Advanced PV Performance Modelling Based on Different Levels of Irradiance Data Accuracy
In photovoltaic (PV) systems, energy yield is one of the essential pieces of information to the stakeholders (grid operators, maintenance operators, financial units, etc.). The amount of energy produced by a photovoltaic system in a specific time period depends on the weather conditions, including s...
| Main Authors: | , , , , , |
|---|---|
| Format: | Article |
| Language: | English |
| Published: |
MDPI AG
2020-05-01
|
| Series: | Energies |
| Subjects: | |
| Online Access: | https://www.mdpi.com/1996-1073/13/9/2166 |
| _version_ | 1797569122110799872 |
|---|---|
| author | Julián Ascencio-Vásquez Jakob Bevc Kristjan Reba Kristijan Brecl Marko Jankovec Marko Topič |
| author_facet | Julián Ascencio-Vásquez Jakob Bevc Kristjan Reba Kristijan Brecl Marko Jankovec Marko Topič |
| author_sort | Julián Ascencio-Vásquez |
| collection | DOAJ |
| description | In photovoltaic (PV) systems, energy yield is one of the essential pieces of information to the stakeholders (grid operators, maintenance operators, financial units, etc.). The amount of energy produced by a photovoltaic system in a specific time period depends on the weather conditions, including snow and dust, the actual PV modules’ and inverters’ efficiency and balance-of-system losses. The energy yield can be estimated by using empirical models with accurate input data. However, most of the PV systems do not include on-site high-class measurement devices for irradiance and other weather conditions. For this reason, the use of reanalysis-based or satellite-based data is currently of significant interest in the PV community and combining the data with decomposition and transposition irradiance models, the actual Plane-of-Array operating conditions can be determined. In this paper, we are proposing an efficient and accurate approach for PV output energy modelling by combining a new data filtering procedure and fast machine learning algorithm Light Gradient Boosting Machine (LightGBM). The applicability of the procedure is presented on three levels of irradiance data accuracy (low, medium, and high) depending on the source or modelling used. A new filtering algorithm is proposed to exclude erroneous data due to system failures or unreal weather conditions (i.e., shading, partial snow coverage, reflections, soiling deposition, etc.). The cleaned data is then used to train three empirical models and three machine learning approaches, where we emphasize the advantages of the LightGBM. The experiments are carried out on a 17 kW roof-top PV system installed in Ljubljana, Slovenia, in a temperate climate zone. |
| first_indexed | 2024-03-10T20:06:25Z |
| format | Article |
| id | doaj.art-518bbc3ffc15488b928ca8bfab5a55eb |
| institution | Directory Open Access Journal |
| issn | 1996-1073 |
| language | English |
| last_indexed | 2024-03-10T20:06:25Z |
| publishDate | 2020-05-01 |
| publisher | MDPI AG |
| record_format | Article |
| series | Energies |
| spelling | doaj.art-518bbc3ffc15488b928ca8bfab5a55eb2023-11-19T23:15:02ZengMDPI AGEnergies1996-10732020-05-01139216610.3390/en13092166Advanced PV Performance Modelling Based on Different Levels of Irradiance Data AccuracyJulián Ascencio-Vásquez0Jakob Bevc1Kristjan Reba2Kristijan Brecl3Marko Jankovec4Marko Topič5Faculty of Electrical Engineering, University of Ljubljana, Tržaška cesta 25, 1000 Ljubljana, SloveniaFaculty of Computer and Information Science, University of Ljubljana, Večna pot 113, 1000 Ljubljana, SloveniaFaculty of Computer and Information Science, University of Ljubljana, Večna pot 113, 1000 Ljubljana, SloveniaFaculty of Electrical Engineering, University of Ljubljana, Tržaška cesta 25, 1000 Ljubljana, SloveniaFaculty of Electrical Engineering, University of Ljubljana, Tržaška cesta 25, 1000 Ljubljana, SloveniaFaculty of Electrical Engineering, University of Ljubljana, Tržaška cesta 25, 1000 Ljubljana, SloveniaIn photovoltaic (PV) systems, energy yield is one of the essential pieces of information to the stakeholders (grid operators, maintenance operators, financial units, etc.). The amount of energy produced by a photovoltaic system in a specific time period depends on the weather conditions, including snow and dust, the actual PV modules’ and inverters’ efficiency and balance-of-system losses. The energy yield can be estimated by using empirical models with accurate input data. However, most of the PV systems do not include on-site high-class measurement devices for irradiance and other weather conditions. For this reason, the use of reanalysis-based or satellite-based data is currently of significant interest in the PV community and combining the data with decomposition and transposition irradiance models, the actual Plane-of-Array operating conditions can be determined. In this paper, we are proposing an efficient and accurate approach for PV output energy modelling by combining a new data filtering procedure and fast machine learning algorithm Light Gradient Boosting Machine (LightGBM). The applicability of the procedure is presented on three levels of irradiance data accuracy (low, medium, and high) depending on the source or modelling used. A new filtering algorithm is proposed to exclude erroneous data due to system failures or unreal weather conditions (i.e., shading, partial snow coverage, reflections, soiling deposition, etc.). The cleaned data is then used to train three empirical models and three machine learning approaches, where we emphasize the advantages of the LightGBM. The experiments are carried out on a 17 kW roof-top PV system installed in Ljubljana, Slovenia, in a temperate climate zone.https://www.mdpi.com/1996-1073/13/9/2166PV systemPV performance modellingdata filteringmachine learninglightGBM |
| spellingShingle | Julián Ascencio-Vásquez Jakob Bevc Kristjan Reba Kristijan Brecl Marko Jankovec Marko Topič Advanced PV Performance Modelling Based on Different Levels of Irradiance Data Accuracy Energies PV system PV performance modelling data filtering machine learning lightGBM |
| title | Advanced PV Performance Modelling Based on Different Levels of Irradiance Data Accuracy |
| title_full | Advanced PV Performance Modelling Based on Different Levels of Irradiance Data Accuracy |
| title_fullStr | Advanced PV Performance Modelling Based on Different Levels of Irradiance Data Accuracy |
| title_full_unstemmed | Advanced PV Performance Modelling Based on Different Levels of Irradiance Data Accuracy |
| title_short | Advanced PV Performance Modelling Based on Different Levels of Irradiance Data Accuracy |
| title_sort | advanced pv performance modelling based on different levels of irradiance data accuracy |
| topic | PV system PV performance modelling data filtering machine learning lightGBM |
| url | https://www.mdpi.com/1996-1073/13/9/2166 |
| work_keys_str_mv | AT julianascenciovasquez advancedpvperformancemodellingbasedondifferentlevelsofirradiancedataaccuracy AT jakobbevc advancedpvperformancemodellingbasedondifferentlevelsofirradiancedataaccuracy AT kristjanreba advancedpvperformancemodellingbasedondifferentlevelsofirradiancedataaccuracy AT kristijanbrecl advancedpvperformancemodellingbasedondifferentlevelsofirradiancedataaccuracy AT markojankovec advancedpvperformancemodellingbasedondifferentlevelsofirradiancedataaccuracy AT markotopic advancedpvperformancemodellingbasedondifferentlevelsofirradiancedataaccuracy |