Machine Learning Based Approaches for Modeling the Output Power of Photovoltaic Array in Real Outdoor Conditions
It is important to investigate the long-term performances of an accurate modeling of photovoltaic (PV) systems, especially in the prediction of output power, with single and double diode models as the configurations mainly applied for this purpose. However, the use of one configuration to model PV p...
| Main Authors: | , |
|---|---|
| Format: | Article |
| Language: | English |
| Published: |
MDPI AG
2020-02-01
|
| Series: | Electronics |
| Subjects: | |
| Online Access: | https://www.mdpi.com/2079-9292/9/2/315 |
| _version_ | 1798034430260936704 |
|---|---|
| author | Malvoni Maria Chaibi Yassine |
| author_facet | Malvoni Maria Chaibi Yassine |
| author_sort | Malvoni Maria |
| collection | DOAJ |
| description | It is important to investigate the long-term performances of an accurate modeling of photovoltaic (PV) systems, especially in the prediction of output power, with single and double diode models as the configurations mainly applied for this purpose. However, the use of one configuration to model PV panel limits the accuracy of its predicted performances. This paper proposes a new hybrid approach based on classification algorithms in the machine learning framework that combines both single and double models in accordance with the climatic condition in order to predict the output PV power with higher accuracy. Classification trees, k-nearest neighbor, discriminant analysis, Naïve Bayes, support vector machines (SVMs), and classification ensembles algorithms are investigated to estimate the PV power under different conditions of the Mediterranean climate. The examined classification algorithms demonstrate that the double diode model seems more relevant for low and medium levels of solar irradiance and temperature. Accuracy between 86% and 87.5% demonstrates the high potential of the classification techniques in the PV power predicting. The normalized mean absolute error up to 1.5% ensures errors less than those obtained from both single-diode and double-diode equivalent-circuit models with a reduction up to 0.15%. The proposed hybrid approach using machine learning (ML) algorithms could be a key solution for photovoltaic and industrial software to predict more accurate performances. |
| first_indexed | 2024-04-11T20:44:17Z |
| format | Article |
| id | doaj.art-308d9c8dc6b84c739362f35decfb713a |
| institution | Directory Open Access Journal |
| issn | 2079-9292 |
| language | English |
| last_indexed | 2024-04-11T20:44:17Z |
| publishDate | 2020-02-01 |
| publisher | MDPI AG |
| record_format | Article |
| series | Electronics |
| spelling | doaj.art-308d9c8dc6b84c739362f35decfb713a2022-12-22T04:04:05ZengMDPI AGElectronics2079-92922020-02-019231510.3390/electronics9020315electronics9020315Machine Learning Based Approaches for Modeling the Output Power of Photovoltaic Array in Real Outdoor ConditionsMalvoni Maria0Chaibi Yassine1School of Electrical and Computer Engineering, National Technical University of Athens 15780, GreeceSmartiLab Laboratory, Moroccan School of Engineering Sciences (EMSI), Rabat 10090, MoroccoIt is important to investigate the long-term performances of an accurate modeling of photovoltaic (PV) systems, especially in the prediction of output power, with single and double diode models as the configurations mainly applied for this purpose. However, the use of one configuration to model PV panel limits the accuracy of its predicted performances. This paper proposes a new hybrid approach based on classification algorithms in the machine learning framework that combines both single and double models in accordance with the climatic condition in order to predict the output PV power with higher accuracy. Classification trees, k-nearest neighbor, discriminant analysis, Naïve Bayes, support vector machines (SVMs), and classification ensembles algorithms are investigated to estimate the PV power under different conditions of the Mediterranean climate. The examined classification algorithms demonstrate that the double diode model seems more relevant for low and medium levels of solar irradiance and temperature. Accuracy between 86% and 87.5% demonstrates the high potential of the classification techniques in the PV power predicting. The normalized mean absolute error up to 1.5% ensures errors less than those obtained from both single-diode and double-diode equivalent-circuit models with a reduction up to 0.15%. The proposed hybrid approach using machine learning (ML) algorithms could be a key solution for photovoltaic and industrial software to predict more accurate performances.https://www.mdpi.com/2079-9292/9/2/315pv modules modelingequivalent-circuit modelsprediction of performancesmachine learningclassification algorithms |
| spellingShingle | Malvoni Maria Chaibi Yassine Machine Learning Based Approaches for Modeling the Output Power of Photovoltaic Array in Real Outdoor Conditions Electronics pv modules modeling equivalent-circuit models prediction of performances machine learning classification algorithms |
| title | Machine Learning Based Approaches for Modeling the Output Power of Photovoltaic Array in Real Outdoor Conditions |
| title_full | Machine Learning Based Approaches for Modeling the Output Power of Photovoltaic Array in Real Outdoor Conditions |
| title_fullStr | Machine Learning Based Approaches for Modeling the Output Power of Photovoltaic Array in Real Outdoor Conditions |
| title_full_unstemmed | Machine Learning Based Approaches for Modeling the Output Power of Photovoltaic Array in Real Outdoor Conditions |
| title_short | Machine Learning Based Approaches for Modeling the Output Power of Photovoltaic Array in Real Outdoor Conditions |
| title_sort | machine learning based approaches for modeling the output power of photovoltaic array in real outdoor conditions |
| topic | pv modules modeling equivalent-circuit models prediction of performances machine learning classification algorithms |
| url | https://www.mdpi.com/2079-9292/9/2/315 |
| work_keys_str_mv | AT malvonimaria machinelearningbasedapproachesformodelingtheoutputpowerofphotovoltaicarrayinrealoutdoorconditions AT chaibiyassine machinelearningbasedapproachesformodelingtheoutputpowerofphotovoltaicarrayinrealoutdoorconditions |