaging distances and camera pitch angles. Fault detection remained robust up to approximately 80 m, but georeferencing error became the primary limiting factor. Finally, we conduct a UAV swarm-based inspection of a PV plant, integrating automatic fault detection and localization, and compare the results with ground truth data.
{"title":"Data Quality Analyses for Automatic Aerial Thermography Inspection of PV Power Plants","authors":"Victoria Lofstad-Lie;Aleksander Simonsen;Tønnes Frostad Nygaard;Erik Stensrud Marstein","doi":"10.1109/JPHOTOV.2025.3587297","DOIUrl":"https://doi.org/10.1109/JPHOTOV.2025.3587297","url":null,"abstract":"As the installed capacity of photovoltaic power plants continues its near exponential growth, cost-efficient operation and maintenance strategies become increasingly crucial. Aerial infrared thermography has enabled fast and robust fault detection in utility-scale PV plants. In this article, we explore two key approaches to improve inspection efficiency: increase the flight altitude and deploy swarms of unmanned aerial vehicles. A larger imaging distance expands the field of view but reduces fault detectability and georeferencing accuracy. In this work, we study the tradeoff between inspection efficiency and data quality for automatic fault detection and localization. The YOLO11 machine learning model was trained to detect defects in thermal images, and its performance was evaluated to vary imaging distances and camera pitch angles. Fault detection remained robust up to approximately 80 m, but georeferencing error became the primary limiting factor. Finally, we conduct a UAV swarm-based inspection of a PV plant, integrating automatic fault detection and localization, and compare the results with ground truth data.","PeriodicalId":445,"journal":{"name":"IEEE Journal of Photovoltaics","volume":"15 5","pages":"722-731"},"PeriodicalIF":2.6,"publicationDate":"2025-07-23","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"https://ieeexplore.ieee.org/stamp/stamp.jsp?tp=&arnumber=11091333","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"144887709","PeriodicalName":null,"FirstCategoryId":null,"ListUrlMain":null,"RegionNum":3,"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 : 2025-07-07DOI: 10.1109/JPHOTOV.2025.3581692
Alexander Melnikov;Andreas Mandelis;Peng Song;Junyan Liu
The question of identifying the dominant capacitance in Si solar cell optoelectronic transport phenomena under open circuit conditions is explored using quantitative noncontacting laser photocarrier radiometry (PCR) as a dynamic spectrally gated photoluminescence method. The combined theoretical and experimental approach addresses the dependence of the PCR signal on the capacitance of the charge transport layer (CTL) and of the base layer of the p-n junction which, in conjunction with the solar cell series resistance, form RC diffusive time constants shown to be sensitively measurable using PCR frequency scans. The experimental strategy is based on the dependence of layer capacitance on the laser-illuminated area and involves frequency responses under partial or total surface area illumination. It is shown that the recombination lifetime and CTL diffusion lifetime ${{tau }_{RC}}$ are mainly responsible for the kinetics and extraction of nonequilibrium optically generated carrier density waves in three types of photovoltaic Si solar cells. It is concluded that ${{tau }_{RC}},$which is related to the thin upper CTL and the associated recombination lifetime, plays the main role in the dynamic optoelectronic PCR frequency response of all tested devices. ${rm{Through the capacitance of this layer}}, {{tau }_{RC}}$ strongly affects free photocarrier transport across the p-n junction, surface distribution, and electrode collection, therefore CTL capacitance should become a major focus of solar efficiency enhancement designs and studies.
{"title":"Charge Transport Layer Capacitance Contribution to Si Solar Cell Optoelectronic Properties Investigated Using Photocarrier Radiometry","authors":"Alexander Melnikov;Andreas Mandelis;Peng Song;Junyan Liu","doi":"10.1109/JPHOTOV.2025.3581692","DOIUrl":"https://doi.org/10.1109/JPHOTOV.2025.3581692","url":null,"abstract":"The question of identifying the dominant capacitance in Si solar cell optoelectronic transport phenomena under open circuit conditions is explored using quantitative noncontacting laser photocarrier radiometry (PCR) as a dynamic spectrally gated photoluminescence method. The combined theoretical and experimental approach addresses the dependence of the PCR signal on the capacitance of the charge transport layer (CTL) and of the base layer of the p-n junction which, in conjunction with the solar cell series resistance, form <italic>RC</i> diffusive time constants shown to be sensitively measurable using PCR frequency scans. The experimental strategy is based on the dependence of layer capacitance on the laser-illuminated area and involves frequency responses under partial or total surface area illumination. It is shown that the recombination lifetime and CTL diffusion lifetime <inline-formula><tex-math>${{tau }_{RC}}$</tex-math></inline-formula> are mainly responsible for the kinetics and extraction of nonequilibrium optically generated carrier density waves in three types of photovoltaic Si solar cells. It is concluded that <inline-formula><tex-math>${{tau }_{RC}},$</tex-math></inline-formula>which is related to the thin upper CTL and the associated recombination lifetime, plays the main role in the dynamic optoelectronic PCR frequency response of all tested devices. <inline-formula><tex-math>${rm{Through the capacitance of this layer}}, {{tau }_{RC}}$</tex-math></inline-formula> strongly affects free photocarrier transport across the p-n junction, surface distribution, and electrode collection, therefore CTL capacitance should become a major focus of solar efficiency enhancement designs and studies.","PeriodicalId":445,"journal":{"name":"IEEE Journal of Photovoltaics","volume":"15 5","pages":"662-671"},"PeriodicalIF":2.6,"publicationDate":"2025-07-07","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"144887616","PeriodicalName":null,"FirstCategoryId":null,"ListUrlMain":null,"RegionNum":3,"RegionCategory":"工程技术","ArticlePicture":[],"TitleCN":null,"AbstractTextCN":null,"PMCID":"","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：