Pub Date : 2021-06-20DOI: 10.1109/PVSC43889.2021.9518512
Yoann Buratti, Zubair Abdullah‐Vetter, A. Sowmya, T. Trupke, Z. Hameiri
Identifying and quantifying loss mechanisms in solar cells are key requirements for increasing cell efficiencies. In this study, we present a novel method based on luminescence images to identify and quantify losses in silicon cells using a state of art deep learning technique: generative adversarial networks. In addition to the common use of defect identification, we also use the images to isolate a specific defect and to quantify its impact on cell efficiency. This is achieved by reconstructing a defect-free luminescence image and comparing it to the original image to determine the performance shortfall. The large-scale loss-analysis powered by the proposed deep learning method has the potential to significantly improve the quantitative analysis of luminescence image data, both in research and development and in high volume manufacturing.
{"title":"A Deep Learning Approach for Loss-Analysis from Luminescence Images","authors":"Yoann Buratti, Zubair Abdullah‐Vetter, A. Sowmya, T. Trupke, Z. Hameiri","doi":"10.1109/PVSC43889.2021.9518512","DOIUrl":"https://doi.org/10.1109/PVSC43889.2021.9518512","url":null,"abstract":"Identifying and quantifying loss mechanisms in solar cells are key requirements for increasing cell efficiencies. In this study, we present a novel method based on luminescence images to identify and quantify losses in silicon cells using a state of art deep learning technique: generative adversarial networks. In addition to the common use of defect identification, we also use the images to isolate a specific defect and to quantify its impact on cell efficiency. This is achieved by reconstructing a defect-free luminescence image and comparing it to the original image to determine the performance shortfall. The large-scale loss-analysis powered by the proposed deep learning method has the potential to significantly improve the quantitative analysis of luminescence image data, both in research and development and in high volume manufacturing.","PeriodicalId":6788,"journal":{"name":"2021 IEEE 48th Photovoltaic Specialists Conference (PVSC)","volume":"39 1","pages":"0097-0100"},"PeriodicalIF":0.0,"publicationDate":"2021-06-20","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"75528354","PeriodicalName":null,"FirstCategoryId":null,"ListUrlMain":null,"RegionNum":0,"RegionCategory":"","ArticlePicture":[],"TitleCN":null,"AbstractTextCN":null,"PMCID":"","EPubDate":null,"PubModel":null,"JCR":null,"JCRName":null,"Score":null,"Total":0}
Pub Date : 2021-06-20DOI: 10.1109/PVSC43889.2021.9518782
A. Nihar, A. Curran, A. M. Karimi, J. Braid, L. Bruckman, Mehmet Koyutürk, Yinghui Wu, R. French
We present the application of FAIR principles to photovoltaic time series data to increase their reusability within the photovoltaic research community. The main requirements for a "FAIRified" dataset is to have a clearly defined data format, and to make accessible all metadata for this dataset to humans and machines. To achieve FAIRification, we implement a data model that separates the photovoltaic data and its metadata. The metadata and their descriptions are registered on a data repository in a human and machine readable format, using JSON-LD. Also, secure APIs are developed to access photovoltaic data. This approach has long term scalability and maintainability.
{"title":"Toward Findable, Accessible, Interoperable and Reusable (FAIR) Photovoltaic System Time Series Data","authors":"A. Nihar, A. Curran, A. M. Karimi, J. Braid, L. Bruckman, Mehmet Koyutürk, Yinghui Wu, R. French","doi":"10.1109/PVSC43889.2021.9518782","DOIUrl":"https://doi.org/10.1109/PVSC43889.2021.9518782","url":null,"abstract":"We present the application of FAIR principles to photovoltaic time series data to increase their reusability within the photovoltaic research community. The main requirements for a \"FAIRified\" dataset is to have a clearly defined data format, and to make accessible all metadata for this dataset to humans and machines. To achieve FAIRification, we implement a data model that separates the photovoltaic data and its metadata. The metadata and their descriptions are registered on a data repository in a human and machine readable format, using JSON-LD. Also, secure APIs are developed to access photovoltaic data. This approach has long term scalability and maintainability.","PeriodicalId":6788,"journal":{"name":"2021 IEEE 48th Photovoltaic Specialists Conference (PVSC)","volume":"36 1","pages":"1701-1706"},"PeriodicalIF":0.0,"publicationDate":"2021-06-20","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"74794797","PeriodicalName":null,"FirstCategoryId":null,"ListUrlMain":null,"RegionNum":0,"RegionCategory":"","ArticlePicture":[],"TitleCN":null,"AbstractTextCN":null,"PMCID":"","EPubDate":null,"PubModel":null,"JCR":null,"JCRName":null,"Score":null,"Total":0}
Pub Date : 2021-06-20DOI: 10.1109/PVSC43889.2021.9518715
J. Sutter, P. Tockhorn, P. Wagner, K. Jäger, A. Al‐Ashouri, B. Stannowski, S. Albrecht, C. Becker
The power conversion efficiency (PCE) of perovskite/silicon tandem solar cells (PSTSCs) is expected to increase with optimized light management. In this work, we report on PSTSCs containing nanostructures enabling PCEs exceeding 26%. A hexagonal sinusoidal nanostructure with 750nm period was used. The structure was transferred into silicon by nanoimprint lithography and reactive ion etching. Perovskite top cells were deposited by spin-coating resulting in a full coverage of the nanostructure. PSTSC comprising these nanostructures yielded a steady-state PCE of 26.1% and a short-circuit current density of 19.5mA·cm−2.
{"title":"Periodically Nanostructured Perovskite/Silicon Tandem Solar Cells with Power Conversion Efficiency Exceeding 26%","authors":"J. Sutter, P. Tockhorn, P. Wagner, K. Jäger, A. Al‐Ashouri, B. Stannowski, S. Albrecht, C. Becker","doi":"10.1109/PVSC43889.2021.9518715","DOIUrl":"https://doi.org/10.1109/PVSC43889.2021.9518715","url":null,"abstract":"The power conversion efficiency (PCE) of perovskite/silicon tandem solar cells (PSTSCs) is expected to increase with optimized light management. In this work, we report on PSTSCs containing nanostructures enabling PCEs exceeding 26%. A hexagonal sinusoidal nanostructure with 750nm period was used. The structure was transferred into silicon by nanoimprint lithography and reactive ion etching. Perovskite top cells were deposited by spin-coating resulting in a full coverage of the nanostructure. PSTSC comprising these nanostructures yielded a steady-state PCE of 26.1% and a short-circuit current density of 19.5mA·cm−2.","PeriodicalId":6788,"journal":{"name":"2021 IEEE 48th Photovoltaic Specialists Conference (PVSC)","volume":"16 1","pages":"1034-1036"},"PeriodicalIF":0.0,"publicationDate":"2021-06-20","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"74255721","PeriodicalName":null,"FirstCategoryId":null,"ListUrlMain":null,"RegionNum":0,"RegionCategory":"","ArticlePicture":[],"TitleCN":null,"AbstractTextCN":null,"PMCID":"","EPubDate":null,"PubModel":null,"JCR":null,"JCRName":null,"Score":null,"Total":0}
Pub Date : 2021-06-20DOI: 10.1109/PVSC43889.2021.9518703
A. Ebong, S. Huneycutt, Sarah Grempels, K. Ankireddy, R. Dharmadasa, T. Druffel
The metallization of solar cells remains a dominating factor for the total cost of solar cell manufacturing and must be reduced. A prime candidate to replace the traditional Ag is Cu since it is close in conductivity but about 100 times lower cost. However, the oxidation of Cu in atmosphere and its diffusion into Si have been troublesome factors preventing its implementation. These two challenges were considered to formulate the thick film Cu paste and the 19.4% efficiency, fill factor of 76.02%, short-circuit current density of 39.0 mA/cm2 and open-circuit voltage of 654.4 mV, show these challenges have been overcome.
{"title":"Progress of Atmospheric Screen-printable Cu Paste for High Efficiency PERC Solar Cells","authors":"A. Ebong, S. Huneycutt, Sarah Grempels, K. Ankireddy, R. Dharmadasa, T. Druffel","doi":"10.1109/PVSC43889.2021.9518703","DOIUrl":"https://doi.org/10.1109/PVSC43889.2021.9518703","url":null,"abstract":"The metallization of solar cells remains a dominating factor for the total cost of solar cell manufacturing and must be reduced. A prime candidate to replace the traditional Ag is Cu since it is close in conductivity but about 100 times lower cost. However, the oxidation of Cu in atmosphere and its diffusion into Si have been troublesome factors preventing its implementation. These two challenges were considered to formulate the thick film Cu paste and the 19.4% efficiency, fill factor of 76.02%, short-circuit current density of 39.0 mA/cm2 and open-circuit voltage of 654.4 mV, show these challenges have been overcome.","PeriodicalId":6788,"journal":{"name":"2021 IEEE 48th Photovoltaic Specialists Conference (PVSC)","volume":"20 1","pages":"1417-1420"},"PeriodicalIF":0.0,"publicationDate":"2021-06-20","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"74092891","PeriodicalName":null,"FirstCategoryId":null,"ListUrlMain":null,"RegionNum":0,"RegionCategory":"","ArticlePicture":[],"TitleCN":null,"AbstractTextCN":null,"PMCID":"","EPubDate":null,"PubModel":null,"JCR":null,"JCRName":null,"Score":null,"Total":0}
Pub Date : 2021-06-20DOI: 10.1109/PVSC43889.2021.9518939
O. Segbefia, Anne Gerd Imenes, I. Burud, T. Sætre
In this work, the temperature sensitivities of field-aged multicrystalline silicon PV modules affected by microcracks are investigated. It is found that the temperature coefficient of efficiency of all modules has increased more than 10 times over the 20 years period, mainly due to a degradation in the temperature coefficients of fill factor. Temperature coefficient of efficiency of PV modules affected by microcracks changed from -0.44 %/ °C to -1.51 %/°C under solar irradiance conditions at 1010 - 1030 W/m2. Inconsistent values for the Evans–Floschuetz efficiency ratio versus temperature plots for the microcrack affected modules were also observed.
{"title":"Temperature profiles of field-aged multicrystalline silicon photovoltaic modules affected by microcracks","authors":"O. Segbefia, Anne Gerd Imenes, I. Burud, T. Sætre","doi":"10.1109/PVSC43889.2021.9518939","DOIUrl":"https://doi.org/10.1109/PVSC43889.2021.9518939","url":null,"abstract":"In this work, the temperature sensitivities of field-aged multicrystalline silicon PV modules affected by microcracks are investigated. It is found that the temperature coefficient of efficiency of all modules has increased more than 10 times over the 20 years period, mainly due to a degradation in the temperature coefficients of fill factor. Temperature coefficient of efficiency of PV modules affected by microcracks changed from -0.44 %/ °C to -1.51 %/°C under solar irradiance conditions at 1010 - 1030 W/m2. Inconsistent values for the Evans–Floschuetz efficiency ratio versus temperature plots for the microcrack affected modules were also observed.","PeriodicalId":6788,"journal":{"name":"2021 IEEE 48th Photovoltaic Specialists Conference (PVSC)","volume":"106 1","pages":"0001-0006"},"PeriodicalIF":0.0,"publicationDate":"2021-06-20","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"79253188","PeriodicalName":null,"FirstCategoryId":null,"ListUrlMain":null,"RegionNum":0,"RegionCategory":"","ArticlePicture":[],"TitleCN":null,"AbstractTextCN":null,"PMCID":"","EPubDate":null,"PubModel":null,"JCR":null,"JCRName":null,"Score":null,"Total":0}
Pub Date : 2021-06-20DOI: 10.1109/PVSC43889.2021.9518482
M. Florides, G. Makrides, G. Georghiou
High voltage photovoltaic (PV) systems are affected by potential induced degradation (PID). PID detection by conventional data analysis methods could take a long time, leading to unnoticed energy loss. If PID is detected at an early stage, energy loss could be avoided by taking appropriate measures. This paper presents a new method for detecting PID at an early stage (< 1% power loss). The method is based on low-current DC signals and, hence, it could be implemented in a low-cost sensor. The method was tested experimentally on standard multi-cell crystalline silicon PV modules and successfully detected PID before 1% power loss.
{"title":"Early Detection of Potential Induced Degradation in the Field: Testing a New Method for Silicon PV Modules","authors":"M. Florides, G. Makrides, G. Georghiou","doi":"10.1109/PVSC43889.2021.9518482","DOIUrl":"https://doi.org/10.1109/PVSC43889.2021.9518482","url":null,"abstract":"High voltage photovoltaic (PV) systems are affected by potential induced degradation (PID). PID detection by conventional data analysis methods could take a long time, leading to unnoticed energy loss. If PID is detected at an early stage, energy loss could be avoided by taking appropriate measures. This paper presents a new method for detecting PID at an early stage (< 1% power loss). The method is based on low-current DC signals and, hence, it could be implemented in a low-cost sensor. The method was tested experimentally on standard multi-cell crystalline silicon PV modules and successfully detected PID before 1% power loss.","PeriodicalId":6788,"journal":{"name":"2021 IEEE 48th Photovoltaic Specialists Conference (PVSC)","volume":"80 1","pages":"0950-0953"},"PeriodicalIF":0.0,"publicationDate":"2021-06-20","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"79310927","PeriodicalName":null,"FirstCategoryId":null,"ListUrlMain":null,"RegionNum":0,"RegionCategory":"","ArticlePicture":[],"TitleCN":null,"AbstractTextCN":null,"PMCID":"","EPubDate":null,"PubModel":null,"JCR":null,"JCRName":null,"Score":null,"Total":0}
Pub Date : 2021-06-20DOI: 10.1109/PVSC43889.2021.9518721
Arrik Khanna, R. Pandey, Jaya Madan, Arvind Dhingra
Colloidal quantum dots (CQDs) solar cells filtered with lead sulfide (PbS) have provided a great alternate for lasting solar device. This is due to its capability of reaping infrared photons, increased exciton generation and tunable bandgap. However, creating a highly stable PbS CQD with high conversion efficiency is challenge on the grounds to the material quality of the PbS CQD based absorber layer. Power conversion efficiency (PCE) can be put up by reducing the bulk defect density forth at an optimum absorber layer thickness. Here in this research article effect of absorber layer thickness and bulk defect density is investigated for wide bandgap (Eg=1.56 eV) based PbS CQD absorber layer solar cell in order to ameliorate the PCE. This has been achieved by wavering the thickness from 50 nm to 500 nm and the bulk defect density from 1 x 1014 cm-3 to 1 x 1016 cm-3 in 10 steps each. Simulation are carried using SCAPS-1D and it published the uppermost PCE of 13.14 at bulk defect density of 1014 cm-3 and the thickness of 500 nm.
{"title":"Thickness Optimisation and Defect Analysis of Wide Bandgap PbS-CQD Solar Cell by SCAPS-1D Simulations","authors":"Arrik Khanna, R. Pandey, Jaya Madan, Arvind Dhingra","doi":"10.1109/PVSC43889.2021.9518721","DOIUrl":"https://doi.org/10.1109/PVSC43889.2021.9518721","url":null,"abstract":"Colloidal quantum dots (CQDs) solar cells filtered with lead sulfide (PbS) have provided a great alternate for lasting solar device. This is due to its capability of reaping infrared photons, increased exciton generation and tunable bandgap. However, creating a highly stable PbS CQD with high conversion efficiency is challenge on the grounds to the material quality of the PbS CQD based absorber layer. Power conversion efficiency (PCE) can be put up by reducing the bulk defect density forth at an optimum absorber layer thickness. Here in this research article effect of absorber layer thickness and bulk defect density is investigated for wide bandgap (Eg=1.56 eV) based PbS CQD absorber layer solar cell in order to ameliorate the PCE. This has been achieved by wavering the thickness from 50 nm to 500 nm and the bulk defect density from 1 x 1014 cm-3 to 1 x 1016 cm-3 in 10 steps each. Simulation are carried using SCAPS-1D and it published the uppermost PCE of 13.14 at bulk defect density of 1014 cm-3 and the thickness of 500 nm.","PeriodicalId":6788,"journal":{"name":"2021 IEEE 48th Photovoltaic Specialists Conference (PVSC)","volume":"1 1","pages":"2191-2193"},"PeriodicalIF":0.0,"publicationDate":"2021-06-20","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"84807782","PeriodicalName":null,"FirstCategoryId":null,"ListUrlMain":null,"RegionNum":0,"RegionCategory":"","ArticlePicture":[],"TitleCN":null,"AbstractTextCN":null,"PMCID":"","EPubDate":null,"PubModel":null,"JCR":null,"JCRName":null,"Score":null,"Total":0}
Pub Date : 2021-06-20DOI: 10.1109/PVSC43889.2021.9518520
C. Schultz, M. Fenske, J. Dagar, F. Kosasih, Cornelia Junghans, A. Bartelt, C. Ducati, R. Schlatmann, E. Unger, B. Stegemann
P3 patterning with ns and ps laser pulses for monolithic series interconnection of perovskite solar cells was systematically investigated. The use of ns laser pulses generates a larger amount of PbI2 and a Br-rich interface layer in the processed area, which proved to be beneficial for P3 patterning due to improved defect passivation. Thus, the P3 step should be carried out with ns laser pulses for an optimized separation of adjacent cells, while ps laser pulses were recommended for the P2 interconnect. Accordingly, suitable laser parameters for optimal laser patterning are demonstrated and novel insights into the controversial issue about the influence of PbI2 on the overall photovoltaic performance of perovskite solar cells are presented.
{"title":"P3 Nanosecond Laser Patterning of Perovskite Solar Cells: Defect Passivation Through Formation of PbI2 and Br-rich Interface Layers","authors":"C. Schultz, M. Fenske, J. Dagar, F. Kosasih, Cornelia Junghans, A. Bartelt, C. Ducati, R. Schlatmann, E. Unger, B. Stegemann","doi":"10.1109/PVSC43889.2021.9518520","DOIUrl":"https://doi.org/10.1109/PVSC43889.2021.9518520","url":null,"abstract":"P3 patterning with ns and ps laser pulses for monolithic series interconnection of perovskite solar cells was systematically investigated. The use of ns laser pulses generates a larger amount of PbI2 and a Br-rich interface layer in the processed area, which proved to be beneficial for P3 patterning due to improved defect passivation. Thus, the P3 step should be carried out with ns laser pulses for an optimized separation of adjacent cells, while ps laser pulses were recommended for the P2 interconnect. Accordingly, suitable laser parameters for optimal laser patterning are demonstrated and novel insights into the controversial issue about the influence of PbI2 on the overall photovoltaic performance of perovskite solar cells are presented.","PeriodicalId":6788,"journal":{"name":"2021 IEEE 48th Photovoltaic Specialists Conference (PVSC)","volume":"15 1","pages":"1030-1033"},"PeriodicalIF":0.0,"publicationDate":"2021-06-20","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"84814369","PeriodicalName":null,"FirstCategoryId":null,"ListUrlMain":null,"RegionNum":0,"RegionCategory":"","ArticlePicture":[],"TitleCN":null,"AbstractTextCN":null,"PMCID":"","EPubDate":null,"PubModel":null,"JCR":null,"JCRName":null,"Score":null,"Total":0}
Pub Date : 2021-06-20DOI: 10.1109/PVSC43889.2021.9518642
Xinlu Lin, Yufeng Zhang, Ziyao Zhu, Qiuchen Wu, Xiangxin Liu
P-type copper-doped zinc telluride (ZnTe:Cu) is a good candidate as a back contact of cadmium telluride (CdTe) solar cell. The deposition rate, transmittance and resistivity of ZnTe:Cu films deposited via target bias radio frequency (r.f.) sputtering was studied. The target bias voltage considerably influenced ZnTe:Cu film resistivity. In the meantime we find that post-deposition heat treatment (PDHT) significantly reduces the electrical resistivity of the ZnTe:Cu films, which is due to increases in both carrier concentration and mobility. It is inspiring for us to further improve the conductivity of ZnTe:Cu by applying the r.f. coupled d.c. sputtering and PDHT.
{"title":"Synthesis of high-quality ZnTe:Cu films as a back contact layer for CdTe solar cells","authors":"Xinlu Lin, Yufeng Zhang, Ziyao Zhu, Qiuchen Wu, Xiangxin Liu","doi":"10.1109/PVSC43889.2021.9518642","DOIUrl":"https://doi.org/10.1109/PVSC43889.2021.9518642","url":null,"abstract":"P-type copper-doped zinc telluride (ZnTe:Cu) is a good candidate as a back contact of cadmium telluride (CdTe) solar cell. The deposition rate, transmittance and resistivity of ZnTe:Cu films deposited via target bias radio frequency (r.f.) sputtering was studied. The target bias voltage considerably influenced ZnTe:Cu film resistivity. In the meantime we find that post-deposition heat treatment (PDHT) significantly reduces the electrical resistivity of the ZnTe:Cu films, which is due to increases in both carrier concentration and mobility. It is inspiring for us to further improve the conductivity of ZnTe:Cu by applying the r.f. coupled d.c. sputtering and PDHT.","PeriodicalId":6788,"journal":{"name":"2021 IEEE 48th Photovoltaic Specialists Conference (PVSC)","volume":"536 1","pages":"0867-0873"},"PeriodicalIF":0.0,"publicationDate":"2021-06-20","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"85037924","PeriodicalName":null,"FirstCategoryId":null,"ListUrlMain":null,"RegionNum":0,"RegionCategory":"","ArticlePicture":[],"TitleCN":null,"AbstractTextCN":null,"PMCID":"","EPubDate":null,"PubModel":null,"JCR":null,"JCRName":null,"Score":null,"Total":0}
Pub Date : 2021-06-20DOI: 10.1109/PVSC43889.2021.9518472
R. Sadnan, A. Dubey
Solving nonlinear optimal power flow (OPF) problem is computationally expensive, and poses scalability challenges for power distribution networks. An alternative to solving the original nonlinear OPF is the linear approximated OPF models. Although, these linear approximated OPF models are fast, the resulting solutions may result in significant optimality gap. Lately, the application of machine learning (ML) methods in successfully solving the nonlinear OPF has been reported. These methods learn and estimate the nonlinear control policies using a purely data-driven approach. In this paper, we propose an approach to complements the ML based approach to solving OPF using solutions from known linearized OPF model. Specifically, we use supervised learning to map the solutions of linear OPF to nonlinear control variables. Unlike, the traditional ML based methods for OPF that approximate the full distribution feeder model using function approximation, our approach uses a two-node approximation of radial networks. The proposed approach is validated using IEEE 123 bus test system for OPF solutions obtained using the nonlinear OPF models.
{"title":"Learning Optimal Power Flow Solutions using Linearized Models in Power Distribution Systems","authors":"R. Sadnan, A. Dubey","doi":"10.1109/PVSC43889.2021.9518472","DOIUrl":"https://doi.org/10.1109/PVSC43889.2021.9518472","url":null,"abstract":"Solving nonlinear optimal power flow (OPF) problem is computationally expensive, and poses scalability challenges for power distribution networks. An alternative to solving the original nonlinear OPF is the linear approximated OPF models. Although, these linear approximated OPF models are fast, the resulting solutions may result in significant optimality gap. Lately, the application of machine learning (ML) methods in successfully solving the nonlinear OPF has been reported. These methods learn and estimate the nonlinear control policies using a purely data-driven approach. In this paper, we propose an approach to complements the ML based approach to solving OPF using solutions from known linearized OPF model. Specifically, we use supervised learning to map the solutions of linear OPF to nonlinear control variables. Unlike, the traditional ML based methods for OPF that approximate the full distribution feeder model using function approximation, our approach uses a two-node approximation of radial networks. The proposed approach is validated using IEEE 123 bus test system for OPF solutions obtained using the nonlinear OPF models.","PeriodicalId":6788,"journal":{"name":"2021 IEEE 48th Photovoltaic Specialists Conference (PVSC)","volume":"6 1","pages":"1586-1590"},"PeriodicalIF":0.0,"publicationDate":"2021-06-20","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"82047676","PeriodicalName":null,"FirstCategoryId":null,"ListUrlMain":null,"RegionNum":0,"RegionCategory":"","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：