Hour-ahead wind power forecast based on random forests
Due to its chaotic nature, the wind behavior is difficult to forecast. Predicting wind power is a real challenge for dispatchers who need to estimate renewable generation in advance to establish their strategies. To achieve an accurate wind power prediction, it is important to determine first which...
Ausführliche Beschreibung
Gespeichert in:
| Autor*in: |
Lahouar, A. [verfasserIn] |
|---|
| Format: |
E-Artikel |
|---|---|
| Sprache: |
Englisch |
| Erschienen: |
2017transfer abstract |
|---|
| Schlagwörter: |
|---|
| Umfang: |
13 |
|---|
| Übergeordnetes Werk: |
Enthalten in: Technologies and practice of CO - HU, Yongle ELSEVIER, 2019, an international journal : the official journal of WREN, The World Renewable Energy Network, Amsterdam [u.a.] |
|---|---|
| Übergeordnetes Werk: |
volume:109 ; year:2017 ; pages:529-541 ; extent:13 |
| Links: |
|---|
| DOI / URN: |
10.1016/j.renene.2017.03.064 |
|---|
| Katalog-ID: |
ELV015348369 |
|---|
| LEADER | 01000caa a22002652 4500 | ||
|---|---|---|---|
| 001 | ELV015348369 | ||
| 003 | DE-627 | ||
| 005 | 20230625115110.0 | ||
| 007 | cr uuu---uuuuu | ||
| 008 | 180602s2017 xx |||||o 00| ||eng c | ||
| 024 | 7 | |a 10.1016/j.renene.2017.03.064 |2 doi | |
| 028 | 5 | 2 | |a GBVA2017016000018.pica |
| 035 | |a (DE-627)ELV015348369 | ||
| 035 | |a (ELSEVIER)S0960-1481(17)30255-0 | ||
| 040 | |a DE-627 |b ger |c DE-627 |e rakwb | ||
| 041 | |a eng | ||
| 082 | 0 | |a 530 |a 620 | |
| 082 | 0 | 4 | |a 530 |q DE-600 |
| 082 | 0 | 4 | |a 620 |q DE-600 |
| 100 | 1 | |a Lahouar, A. |e verfasserin |4 aut | |
| 245 | 1 | 0 | |a Hour-ahead wind power forecast based on random forests |
| 264 | 1 | |c 2017transfer abstract | |
| 300 | |a 13 | ||
| 336 | |a nicht spezifiziert |b zzz |2 rdacontent | ||
| 337 | |a nicht spezifiziert |b z |2 rdamedia | ||
| 338 | |a nicht spezifiziert |b zu |2 rdacarrier | ||
| 520 | |a Due to its chaotic nature, the wind behavior is difficult to forecast. Predicting wind power is a real challenge for dispatchers who need to estimate renewable generation in advance to establish their strategies. To achieve an accurate wind power prediction, it is important to determine first which meteorological data need to be included in the predictor. For that purpose, this paper focuses on choosing the appropriate weather factors, namely spatially averaged wind speed and wind direction. These factors are selected according to correlation and importance measures. Then, the random forest method is proposed to build an hour-ahead wind power predictor. The random forest does not need to be tuned or optimized, contrary to most other learning machines. Both point and probabilistic forecasts are performed using the same inputs. The emphasis is put on the effect of wind speed and direction on the model performance, and the immunity of random forest to irrelevant inputs. The wind data used to test the proposed model are taken from Sidi Daoud wind farm in Tunisia. Results show an interesting improvement of forecast accuracy using the proposed model, as well as an important reduction of the different error criteria compared to classical neural network prediction. | ||
| 520 | |a Due to its chaotic nature, the wind behavior is difficult to forecast. Predicting wind power is a real challenge for dispatchers who need to estimate renewable generation in advance to establish their strategies. To achieve an accurate wind power prediction, it is important to determine first which meteorological data need to be included in the predictor. For that purpose, this paper focuses on choosing the appropriate weather factors, namely spatially averaged wind speed and wind direction. These factors are selected according to correlation and importance measures. Then, the random forest method is proposed to build an hour-ahead wind power predictor. The random forest does not need to be tuned or optimized, contrary to most other learning machines. Both point and probabilistic forecasts are performed using the same inputs. The emphasis is put on the effect of wind speed and direction on the model performance, and the immunity of random forest to irrelevant inputs. The wind data used to test the proposed model are taken from Sidi Daoud wind farm in Tunisia. Results show an interesting improvement of forecast accuracy using the proposed model, as well as an important reduction of the different error criteria compared to classical neural network prediction. | ||
| 650 | 7 | |a Wind direction |2 Elsevier | |
| 650 | 7 | |a Wind power forecast |2 Elsevier | |
| 650 | 7 | |a Spatially averaged wind speed |2 Elsevier | |
| 650 | 7 | |a Random forest |2 Elsevier | |
| 650 | 7 | |a Hour-ahead |2 Elsevier | |
| 650 | 7 | |a Importance of inputs |2 Elsevier | |
| 700 | 1 | |a Ben Hadj Slama, J. |4 oth | |
| 773 | 0 | 8 | |i Enthalten in |n Elsevier Science |a HU, Yongle ELSEVIER |t Technologies and practice of CO |d 2019 |d an international journal : the official journal of WREN, The World Renewable Energy Network |g Amsterdam [u.a.] |w (DE-627)ELV002723662 |
| 773 | 1 | 8 | |g volume:109 |g year:2017 |g pages:529-541 |g extent:13 |
| 856 | 4 | 0 | |u https://doi.org/10.1016/j.renene.2017.03.064 |3 Volltext |
| 912 | |a GBV_USEFLAG_U | ||
| 912 | |a GBV_ELV | ||
| 912 | |a SYSFLAG_U | ||
| 951 | |a AR | ||
| 952 | |d 109 |j 2017 |h 529-541 |g 13 | ||
| 953 | |2 045F |a 530 | ||
| author_variant |
a l al |
|---|---|
| matchkey_str |
lahouarabenhadjslamaj:2017----:orhawnpwroeataeo |
| hierarchy_sort_str |
2017transfer abstract |
| publishDate |
2017 |
| allfields |
10.1016/j.renene.2017.03.064 doi GBVA2017016000018.pica (DE-627)ELV015348369 (ELSEVIER)S0960-1481(17)30255-0 DE-627 ger DE-627 rakwb eng 530 620 530 DE-600 620 DE-600 Lahouar, A. verfasserin aut Hour-ahead wind power forecast based on random forests 2017transfer abstract 13 nicht spezifiziert zzz rdacontent nicht spezifiziert z rdamedia nicht spezifiziert zu rdacarrier Due to its chaotic nature, the wind behavior is difficult to forecast. Predicting wind power is a real challenge for dispatchers who need to estimate renewable generation in advance to establish their strategies. To achieve an accurate wind power prediction, it is important to determine first which meteorological data need to be included in the predictor. For that purpose, this paper focuses on choosing the appropriate weather factors, namely spatially averaged wind speed and wind direction. These factors are selected according to correlation and importance measures. Then, the random forest method is proposed to build an hour-ahead wind power predictor. The random forest does not need to be tuned or optimized, contrary to most other learning machines. Both point and probabilistic forecasts are performed using the same inputs. The emphasis is put on the effect of wind speed and direction on the model performance, and the immunity of random forest to irrelevant inputs. The wind data used to test the proposed model are taken from Sidi Daoud wind farm in Tunisia. Results show an interesting improvement of forecast accuracy using the proposed model, as well as an important reduction of the different error criteria compared to classical neural network prediction. Due to its chaotic nature, the wind behavior is difficult to forecast. Predicting wind power is a real challenge for dispatchers who need to estimate renewable generation in advance to establish their strategies. To achieve an accurate wind power prediction, it is important to determine first which meteorological data need to be included in the predictor. For that purpose, this paper focuses on choosing the appropriate weather factors, namely spatially averaged wind speed and wind direction. These factors are selected according to correlation and importance measures. Then, the random forest method is proposed to build an hour-ahead wind power predictor. The random forest does not need to be tuned or optimized, contrary to most other learning machines. Both point and probabilistic forecasts are performed using the same inputs. The emphasis is put on the effect of wind speed and direction on the model performance, and the immunity of random forest to irrelevant inputs. The wind data used to test the proposed model are taken from Sidi Daoud wind farm in Tunisia. Results show an interesting improvement of forecast accuracy using the proposed model, as well as an important reduction of the different error criteria compared to classical neural network prediction. Wind direction Elsevier Wind power forecast Elsevier Spatially averaged wind speed Elsevier Random forest Elsevier Hour-ahead Elsevier Importance of inputs Elsevier Ben Hadj Slama, J. oth Enthalten in Elsevier Science HU, Yongle ELSEVIER Technologies and practice of CO 2019 an international journal : the official journal of WREN, The World Renewable Energy Network Amsterdam [u.a.] (DE-627)ELV002723662 volume:109 year:2017 pages:529-541 extent:13 https://doi.org/10.1016/j.renene.2017.03.064 Volltext GBV_USEFLAG_U GBV_ELV SYSFLAG_U AR 109 2017 529-541 13 045F 530 |
| spelling |
10.1016/j.renene.2017.03.064 doi GBVA2017016000018.pica (DE-627)ELV015348369 (ELSEVIER)S0960-1481(17)30255-0 DE-627 ger DE-627 rakwb eng 530 620 530 DE-600 620 DE-600 Lahouar, A. verfasserin aut Hour-ahead wind power forecast based on random forests 2017transfer abstract 13 nicht spezifiziert zzz rdacontent nicht spezifiziert z rdamedia nicht spezifiziert zu rdacarrier Due to its chaotic nature, the wind behavior is difficult to forecast. Predicting wind power is a real challenge for dispatchers who need to estimate renewable generation in advance to establish their strategies. To achieve an accurate wind power prediction, it is important to determine first which meteorological data need to be included in the predictor. For that purpose, this paper focuses on choosing the appropriate weather factors, namely spatially averaged wind speed and wind direction. These factors are selected according to correlation and importance measures. Then, the random forest method is proposed to build an hour-ahead wind power predictor. The random forest does not need to be tuned or optimized, contrary to most other learning machines. Both point and probabilistic forecasts are performed using the same inputs. The emphasis is put on the effect of wind speed and direction on the model performance, and the immunity of random forest to irrelevant inputs. The wind data used to test the proposed model are taken from Sidi Daoud wind farm in Tunisia. Results show an interesting improvement of forecast accuracy using the proposed model, as well as an important reduction of the different error criteria compared to classical neural network prediction. Due to its chaotic nature, the wind behavior is difficult to forecast. Predicting wind power is a real challenge for dispatchers who need to estimate renewable generation in advance to establish their strategies. To achieve an accurate wind power prediction, it is important to determine first which meteorological data need to be included in the predictor. For that purpose, this paper focuses on choosing the appropriate weather factors, namely spatially averaged wind speed and wind direction. These factors are selected according to correlation and importance measures. Then, the random forest method is proposed to build an hour-ahead wind power predictor. The random forest does not need to be tuned or optimized, contrary to most other learning machines. Both point and probabilistic forecasts are performed using the same inputs. The emphasis is put on the effect of wind speed and direction on the model performance, and the immunity of random forest to irrelevant inputs. The wind data used to test the proposed model are taken from Sidi Daoud wind farm in Tunisia. Results show an interesting improvement of forecast accuracy using the proposed model, as well as an important reduction of the different error criteria compared to classical neural network prediction. Wind direction Elsevier Wind power forecast Elsevier Spatially averaged wind speed Elsevier Random forest Elsevier Hour-ahead Elsevier Importance of inputs Elsevier Ben Hadj Slama, J. oth Enthalten in Elsevier Science HU, Yongle ELSEVIER Technologies and practice of CO 2019 an international journal : the official journal of WREN, The World Renewable Energy Network Amsterdam [u.a.] (DE-627)ELV002723662 volume:109 year:2017 pages:529-541 extent:13 https://doi.org/10.1016/j.renene.2017.03.064 Volltext GBV_USEFLAG_U GBV_ELV SYSFLAG_U AR 109 2017 529-541 13 045F 530 |
| allfields_unstemmed |
10.1016/j.renene.2017.03.064 doi GBVA2017016000018.pica (DE-627)ELV015348369 (ELSEVIER)S0960-1481(17)30255-0 DE-627 ger DE-627 rakwb eng 530 620 530 DE-600 620 DE-600 Lahouar, A. verfasserin aut Hour-ahead wind power forecast based on random forests 2017transfer abstract 13 nicht spezifiziert zzz rdacontent nicht spezifiziert z rdamedia nicht spezifiziert zu rdacarrier Due to its chaotic nature, the wind behavior is difficult to forecast. Predicting wind power is a real challenge for dispatchers who need to estimate renewable generation in advance to establish their strategies. To achieve an accurate wind power prediction, it is important to determine first which meteorological data need to be included in the predictor. For that purpose, this paper focuses on choosing the appropriate weather factors, namely spatially averaged wind speed and wind direction. These factors are selected according to correlation and importance measures. Then, the random forest method is proposed to build an hour-ahead wind power predictor. The random forest does not need to be tuned or optimized, contrary to most other learning machines. Both point and probabilistic forecasts are performed using the same inputs. The emphasis is put on the effect of wind speed and direction on the model performance, and the immunity of random forest to irrelevant inputs. The wind data used to test the proposed model are taken from Sidi Daoud wind farm in Tunisia. Results show an interesting improvement of forecast accuracy using the proposed model, as well as an important reduction of the different error criteria compared to classical neural network prediction. Due to its chaotic nature, the wind behavior is difficult to forecast. Predicting wind power is a real challenge for dispatchers who need to estimate renewable generation in advance to establish their strategies. To achieve an accurate wind power prediction, it is important to determine first which meteorological data need to be included in the predictor. For that purpose, this paper focuses on choosing the appropriate weather factors, namely spatially averaged wind speed and wind direction. These factors are selected according to correlation and importance measures. Then, the random forest method is proposed to build an hour-ahead wind power predictor. The random forest does not need to be tuned or optimized, contrary to most other learning machines. Both point and probabilistic forecasts are performed using the same inputs. The emphasis is put on the effect of wind speed and direction on the model performance, and the immunity of random forest to irrelevant inputs. The wind data used to test the proposed model are taken from Sidi Daoud wind farm in Tunisia. Results show an interesting improvement of forecast accuracy using the proposed model, as well as an important reduction of the different error criteria compared to classical neural network prediction. Wind direction Elsevier Wind power forecast Elsevier Spatially averaged wind speed Elsevier Random forest Elsevier Hour-ahead Elsevier Importance of inputs Elsevier Ben Hadj Slama, J. oth Enthalten in Elsevier Science HU, Yongle ELSEVIER Technologies and practice of CO 2019 an international journal : the official journal of WREN, The World Renewable Energy Network Amsterdam [u.a.] (DE-627)ELV002723662 volume:109 year:2017 pages:529-541 extent:13 https://doi.org/10.1016/j.renene.2017.03.064 Volltext GBV_USEFLAG_U GBV_ELV SYSFLAG_U AR 109 2017 529-541 13 045F 530 |
| allfieldsGer |
10.1016/j.renene.2017.03.064 doi GBVA2017016000018.pica (DE-627)ELV015348369 (ELSEVIER)S0960-1481(17)30255-0 DE-627 ger DE-627 rakwb eng 530 620 530 DE-600 620 DE-600 Lahouar, A. verfasserin aut Hour-ahead wind power forecast based on random forests 2017transfer abstract 13 nicht spezifiziert zzz rdacontent nicht spezifiziert z rdamedia nicht spezifiziert zu rdacarrier Due to its chaotic nature, the wind behavior is difficult to forecast. Predicting wind power is a real challenge for dispatchers who need to estimate renewable generation in advance to establish their strategies. To achieve an accurate wind power prediction, it is important to determine first which meteorological data need to be included in the predictor. For that purpose, this paper focuses on choosing the appropriate weather factors, namely spatially averaged wind speed and wind direction. These factors are selected according to correlation and importance measures. Then, the random forest method is proposed to build an hour-ahead wind power predictor. The random forest does not need to be tuned or optimized, contrary to most other learning machines. Both point and probabilistic forecasts are performed using the same inputs. The emphasis is put on the effect of wind speed and direction on the model performance, and the immunity of random forest to irrelevant inputs. The wind data used to test the proposed model are taken from Sidi Daoud wind farm in Tunisia. Results show an interesting improvement of forecast accuracy using the proposed model, as well as an important reduction of the different error criteria compared to classical neural network prediction. Due to its chaotic nature, the wind behavior is difficult to forecast. Predicting wind power is a real challenge for dispatchers who need to estimate renewable generation in advance to establish their strategies. To achieve an accurate wind power prediction, it is important to determine first which meteorological data need to be included in the predictor. For that purpose, this paper focuses on choosing the appropriate weather factors, namely spatially averaged wind speed and wind direction. These factors are selected according to correlation and importance measures. Then, the random forest method is proposed to build an hour-ahead wind power predictor. The random forest does not need to be tuned or optimized, contrary to most other learning machines. Both point and probabilistic forecasts are performed using the same inputs. The emphasis is put on the effect of wind speed and direction on the model performance, and the immunity of random forest to irrelevant inputs. The wind data used to test the proposed model are taken from Sidi Daoud wind farm in Tunisia. Results show an interesting improvement of forecast accuracy using the proposed model, as well as an important reduction of the different error criteria compared to classical neural network prediction. Wind direction Elsevier Wind power forecast Elsevier Spatially averaged wind speed Elsevier Random forest Elsevier Hour-ahead Elsevier Importance of inputs Elsevier Ben Hadj Slama, J. oth Enthalten in Elsevier Science HU, Yongle ELSEVIER Technologies and practice of CO 2019 an international journal : the official journal of WREN, The World Renewable Energy Network Amsterdam [u.a.] (DE-627)ELV002723662 volume:109 year:2017 pages:529-541 extent:13 https://doi.org/10.1016/j.renene.2017.03.064 Volltext GBV_USEFLAG_U GBV_ELV SYSFLAG_U AR 109 2017 529-541 13 045F 530 |
| allfieldsSound |
10.1016/j.renene.2017.03.064 doi GBVA2017016000018.pica (DE-627)ELV015348369 (ELSEVIER)S0960-1481(17)30255-0 DE-627 ger DE-627 rakwb eng 530 620 530 DE-600 620 DE-600 Lahouar, A. verfasserin aut Hour-ahead wind power forecast based on random forests 2017transfer abstract 13 nicht spezifiziert zzz rdacontent nicht spezifiziert z rdamedia nicht spezifiziert zu rdacarrier Due to its chaotic nature, the wind behavior is difficult to forecast. Predicting wind power is a real challenge for dispatchers who need to estimate renewable generation in advance to establish their strategies. To achieve an accurate wind power prediction, it is important to determine first which meteorological data need to be included in the predictor. For that purpose, this paper focuses on choosing the appropriate weather factors, namely spatially averaged wind speed and wind direction. These factors are selected according to correlation and importance measures. Then, the random forest method is proposed to build an hour-ahead wind power predictor. The random forest does not need to be tuned or optimized, contrary to most other learning machines. Both point and probabilistic forecasts are performed using the same inputs. The emphasis is put on the effect of wind speed and direction on the model performance, and the immunity of random forest to irrelevant inputs. The wind data used to test the proposed model are taken from Sidi Daoud wind farm in Tunisia. Results show an interesting improvement of forecast accuracy using the proposed model, as well as an important reduction of the different error criteria compared to classical neural network prediction. Due to its chaotic nature, the wind behavior is difficult to forecast. Predicting wind power is a real challenge for dispatchers who need to estimate renewable generation in advance to establish their strategies. To achieve an accurate wind power prediction, it is important to determine first which meteorological data need to be included in the predictor. For that purpose, this paper focuses on choosing the appropriate weather factors, namely spatially averaged wind speed and wind direction. These factors are selected according to correlation and importance measures. Then, the random forest method is proposed to build an hour-ahead wind power predictor. The random forest does not need to be tuned or optimized, contrary to most other learning machines. Both point and probabilistic forecasts are performed using the same inputs. The emphasis is put on the effect of wind speed and direction on the model performance, and the immunity of random forest to irrelevant inputs. The wind data used to test the proposed model are taken from Sidi Daoud wind farm in Tunisia. Results show an interesting improvement of forecast accuracy using the proposed model, as well as an important reduction of the different error criteria compared to classical neural network prediction. Wind direction Elsevier Wind power forecast Elsevier Spatially averaged wind speed Elsevier Random forest Elsevier Hour-ahead Elsevier Importance of inputs Elsevier Ben Hadj Slama, J. oth Enthalten in Elsevier Science HU, Yongle ELSEVIER Technologies and practice of CO 2019 an international journal : the official journal of WREN, The World Renewable Energy Network Amsterdam [u.a.] (DE-627)ELV002723662 volume:109 year:2017 pages:529-541 extent:13 https://doi.org/10.1016/j.renene.2017.03.064 Volltext GBV_USEFLAG_U GBV_ELV SYSFLAG_U AR 109 2017 529-541 13 045F 530 |
| language |
English |
| source |
Enthalten in Technologies and practice of CO Amsterdam [u.a.] volume:109 year:2017 pages:529-541 extent:13 |
| sourceStr |
Enthalten in Technologies and practice of CO Amsterdam [u.a.] volume:109 year:2017 pages:529-541 extent:13 |
| format_phy_str_mv |
Article |
| institution |
findex.gbv.de |
| topic_facet |
Wind direction Wind power forecast Spatially averaged wind speed Random forest Hour-ahead Importance of inputs |
| dewey-raw |
530 |
| isfreeaccess_bool |
false |
| container_title |
Technologies and practice of CO |
| authorswithroles_txt_mv |
Lahouar, A. @@aut@@ Ben Hadj Slama, J. @@oth@@ |
| publishDateDaySort_date |
2017-01-01T00:00:00Z |
| hierarchy_top_id |
ELV002723662 |
| dewey-sort |
3530 |
| id |
ELV015348369 |
| language_de |
englisch |
| fullrecord |
<?xml version="1.0" encoding="UTF-8"?><collection xmlns="http://www.loc.gov/MARC21/slim"><record><leader>01000caa a22002652 4500</leader><controlfield tag="001">ELV015348369</controlfield><controlfield tag="003">DE-627</controlfield><controlfield tag="005">20230625115110.0</controlfield><controlfield tag="007">cr uuu---uuuuu</controlfield><controlfield tag="008">180602s2017 xx |||||o 00| ||eng c</controlfield><datafield tag="024" ind1="7" ind2=" "><subfield code="a">10.1016/j.renene.2017.03.064</subfield><subfield code="2">doi</subfield></datafield><datafield tag="028" ind1="5" ind2="2"><subfield code="a">GBVA2017016000018.pica</subfield></datafield><datafield tag="035" ind1=" " ind2=" "><subfield code="a">(DE-627)ELV015348369</subfield></datafield><datafield tag="035" ind1=" " ind2=" "><subfield code="a">(ELSEVIER)S0960-1481(17)30255-0</subfield></datafield><datafield tag="040" ind1=" " ind2=" "><subfield code="a">DE-627</subfield><subfield code="b">ger</subfield><subfield code="c">DE-627</subfield><subfield code="e">rakwb</subfield></datafield><datafield tag="041" ind1=" " ind2=" "><subfield code="a">eng</subfield></datafield><datafield tag="082" ind1="0" ind2=" "><subfield code="a">530</subfield><subfield code="a">620</subfield></datafield><datafield tag="082" ind1="0" ind2="4"><subfield code="a">530</subfield><subfield code="q">DE-600</subfield></datafield><datafield tag="082" ind1="0" ind2="4"><subfield code="a">620</subfield><subfield code="q">DE-600</subfield></datafield><datafield tag="100" ind1="1" ind2=" "><subfield code="a">Lahouar, A.</subfield><subfield code="e">verfasserin</subfield><subfield code="4">aut</subfield></datafield><datafield tag="245" ind1="1" ind2="0"><subfield code="a">Hour-ahead wind power forecast based on random forests</subfield></datafield><datafield tag="264" ind1=" " ind2="1"><subfield code="c">2017transfer abstract</subfield></datafield><datafield tag="300" ind1=" " ind2=" "><subfield code="a">13</subfield></datafield><datafield tag="336" ind1=" " ind2=" "><subfield code="a">nicht spezifiziert</subfield><subfield code="b">zzz</subfield><subfield code="2">rdacontent</subfield></datafield><datafield tag="337" ind1=" " ind2=" "><subfield code="a">nicht spezifiziert</subfield><subfield code="b">z</subfield><subfield code="2">rdamedia</subfield></datafield><datafield tag="338" ind1=" " ind2=" "><subfield code="a">nicht spezifiziert</subfield><subfield code="b">zu</subfield><subfield code="2">rdacarrier</subfield></datafield><datafield tag="520" ind1=" " ind2=" "><subfield code="a">Due to its chaotic nature, the wind behavior is difficult to forecast. Predicting wind power is a real challenge for dispatchers who need to estimate renewable generation in advance to establish their strategies. To achieve an accurate wind power prediction, it is important to determine first which meteorological data need to be included in the predictor. For that purpose, this paper focuses on choosing the appropriate weather factors, namely spatially averaged wind speed and wind direction. These factors are selected according to correlation and importance measures. Then, the random forest method is proposed to build an hour-ahead wind power predictor. The random forest does not need to be tuned or optimized, contrary to most other learning machines. Both point and probabilistic forecasts are performed using the same inputs. The emphasis is put on the effect of wind speed and direction on the model performance, and the immunity of random forest to irrelevant inputs. The wind data used to test the proposed model are taken from Sidi Daoud wind farm in Tunisia. Results show an interesting improvement of forecast accuracy using the proposed model, as well as an important reduction of the different error criteria compared to classical neural network prediction.</subfield></datafield><datafield tag="520" ind1=" " ind2=" "><subfield code="a">Due to its chaotic nature, the wind behavior is difficult to forecast. Predicting wind power is a real challenge for dispatchers who need to estimate renewable generation in advance to establish their strategies. To achieve an accurate wind power prediction, it is important to determine first which meteorological data need to be included in the predictor. For that purpose, this paper focuses on choosing the appropriate weather factors, namely spatially averaged wind speed and wind direction. These factors are selected according to correlation and importance measures. Then, the random forest method is proposed to build an hour-ahead wind power predictor. The random forest does not need to be tuned or optimized, contrary to most other learning machines. Both point and probabilistic forecasts are performed using the same inputs. The emphasis is put on the effect of wind speed and direction on the model performance, and the immunity of random forest to irrelevant inputs. The wind data used to test the proposed model are taken from Sidi Daoud wind farm in Tunisia. Results show an interesting improvement of forecast accuracy using the proposed model, as well as an important reduction of the different error criteria compared to classical neural network prediction.</subfield></datafield><datafield tag="650" ind1=" " ind2="7"><subfield code="a">Wind direction</subfield><subfield code="2">Elsevier</subfield></datafield><datafield tag="650" ind1=" " ind2="7"><subfield code="a">Wind power forecast</subfield><subfield code="2">Elsevier</subfield></datafield><datafield tag="650" ind1=" " ind2="7"><subfield code="a">Spatially averaged wind speed</subfield><subfield code="2">Elsevier</subfield></datafield><datafield tag="650" ind1=" " ind2="7"><subfield code="a">Random forest</subfield><subfield code="2">Elsevier</subfield></datafield><datafield tag="650" ind1=" " ind2="7"><subfield code="a">Hour-ahead</subfield><subfield code="2">Elsevier</subfield></datafield><datafield tag="650" ind1=" " ind2="7"><subfield code="a">Importance of inputs</subfield><subfield code="2">Elsevier</subfield></datafield><datafield tag="700" ind1="1" ind2=" "><subfield code="a">Ben Hadj Slama, J.</subfield><subfield code="4">oth</subfield></datafield><datafield tag="773" ind1="0" ind2="8"><subfield code="i">Enthalten in</subfield><subfield code="n">Elsevier Science</subfield><subfield code="a">HU, Yongle ELSEVIER</subfield><subfield code="t">Technologies and practice of CO</subfield><subfield code="d">2019</subfield><subfield code="d">an international journal : the official journal of WREN, The World Renewable Energy Network</subfield><subfield code="g">Amsterdam [u.a.]</subfield><subfield code="w">(DE-627)ELV002723662</subfield></datafield><datafield tag="773" ind1="1" ind2="8"><subfield code="g">volume:109</subfield><subfield code="g">year:2017</subfield><subfield code="g">pages:529-541</subfield><subfield code="g">extent:13</subfield></datafield><datafield tag="856" ind1="4" ind2="0"><subfield code="u">https://doi.org/10.1016/j.renene.2017.03.064</subfield><subfield code="3">Volltext</subfield></datafield><datafield tag="912" ind1=" " ind2=" "><subfield code="a">GBV_USEFLAG_U</subfield></datafield><datafield tag="912" ind1=" " ind2=" "><subfield code="a">GBV_ELV</subfield></datafield><datafield tag="912" ind1=" " ind2=" "><subfield code="a">SYSFLAG_U</subfield></datafield><datafield tag="951" ind1=" " ind2=" "><subfield code="a">AR</subfield></datafield><datafield tag="952" ind1=" " ind2=" "><subfield code="d">109</subfield><subfield code="j">2017</subfield><subfield code="h">529-541</subfield><subfield code="g">13</subfield></datafield><datafield tag="953" ind1=" " ind2=" "><subfield code="2">045F</subfield><subfield code="a">530</subfield></datafield></record></collection>
|
| author |
Lahouar, A. |
| spellingShingle |
Lahouar, A. ddc 530 ddc 620 Elsevier Wind direction Elsevier Wind power forecast Elsevier Spatially averaged wind speed Elsevier Random forest Elsevier Hour-ahead Elsevier Importance of inputs Hour-ahead wind power forecast based on random forests |
| authorStr |
Lahouar, A. |
| ppnlink_with_tag_str_mv |
@@773@@(DE-627)ELV002723662 |
| format |
electronic Article |
| dewey-ones |
530 - Physics 620 - Engineering & allied operations |
| delete_txt_mv |
keep |
| author_role |
aut |
| collection |
elsevier |
| remote_str |
true |
| illustrated |
Not Illustrated |
| topic_title |
530 620 530 DE-600 620 DE-600 Hour-ahead wind power forecast based on random forests Wind direction Elsevier Wind power forecast Elsevier Spatially averaged wind speed Elsevier Random forest Elsevier Hour-ahead Elsevier Importance of inputs Elsevier |
| topic |
ddc 530 ddc 620 Elsevier Wind direction Elsevier Wind power forecast Elsevier Spatially averaged wind speed Elsevier Random forest Elsevier Hour-ahead Elsevier Importance of inputs |
| topic_unstemmed |
ddc 530 ddc 620 Elsevier Wind direction Elsevier Wind power forecast Elsevier Spatially averaged wind speed Elsevier Random forest Elsevier Hour-ahead Elsevier Importance of inputs |
| topic_browse |
ddc 530 ddc 620 Elsevier Wind direction Elsevier Wind power forecast Elsevier Spatially averaged wind speed Elsevier Random forest Elsevier Hour-ahead Elsevier Importance of inputs |
| format_facet |
Elektronische Aufsätze Aufsätze Elektronische Ressource |
| format_main_str_mv |
Text Zeitschrift/Artikel |
| carriertype_str_mv |
zu |
| author2_variant |
h s j b hsj hsjb |
| hierarchy_parent_title |
Technologies and practice of CO |
| hierarchy_parent_id |
ELV002723662 |
| dewey-tens |
530 - Physics 620 - Engineering |
| hierarchy_top_title |
Technologies and practice of CO |
| isfreeaccess_txt |
false |
| familylinks_str_mv |
(DE-627)ELV002723662 |
| title |
Hour-ahead wind power forecast based on random forests |
| ctrlnum |
(DE-627)ELV015348369 (ELSEVIER)S0960-1481(17)30255-0 |
| title_full |
Hour-ahead wind power forecast based on random forests |
| author_sort |
Lahouar, A. |
| journal |
Technologies and practice of CO |
| journalStr |
Technologies and practice of CO |
| lang_code |
eng |
| isOA_bool |
false |
| dewey-hundreds |
500 - Science 600 - Technology |
| recordtype |
marc |
| publishDateSort |
2017 |
| contenttype_str_mv |
zzz |
| container_start_page |
529 |
| author_browse |
Lahouar, A. |
| container_volume |
109 |
| physical |
13 |
| class |
530 620 530 DE-600 620 DE-600 |
| format_se |
Elektronische Aufsätze |
| author-letter |
Lahouar, A. |
| doi_str_mv |
10.1016/j.renene.2017.03.064 |
| dewey-full |
530 620 |
| title_sort |
hour-ahead wind power forecast based on random forests |
| title_auth |
Hour-ahead wind power forecast based on random forests |
| abstract |
Due to its chaotic nature, the wind behavior is difficult to forecast. Predicting wind power is a real challenge for dispatchers who need to estimate renewable generation in advance to establish their strategies. To achieve an accurate wind power prediction, it is important to determine first which meteorological data need to be included in the predictor. For that purpose, this paper focuses on choosing the appropriate weather factors, namely spatially averaged wind speed and wind direction. These factors are selected according to correlation and importance measures. Then, the random forest method is proposed to build an hour-ahead wind power predictor. The random forest does not need to be tuned or optimized, contrary to most other learning machines. Both point and probabilistic forecasts are performed using the same inputs. The emphasis is put on the effect of wind speed and direction on the model performance, and the immunity of random forest to irrelevant inputs. The wind data used to test the proposed model are taken from Sidi Daoud wind farm in Tunisia. Results show an interesting improvement of forecast accuracy using the proposed model, as well as an important reduction of the different error criteria compared to classical neural network prediction. |
| abstractGer |
Due to its chaotic nature, the wind behavior is difficult to forecast. Predicting wind power is a real challenge for dispatchers who need to estimate renewable generation in advance to establish their strategies. To achieve an accurate wind power prediction, it is important to determine first which meteorological data need to be included in the predictor. For that purpose, this paper focuses on choosing the appropriate weather factors, namely spatially averaged wind speed and wind direction. These factors are selected according to correlation and importance measures. Then, the random forest method is proposed to build an hour-ahead wind power predictor. The random forest does not need to be tuned or optimized, contrary to most other learning machines. Both point and probabilistic forecasts are performed using the same inputs. The emphasis is put on the effect of wind speed and direction on the model performance, and the immunity of random forest to irrelevant inputs. The wind data used to test the proposed model are taken from Sidi Daoud wind farm in Tunisia. Results show an interesting improvement of forecast accuracy using the proposed model, as well as an important reduction of the different error criteria compared to classical neural network prediction. |
| abstract_unstemmed |
Due to its chaotic nature, the wind behavior is difficult to forecast. Predicting wind power is a real challenge for dispatchers who need to estimate renewable generation in advance to establish their strategies. To achieve an accurate wind power prediction, it is important to determine first which meteorological data need to be included in the predictor. For that purpose, this paper focuses on choosing the appropriate weather factors, namely spatially averaged wind speed and wind direction. These factors are selected according to correlation and importance measures. Then, the random forest method is proposed to build an hour-ahead wind power predictor. The random forest does not need to be tuned or optimized, contrary to most other learning machines. Both point and probabilistic forecasts are performed using the same inputs. The emphasis is put on the effect of wind speed and direction on the model performance, and the immunity of random forest to irrelevant inputs. The wind data used to test the proposed model are taken from Sidi Daoud wind farm in Tunisia. Results show an interesting improvement of forecast accuracy using the proposed model, as well as an important reduction of the different error criteria compared to classical neural network prediction. |
| collection_details |
GBV_USEFLAG_U GBV_ELV SYSFLAG_U |
| title_short |
Hour-ahead wind power forecast based on random forests |
| url |
https://doi.org/10.1016/j.renene.2017.03.064 |
| remote_bool |
true |
| author2 |
Ben Hadj Slama, J. |
| author2Str |
Ben Hadj Slama, J. |
| ppnlink |
ELV002723662 |
| mediatype_str_mv |
z |
| isOA_txt |
false |
| hochschulschrift_bool |
false |
| author2_role |
oth |
| doi_str |
10.1016/j.renene.2017.03.064 |
| up_date |
2024-07-06T17:29:35.512Z |
| _version_ |
1803851635636568064 |
| fullrecord_marcxml |
<?xml version="1.0" encoding="UTF-8"?><collection xmlns="http://www.loc.gov/MARC21/slim"><record><leader>01000caa a22002652 4500</leader><controlfield tag="001">ELV015348369</controlfield><controlfield tag="003">DE-627</controlfield><controlfield tag="005">20230625115110.0</controlfield><controlfield tag="007">cr uuu---uuuuu</controlfield><controlfield tag="008">180602s2017 xx |||||o 00| ||eng c</controlfield><datafield tag="024" ind1="7" ind2=" "><subfield code="a">10.1016/j.renene.2017.03.064</subfield><subfield code="2">doi</subfield></datafield><datafield tag="028" ind1="5" ind2="2"><subfield code="a">GBVA2017016000018.pica</subfield></datafield><datafield tag="035" ind1=" " ind2=" "><subfield code="a">(DE-627)ELV015348369</subfield></datafield><datafield tag="035" ind1=" " ind2=" "><subfield code="a">(ELSEVIER)S0960-1481(17)30255-0</subfield></datafield><datafield tag="040" ind1=" " ind2=" "><subfield code="a">DE-627</subfield><subfield code="b">ger</subfield><subfield code="c">DE-627</subfield><subfield code="e">rakwb</subfield></datafield><datafield tag="041" ind1=" " ind2=" "><subfield code="a">eng</subfield></datafield><datafield tag="082" ind1="0" ind2=" "><subfield code="a">530</subfield><subfield code="a">620</subfield></datafield><datafield tag="082" ind1="0" ind2="4"><subfield code="a">530</subfield><subfield code="q">DE-600</subfield></datafield><datafield tag="082" ind1="0" ind2="4"><subfield code="a">620</subfield><subfield code="q">DE-600</subfield></datafield><datafield tag="100" ind1="1" ind2=" "><subfield code="a">Lahouar, A.</subfield><subfield code="e">verfasserin</subfield><subfield code="4">aut</subfield></datafield><datafield tag="245" ind1="1" ind2="0"><subfield code="a">Hour-ahead wind power forecast based on random forests</subfield></datafield><datafield tag="264" ind1=" " ind2="1"><subfield code="c">2017transfer abstract</subfield></datafield><datafield tag="300" ind1=" " ind2=" "><subfield code="a">13</subfield></datafield><datafield tag="336" ind1=" " ind2=" "><subfield code="a">nicht spezifiziert</subfield><subfield code="b">zzz</subfield><subfield code="2">rdacontent</subfield></datafield><datafield tag="337" ind1=" " ind2=" "><subfield code="a">nicht spezifiziert</subfield><subfield code="b">z</subfield><subfield code="2">rdamedia</subfield></datafield><datafield tag="338" ind1=" " ind2=" "><subfield code="a">nicht spezifiziert</subfield><subfield code="b">zu</subfield><subfield code="2">rdacarrier</subfield></datafield><datafield tag="520" ind1=" " ind2=" "><subfield code="a">Due to its chaotic nature, the wind behavior is difficult to forecast. Predicting wind power is a real challenge for dispatchers who need to estimate renewable generation in advance to establish their strategies. To achieve an accurate wind power prediction, it is important to determine first which meteorological data need to be included in the predictor. For that purpose, this paper focuses on choosing the appropriate weather factors, namely spatially averaged wind speed and wind direction. These factors are selected according to correlation and importance measures. Then, the random forest method is proposed to build an hour-ahead wind power predictor. The random forest does not need to be tuned or optimized, contrary to most other learning machines. Both point and probabilistic forecasts are performed using the same inputs. The emphasis is put on the effect of wind speed and direction on the model performance, and the immunity of random forest to irrelevant inputs. The wind data used to test the proposed model are taken from Sidi Daoud wind farm in Tunisia. Results show an interesting improvement of forecast accuracy using the proposed model, as well as an important reduction of the different error criteria compared to classical neural network prediction.</subfield></datafield><datafield tag="520" ind1=" " ind2=" "><subfield code="a">Due to its chaotic nature, the wind behavior is difficult to forecast. Predicting wind power is a real challenge for dispatchers who need to estimate renewable generation in advance to establish their strategies. To achieve an accurate wind power prediction, it is important to determine first which meteorological data need to be included in the predictor. For that purpose, this paper focuses on choosing the appropriate weather factors, namely spatially averaged wind speed and wind direction. These factors are selected according to correlation and importance measures. Then, the random forest method is proposed to build an hour-ahead wind power predictor. The random forest does not need to be tuned or optimized, contrary to most other learning machines. Both point and probabilistic forecasts are performed using the same inputs. The emphasis is put on the effect of wind speed and direction on the model performance, and the immunity of random forest to irrelevant inputs. The wind data used to test the proposed model are taken from Sidi Daoud wind farm in Tunisia. Results show an interesting improvement of forecast accuracy using the proposed model, as well as an important reduction of the different error criteria compared to classical neural network prediction.</subfield></datafield><datafield tag="650" ind1=" " ind2="7"><subfield code="a">Wind direction</subfield><subfield code="2">Elsevier</subfield></datafield><datafield tag="650" ind1=" " ind2="7"><subfield code="a">Wind power forecast</subfield><subfield code="2">Elsevier</subfield></datafield><datafield tag="650" ind1=" " ind2="7"><subfield code="a">Spatially averaged wind speed</subfield><subfield code="2">Elsevier</subfield></datafield><datafield tag="650" ind1=" " ind2="7"><subfield code="a">Random forest</subfield><subfield code="2">Elsevier</subfield></datafield><datafield tag="650" ind1=" " ind2="7"><subfield code="a">Hour-ahead</subfield><subfield code="2">Elsevier</subfield></datafield><datafield tag="650" ind1=" " ind2="7"><subfield code="a">Importance of inputs</subfield><subfield code="2">Elsevier</subfield></datafield><datafield tag="700" ind1="1" ind2=" "><subfield code="a">Ben Hadj Slama, J.</subfield><subfield code="4">oth</subfield></datafield><datafield tag="773" ind1="0" ind2="8"><subfield code="i">Enthalten in</subfield><subfield code="n">Elsevier Science</subfield><subfield code="a">HU, Yongle ELSEVIER</subfield><subfield code="t">Technologies and practice of CO</subfield><subfield code="d">2019</subfield><subfield code="d">an international journal : the official journal of WREN, The World Renewable Energy Network</subfield><subfield code="g">Amsterdam [u.a.]</subfield><subfield code="w">(DE-627)ELV002723662</subfield></datafield><datafield tag="773" ind1="1" ind2="8"><subfield code="g">volume:109</subfield><subfield code="g">year:2017</subfield><subfield code="g">pages:529-541</subfield><subfield code="g">extent:13</subfield></datafield><datafield tag="856" ind1="4" ind2="0"><subfield code="u">https://doi.org/10.1016/j.renene.2017.03.064</subfield><subfield code="3">Volltext</subfield></datafield><datafield tag="912" ind1=" " ind2=" "><subfield code="a">GBV_USEFLAG_U</subfield></datafield><datafield tag="912" ind1=" " ind2=" "><subfield code="a">GBV_ELV</subfield></datafield><datafield tag="912" ind1=" " ind2=" "><subfield code="a">SYSFLAG_U</subfield></datafield><datafield tag="951" ind1=" " ind2=" "><subfield code="a">AR</subfield></datafield><datafield tag="952" ind1=" " ind2=" "><subfield code="d">109</subfield><subfield code="j">2017</subfield><subfield code="h">529-541</subfield><subfield code="g">13</subfield></datafield><datafield tag="953" ind1=" " ind2=" "><subfield code="2">045F</subfield><subfield code="a">530</subfield></datafield></record></collection>
|
| score |
7.400344 |