Energy load forecasting model based on deep neural networks for smart grids
Abstract In recent, smart grid has emerged as a promising technology to facilitate the future electric power grid and to balance between supply and demand. However, the intermittent nature of distributed energy resources causes dynamic uncertainties and nonlinearity in the smart grid environment. Th...
Ausführliche Beschreibung
Gespeichert in:
| Autor*in: |
Mohammad, Faisal [verfasserIn] Kim, Young-Chon [verfasserIn] |
|---|
| Format: |
E-Artikel |
|---|---|
| Sprache: |
Englisch |
| Erschienen: |
2019 |
|---|
| Schlagwörter: |
|---|
| Übergeordnetes Werk: |
Enthalten in: International Journal of Systems Assurance Engineering and Management - Springer-Verlag, 2010, 11(2019), 4 vom: 06. Sept., Seite 824-834 |
|---|---|
| Übergeordnetes Werk: |
volume:11 ; year:2019 ; number:4 ; day:06 ; month:09 ; pages:824-834 |
| Links: |
|---|
| DOI / URN: |
10.1007/s13198-019-00884-9 |
|---|
| Katalog-ID: |
SPR040603849 |
|---|
| LEADER | 01000caa a22002652 4500 | ||
|---|---|---|---|
| 001 | SPR040603849 | ||
| 003 | DE-627 | ||
| 005 | 20201126024632.0 | ||
| 007 | cr uuu---uuuuu | ||
| 008 | 201007s2019 xx |||||o 00| ||eng c | ||
| 024 | 7 | |a 10.1007/s13198-019-00884-9 |2 doi | |
| 035 | |a (DE-627)SPR040603849 | ||
| 035 | |a (SPR)s13198-019-00884-9-e | ||
| 040 | |a DE-627 |b ger |c DE-627 |e rakwb | ||
| 041 | |a eng | ||
| 100 | 1 | |a Mohammad, Faisal |e verfasserin |4 aut | |
| 245 | 1 | 0 | |a Energy load forecasting model based on deep neural networks for smart grids |
| 264 | 1 | |c 2019 | |
| 336 | |a Text |b txt |2 rdacontent | ||
| 337 | |a Computermedien |b c |2 rdamedia | ||
| 338 | |a Online-Ressource |b cr |2 rdacarrier | ||
| 520 | |a Abstract In recent, smart grid has emerged as a promising technology to facilitate the future electric power grid and to balance between supply and demand. However, the intermittent nature of distributed energy resources causes dynamic uncertainties and nonlinearity in the smart grid environment. This may result in a large stress on power grid and has a big influence on energy planning, especially the generation and distribution. Therefore, energy load forecasting plays an important role in facilitating the operation of the future smart grid. Using the traditional statistical and machine learning approach there exists a significant forecasting error and high degree of overfitting. In this paper, we propose an energy load forecasting (ELF) model based on deep neural network architectures to manage the energy consumption in smart grids. First we investigate the applicability of two deep neural network architectures: deep feed-forward neural network (deep-FNN) and deep recurrent neural network (deep-RNN). To evaluate the models with low error, we simulate both architectures with multi size training set. Further, various activation functions and different combinations of hidden layer architectures are also tested. The simulation results are compared in terms of mean absolute percentage error. The results show that the proposed ELF model has attained better generalization and outperform the existing load forecasting models based on the shallow neural network, ensemble tree bagger and generalized linear regression. | ||
| 650 | 4 | |a Load forecasting |7 (dpeaa)DE-He213 | |
| 650 | 4 | |a Deep neural network |7 (dpeaa)DE-He213 | |
| 650 | 4 | |a Deep-feed-forward neural network |7 (dpeaa)DE-He213 | |
| 650 | 4 | |a Deep-recurrent neural network |7 (dpeaa)DE-He213 | |
| 650 | 4 | |a Activation function |7 (dpeaa)DE-He213 | |
| 650 | 4 | |a Hidden layer |7 (dpeaa)DE-He213 | |
| 650 | 4 | |a Levenberg–Marquardt algorithm |7 (dpeaa)DE-He213 | |
| 700 | 1 | |a Kim, Young-Chon |e verfasserin |4 aut | |
| 773 | 0 | 8 | |i Enthalten in |t International Journal of Systems Assurance Engineering and Management |d Springer-Verlag, 2010 |g 11(2019), 4 vom: 06. Sept., Seite 824-834 |w (DE-627)SPR031222420 |7 nnns |
| 773 | 1 | 8 | |g volume:11 |g year:2019 |g number:4 |g day:06 |g month:09 |g pages:824-834 |
| 856 | 4 | 0 | |u https://dx.doi.org/10.1007/s13198-019-00884-9 |z lizenzpflichtig |3 Volltext |
| 912 | |a GBV_USEFLAG_A | ||
| 912 | |a SYSFLAG_A | ||
| 912 | |a GBV_SPRINGER | ||
| 951 | |a AR | ||
| 952 | |d 11 |j 2019 |e 4 |b 06 |c 09 |h 824-834 | ||
| author_variant |
f m fm y c k yck |
|---|---|
| matchkey_str |
mohammadfaisalkimyoungchon:2019----:nryodoeatnmdlaeodenuanto |
| hierarchy_sort_str |
2019 |
| publishDate |
2019 |
| allfields |
10.1007/s13198-019-00884-9 doi (DE-627)SPR040603849 (SPR)s13198-019-00884-9-e DE-627 ger DE-627 rakwb eng Mohammad, Faisal verfasserin aut Energy load forecasting model based on deep neural networks for smart grids 2019 Text txt rdacontent Computermedien c rdamedia Online-Ressource cr rdacarrier Abstract In recent, smart grid has emerged as a promising technology to facilitate the future electric power grid and to balance between supply and demand. However, the intermittent nature of distributed energy resources causes dynamic uncertainties and nonlinearity in the smart grid environment. This may result in a large stress on power grid and has a big influence on energy planning, especially the generation and distribution. Therefore, energy load forecasting plays an important role in facilitating the operation of the future smart grid. Using the traditional statistical and machine learning approach there exists a significant forecasting error and high degree of overfitting. In this paper, we propose an energy load forecasting (ELF) model based on deep neural network architectures to manage the energy consumption in smart grids. First we investigate the applicability of two deep neural network architectures: deep feed-forward neural network (deep-FNN) and deep recurrent neural network (deep-RNN). To evaluate the models with low error, we simulate both architectures with multi size training set. Further, various activation functions and different combinations of hidden layer architectures are also tested. The simulation results are compared in terms of mean absolute percentage error. The results show that the proposed ELF model has attained better generalization and outperform the existing load forecasting models based on the shallow neural network, ensemble tree bagger and generalized linear regression. Load forecasting (dpeaa)DE-He213 Deep neural network (dpeaa)DE-He213 Deep-feed-forward neural network (dpeaa)DE-He213 Deep-recurrent neural network (dpeaa)DE-He213 Activation function (dpeaa)DE-He213 Hidden layer (dpeaa)DE-He213 Levenberg–Marquardt algorithm (dpeaa)DE-He213 Kim, Young-Chon verfasserin aut Enthalten in International Journal of Systems Assurance Engineering and Management Springer-Verlag, 2010 11(2019), 4 vom: 06. Sept., Seite 824-834 (DE-627)SPR031222420 nnns volume:11 year:2019 number:4 day:06 month:09 pages:824-834 https://dx.doi.org/10.1007/s13198-019-00884-9 lizenzpflichtig Volltext GBV_USEFLAG_A SYSFLAG_A GBV_SPRINGER AR 11 2019 4 06 09 824-834 |
| spelling |
10.1007/s13198-019-00884-9 doi (DE-627)SPR040603849 (SPR)s13198-019-00884-9-e DE-627 ger DE-627 rakwb eng Mohammad, Faisal verfasserin aut Energy load forecasting model based on deep neural networks for smart grids 2019 Text txt rdacontent Computermedien c rdamedia Online-Ressource cr rdacarrier Abstract In recent, smart grid has emerged as a promising technology to facilitate the future electric power grid and to balance between supply and demand. However, the intermittent nature of distributed energy resources causes dynamic uncertainties and nonlinearity in the smart grid environment. This may result in a large stress on power grid and has a big influence on energy planning, especially the generation and distribution. Therefore, energy load forecasting plays an important role in facilitating the operation of the future smart grid. Using the traditional statistical and machine learning approach there exists a significant forecasting error and high degree of overfitting. In this paper, we propose an energy load forecasting (ELF) model based on deep neural network architectures to manage the energy consumption in smart grids. First we investigate the applicability of two deep neural network architectures: deep feed-forward neural network (deep-FNN) and deep recurrent neural network (deep-RNN). To evaluate the models with low error, we simulate both architectures with multi size training set. Further, various activation functions and different combinations of hidden layer architectures are also tested. The simulation results are compared in terms of mean absolute percentage error. The results show that the proposed ELF model has attained better generalization and outperform the existing load forecasting models based on the shallow neural network, ensemble tree bagger and generalized linear regression. Load forecasting (dpeaa)DE-He213 Deep neural network (dpeaa)DE-He213 Deep-feed-forward neural network (dpeaa)DE-He213 Deep-recurrent neural network (dpeaa)DE-He213 Activation function (dpeaa)DE-He213 Hidden layer (dpeaa)DE-He213 Levenberg–Marquardt algorithm (dpeaa)DE-He213 Kim, Young-Chon verfasserin aut Enthalten in International Journal of Systems Assurance Engineering and Management Springer-Verlag, 2010 11(2019), 4 vom: 06. Sept., Seite 824-834 (DE-627)SPR031222420 nnns volume:11 year:2019 number:4 day:06 month:09 pages:824-834 https://dx.doi.org/10.1007/s13198-019-00884-9 lizenzpflichtig Volltext GBV_USEFLAG_A SYSFLAG_A GBV_SPRINGER AR 11 2019 4 06 09 824-834 |
| allfields_unstemmed |
10.1007/s13198-019-00884-9 doi (DE-627)SPR040603849 (SPR)s13198-019-00884-9-e DE-627 ger DE-627 rakwb eng Mohammad, Faisal verfasserin aut Energy load forecasting model based on deep neural networks for smart grids 2019 Text txt rdacontent Computermedien c rdamedia Online-Ressource cr rdacarrier Abstract In recent, smart grid has emerged as a promising technology to facilitate the future electric power grid and to balance between supply and demand. However, the intermittent nature of distributed energy resources causes dynamic uncertainties and nonlinearity in the smart grid environment. This may result in a large stress on power grid and has a big influence on energy planning, especially the generation and distribution. Therefore, energy load forecasting plays an important role in facilitating the operation of the future smart grid. Using the traditional statistical and machine learning approach there exists a significant forecasting error and high degree of overfitting. In this paper, we propose an energy load forecasting (ELF) model based on deep neural network architectures to manage the energy consumption in smart grids. First we investigate the applicability of two deep neural network architectures: deep feed-forward neural network (deep-FNN) and deep recurrent neural network (deep-RNN). To evaluate the models with low error, we simulate both architectures with multi size training set. Further, various activation functions and different combinations of hidden layer architectures are also tested. The simulation results are compared in terms of mean absolute percentage error. The results show that the proposed ELF model has attained better generalization and outperform the existing load forecasting models based on the shallow neural network, ensemble tree bagger and generalized linear regression. Load forecasting (dpeaa)DE-He213 Deep neural network (dpeaa)DE-He213 Deep-feed-forward neural network (dpeaa)DE-He213 Deep-recurrent neural network (dpeaa)DE-He213 Activation function (dpeaa)DE-He213 Hidden layer (dpeaa)DE-He213 Levenberg–Marquardt algorithm (dpeaa)DE-He213 Kim, Young-Chon verfasserin aut Enthalten in International Journal of Systems Assurance Engineering and Management Springer-Verlag, 2010 11(2019), 4 vom: 06. Sept., Seite 824-834 (DE-627)SPR031222420 nnns volume:11 year:2019 number:4 day:06 month:09 pages:824-834 https://dx.doi.org/10.1007/s13198-019-00884-9 lizenzpflichtig Volltext GBV_USEFLAG_A SYSFLAG_A GBV_SPRINGER AR 11 2019 4 06 09 824-834 |
| allfieldsGer |
10.1007/s13198-019-00884-9 doi (DE-627)SPR040603849 (SPR)s13198-019-00884-9-e DE-627 ger DE-627 rakwb eng Mohammad, Faisal verfasserin aut Energy load forecasting model based on deep neural networks for smart grids 2019 Text txt rdacontent Computermedien c rdamedia Online-Ressource cr rdacarrier Abstract In recent, smart grid has emerged as a promising technology to facilitate the future electric power grid and to balance between supply and demand. However, the intermittent nature of distributed energy resources causes dynamic uncertainties and nonlinearity in the smart grid environment. This may result in a large stress on power grid and has a big influence on energy planning, especially the generation and distribution. Therefore, energy load forecasting plays an important role in facilitating the operation of the future smart grid. Using the traditional statistical and machine learning approach there exists a significant forecasting error and high degree of overfitting. In this paper, we propose an energy load forecasting (ELF) model based on deep neural network architectures to manage the energy consumption in smart grids. First we investigate the applicability of two deep neural network architectures: deep feed-forward neural network (deep-FNN) and deep recurrent neural network (deep-RNN). To evaluate the models with low error, we simulate both architectures with multi size training set. Further, various activation functions and different combinations of hidden layer architectures are also tested. The simulation results are compared in terms of mean absolute percentage error. The results show that the proposed ELF model has attained better generalization and outperform the existing load forecasting models based on the shallow neural network, ensemble tree bagger and generalized linear regression. Load forecasting (dpeaa)DE-He213 Deep neural network (dpeaa)DE-He213 Deep-feed-forward neural network (dpeaa)DE-He213 Deep-recurrent neural network (dpeaa)DE-He213 Activation function (dpeaa)DE-He213 Hidden layer (dpeaa)DE-He213 Levenberg–Marquardt algorithm (dpeaa)DE-He213 Kim, Young-Chon verfasserin aut Enthalten in International Journal of Systems Assurance Engineering and Management Springer-Verlag, 2010 11(2019), 4 vom: 06. Sept., Seite 824-834 (DE-627)SPR031222420 nnns volume:11 year:2019 number:4 day:06 month:09 pages:824-834 https://dx.doi.org/10.1007/s13198-019-00884-9 lizenzpflichtig Volltext GBV_USEFLAG_A SYSFLAG_A GBV_SPRINGER AR 11 2019 4 06 09 824-834 |
| allfieldsSound |
10.1007/s13198-019-00884-9 doi (DE-627)SPR040603849 (SPR)s13198-019-00884-9-e DE-627 ger DE-627 rakwb eng Mohammad, Faisal verfasserin aut Energy load forecasting model based on deep neural networks for smart grids 2019 Text txt rdacontent Computermedien c rdamedia Online-Ressource cr rdacarrier Abstract In recent, smart grid has emerged as a promising technology to facilitate the future electric power grid and to balance between supply and demand. However, the intermittent nature of distributed energy resources causes dynamic uncertainties and nonlinearity in the smart grid environment. This may result in a large stress on power grid and has a big influence on energy planning, especially the generation and distribution. Therefore, energy load forecasting plays an important role in facilitating the operation of the future smart grid. Using the traditional statistical and machine learning approach there exists a significant forecasting error and high degree of overfitting. In this paper, we propose an energy load forecasting (ELF) model based on deep neural network architectures to manage the energy consumption in smart grids. First we investigate the applicability of two deep neural network architectures: deep feed-forward neural network (deep-FNN) and deep recurrent neural network (deep-RNN). To evaluate the models with low error, we simulate both architectures with multi size training set. Further, various activation functions and different combinations of hidden layer architectures are also tested. The simulation results are compared in terms of mean absolute percentage error. The results show that the proposed ELF model has attained better generalization and outperform the existing load forecasting models based on the shallow neural network, ensemble tree bagger and generalized linear regression. Load forecasting (dpeaa)DE-He213 Deep neural network (dpeaa)DE-He213 Deep-feed-forward neural network (dpeaa)DE-He213 Deep-recurrent neural network (dpeaa)DE-He213 Activation function (dpeaa)DE-He213 Hidden layer (dpeaa)DE-He213 Levenberg–Marquardt algorithm (dpeaa)DE-He213 Kim, Young-Chon verfasserin aut Enthalten in International Journal of Systems Assurance Engineering and Management Springer-Verlag, 2010 11(2019), 4 vom: 06. Sept., Seite 824-834 (DE-627)SPR031222420 nnns volume:11 year:2019 number:4 day:06 month:09 pages:824-834 https://dx.doi.org/10.1007/s13198-019-00884-9 lizenzpflichtig Volltext GBV_USEFLAG_A SYSFLAG_A GBV_SPRINGER AR 11 2019 4 06 09 824-834 |
| language |
English |
| source |
Enthalten in International Journal of Systems Assurance Engineering and Management 11(2019), 4 vom: 06. Sept., Seite 824-834 volume:11 year:2019 number:4 day:06 month:09 pages:824-834 |
| sourceStr |
Enthalten in International Journal of Systems Assurance Engineering and Management 11(2019), 4 vom: 06. Sept., Seite 824-834 volume:11 year:2019 number:4 day:06 month:09 pages:824-834 |
| format_phy_str_mv |
Article |
| institution |
findex.gbv.de |
| topic_facet |
Load forecasting Deep neural network Deep-feed-forward neural network Deep-recurrent neural network Activation function Hidden layer Levenberg–Marquardt algorithm |
| isfreeaccess_bool |
false |
| container_title |
International Journal of Systems Assurance Engineering and Management |
| authorswithroles_txt_mv |
Mohammad, Faisal @@aut@@ Kim, Young-Chon @@aut@@ |
| publishDateDaySort_date |
2019-09-06T00:00:00Z |
| hierarchy_top_id |
SPR031222420 |
| id |
SPR040603849 |
| 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">SPR040603849</controlfield><controlfield tag="003">DE-627</controlfield><controlfield tag="005">20201126024632.0</controlfield><controlfield tag="007">cr uuu---uuuuu</controlfield><controlfield tag="008">201007s2019 xx |||||o 00| ||eng c</controlfield><datafield tag="024" ind1="7" ind2=" "><subfield code="a">10.1007/s13198-019-00884-9</subfield><subfield code="2">doi</subfield></datafield><datafield tag="035" ind1=" " ind2=" "><subfield code="a">(DE-627)SPR040603849</subfield></datafield><datafield tag="035" ind1=" " ind2=" "><subfield code="a">(SPR)s13198-019-00884-9-e</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="100" ind1="1" ind2=" "><subfield code="a">Mohammad, Faisal</subfield><subfield code="e">verfasserin</subfield><subfield code="4">aut</subfield></datafield><datafield tag="245" ind1="1" ind2="0"><subfield code="a">Energy load forecasting model based on deep neural networks for smart grids</subfield></datafield><datafield tag="264" ind1=" " ind2="1"><subfield code="c">2019</subfield></datafield><datafield tag="336" ind1=" " ind2=" "><subfield code="a">Text</subfield><subfield code="b">txt</subfield><subfield code="2">rdacontent</subfield></datafield><datafield tag="337" ind1=" " ind2=" "><subfield code="a">Computermedien</subfield><subfield code="b">c</subfield><subfield code="2">rdamedia</subfield></datafield><datafield tag="338" ind1=" " ind2=" "><subfield code="a">Online-Ressource</subfield><subfield code="b">cr</subfield><subfield code="2">rdacarrier</subfield></datafield><datafield tag="520" ind1=" " ind2=" "><subfield code="a">Abstract In recent, smart grid has emerged as a promising technology to facilitate the future electric power grid and to balance between supply and demand. However, the intermittent nature of distributed energy resources causes dynamic uncertainties and nonlinearity in the smart grid environment. This may result in a large stress on power grid and has a big influence on energy planning, especially the generation and distribution. Therefore, energy load forecasting plays an important role in facilitating the operation of the future smart grid. Using the traditional statistical and machine learning approach there exists a significant forecasting error and high degree of overfitting. In this paper, we propose an energy load forecasting (ELF) model based on deep neural network architectures to manage the energy consumption in smart grids. First we investigate the applicability of two deep neural network architectures: deep feed-forward neural network (deep-FNN) and deep recurrent neural network (deep-RNN). To evaluate the models with low error, we simulate both architectures with multi size training set. Further, various activation functions and different combinations of hidden layer architectures are also tested. The simulation results are compared in terms of mean absolute percentage error. The results show that the proposed ELF model has attained better generalization and outperform the existing load forecasting models based on the shallow neural network, ensemble tree bagger and generalized linear regression.</subfield></datafield><datafield tag="650" ind1=" " ind2="4"><subfield code="a">Load forecasting</subfield><subfield code="7">(dpeaa)DE-He213</subfield></datafield><datafield tag="650" ind1=" " ind2="4"><subfield code="a">Deep neural network</subfield><subfield code="7">(dpeaa)DE-He213</subfield></datafield><datafield tag="650" ind1=" " ind2="4"><subfield code="a">Deep-feed-forward neural network</subfield><subfield code="7">(dpeaa)DE-He213</subfield></datafield><datafield tag="650" ind1=" " ind2="4"><subfield code="a">Deep-recurrent neural network</subfield><subfield code="7">(dpeaa)DE-He213</subfield></datafield><datafield tag="650" ind1=" " ind2="4"><subfield code="a">Activation function</subfield><subfield code="7">(dpeaa)DE-He213</subfield></datafield><datafield tag="650" ind1=" " ind2="4"><subfield code="a">Hidden layer</subfield><subfield code="7">(dpeaa)DE-He213</subfield></datafield><datafield tag="650" ind1=" " ind2="4"><subfield code="a">Levenberg–Marquardt algorithm</subfield><subfield code="7">(dpeaa)DE-He213</subfield></datafield><datafield tag="700" ind1="1" ind2=" "><subfield code="a">Kim, Young-Chon</subfield><subfield code="e">verfasserin</subfield><subfield code="4">aut</subfield></datafield><datafield tag="773" ind1="0" ind2="8"><subfield code="i">Enthalten in</subfield><subfield code="t">International Journal of Systems Assurance Engineering and Management</subfield><subfield code="d">Springer-Verlag, 2010</subfield><subfield code="g">11(2019), 4 vom: 06. Sept., Seite 824-834</subfield><subfield code="w">(DE-627)SPR031222420</subfield><subfield code="7">nnns</subfield></datafield><datafield tag="773" ind1="1" ind2="8"><subfield code="g">volume:11</subfield><subfield code="g">year:2019</subfield><subfield code="g">number:4</subfield><subfield code="g">day:06</subfield><subfield code="g">month:09</subfield><subfield code="g">pages:824-834</subfield></datafield><datafield tag="856" ind1="4" ind2="0"><subfield code="u">https://dx.doi.org/10.1007/s13198-019-00884-9</subfield><subfield code="z">lizenzpflichtig</subfield><subfield code="3">Volltext</subfield></datafield><datafield tag="912" ind1=" " ind2=" "><subfield code="a">GBV_USEFLAG_A</subfield></datafield><datafield tag="912" ind1=" " ind2=" "><subfield code="a">SYSFLAG_A</subfield></datafield><datafield tag="912" ind1=" " ind2=" "><subfield code="a">GBV_SPRINGER</subfield></datafield><datafield tag="951" ind1=" " ind2=" "><subfield code="a">AR</subfield></datafield><datafield tag="952" ind1=" " ind2=" "><subfield code="d">11</subfield><subfield code="j">2019</subfield><subfield code="e">4</subfield><subfield code="b">06</subfield><subfield code="c">09</subfield><subfield code="h">824-834</subfield></datafield></record></collection>
|
| author |
Mohammad, Faisal |
| spellingShingle |
Mohammad, Faisal misc Load forecasting misc Deep neural network misc Deep-feed-forward neural network misc Deep-recurrent neural network misc Activation function misc Hidden layer misc Levenberg–Marquardt algorithm Energy load forecasting model based on deep neural networks for smart grids |
| authorStr |
Mohammad, Faisal |
| ppnlink_with_tag_str_mv |
@@773@@(DE-627)SPR031222420 |
| format |
electronic Article |
| delete_txt_mv |
keep |
| author_role |
aut aut |
| collection |
springer |
| remote_str |
true |
| illustrated |
Not Illustrated |
| topic_title |
Energy load forecasting model based on deep neural networks for smart grids Load forecasting (dpeaa)DE-He213 Deep neural network (dpeaa)DE-He213 Deep-feed-forward neural network (dpeaa)DE-He213 Deep-recurrent neural network (dpeaa)DE-He213 Activation function (dpeaa)DE-He213 Hidden layer (dpeaa)DE-He213 Levenberg–Marquardt algorithm (dpeaa)DE-He213 |
| topic |
misc Load forecasting misc Deep neural network misc Deep-feed-forward neural network misc Deep-recurrent neural network misc Activation function misc Hidden layer misc Levenberg–Marquardt algorithm |
| topic_unstemmed |
misc Load forecasting misc Deep neural network misc Deep-feed-forward neural network misc Deep-recurrent neural network misc Activation function misc Hidden layer misc Levenberg–Marquardt algorithm |
| topic_browse |
misc Load forecasting misc Deep neural network misc Deep-feed-forward neural network misc Deep-recurrent neural network misc Activation function misc Hidden layer misc Levenberg–Marquardt algorithm |
| format_facet |
Elektronische Aufsätze Aufsätze Elektronische Ressource |
| format_main_str_mv |
Text Zeitschrift/Artikel |
| carriertype_str_mv |
cr |
| hierarchy_parent_title |
International Journal of Systems Assurance Engineering and Management |
| hierarchy_parent_id |
SPR031222420 |
| hierarchy_top_title |
International Journal of Systems Assurance Engineering and Management |
| isfreeaccess_txt |
false |
| familylinks_str_mv |
(DE-627)SPR031222420 |
| title |
Energy load forecasting model based on deep neural networks for smart grids |
| ctrlnum |
(DE-627)SPR040603849 (SPR)s13198-019-00884-9-e |
| title_full |
Energy load forecasting model based on deep neural networks for smart grids |
| author_sort |
Mohammad, Faisal |
| journal |
International Journal of Systems Assurance Engineering and Management |
| journalStr |
International Journal of Systems Assurance Engineering and Management |
| lang_code |
eng |
| isOA_bool |
false |
| recordtype |
marc |
| publishDateSort |
2019 |
| contenttype_str_mv |
txt |
| container_start_page |
824 |
| author_browse |
Mohammad, Faisal Kim, Young-Chon |
| container_volume |
11 |
| format_se |
Elektronische Aufsätze |
| author-letter |
Mohammad, Faisal |
| doi_str_mv |
10.1007/s13198-019-00884-9 |
| author2-role |
verfasserin |
| title_sort |
energy load forecasting model based on deep neural networks for smart grids |
| title_auth |
Energy load forecasting model based on deep neural networks for smart grids |
| abstract |
Abstract In recent, smart grid has emerged as a promising technology to facilitate the future electric power grid and to balance between supply and demand. However, the intermittent nature of distributed energy resources causes dynamic uncertainties and nonlinearity in the smart grid environment. This may result in a large stress on power grid and has a big influence on energy planning, especially the generation and distribution. Therefore, energy load forecasting plays an important role in facilitating the operation of the future smart grid. Using the traditional statistical and machine learning approach there exists a significant forecasting error and high degree of overfitting. In this paper, we propose an energy load forecasting (ELF) model based on deep neural network architectures to manage the energy consumption in smart grids. First we investigate the applicability of two deep neural network architectures: deep feed-forward neural network (deep-FNN) and deep recurrent neural network (deep-RNN). To evaluate the models with low error, we simulate both architectures with multi size training set. Further, various activation functions and different combinations of hidden layer architectures are also tested. The simulation results are compared in terms of mean absolute percentage error. The results show that the proposed ELF model has attained better generalization and outperform the existing load forecasting models based on the shallow neural network, ensemble tree bagger and generalized linear regression. |
| abstractGer |
Abstract In recent, smart grid has emerged as a promising technology to facilitate the future electric power grid and to balance between supply and demand. However, the intermittent nature of distributed energy resources causes dynamic uncertainties and nonlinearity in the smart grid environment. This may result in a large stress on power grid and has a big influence on energy planning, especially the generation and distribution. Therefore, energy load forecasting plays an important role in facilitating the operation of the future smart grid. Using the traditional statistical and machine learning approach there exists a significant forecasting error and high degree of overfitting. In this paper, we propose an energy load forecasting (ELF) model based on deep neural network architectures to manage the energy consumption in smart grids. First we investigate the applicability of two deep neural network architectures: deep feed-forward neural network (deep-FNN) and deep recurrent neural network (deep-RNN). To evaluate the models with low error, we simulate both architectures with multi size training set. Further, various activation functions and different combinations of hidden layer architectures are also tested. The simulation results are compared in terms of mean absolute percentage error. The results show that the proposed ELF model has attained better generalization and outperform the existing load forecasting models based on the shallow neural network, ensemble tree bagger and generalized linear regression. |
| abstract_unstemmed |
Abstract In recent, smart grid has emerged as a promising technology to facilitate the future electric power grid and to balance between supply and demand. However, the intermittent nature of distributed energy resources causes dynamic uncertainties and nonlinearity in the smart grid environment. This may result in a large stress on power grid and has a big influence on energy planning, especially the generation and distribution. Therefore, energy load forecasting plays an important role in facilitating the operation of the future smart grid. Using the traditional statistical and machine learning approach there exists a significant forecasting error and high degree of overfitting. In this paper, we propose an energy load forecasting (ELF) model based on deep neural network architectures to manage the energy consumption in smart grids. First we investigate the applicability of two deep neural network architectures: deep feed-forward neural network (deep-FNN) and deep recurrent neural network (deep-RNN). To evaluate the models with low error, we simulate both architectures with multi size training set. Further, various activation functions and different combinations of hidden layer architectures are also tested. The simulation results are compared in terms of mean absolute percentage error. The results show that the proposed ELF model has attained better generalization and outperform the existing load forecasting models based on the shallow neural network, ensemble tree bagger and generalized linear regression. |
| collection_details |
GBV_USEFLAG_A SYSFLAG_A GBV_SPRINGER |
| container_issue |
4 |
| title_short |
Energy load forecasting model based on deep neural networks for smart grids |
| url |
https://dx.doi.org/10.1007/s13198-019-00884-9 |
| remote_bool |
true |
| author2 |
Kim, Young-Chon |
| author2Str |
Kim, Young-Chon |
| ppnlink |
SPR031222420 |
| mediatype_str_mv |
c |
| isOA_txt |
false |
| hochschulschrift_bool |
false |
| doi_str |
10.1007/s13198-019-00884-9 |
| up_date |
2024-07-03T17:03:56.598Z |
| _version_ |
1803578231068033024 |
| 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">SPR040603849</controlfield><controlfield tag="003">DE-627</controlfield><controlfield tag="005">20201126024632.0</controlfield><controlfield tag="007">cr uuu---uuuuu</controlfield><controlfield tag="008">201007s2019 xx |||||o 00| ||eng c</controlfield><datafield tag="024" ind1="7" ind2=" "><subfield code="a">10.1007/s13198-019-00884-9</subfield><subfield code="2">doi</subfield></datafield><datafield tag="035" ind1=" " ind2=" "><subfield code="a">(DE-627)SPR040603849</subfield></datafield><datafield tag="035" ind1=" " ind2=" "><subfield code="a">(SPR)s13198-019-00884-9-e</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="100" ind1="1" ind2=" "><subfield code="a">Mohammad, Faisal</subfield><subfield code="e">verfasserin</subfield><subfield code="4">aut</subfield></datafield><datafield tag="245" ind1="1" ind2="0"><subfield code="a">Energy load forecasting model based on deep neural networks for smart grids</subfield></datafield><datafield tag="264" ind1=" " ind2="1"><subfield code="c">2019</subfield></datafield><datafield tag="336" ind1=" " ind2=" "><subfield code="a">Text</subfield><subfield code="b">txt</subfield><subfield code="2">rdacontent</subfield></datafield><datafield tag="337" ind1=" " ind2=" "><subfield code="a">Computermedien</subfield><subfield code="b">c</subfield><subfield code="2">rdamedia</subfield></datafield><datafield tag="338" ind1=" " ind2=" "><subfield code="a">Online-Ressource</subfield><subfield code="b">cr</subfield><subfield code="2">rdacarrier</subfield></datafield><datafield tag="520" ind1=" " ind2=" "><subfield code="a">Abstract In recent, smart grid has emerged as a promising technology to facilitate the future electric power grid and to balance between supply and demand. However, the intermittent nature of distributed energy resources causes dynamic uncertainties and nonlinearity in the smart grid environment. This may result in a large stress on power grid and has a big influence on energy planning, especially the generation and distribution. Therefore, energy load forecasting plays an important role in facilitating the operation of the future smart grid. Using the traditional statistical and machine learning approach there exists a significant forecasting error and high degree of overfitting. In this paper, we propose an energy load forecasting (ELF) model based on deep neural network architectures to manage the energy consumption in smart grids. First we investigate the applicability of two deep neural network architectures: deep feed-forward neural network (deep-FNN) and deep recurrent neural network (deep-RNN). To evaluate the models with low error, we simulate both architectures with multi size training set. Further, various activation functions and different combinations of hidden layer architectures are also tested. The simulation results are compared in terms of mean absolute percentage error. The results show that the proposed ELF model has attained better generalization and outperform the existing load forecasting models based on the shallow neural network, ensemble tree bagger and generalized linear regression.</subfield></datafield><datafield tag="650" ind1=" " ind2="4"><subfield code="a">Load forecasting</subfield><subfield code="7">(dpeaa)DE-He213</subfield></datafield><datafield tag="650" ind1=" " ind2="4"><subfield code="a">Deep neural network</subfield><subfield code="7">(dpeaa)DE-He213</subfield></datafield><datafield tag="650" ind1=" " ind2="4"><subfield code="a">Deep-feed-forward neural network</subfield><subfield code="7">(dpeaa)DE-He213</subfield></datafield><datafield tag="650" ind1=" " ind2="4"><subfield code="a">Deep-recurrent neural network</subfield><subfield code="7">(dpeaa)DE-He213</subfield></datafield><datafield tag="650" ind1=" " ind2="4"><subfield code="a">Activation function</subfield><subfield code="7">(dpeaa)DE-He213</subfield></datafield><datafield tag="650" ind1=" " ind2="4"><subfield code="a">Hidden layer</subfield><subfield code="7">(dpeaa)DE-He213</subfield></datafield><datafield tag="650" ind1=" " ind2="4"><subfield code="a">Levenberg–Marquardt algorithm</subfield><subfield code="7">(dpeaa)DE-He213</subfield></datafield><datafield tag="700" ind1="1" ind2=" "><subfield code="a">Kim, Young-Chon</subfield><subfield code="e">verfasserin</subfield><subfield code="4">aut</subfield></datafield><datafield tag="773" ind1="0" ind2="8"><subfield code="i">Enthalten in</subfield><subfield code="t">International Journal of Systems Assurance Engineering and Management</subfield><subfield code="d">Springer-Verlag, 2010</subfield><subfield code="g">11(2019), 4 vom: 06. Sept., Seite 824-834</subfield><subfield code="w">(DE-627)SPR031222420</subfield><subfield code="7">nnns</subfield></datafield><datafield tag="773" ind1="1" ind2="8"><subfield code="g">volume:11</subfield><subfield code="g">year:2019</subfield><subfield code="g">number:4</subfield><subfield code="g">day:06</subfield><subfield code="g">month:09</subfield><subfield code="g">pages:824-834</subfield></datafield><datafield tag="856" ind1="4" ind2="0"><subfield code="u">https://dx.doi.org/10.1007/s13198-019-00884-9</subfield><subfield code="z">lizenzpflichtig</subfield><subfield code="3">Volltext</subfield></datafield><datafield tag="912" ind1=" " ind2=" "><subfield code="a">GBV_USEFLAG_A</subfield></datafield><datafield tag="912" ind1=" " ind2=" "><subfield code="a">SYSFLAG_A</subfield></datafield><datafield tag="912" ind1=" " ind2=" "><subfield code="a">GBV_SPRINGER</subfield></datafield><datafield tag="951" ind1=" " ind2=" "><subfield code="a">AR</subfield></datafield><datafield tag="952" ind1=" " ind2=" "><subfield code="d">11</subfield><subfield code="j">2019</subfield><subfield code="e">4</subfield><subfield code="b">06</subfield><subfield code="c">09</subfield><subfield code="h">824-834</subfield></datafield></record></collection>
|
| score |
7.399684 |