Machine Learning Algorithm for Assessing Photovoltaic Panels Partial Shading Losses based on Inverter Data

Partial shading is one type of fault where photovoltaic panels cast shadows between each other, reducing their production and hastening their ageing. In this paper, we document and describe two distinct Machine Learning models that aim to identify and assess the impact of partial shading in a real...

Full description

Saved in:
Bibliographic Details
Main Authors: Armando Luís Sousa Araujo, Tiago Francisco Pires
Format: Article
Language:English
Published: Universidade do Porto 2025-03-01
Series:U.Porto Journal of Engineering
Subjects:
Online Access:https://journalengineering.fe.up.pt/index.php/upjeng/article/view/2742
Tags: Add Tag
No Tags, Be the first to tag this record!
_version_ 1850117197212418048
author Armando Luís Sousa Araujo
Tiago Francisco Pires
author_facet Armando Luís Sousa Araujo
Tiago Francisco Pires
author_sort Armando Luís Sousa Araujo
collection DOAJ
description Partial shading is one type of fault where photovoltaic panels cast shadows between each other, reducing their production and hastening their ageing. In this paper, we document and describe two distinct Machine Learning models that aim to identify and assess the impact of partial shading in a real case study. These algorithms recognise similarities and patterns using expected and measured power data. The predicted power is calculated using the measured panel irradiance, current, and voltage using a photovoltaic panel electric circuit model. The first Machine Learning model employs K-means clustering to analyse the differences between expected and measured power, grouping data based on these deviations. The second Machine Learning model leverages the outputs of the K-means model as labels for a Long Short-Term Memory neural network, which classifies periods of partial shading. Experimental data from both models are presented, with the K-means model achieving a closer approximation to the reference values. However, the Long Short-Term Memory model demonstrated flexibility and scalability without requiring prior dataset knowledge from the end user.
format Article
id doaj-art-d07c3d0f90314aaa9c5a08cf74860125
institution OA Journals
issn 2183-6493
language English
publishDate 2025-03-01
publisher Universidade do Porto
record_format Article
series U.Porto Journal of Engineering
spelling doaj-art-d07c3d0f90314aaa9c5a08cf748601252025-08-20T02:36:08ZengUniversidade do PortoU.Porto Journal of Engineering2183-64932025-03-0111110.24840/2183-6493_0011-001_002742Machine Learning Algorithm for Assessing Photovoltaic Panels Partial Shading Losses based on Inverter DataArmando Luís Sousa Araujo0https://orcid.org/0000-0003-0317-7111Tiago Francisco Pires1https://orcid.org/0009-0001-8802-7552Universidade do Porto, Faculdade de EngenhariaUniversidade do Porto, Faculdade de Engenharia Partial shading is one type of fault where photovoltaic panels cast shadows between each other, reducing their production and hastening their ageing. In this paper, we document and describe two distinct Machine Learning models that aim to identify and assess the impact of partial shading in a real case study. These algorithms recognise similarities and patterns using expected and measured power data. The predicted power is calculated using the measured panel irradiance, current, and voltage using a photovoltaic panel electric circuit model. The first Machine Learning model employs K-means clustering to analyse the differences between expected and measured power, grouping data based on these deviations. The second Machine Learning model leverages the outputs of the K-means model as labels for a Long Short-Term Memory neural network, which classifies periods of partial shading. Experimental data from both models are presented, with the K-means model achieving a closer approximation to the reference values. However, the Long Short-Term Memory model demonstrated flexibility and scalability without requiring prior dataset knowledge from the end user. https://journalengineering.fe.up.pt/index.php/upjeng/article/view/2742Partial ShadingSolar PanelsPhotovoltaic SystemsMachine LearningK-Means ClusteringLSTM Neural Networks
spellingShingle Armando Luís Sousa Araujo
Tiago Francisco Pires
Machine Learning Algorithm for Assessing Photovoltaic Panels Partial Shading Losses based on Inverter Data
U.Porto Journal of Engineering
Partial Shading
Solar Panels
Photovoltaic Systems
Machine Learning
K-Means Clustering
LSTM Neural Networks
title Machine Learning Algorithm for Assessing Photovoltaic Panels Partial Shading Losses based on Inverter Data
title_full Machine Learning Algorithm for Assessing Photovoltaic Panels Partial Shading Losses based on Inverter Data
title_fullStr Machine Learning Algorithm for Assessing Photovoltaic Panels Partial Shading Losses based on Inverter Data
title_full_unstemmed Machine Learning Algorithm for Assessing Photovoltaic Panels Partial Shading Losses based on Inverter Data
title_short Machine Learning Algorithm for Assessing Photovoltaic Panels Partial Shading Losses based on Inverter Data
title_sort machine learning algorithm for assessing photovoltaic panels partial shading losses based on inverter data
topic Partial Shading
Solar Panels
Photovoltaic Systems
Machine Learning
K-Means Clustering
LSTM Neural Networks
url https://journalengineering.fe.up.pt/index.php/upjeng/article/view/2742
work_keys_str_mv AT armandoluissousaaraujo machinelearningalgorithmforassessingphotovoltaicpanelspartialshadinglossesbasedoninverterdata
AT tiagofranciscopires machinelearningalgorithmforassessingphotovoltaicpanelspartialshadinglossesbasedoninverterdata