Short term net load forecasting using computational intelligence techniques

Net load forecasting has become increasingly complex due to the high penetration of renewables and evolving data subject to so-called concept drift, i.e., sudden and large changes in the energy flow pattern. Accurate net load forecasting is essential to prevent unexpected imbalances across all volta...

Celý popis

Uložené v:
Podrobná bibliografia
Vydané v:7th E-Mobility Power System Integration Symposium (EMOB 2023) Ročník 2023; s. 139 - 145
Hlavní autori: Laouali, I. H., Italiano, N., Casaleiro, Â., Alvite, I., da Silva, N. P.
Médium: Konferenčný príspevok..
Jazyk:English
Vydavateľské údaje: The Institution of Engineering and Technology 2023
On-line prístup:Získať plný text
Tagy: Pridať tag
Žiadne tagy, Buďte prvý, kto otaguje tento záznam!
Abstract Net load forecasting has become increasingly complex due to the high penetration of renewables and evolving data subject to so-called concept drift, i.e., sudden and large changes in the energy flow pattern. Accurate net load forecasting is essential to prevent unexpected imbalances across all voltage levels of the electricity grid, as well as to promote the stability and reliability of the power system. Therefore, the use of accurate forecasting techniques is essential to manage and optimize the use of available resources at the TSO-DSO interface. This paper evaluates several forecasting methods, including an adaptive random forest method based on incremental learning incorporating a drift detector, a method based on a recurrent neural network using long short-term memory (LSTM), and a method based on an ensemble of models including decision trees (DT), support vector machines (SVM), extreme gradient boosting algorithms (XGBoost), and Lasso regressions. The experiment was conducted using the net load data collected at the TSO-DSO interface in Portugal, where concept drift can be observed, possibly due to increasing integration of distributed energy resources behind the meter. The study examined two scenarios. In the first scenario, the models were trained using a large training set that included significant drifts, while in the second scenario, the models were trained prior to the occurrence of the drifts. The results showed that the approach using the adaptive model is more robust to the concept drift and performs better compared to the other traditional methods, especially in scenarios where there are significant changes in the net load patterns over time.
AbstractList Net load forecasting has become increasingly complex due to the high penetration of renewables and evolving data subject to so-called concept drift, i.e., sudden and large changes in the energy flow pattern. Accurate net load forecasting is essential to prevent unexpected imbalances across all voltage levels of the electricity grid, as well as to promote the stability and reliability of the power system. Therefore, the use of accurate forecasting techniques is essential to manage and optimize the use of available resources at the TSO-DSO interface. This paper evaluates several forecasting methods, including an adaptive random forest method based on incremental learning incorporating a drift detector, a method based on a recurrent neural network using long short-term memory (LSTM), and a method based on an ensemble of models including decision trees (DT), support vector machines (SVM), extreme gradient boosting algorithms (XGBoost), and Lasso regressions. The experiment was conducted using the net load data collected at the TSO-DSO interface in Portugal, where concept drift can be observed, possibly due to increasing integration of distributed energy resources behind the meter. The study examined two scenarios. In the first scenario, the models were trained using a large training set that included significant drifts, while in the second scenario, the models were trained prior to the occurrence of the drifts. The results showed that the approach using the adaptive model is more robust to the concept drift and performs better compared to the other traditional methods, especially in scenarios where there are significant changes in the net load patterns over time.
Author da Silva, N. P.
Italiano, N.
Alvite, I.
Laouali, I. H.
Casaleiro, Â.
Author_xml – sequence: 1
  givenname: I. H.
  surname: Laouali
  fullname: Laouali, I. H.
  email: inoussa.laouali@rdnester.com
  organization: R&D Nester, Centro de Investigação em Energia REN - State Grid, S.A., Lisbon, Portugal
– sequence: 2
  givenname: N.
  surname: Italiano
  fullname: Italiano, N.
  organization: R&D Nester, Centro de Investigação em Energia REN - State Grid, S.A., Lisbon, Portugal
– sequence: 3
  givenname: Â.
  surname: Casaleiro
  fullname: Casaleiro, Â.
  organization: R&D Nester, Centro de Investigação em Energia REN - State Grid, S.A., Lisbon, Portugal
– sequence: 4
  givenname: I.
  surname: Alvite
  fullname: Alvite, I.
  organization: R&D Nester, Centro de Investigação em Energia REN - State Grid, S.A., Lisbon, Portugal
– sequence: 5
  givenname: N. P.
  surname: da Silva
  fullname: da Silva, N. P.
  organization: R&D Nester, Centro de Investigação em Energia REN - State Grid, S.A., Lisbon, Portugal
BookMark eNotjLFOwzAURY0EElAysjH4BxLy_JI4b0QVUEQlBmCubOeltZTaIXEG_p4ikK7Omc69FuchBhbiFsoCyoruvRsLVSosVEPNmchIt9Ai1adpdSmyefa2rBF1DU19JV7fD3FKMvF0lIGTHKLpZB8ndmZOPuzlMv_SxeO4JJN8DGaQPiQeBr_n4PiUukPwXwvPN-KiN8PM2b9X4vPp8WO9ybdvzy_rh23uQFHK2aLuLHR102uFRLZXbOpOEyhTWuTKds6apoKGALG1RhlEJnCGFDEDrsTd369n5t04-aOZvndQoqoqQvwB3pBPfA
ContentType Conference Proceeding
DBID 6IE
6IF
6IG
6IH
6IL
6IM
6IN
CBEJK
RIE
RIL
RIO
DOI 10.1049/icp.2023.2696
DatabaseName IEEE Electronic Library (IEL) Conference Proceedings
IEEE Proceedings Order Plans (POP All) 2005-Present
IEEE Proceedings Order Plan (POP) 2005-present
IEEE Proceedings Order Plan (POP) 1998-present by volume
IEEE Xplore POP ALL
IEEE Proceedings Order Plan (POP) 2005-present by volume
IEEE Xplore POP ALL
IEEE Xplore All Conference Proceedings
IEEE Xplore
IEEE Proceedings Order Plans (POP All) 1998-Present
IEEE Proceedings Order Plans (POP) 1998-present
DatabaseTitleList
Database_xml – sequence: 1
  dbid: RIE
  name: IEEE Xplore
  url: https://ieeexplore.ieee.org/
  sourceTypes: Publisher
DeliveryMethod fulltext_linktorsrc
EISBN 9781839539572
1839539577
EndPage 145
ExternalDocumentID 10324493
Genre orig-research
GroupedDBID 6IE
6IF
6IG
6IH
6IL
6IM
6IN
ALMA_UNASSIGNED_HOLDINGS
BEFXN
BFFAM
BGNUA
BKEBE
BPEOZ
CBEJK
OCL
RIE
RIL
RIO
ID FETCH-LOGICAL-c129t-eb37db1d56f72399bf2ea5d7912a0b3e4bdcba641691338ba2a33e91ca929ee13
IEDL.DBID RIE
IngestDate Wed Oct 30 05:48:38 EDT 2024
IsPeerReviewed false
IsScholarly false
Language English
LinkModel DirectLink
MergedId FETCHMERGED-LOGICAL-c129t-eb37db1d56f72399bf2ea5d7912a0b3e4bdcba641691338ba2a33e91ca929ee13
PageCount 7
ParticipantIDs ieee_primary_10324493
PublicationCentury 2000
PublicationDate 2023-00-00
PublicationDateYYYYMMDD 2023-01-01
PublicationDate_xml – year: 2023
  text: 2023-00-00
PublicationDecade 2020
PublicationTitle 7th E-Mobility Power System Integration Symposium (EMOB 2023)
PublicationTitleAbbrev EMOB 2023
PublicationYear 2023
Publisher The Institution of Engineering and Technology
Publisher_xml – name: The Institution of Engineering and Technology
SSID ssib053375165
Score 1.8182507
Snippet Net load forecasting has become increasingly complex due to the high penetration of renewables and evolving data subject to so-called concept drift, i.e.,...
SourceID ieee
SourceType Publisher
StartPage 139
Title Short term net load forecasting using computational intelligence techniques
URI https://ieeexplore.ieee.org/document/10324493
Volume 2023
hasFullText 1
inHoldings 1
isFullTextHit
isPrint
link http://cvtisr.summon.serialssolutions.com/2.0.0/link/0/eLvHCXMwlZ1LS8NAEMcHWzx4UjHimz14TdtsHpucxSIopeCD3sruZqIBSaRJ_fzObNLWiwdvIQQCs9nMf2ZnfgNwG6SGmY-Zb2Kd-qRvpW8wCClK4SIMWcjEzSF7e1KzWbpYZPO-Wd31wiCiKz7DEV-6s_y8tmtOlY0Z_hZFWTiAgVKqa9bafDwkW1QcJHHP0SThOy4tAyllOJKJY_Lvpqc45zE9_Odrj8DbteGJ-dbBHMMeVifw-PxBilnwH1VU2IrPWueClCda3XAJs-BK9ndh3bSGPtMnyl_gTbHFtjYevE7vX-4e_H4igm_JL7c-Rb4qN0EeJ4XiplRTSNRxrrJA6okJMTK5NTqJmIBDsafRUochZoHVpIKQ1uAUhlVd4RmIWFrDp5p2kqUR-Xl6IEXa_kiKgplj5-CxJZZfHfRiuTHCxR_3L-GAbd1lJ65g2K7WeA379rstm9WNW6ofwVyVfQ
linkProvider IEEE
linkToHtml http://cvtisr.summon.serialssolutions.com/2.0.0/link/0/eLvHCXMwlZ1NSwMxEIYHrYKeVKz4bQ5et22ym_04i6XSWgpW6a0k2akWZCvt1t_vTLptvXjwtiwLgcmSeWcy8wzAvUwtMx-zwGqTBqRvVWBRhhSlcBGGmqjYzyF76yX9fjoaZYOqWd33wiCiLz7DBj_6u_x85pacKmsy_C2KsnAX9nQUKblq11r_PiRcEi1jXZE0Sfo2p46RlCpsqNhT-bfzU7z7aB_9c-FjqG8b8cRg42JOYAeLU-i-fJBmFnymigJL8TkzuSDtic4suIhZcC37u3B-XkOV6xPTX-hNsQG3Lurw2n4cPnSCaiZC4MgzlwHFvkluZa7jScJtqXai0Og8yaQyLRtiZHNnTRwxA4eiT2uUCUPMpDOkg5B24QxqxazAcxBaOcv3mq6VpWTMlD5IkQ4AJE3B1LELqLMlxl8r7MV4bYTLP97fwUFn-Nwb95763Ss4ZLuvchXXUCvnS7yBffddThfzW79tP7dPmMQ
openUrl ctx_ver=Z39.88-2004&ctx_enc=info%3Aofi%2Fenc%3AUTF-8&rfr_id=info%3Asid%2Fsummon.serialssolutions.com&rft_val_fmt=info%3Aofi%2Ffmt%3Akev%3Amtx%3Abook&rft.genre=proceeding&rft.title=7th+E-Mobility+Power+System+Integration+Symposium+%28EMOB+2023%29&rft.atitle=Short+term+net+load+forecasting+using+computational+intelligence+techniques&rft.au=Laouali%2C+I.+H.&rft.au=Italiano%2C+N.&rft.au=Casaleiro%2C+%C3%82.&rft.au=Alvite%2C+I.&rft.date=2023-01-01&rft.pub=The+Institution+of+Engineering+and+Technology&rft.volume=2023&rft.spage=139&rft.epage=145&rft_id=info:doi/10.1049%2Ficp.2023.2696&rft.externalDocID=10324493