Data driven approach to forecast the next day aggregate production of scattered small rooftop solar photovoltaic systems without meteorological parameters
Photovoltaic (PV) power has became an attractive research subject, despite the variability and uncertainty of the phenomenon, PV power forecasting is considered as a promising solution for successful PV power integration, and also an important decision making information for both, grid operators and...
| Main Authors: | , , , , |
|---|---|
| Format: | Article |
| Language: | English |
| Published: |
Elsevier
2022-11-01
|
| Series: | Energy Reports |
| Subjects: | |
| Online Access: | http://www.sciencedirect.com/science/article/pii/S2352484722003353 |
| _version_ | 1797901996306464768 |
|---|---|
| author | Ayoub Fentis Mohamed Rafik Lhoussain Bahatti Omar Bouattane Mohammed Mestari |
| author_facet | Ayoub Fentis Mohamed Rafik Lhoussain Bahatti Omar Bouattane Mohammed Mestari |
| author_sort | Ayoub Fentis |
| collection | DOAJ |
| description | Photovoltaic (PV) power has became an attractive research subject, despite the variability and uncertainty of the phenomenon, PV power forecasting is considered as a promising solution for successful PV power integration, and also an important decision making information for both, grid operators and energy traders. Forecasting the aggregated PV power in different spatiotemporal scales is very relevant for grid operators, but unfortunately, in the state of the art, few works deal with this subject. In the aim to forecast directly the next day aggregate photovoltaic power of scattered small rooftop installations based only on historical production data, we propose in this paper a hybrid nonlinear autoregressive regression model, composed from a combination of empirical mode decomposition (EMD), stepwise regression (SWR) and least square support vector regression (LsSVR) techniques. To address the lack of meteorological parameters, we propose a different data preprocessing strategy, this strategy will also allow capturing the diurnal component of the PV power time series in an efficient way. An in depth analysis of the proposed approach using publicly available database was conducted. We compared the results of the proposed approach with three other models, two nonlinear autoregressive models based on LsSVR (AR-LsSVR) and FFNN (AR-FFNN), and the third one is a persistent forecaster. Three accuracy metrics were adopted to compare the different models, the nMAE, nMBE and nMRSE. In general good results were obtained in clear and partially cloudy days, but there are few days characterized by sudden change in the time series pattern that the model cant handle. But still competitive results are obtained, the hybrid model gives an nMAE = 4.12% compared to 4.94%, 4.95% and 164.98% for AR-LsSVR, AR-FFNN and the persistent forecaster respectively. The projection of the obtained results on five recently developed models shows the effectiveness of the proposed approach. |
| first_indexed | 2024-04-10T09:10:48Z |
| format | Article |
| id | doaj.art-3c5c2f95015e4f1e86dcb1b552eb1369 |
| institution | Directory Open Access Journal |
| issn | 2352-4847 |
| language | English |
| last_indexed | 2024-04-10T09:10:48Z |
| publishDate | 2022-11-01 |
| publisher | Elsevier |
| record_format | Article |
| series | Energy Reports |
| spelling | doaj.art-3c5c2f95015e4f1e86dcb1b552eb13692023-02-21T05:10:33ZengElsevierEnergy Reports2352-48472022-11-01832213233Data driven approach to forecast the next day aggregate production of scattered small rooftop solar photovoltaic systems without meteorological parametersAyoub Fentis0Mohamed Rafik1Lhoussain Bahatti2Omar Bouattane3Mohammed Mestari4Laboratory of Informatics, Artificial Intelligence and Cyber security, ENSET Mohammedia, Hassan 2 Boulevard 159, Mohammedia, Morocco; Pluridisciplinary Laboratory of Research and Innovation, Moroccan School of Engineering Sciences, Casablanca, Morocco; Corresponding author at: Laboratory of Informatics, Artificial Intelligence and Cyber security, ENSET Mohammedia, Hassan 2 Boulevard 159, Mohammedia, Morocco.Laboratory of Electrical Engineering and Intelligent Systems, ENSET Mohammedia, Hassan 2 Boulevard 159, Mohammedia, MoroccoLaboratory of Electrical Engineering and Intelligent Systems, ENSET Mohammedia, Hassan 2 Boulevard 159, Mohammedia, MoroccoLaboratory of Electrical Engineering and Intelligent Systems, ENSET Mohammedia, Hassan 2 Boulevard 159, Mohammedia, MoroccoLaboratory of Informatics, Artificial Intelligence and Cyber security, ENSET Mohammedia, Hassan 2 Boulevard 159, Mohammedia, MoroccoPhotovoltaic (PV) power has became an attractive research subject, despite the variability and uncertainty of the phenomenon, PV power forecasting is considered as a promising solution for successful PV power integration, and also an important decision making information for both, grid operators and energy traders. Forecasting the aggregated PV power in different spatiotemporal scales is very relevant for grid operators, but unfortunately, in the state of the art, few works deal with this subject. In the aim to forecast directly the next day aggregate photovoltaic power of scattered small rooftop installations based only on historical production data, we propose in this paper a hybrid nonlinear autoregressive regression model, composed from a combination of empirical mode decomposition (EMD), stepwise regression (SWR) and least square support vector regression (LsSVR) techniques. To address the lack of meteorological parameters, we propose a different data preprocessing strategy, this strategy will also allow capturing the diurnal component of the PV power time series in an efficient way. An in depth analysis of the proposed approach using publicly available database was conducted. We compared the results of the proposed approach with three other models, two nonlinear autoregressive models based on LsSVR (AR-LsSVR) and FFNN (AR-FFNN), and the third one is a persistent forecaster. Three accuracy metrics were adopted to compare the different models, the nMAE, nMBE and nMRSE. In general good results were obtained in clear and partially cloudy days, but there are few days characterized by sudden change in the time series pattern that the model cant handle. But still competitive results are obtained, the hybrid model gives an nMAE = 4.12% compared to 4.94%, 4.95% and 164.98% for AR-LsSVR, AR-FFNN and the persistent forecaster respectively. The projection of the obtained results on five recently developed models shows the effectiveness of the proposed approach.http://www.sciencedirect.com/science/article/pii/S2352484722003353PV power forecastingRenewable energyMachine learningTime series forecasting |
| spellingShingle | Ayoub Fentis Mohamed Rafik Lhoussain Bahatti Omar Bouattane Mohammed Mestari Data driven approach to forecast the next day aggregate production of scattered small rooftop solar photovoltaic systems without meteorological parameters Energy Reports PV power forecasting Renewable energy Machine learning Time series forecasting |
| title | Data driven approach to forecast the next day aggregate production of scattered small rooftop solar photovoltaic systems without meteorological parameters |
| title_full | Data driven approach to forecast the next day aggregate production of scattered small rooftop solar photovoltaic systems without meteorological parameters |
| title_fullStr | Data driven approach to forecast the next day aggregate production of scattered small rooftop solar photovoltaic systems without meteorological parameters |
| title_full_unstemmed | Data driven approach to forecast the next day aggregate production of scattered small rooftop solar photovoltaic systems without meteorological parameters |
| title_short | Data driven approach to forecast the next day aggregate production of scattered small rooftop solar photovoltaic systems without meteorological parameters |
| title_sort | data driven approach to forecast the next day aggregate production of scattered small rooftop solar photovoltaic systems without meteorological parameters |
| topic | PV power forecasting Renewable energy Machine learning Time series forecasting |
| url | http://www.sciencedirect.com/science/article/pii/S2352484722003353 |
| work_keys_str_mv | AT ayoubfentis datadrivenapproachtoforecastthenextdayaggregateproductionofscatteredsmallrooftopsolarphotovoltaicsystemswithoutmeteorologicalparameters AT mohamedrafik datadrivenapproachtoforecastthenextdayaggregateproductionofscatteredsmallrooftopsolarphotovoltaicsystemswithoutmeteorologicalparameters AT lhoussainbahatti datadrivenapproachtoforecastthenextdayaggregateproductionofscatteredsmallrooftopsolarphotovoltaicsystemswithoutmeteorologicalparameters AT omarbouattane datadrivenapproachtoforecastthenextdayaggregateproductionofscatteredsmallrooftopsolarphotovoltaicsystemswithoutmeteorologicalparameters AT mohammedmestari datadrivenapproachtoforecastthenextdayaggregateproductionofscatteredsmallrooftopsolarphotovoltaicsystemswithoutmeteorologicalparameters |