Pub Date : 2024-10-04DOI: 10.1109/JPHOTOV.2024.3463974
Tal Kasher;Lauren M. Kaliszewski;Daniel L. Lepkowski;Jacob T. Boyer;Marzieh Baan;Tyler J. Grassman;Steven A. Ringel
To date, the greatest performance limiter in monolithic III-V/Si tandem (multijunction) solar cells, like GaAs$_{0.75}$P$_{0.25}$/Si, is excess threading dislocation densities (TDD) resulting from the lattice-mismatched heteroepitaxy. Recent developments in low-TDD GaAsyP1-y/Si metamorphic buffers were used to grow standalone GaAs$_{0.75}$P$_{0.25}$ top cells on Si with a TDD of 4 × 106 cm−2, ∼2.5 × lower than previous iterations, greatly improving the potential for the production of high-efficiency tandems based on this platform. Nonetheless, these reduced-TDD cells were still found to possess considerable voltage-dependent carrier collection (VDC) losses. As such, to improve JSC and fill factor, without sacrificial reduction in VOC, a doping gradient within the cell base layer was designed and implemented. The updated design reduces VDC losses to levels that would otherwise require further TDD reduction by at least another 2.5 × (to ≤ 1.5 × 106 cm−2) in a typical flat doping profile design. Replacing the p+-Ga$_{0.64}$In$_{0.36}$P back surface field with p+-Al$_{0.2}$Ga$_{0.8}$As$_{0.74}$P$_{0.26}$ provided an additional improvement in both VOC and JSC, yielding device performance equivalent to a 4 × TDD reduction in the previous design. The culmination of these design changes results in a new subcell that outperforms our previous best top cell by ∼4.3% absolute AM1.5G efficiency, with increases in fill factor, JSC, and WOC of about 3.3% absolute, 1.9 mA/cm2, and 0.12 V, respectively. This new design, coupled with the reduced TDD platform, paves a promising path toward the development of higher efficiency GaAs$_{0.75}$P$_{0.25}$/Si tandems upon full device integration.
{"title":"Design for Increased Defect Tolerance in Metamorphic GaAsP-on-Si Top Cells","authors":"Tal Kasher;Lauren M. Kaliszewski;Daniel L. Lepkowski;Jacob T. Boyer;Marzieh Baan;Tyler J. Grassman;Steven A. Ringel","doi":"10.1109/JPHOTOV.2024.3463974","DOIUrl":"https://doi.org/10.1109/JPHOTOV.2024.3463974","url":null,"abstract":"To date, the greatest performance limiter in monolithic III-V/Si tandem (multijunction) solar cells, like GaAs\u0000<inline-formula><tex-math>$_{0.75}$</tex-math></inline-formula>\u0000P\u0000<inline-formula><tex-math>$_{0.25}$</tex-math></inline-formula>\u0000/Si, is excess threading dislocation densities (TDD) resulting from the lattice-mismatched heteroepitaxy. Recent developments in low-TDD GaAs\u0000<italic><sub>y</sub></i>\u0000P\u0000<sub>1-</sub>\u0000<italic><sub>y</sub></i>\u0000/Si metamorphic buffers were used to grow standalone GaAs\u0000<inline-formula><tex-math>$_{0.75}$</tex-math></inline-formula>\u0000P\u0000<inline-formula><tex-math>$_{0.25}$</tex-math></inline-formula>\u0000 top cells on Si with a TDD of 4 × 10\u0000<sup>6</sup>\u0000 cm\u0000<sup>−2</sup>\u0000, ∼2.5 × lower than previous iterations, greatly improving the potential for the production of high-efficiency tandems based on this platform. Nonetheless, these reduced-TDD cells were still found to possess considerable voltage-dependent carrier collection (VDC) losses. As such, to improve \u0000<italic>J</i>\u0000<sub>SC</sub>\u0000 and fill factor, without sacrificial reduction in \u0000<italic>V</i>\u0000<sub>OC</sub>\u0000, a doping gradient within the cell base layer was designed and implemented. The updated design reduces VDC losses to levels that would otherwise require further TDD reduction by at least another 2.5 × (to ≤ 1.5 × 10\u0000<sup>6</sup>\u0000 cm\u0000<sup>−2</sup>\u0000) in a typical flat doping profile design. Replacing the p\u0000<sup>+</sup>\u0000-Ga\u0000<inline-formula><tex-math>$_{0.64}$</tex-math></inline-formula>\u0000In\u0000<inline-formula><tex-math>$_{0.36}$</tex-math></inline-formula>\u0000P back surface field with p\u0000<sup>+</sup>\u0000-Al\u0000<inline-formula><tex-math>$_{0.2}$</tex-math></inline-formula>\u0000Ga\u0000<inline-formula><tex-math>$_{0.8}$</tex-math></inline-formula>\u0000As\u0000<inline-formula><tex-math>$_{0.74}$</tex-math></inline-formula>\u0000P\u0000<inline-formula><tex-math>$_{0.26}$</tex-math></inline-formula>\u0000 provided an additional improvement in both \u0000<italic>V</i>\u0000<sub>OC</sub>\u0000 and \u0000<italic>J</i>\u0000<sub>SC</sub>\u0000, yielding device performance equivalent to a 4 × TDD reduction in the previous design. The culmination of these design changes results in a new subcell that outperforms our previous best top cell by ∼4.3% absolute AM1.5G efficiency, with increases in fill factor, \u0000<italic>J</i>\u0000<sub>SC</sub>\u0000, and \u0000<italic>W</i>\u0000<sub>OC</sub>\u0000 of about 3.3% absolute, 1.9 mA/cm\u0000<sup>2</sup>\u0000, and 0.12 V, respectively. This new design, coupled with the reduced TDD platform, paves a promising path toward the development of higher efficiency GaAs\u0000<inline-formula><tex-math>$_{0.75}$</tex-math></inline-formula>\u0000P\u0000<inline-formula><tex-math>$_{0.25}$</tex-math></inline-formula>\u0000/Si tandems upon full device integration.","PeriodicalId":445,"journal":{"name":"IEEE Journal of Photovoltaics","volume":"14 6","pages":"911-919"},"PeriodicalIF":2.5,"publicationDate":"2024-10-04","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"142518012","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 : 2024-10-03DOI: 10.1109/JPHOTOV.2024.3463950
Vincent Meslier;Bertrand Chambion;Pierre-Olivier Bouchard;Jean-Luc Bouvard
The thermal expansion behavior of polymers is a crucial property for manufacturing photovoltaic (PV) modules. The thermal expansion mismatch between the different module components induces residual stresses in the structure after manufacturing. Some of them are located at the interface between materials, leading to delamination and reliability issues during the PV module lifetime. For tandem applications, the thermal expansion mismatch is also an issue since it leads to the separation between the bottom and top cells. In this article, the thermal expansion behavior of a thermoplastic polyolefin (TPO) encapsulant used in the PV industry is assessed by stereo digital image correlation. This contactless method measures the thermal expansion in the two directions of the polymer thin film. The method is accurate enough to capture transition phases of the material, namely the crystallites fusion and formation. The thermal expansion behavior of the TPO thin film is shown to be anisotropic and dependent on its thermal history. The material contracts when heated, both after manufacturing and after aging; this has not yet been investigated. The aging temperature has an influence on the thermal contraction temperature but does not erase the shrinking behavior. The thermal expansion behavior is explained by a microstructural approach. The microstructure is investigated by differential scanning calorimetry. After crystallites melting, the molecular mobility and residual internal stresses account for the observed shrinking behavior. This behavior may affect the reliability of PV modules through delamination, cells cracks, or separation of the top and bottom cells.
{"title":"Thermal Expansion Behavior of a Thermoplastic Polyolefin for Photovoltaic Application Over Hygrothermal Aging","authors":"Vincent Meslier;Bertrand Chambion;Pierre-Olivier Bouchard;Jean-Luc Bouvard","doi":"10.1109/JPHOTOV.2024.3463950","DOIUrl":"https://doi.org/10.1109/JPHOTOV.2024.3463950","url":null,"abstract":"The thermal expansion behavior of polymers is a crucial property for manufacturing photovoltaic (PV) modules. The thermal expansion mismatch between the different module components induces residual stresses in the structure after manufacturing. Some of them are located at the interface between materials, leading to delamination and reliability issues during the PV module lifetime. For tandem applications, the thermal expansion mismatch is also an issue since it leads to the separation between the bottom and top cells. In this article, the thermal expansion behavior of a thermoplastic polyolefin (TPO) encapsulant used in the PV industry is assessed by stereo digital image correlation. This contactless method measures the thermal expansion in the two directions of the polymer thin film. The method is accurate enough to capture transition phases of the material, namely the crystallites fusion and formation. The thermal expansion behavior of the TPO thin film is shown to be anisotropic and dependent on its thermal history. The material contracts when heated, both after manufacturing and after aging; this has not yet been investigated. The aging temperature has an influence on the thermal contraction temperature but does not erase the shrinking behavior. The thermal expansion behavior is explained by a microstructural approach. The microstructure is investigated by differential scanning calorimetry. After crystallites melting, the molecular mobility and residual internal stresses account for the observed shrinking behavior. This behavior may affect the reliability of PV modules through delamination, cells cracks, or separation of the top and bottom cells.","PeriodicalId":445,"journal":{"name":"IEEE Journal of Photovoltaics","volume":"14 6","pages":"920-929"},"PeriodicalIF":2.5,"publicationDate":"2024-10-03","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"142518220","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 : 2024-09-30DOI: 10.1109/JPHOTOV.2024.3456829
N. A. Sadchikov;N. Y. Davidyuk;D. A. Malevskiy;P. V. Pokrovskiy;A. V. Andreeva;V. R. Larionov
To evaluate the overheating temperature of solar cells in concentrator photovoltaic (CPV) modules during solar radiation conversion, we propose a method for determining the thermal resistivity between the solar cell and its environment (rth) in laboratory conditions at room temperature and in the absence of forced ventilation. The essence of this method is the measurement of the temperature change of the solar cells inside the CPV module under thermal load generated by direct current flow through the solar cell. The change in temperature of the solar cells in CPV modules under thermal load is determined by calculating the voltage difference across the module contacts during fast measurements of the I–V curve at room temperature and the I–V curve when the solar cells of the module are heated by direct current. The developed methodology eliminates uncertainties associated with the location of temperature sensors and unstable meteorological conditions. In the present work, this technique is used to study the overheating temperature of solar cells of “Small lenses, Multijunction cells, All from glass, Lamination, Fresnel, Optics, Concentration” design CPV modules varying in materials and thicknesses of heat sinks. In laboratory conditions, we determined the values of rth of small CPV modules and full-size CPV modules, containing, respectively, 8 and 128 pairs of Fresnel lens—triple-junction InGaP/InGaAs/Ge solar cells soldered to a metal heat sinks of similar design. Copper or steel was used as materials for the heat sinks.
{"title":"Indoor Characterization of Solar Concentrator SMALFOC Modules Through Cell-to-Ambient Thermal Resistance Measurements","authors":"N. A. Sadchikov;N. Y. Davidyuk;D. A. Malevskiy;P. V. Pokrovskiy;A. V. Andreeva;V. R. Larionov","doi":"10.1109/JPHOTOV.2024.3456829","DOIUrl":"https://doi.org/10.1109/JPHOTOV.2024.3456829","url":null,"abstract":"To evaluate the overheating temperature of solar cells in concentrator photovoltaic (CPV) modules during solar radiation conversion, we propose a method for determining the thermal resistivity between the solar cell and its environment (\u0000<italic>r</i>\u0000<sub>th</sub>\u0000) in laboratory conditions at room temperature and in the absence of forced ventilation. The essence of this method is the measurement of the temperature change of the solar cells inside the CPV module under thermal load generated by direct current flow through the solar cell. The change in temperature of the solar cells in CPV modules under thermal load is determined by calculating the voltage difference across the module contacts during fast measurements of the \u0000<italic>I–V</i>\u0000 curve at room temperature and the \u0000<italic>I–V</i>\u0000 curve when the solar cells of the module are heated by direct current. The developed methodology eliminates uncertainties associated with the location of temperature sensors and unstable meteorological conditions. In the present work, this technique is used to study the overheating temperature of solar cells of “Small lenses, Multijunction cells, All from glass, Lamination, Fresnel, Optics, Concentration” design CPV modules varying in materials and thicknesses of heat sinks. In laboratory conditions, we determined the values of \u0000<italic>r</i>\u0000<sub>th</sub>\u0000 of small CPV modules and full-size CPV modules, containing, respectively, 8 and 128 pairs of Fresnel lens—triple-junction InGaP/InGaAs/Ge solar cells soldered to a metal heat sinks of similar design. Copper or steel was used as materials for the heat sinks.","PeriodicalId":445,"journal":{"name":"IEEE Journal of Photovoltaics","volume":"14 6","pages":"871-881"},"PeriodicalIF":2.5,"publicationDate":"2024-09-30","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"142518014","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 : 2024-09-11DOI: 10.1109/JPHOTOV.2024.3453653
Eman Sawires;Sameh Abdellatif
This study introduces a pioneering transistor-based equivalent circuit model explicitly tailored for mesostructured-based solar cells, primarily focusing on dye-sensitized solar cells (DSSCs) and perovskite solar cells (PSCs). By incorporating the experimental data spanning various inorganic, organic, and hybrid solar cell technologies across different optical injection levels, the model aims to provide a comprehensive understanding of the electrical behavior of these advanced photovoltaic devices. In addition to the circuit schematic, a Verilog-A script was created to elucidate the behavior of the cells, facilitating the utilization of such a block by the research community in developing interfacing circuits and implementing dc–dc converters within the framework of CMOS technology. Root-mean-square error analysis assesses the model's accuracy in predicting the experimental data. At the same time, the investigation extends to include the dynamic response of the cells through current–time analysis, as well as power losses. Notably, the response curve of the perovskite cell exhibits rapid escalation to peak current levels and displays heightened sensitivity to changes in illumination levels compared with DSSCs, with a response time of 1 ms for PSCs as opposed to 5 ms for DSSCs.
{"title":"Advanced Transistor-Based Dynamic Equivalent Circuit Modeling of Mesostructured-Based Solar Cells","authors":"Eman Sawires;Sameh Abdellatif","doi":"10.1109/JPHOTOV.2024.3453653","DOIUrl":"10.1109/JPHOTOV.2024.3453653","url":null,"abstract":"This study introduces a pioneering transistor-based equivalent circuit model explicitly tailored for mesostructured-based solar cells, primarily focusing on dye-sensitized solar cells (DSSCs) and perovskite solar cells (PSCs). By incorporating the experimental data spanning various inorganic, organic, and hybrid solar cell technologies across different optical injection levels, the model aims to provide a comprehensive understanding of the electrical behavior of these advanced photovoltaic devices. In addition to the circuit schematic, a Verilog-A script was created to elucidate the behavior of the cells, facilitating the utilization of such a block by the research community in developing interfacing circuits and implementing dc–dc converters within the framework of CMOS technology. Root-mean-square error analysis assesses the model's accuracy in predicting the experimental data. At the same time, the investigation extends to include the dynamic response of the cells through current–time analysis, as well as power losses. Notably, the response curve of the perovskite cell exhibits rapid escalation to peak current levels and displays heightened sensitivity to changes in illumination levels compared with DSSCs, with a response time of 1 ms for PSCs as opposed to 5 ms for DSSCs.","PeriodicalId":445,"journal":{"name":"IEEE Journal of Photovoltaics","volume":"14 6","pages":"882-889"},"PeriodicalIF":2.5,"publicationDate":"2024-09-11","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"142208776","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 : 2024-09-10DOI: 10.1109/JPHOTOV.2024.3450020
Nancy M. Haegel;Sarah R. Kurtz
Photovoltaics (PV) represented ∼61% of newly installed global electricity generating capacity for 2023. The amount of electricity generated by nonhydro renewables (wind, solar, geothermal, and biomass) reached another record high and exceeded generation by global hydropower for the first time in history. Fractional year-to-year growth in both PV installations and PV-generated electricity continued at remarkable levels (∼35% and ∼24%, respectively), while grid scale battery storage grew even faster (∼120%). Combined fractional electricity generation from all low carbon sources (hydro, nuclear, and renewables) reached ∼39%. Following its initial publication in 2021, this annual article will continue to collect information from multiple sources and present it systematically as a reference for IEEE Journal of Photovoltaics readers.
{"title":"Global Progress Toward Renewable Electricity: Tracking the Role of Solar (Version 4)","authors":"Nancy M. Haegel;Sarah R. Kurtz","doi":"10.1109/JPHOTOV.2024.3450020","DOIUrl":"10.1109/JPHOTOV.2024.3450020","url":null,"abstract":"Photovoltaics (PV) represented ∼61% of newly installed global electricity generating capacity for 2023. The amount of electricity generated by nonhydro renewables (wind, solar, geothermal, and biomass) reached another record high and exceeded generation by global hydropower for the first time in history. Fractional year-to-year growth in both PV installations and PV-generated electricity continued at remarkable levels (∼35% and ∼24%, respectively), while grid scale battery storage grew even faster (∼120%). Combined fractional electricity generation from all low carbon sources (hydro, nuclear, and renewables) reached ∼39%. Following its initial publication in 2021, this annual article will continue to collect information from multiple sources and present it systematically as a reference for <sc>IEEE Journal of Photovoltaics</small> readers.","PeriodicalId":445,"journal":{"name":"IEEE Journal of Photovoltaics","volume":"15 2","pages":"206-214"},"PeriodicalIF":2.5,"publicationDate":"2024-09-10","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"https://ieeexplore.ieee.org/stamp/stamp.jsp?tp=&arnumber=10673798","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"142208775","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 : 2024-09-09DOI: 10.1109/JPHOTOV.2024.3453601
Samuel Beyene;Bao Hoang;Catherine C. Keys;B. D. Weaver;Ani Khachatrian
Electric orbit raising (EOR) radiation-induced coverglass (CG) damage reduces the amount of light that reaches underlying solar cells and decreases photoconversion efficiency. This article describes the modeling, simulation, and ground-based radiation tests using Qioptiq CMG borosilicate CG for five selected EOR trajectories, and the impact on the performance of III-V multijunction (MJ) solar cells. The CG optical transmission loss reaches a maximum of ∼20% around 350 nm. However, the spectral response of the MJ solar cells at this wavelength is minimal. The test results show a darkening related to solar cell performance degradation of up to 5% for the worst-case EOR trajectory.
{"title":"Electric Orbit Raising Radiation-Induced Coverglass Darkening and Its Impact on III-V Multijunction Solar Cell Performance","authors":"Samuel Beyene;Bao Hoang;Catherine C. Keys;B. D. Weaver;Ani Khachatrian","doi":"10.1109/JPHOTOV.2024.3453601","DOIUrl":"10.1109/JPHOTOV.2024.3453601","url":null,"abstract":"Electric orbit raising (EOR) radiation-induced coverglass (CG) damage reduces the amount of light that reaches underlying solar cells and decreases photoconversion efficiency. This article describes the modeling, simulation, and ground-based radiation tests using Qioptiq CMG borosilicate CG for five selected EOR trajectories, and the impact on the performance of III-V multijunction (MJ) solar cells. The CG optical transmission loss reaches a maximum of ∼20% around 350 nm. However, the spectral response of the MJ solar cells at this wavelength is minimal. The test results show a darkening related to solar cell performance degradation of up to 5% for the worst-case EOR trajectory.","PeriodicalId":445,"journal":{"name":"IEEE Journal of Photovoltaics","volume":"14 6","pages":"907-910"},"PeriodicalIF":2.5,"publicationDate":"2024-09-09","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"142208777","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 : 2024-09-09DOI: 10.1109/JPHOTOV.2024.3453651
Songmei Wu;Hui Guo;Xiaokang Zhang;Fei Wang
Accurate photovoltaic (PV) power prediction technology plays a crucial role in effectively addressing the challenges posed by the integration of large-scale PV systems into the grid. In this article, we propose a novel PV power combination prediction model based on complete ensemble empirical mode decomposition with adaptive noise (CEEMDAN) in conjunction with a hybrid neural network. To mitigate the influence of strong fluctuations in PV power on prediction outcomes, we employ CEEMDAN to decompose the PV data into several subsequences. Subsequently, sample entropy (SE) is used to quantify the complexity of each subsequence. Subsequences with similar SE values are then restructured to reduce computational load. Moreover, to overcome the limitations of a single neural network in capturing historical data features of PV power, a hybrid sequential convolutional neural network-gate recurrent unit (CNN-GRU) neural network is proposed. The effectiveness of our proposed model is validated through case studies involving PV power stations in two regions. To provide a comprehensive assessment, we conduct comparative validation by building and evaluating alternative models, including long-short term memory (LSTM), GRU, CEEMDAN-LSTM, CEEMDAN-GRU, and CNN-GRU. The results unequivocally demonstrate that the model presented in this article exhibits exceptional prediction performance, characterized by high accuracy and robust generalization.
准确的光伏（PV）功率预测技术在有效应对大规模光伏系统并入电网所带来的挑战方面发挥着至关重要的作用。在本文中，我们提出了一种基于自适应噪声的完整集合经验模式分解（CEEMDAN）和混合神经网络的新型光伏功率组合预测模型。为减轻光伏发电量的强烈波动对预测结果的影响，我们采用 CEEMDAN 将光伏数据分解为多个子序列。随后，样本熵（SE）被用来量化每个子序列的复杂性。然后，对具有相似 SE 值的子序列进行重组，以减少计算负荷。此外，为了克服单一神经网络在捕捉光伏发电历史数据特征方面的局限性，我们提出了一种混合序列卷积神经网络-栅递归单元（CNN-GRU）神经网络。通过对两个地区的光伏发电站进行案例研究，验证了我们提出的模型的有效性。为了提供全面的评估，我们通过构建和评估替代模型进行了比较验证，包括长短期记忆（LSTM）、GRU、CEEMDAN-LSTM、CEEMDAN-GRU 和 CNN-GRU。结果明确表明，本文介绍的模型具有卓越的预测性能，其特点是准确性高、泛化能力强。
{"title":"Short-Term Photovoltaic Power Prediction Based on CEEMDAN and Hybrid Neural Networks","authors":"Songmei Wu;Hui Guo;Xiaokang Zhang;Fei Wang","doi":"10.1109/JPHOTOV.2024.3453651","DOIUrl":"10.1109/JPHOTOV.2024.3453651","url":null,"abstract":"Accurate photovoltaic (PV) power prediction technology plays a crucial role in effectively addressing the challenges posed by the integration of large-scale PV systems into the grid. In this article, we propose a novel PV power combination prediction model based on complete ensemble empirical mode decomposition with adaptive noise (CEEMDAN) in conjunction with a hybrid neural network. To mitigate the influence of strong fluctuations in PV power on prediction outcomes, we employ CEEMDAN to decompose the PV data into several subsequences. Subsequently, sample entropy (SE) is used to quantify the complexity of each subsequence. Subsequences with similar SE values are then restructured to reduce computational load. Moreover, to overcome the limitations of a single neural network in capturing historical data features of PV power, a hybrid sequential convolutional neural network-gate recurrent unit (CNN-GRU) neural network is proposed. The effectiveness of our proposed model is validated through case studies involving PV power stations in two regions. To provide a comprehensive assessment, we conduct comparative validation by building and evaluating alternative models, including long-short term memory (LSTM), GRU, CEEMDAN-LSTM, CEEMDAN-GRU, and CNN-GRU. The results unequivocally demonstrate that the model presented in this article exhibits exceptional prediction performance, characterized by high accuracy and robust generalization.","PeriodicalId":445,"journal":{"name":"IEEE Journal of Photovoltaics","volume":"14 6","pages":"960-969"},"PeriodicalIF":2.5,"publicationDate":"2024-09-09","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"142208807","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 : 2024-09-05DOI: 10.1109/JPHOTOV.2024.3450009
Zaid Mahboob;M. Adil Khan;Ehtisham Lodhi;Tahir Nawaz;Umar S. Khan
Photovoltaic (PV) industries are susceptible to manufacturing defects within their solar cells. To accurately evaluate the efficacy of solar PV modules, the identification of manufacturing defects is imperative. Conventional industrial defect inspections predominantly rely on highly skilled inspectors conducting manual defect assessments, leading to sporadic and subjective identification outcomes. Deep-learning-based fault detection in PV or solar cells has emerged as a primary research area due to its superior efficiency and applicability. Hence, this study introduces a SegFormer-based fault detection framework to automate the visual defect inspection process in PV modules, complete with defect pseudocolorization. The proposed SegFormer-based framework effectively classifies defects into five categories: crack defects, front grid defects, interconnect defects, contact corrosion defects, and bright disconnect. Moreover, a comparative analysis is performed between the SegFormer model and the state-of-the-art fault detection algorithms, such as Deeplab v3, UNET, Deeplab v3+, PAN, PSPNet, and feature pyramid network (FPN). The experimental results reveal that the proposed SegFormer-based framework achieves highly encouraging performance, with a pixelwise accuracy of 96.24%, a weighted F1-score of 96.22%, an unweighted F1-score of 81.96%, and a mean intersection over union of 56.54%, outperforming other existing methods.
{"title":"Using SegFormer for Effective Semantic Cell Segmentation for Fault Detection in Photovoltaic Arrays","authors":"Zaid Mahboob;M. Adil Khan;Ehtisham Lodhi;Tahir Nawaz;Umar S. Khan","doi":"10.1109/JPHOTOV.2024.3450009","DOIUrl":"10.1109/JPHOTOV.2024.3450009","url":null,"abstract":"Photovoltaic (PV) industries are susceptible to manufacturing defects within their solar cells. To accurately evaluate the efficacy of solar PV modules, the identification of manufacturing defects is imperative. Conventional industrial defect inspections predominantly rely on highly skilled inspectors conducting manual defect assessments, leading to sporadic and subjective identification outcomes. Deep-learning-based fault detection in PV or solar cells has emerged as a primary research area due to its superior efficiency and applicability. Hence, this study introduces a SegFormer-based fault detection framework to automate the visual defect inspection process in PV modules, complete with defect pseudocolorization. The proposed SegFormer-based framework effectively classifies defects into five categories: crack defects, front grid defects, interconnect defects, contact corrosion defects, and bright disconnect. Moreover, a comparative analysis is performed between the SegFormer model and the state-of-the-art fault detection algorithms, such as Deeplab v3, UNET, Deeplab v3+, PAN, PSPNet, and feature pyramid network (FPN). The experimental results reveal that the proposed SegFormer-based framework achieves highly encouraging performance, with a pixelwise accuracy of 96.24%, a weighted <italic>F</i>1-score of 96.22%, an unweighted <italic>F</i>1-score of 81.96%, and a mean intersection over union of 56.54%, outperforming other existing methods.","PeriodicalId":445,"journal":{"name":"IEEE Journal of Photovoltaics","volume":"15 2","pages":"320-331"},"PeriodicalIF":2.5,"publicationDate":"2024-09-05","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"142208778","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}
This article proposes a novel approach to photovoltaic panel inspection through the integration of image classification and meteorological data analysis. Utilizing two convolutional neural network models with distinct architectures for classifying thermal and red, green, blue (RGB) images of photovoltaic installations, in addition to an support vector machines model for meteorological data classification, the results from these models are concatenated, allowing the fusion of visual and meteorological information for comprehensive defect detection. Data collection from photovoltaic panels is achieved using a portable device, followed by the application of advanced image processing techniques to identify faults rapidly and accurately with up to 96% accuracy. The inspection results are presented in a user-friendly format, facilitating straightforward interpretation and analysis. This new approach has the potential to significantly enhance the efficiency and durability of solar energy systems, enabling timely maintenance and repair for photovoltaic panel issues.
{"title":"Data-Driven Digital Inspection of Photovoltaic Panels Using a Portable Hybrid Model Combining Meteorological Data and Image Processing","authors":"Ayoub Oufadel;Alae Azouzoute;Hicham Ghennioui;Chaimae Soubai;Ibrahim Taabane","doi":"10.1109/JPHOTOV.2024.3437736","DOIUrl":"10.1109/JPHOTOV.2024.3437736","url":null,"abstract":"This article proposes a novel approach to photovoltaic panel inspection through the integration of image classification and meteorological data analysis. Utilizing two convolutional neural network models with distinct architectures for classifying thermal and red, green, blue (RGB) images of photovoltaic installations, in addition to an support vector machines model for meteorological data classification, the results from these models are concatenated, allowing the fusion of visual and meteorological information for comprehensive defect detection. Data collection from photovoltaic panels is achieved using a portable device, followed by the application of advanced image processing techniques to identify faults rapidly and accurately with up to 96% accuracy. The inspection results are presented in a user-friendly format, facilitating straightforward interpretation and analysis. This new approach has the potential to significantly enhance the efficiency and durability of solar energy systems, enabling timely maintenance and repair for photovoltaic panel issues.","PeriodicalId":445,"journal":{"name":"IEEE Journal of Photovoltaics","volume":"14 6","pages":"937-950"},"PeriodicalIF":2.5,"publicationDate":"2024-09-02","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"142208808","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 : 2024-08-21DOI: 10.1109/JPHOTOV.2024.3444009
{"title":"Call for Papers: Special Issue on Intelligent Sensor Systems for the IEEE Journal of Electron Devices","authors":"","doi":"10.1109/JPHOTOV.2024.3444009","DOIUrl":"https://doi.org/10.1109/JPHOTOV.2024.3444009","url":null,"abstract":"","PeriodicalId":445,"journal":{"name":"IEEE Journal of Photovoltaics","volume":"14 5","pages":"867-868"},"PeriodicalIF":2.5,"publicationDate":"2024-08-21","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"https://ieeexplore.ieee.org/stamp/stamp.jsp?tp=&arnumber=10643379","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"142021613","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}
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：