IoT-Based PV Array Fault Detection and Classification Using Embedded Supervised Learning Methods
Faults on individual modules within a photovoltaic (PV) array can have a significant detrimental effect on the power efficiency and reliability of the entire PV system. In addition, PV module faults can create risks to personnel safety and fire hazards if they are not detected quickly. As IoT hardwa...
| Main Authors: | , , , |
|---|---|
| Format: | Article |
| Language: | English |
| Published: |
MDPI AG
2022-03-01
|
| Series: | Energies |
| Subjects: | |
| Online Access: | https://www.mdpi.com/1996-1073/15/6/2097 |
| _version_ | 1797471793515069440 |
|---|---|
| author | Mojgan Hojabri Samuel Kellerhals Govinda Upadhyay Benjamin Bowler |
| author_facet | Mojgan Hojabri Samuel Kellerhals Govinda Upadhyay Benjamin Bowler |
| author_sort | Mojgan Hojabri |
| collection | DOAJ |
| description | Faults on individual modules within a photovoltaic (PV) array can have a significant detrimental effect on the power efficiency and reliability of the entire PV system. In addition, PV module faults can create risks to personnel safety and fire hazards if they are not detected quickly. As IoT hardware capabilities increase and machine learning frameworks mature, better fault detection performance may be possible using low-cost sensors running machine learning (ML) models that monitor electrical and thermal parameters at an individual module level. In this paper, to evaluate the performance of ML models that are suitable for embedding in low-cost hardware at the module level, eight different PV module faults and their impacts on PV module output are discussed based on a literature review and simulation. The faults are emulated and applied to a real PV system, allowing the collection and labelling of panel-level measurement data. Then, different ML methods are used to classify these faults in comparison to the normal condition. Results confirm that NN obtain 93% classification accuracy for seven selected classes. |
| first_indexed | 2024-03-09T19:53:06Z |
| format | Article |
| id | doaj.art-687b4694c7f146a69dfff5be653cdaa6 |
| institution | Directory Open Access Journal |
| issn | 1996-1073 |
| language | English |
| last_indexed | 2024-03-09T19:53:06Z |
| publishDate | 2022-03-01 |
| publisher | MDPI AG |
| record_format | Article |
| series | Energies |
| spelling | doaj.art-687b4694c7f146a69dfff5be653cdaa62023-11-24T01:04:28ZengMDPI AGEnergies1996-10732022-03-01156209710.3390/en15062097IoT-Based PV Array Fault Detection and Classification Using Embedded Supervised Learning MethodsMojgan Hojabri0Samuel Kellerhals1Govinda Upadhyay2Benjamin Bowler3Competence Center of Digital Energy and Electric Power, Institute of Electrical Engineering, Lucerne University of Applied Sciences and Arts, 6048 Horw, SwitzerlandCompetence Center of Digital Energy and Electric Power, Institute of Electrical Engineering, Lucerne University of Applied Sciences and Arts, 6048 Horw, SwitzerlandSmartHelio Sarl, 1012 Lausanne, SwitzerlandCompetence Center of Digital Energy and Electric Power, Institute of Electrical Engineering, Lucerne University of Applied Sciences and Arts, 6048 Horw, SwitzerlandFaults on individual modules within a photovoltaic (PV) array can have a significant detrimental effect on the power efficiency and reliability of the entire PV system. In addition, PV module faults can create risks to personnel safety and fire hazards if they are not detected quickly. As IoT hardware capabilities increase and machine learning frameworks mature, better fault detection performance may be possible using low-cost sensors running machine learning (ML) models that monitor electrical and thermal parameters at an individual module level. In this paper, to evaluate the performance of ML models that are suitable for embedding in low-cost hardware at the module level, eight different PV module faults and their impacts on PV module output are discussed based on a literature review and simulation. The faults are emulated and applied to a real PV system, allowing the collection and labelling of panel-level measurement data. Then, different ML methods are used to classify these faults in comparison to the normal condition. Results confirm that NN obtain 93% classification accuracy for seven selected classes.https://www.mdpi.com/1996-1073/15/6/2097photovoltaic systemPV faultsedge computingmachine learningIOTfault detection techniques |
| spellingShingle | Mojgan Hojabri Samuel Kellerhals Govinda Upadhyay Benjamin Bowler IoT-Based PV Array Fault Detection and Classification Using Embedded Supervised Learning Methods Energies photovoltaic system PV faults edge computing machine learning IOT fault detection techniques |
| title | IoT-Based PV Array Fault Detection and Classification Using Embedded Supervised Learning Methods |
| title_full | IoT-Based PV Array Fault Detection and Classification Using Embedded Supervised Learning Methods |
| title_fullStr | IoT-Based PV Array Fault Detection and Classification Using Embedded Supervised Learning Methods |
| title_full_unstemmed | IoT-Based PV Array Fault Detection and Classification Using Embedded Supervised Learning Methods |
| title_short | IoT-Based PV Array Fault Detection and Classification Using Embedded Supervised Learning Methods |
| title_sort | iot based pv array fault detection and classification using embedded supervised learning methods |
| topic | photovoltaic system PV faults edge computing machine learning IOT fault detection techniques |
| url | https://www.mdpi.com/1996-1073/15/6/2097 |
| work_keys_str_mv | AT mojganhojabri iotbasedpvarrayfaultdetectionandclassificationusingembeddedsupervisedlearningmethods AT samuelkellerhals iotbasedpvarrayfaultdetectionandclassificationusingembeddedsupervisedlearningmethods AT govindaupadhyay iotbasedpvarrayfaultdetectionandclassificationusingembeddedsupervisedlearningmethods AT benjaminbowler iotbasedpvarrayfaultdetectionandclassificationusingembeddedsupervisedlearningmethods |