PV Analyzer: A Decision Support System for Photovoltaic Solar Cells Libraries

Omer Kaspi; Abraham Yosipof; Hanoch Senderowitz

doi:10.1002/minf.201800067

PV Analyzer: A Decision Support System for Photovoltaic Solar Cells Libraries

Omer Kaspi, Abraham Yosipof, Hanoch Senderowitz

Department of Chemistry

College of Law & Business

Research output: Contribution to journal › Article › peer-review

4 Scopus citations

Abstract

This work describes the integration of several data mining and machine learning tools for researching Photovoltaic (PV) solar cells libraries into a unified workflow embedded within a GUI-supported Decision Support System (DSS), named PV Analyzer. The analyzer's workflow is composed of several data analysis components including basic statistical and visualization methods as well as an algorithm for building predictive machine learning models. The analyzer allows for the identification of interesting trends within the libraries, not easily observable using simple bi-parametric correlations. This may lead to new insights into factor affecting solar cells performances with the ultimate goal of designing better solar cells. The analyzer was developed using MATLAB version R2014a and consequently could be easily extended by adding additional tools and algorithms. Furthermore, while in our hands, the analyzer has been primarily used in the area of PV cells, is it equally applicable to the analysis of any other dataset composed of activities as dependent variables and descriptors as independent variables.

Original language	English
Article number	1800067
Journal	Molecular Informatics
Volume	37
Issue number	9
DOIs	https://doi.org/10.1002/minf.201800067
State	Published - Sep 2018

Bibliographical note

Publisher Copyright:
© 2018 Wiley-VCH Verlag GmbH & Co. KGaA, Weinheim

Funding

The raw data utilized in this manuscript and which are provided in the supporting information were produced in the laboratories of Prof. Arie Zaban at Bar-Ilan University, Ramat Gan, Israel and Professor Elvira Fortunato at the Materials Science Department of New University of Lisbon, Portugal. We are thankful to the members of both labs for sharing the data with us. The authors also acknowledge COST action CA16235 “Performance and Reliability of Photovoltaic Systems: Evaluations of Large-Scale Monitoring Data” (PEARL-PV) for travel support.

Funders	Funder number
Materials Science Department of New University of Lisbon
European Cooperation in Science and Technology	CA16235

Keywords

Data mining
Decision Support System
Machine learning
Material-Informatics
Photovoltaic
QSAR
RANSAC
Solar cell

UN SDGs

This output contributes to the following UN Sustainable Development Goals (SDGs)

Access to Document

10.1002/minf.201800067

Cite this

@article{92c98ce1923e4f85b606dd583a377d46,

title = "PV Analyzer: A Decision Support System for Photovoltaic Solar Cells Libraries",

abstract = "This work describes the integration of several data mining and machine learning tools for researching Photovoltaic (PV) solar cells libraries into a unified workflow embedded within a GUI-supported Decision Support System (DSS), named PV Analyzer. The analyzer's workflow is composed of several data analysis components including basic statistical and visualization methods as well as an algorithm for building predictive machine learning models. The analyzer allows for the identification of interesting trends within the libraries, not easily observable using simple bi-parametric correlations. This may lead to new insights into factor affecting solar cells performances with the ultimate goal of designing better solar cells. The analyzer was developed using MATLAB version R2014a and consequently could be easily extended by adding additional tools and algorithms. Furthermore, while in our hands, the analyzer has been primarily used in the area of PV cells, is it equally applicable to the analysis of any other dataset composed of activities as dependent variables and descriptors as independent variables.",

keywords = "Data mining, Decision Support System, Machine learning, Material-Informatics, Photovoltaic, QSAR, RANSAC, Solar cell",

author = "Omer Kaspi and Abraham Yosipof and Hanoch Senderowitz",

note = "Publisher Copyright: {\textcopyright} 2018 Wiley-VCH Verlag GmbH & Co. KGaA, Weinheim",

year = "2018",

month = sep,

doi = "10.1002/minf.201800067",

language = "אנגלית",

volume = "37",

journal = "Molecular Informatics",

issn = "1868-1743",

publisher = "John Wiley and Sons Inc.",

number = "9",

}

TY - JOUR

T1 - PV Analyzer

T2 - A Decision Support System for Photovoltaic Solar Cells Libraries

AU - Kaspi, Omer

AU - Yosipof, Abraham

AU - Senderowitz, Hanoch

PY - 2018/9

Y1 - 2018/9

N2 - This work describes the integration of several data mining and machine learning tools for researching Photovoltaic (PV) solar cells libraries into a unified workflow embedded within a GUI-supported Decision Support System (DSS), named PV Analyzer. The analyzer's workflow is composed of several data analysis components including basic statistical and visualization methods as well as an algorithm for building predictive machine learning models. The analyzer allows for the identification of interesting trends within the libraries, not easily observable using simple bi-parametric correlations. This may lead to new insights into factor affecting solar cells performances with the ultimate goal of designing better solar cells. The analyzer was developed using MATLAB version R2014a and consequently could be easily extended by adding additional tools and algorithms. Furthermore, while in our hands, the analyzer has been primarily used in the area of PV cells, is it equally applicable to the analysis of any other dataset composed of activities as dependent variables and descriptors as independent variables.

AB - This work describes the integration of several data mining and machine learning tools for researching Photovoltaic (PV) solar cells libraries into a unified workflow embedded within a GUI-supported Decision Support System (DSS), named PV Analyzer. The analyzer's workflow is composed of several data analysis components including basic statistical and visualization methods as well as an algorithm for building predictive machine learning models. The analyzer allows for the identification of interesting trends within the libraries, not easily observable using simple bi-parametric correlations. This may lead to new insights into factor affecting solar cells performances with the ultimate goal of designing better solar cells. The analyzer was developed using MATLAB version R2014a and consequently could be easily extended by adding additional tools and algorithms. Furthermore, while in our hands, the analyzer has been primarily used in the area of PV cells, is it equally applicable to the analysis of any other dataset composed of activities as dependent variables and descriptors as independent variables.

KW - Data mining

KW - Decision Support System

KW - Machine learning

KW - Material-Informatics

KW - Photovoltaic

KW - QSAR

KW - RANSAC

KW - Solar cell

UR - http://www.scopus.com/inward/record.url?scp=85050623262&partnerID=8YFLogxK

U2 - 10.1002/minf.201800067

DO - 10.1002/minf.201800067

M3 - ???researchoutput.researchoutputtypes.contributiontojournal.article???

C2 - 30022619

SN - 1868-1743

VL - 37

JO - Molecular Informatics

JF - Molecular Informatics

IS - 9

M1 - 1800067

ER -

PV Analyzer: A Decision Support System for Photovoltaic Solar Cells Libraries

Abstract

Bibliographical note

Funding

Keywords

UN SDGs

Access to Document

Other files and links

Fingerprint

Cite this