Machine Learning Applied to the Operation of Fully Renewable Energy Systems
This work presents a novel learning algorithm for the operation policy of power systems trying to minimize the cost of fulfilling the energy demand. The algorithm improves upon the classical reinforcement learning methods by controlling the sampling variance in the estimation of the future cost spat...
Uloženo v:
| Vydáno v: | 2023 IEEE PES GTD International Conference and Exposition (GTD) s. 139 - 143 |
|---|---|
| Hlavní autoři: | , , |
| Médium: | Konferenční příspěvek |
| Jazyk: | angličtina |
| Vydáno: |
IEEE
01.05.2023
|
| Témata: | |
| On-line přístup: | Získat plný text |
| Tagy: |
Přidat tag
Žádné tagy, Buďte první, kdo vytvoří štítek k tomuto záznamu!
|
| Abstract | This work presents a novel learning algorithm for the operation policy of power systems trying to minimize the cost of fulfilling the energy demand. The algorithm improves upon the classical reinforcement learning methods by controlling the sampling variance in the estimation of the future cost spatial differences, together with parameter regularization and dynamic exploring techniques. The proposed strategy was applied to a case of what could be the power system of Uruguay by 2050 based strongly in hydro, wind and solar energies, including three lakes, four groups of battery banks, and the basin runoff of the two main Uruguayan rivers. The generation in the year 2022 in Uruguay was 43% hydraulic, 40% wind plus solar, 7% biomass and 10% based on fossil fuels. This composition prints a very relevant stochastic component that makes it difficult to apply machine learning techniques without the kind of algorihms proposed in this work. |
|---|---|
| AbstractList | This work presents a novel learning algorithm for the operation policy of power systems trying to minimize the cost of fulfilling the energy demand. The algorithm improves upon the classical reinforcement learning methods by controlling the sampling variance in the estimation of the future cost spatial differences, together with parameter regularization and dynamic exploring techniques. The proposed strategy was applied to a case of what could be the power system of Uruguay by 2050 based strongly in hydro, wind and solar energies, including three lakes, four groups of battery banks, and the basin runoff of the two main Uruguayan rivers. The generation in the year 2022 in Uruguay was 43% hydraulic, 40% wind plus solar, 7% biomass and 10% based on fossil fuels. This composition prints a very relevant stochastic component that makes it difficult to apply machine learning techniques without the kind of algorihms proposed in this work. |
| Author | Casaravilla, Gonzalo Ramirez, Ignacio Chaer, Ruben |
| Author_xml | – sequence: 1 givenname: Ruben surname: Chaer fullname: Chaer, Ruben email: rchaer@simsee.org organization: Universidad de la República and Electricity Market Administration,Facultad de Ingeniería,Montevideo,Uruguay – sequence: 2 givenname: Ignacio surname: Ramirez fullname: Ramirez, Ignacio email: nacho@fing.edu.uy organization: Universidad de la República,Facultad de Ingeniería,Montevideo,Uruguay – sequence: 3 givenname: Gonzalo surname: Casaravilla fullname: Casaravilla, Gonzalo email: gcp@fing.edu.uy organization: Universidad de la República,Facultad de Ingeniería,Montevideo,Uruguay |
| BookMark | eNotj91KwzAYQCPohc49gV7kBVq_L2ma5HLM_YiVgfZ-pO2XLdClpa1I396BXhzO3YHzwG5jF4mxJ4QUEezLrnzNrM5NKkDIFACUvGFLqw1qcQWEwnv2_uHqc4jEC3JDDPHEV33fBmr41PHpTPzQ0-Cm0EXeeb79btuZf1KkH1e1xDeRhtPMv-Zxosv4yO68a0da_nvByu2mXO-T4rB7W6-KJCDaKUHKfSOlkB7BaSWcr2xtK2W0dBqUzQCVrBok6VUm1XXBGWO8tbVWTZXLBXv-ywYiOvZDuLhhPiKIHHWeyV9xJEnK |
| CODEN | IEEPAD |
| ContentType | Conference Proceeding |
| DBID | 6IE 6IL CBEJK RIE RIL |
| DOI | 10.1109/GTD49768.2023.00053 |
| DatabaseName | IEEE Electronic Library (IEL) Conference Proceedings IEEE Proceedings Order Plan All Online (POP All Online) 1998-present by volume IEEE Xplore All Conference Proceedings IEEE Electronic Library (IEL) IEEE Proceedings Order Plans (POP All) 1998-Present |
| DatabaseTitleList | |
| Database_xml | – sequence: 1 dbid: RIE name: IEEE Xplore Digital Library url: https://ieeexplore.ieee.org/ sourceTypes: Publisher |
| DeliveryMethod | fulltext_linktorsrc |
| EISBN | 9781728170251 1728170257 |
| EndPage | 143 |
| ExternalDocumentID | 10261764 |
| Genre | orig-research |
| GroupedDBID | 6IE 6IL CBEJK RIE RIL |
| ID | FETCH-LOGICAL-i119t-1e6fd3323f10a752afb9c9b5873a705940153bd1e3f5435976a888f99c75db63 |
| IEDL.DBID | RIE |
| IngestDate | Wed Oct 04 09:12:49 EDT 2023 |
| IsPeerReviewed | false |
| IsScholarly | false |
| Language | English |
| LinkModel | DirectLink |
| MergedId | FETCHMERGED-LOGICAL-i119t-1e6fd3323f10a752afb9c9b5873a705940153bd1e3f5435976a888f99c75db63 |
| PageCount | 5 |
| ParticipantIDs | ieee_primary_10261764 |
| PublicationCentury | 2000 |
| PublicationDate | 2023-May |
| PublicationDateYYYYMMDD | 2023-05-01 |
| PublicationDate_xml | – month: 05 year: 2023 text: 2023-May |
| PublicationDecade | 2020 |
| PublicationTitle | 2023 IEEE PES GTD International Conference and Exposition (GTD) |
| PublicationTitleAbbrev | GTD |
| PublicationYear | 2023 |
| Publisher | IEEE |
| Publisher_xml | – name: IEEE |
| Score | 1.8303386 |
| Snippet | This work presents a novel learning algorithm for the operation policy of power systems trying to minimize the cost of fulfilling the energy demand. The... |
| SourceID | ieee |
| SourceType | Publisher |
| StartPage | 139 |
| SubjectTerms | Approximate Stochastic Dynamic Programming Costs Heuristic algorithms Lakes Power system dynamics Reinforcement learning Reinforcement Machine Learning Renewable Energies Solar energy Stochastic processes |
| Title | Machine Learning Applied to the Operation of Fully Renewable Energy Systems |
| URI | https://ieeexplore.ieee.org/document/10261764 |
| hasFullText | 1 |
| inHoldings | 1 |
| isFullTextHit | |
| isPrint | |
| link | http://cvtisr.summon.serialssolutions.com/2.0.0/link/0/eLvHCXMwlV09T8MwED3RioEJEEF8ywNrII7jOJ6hBQlRKpShWxXHd6hLU5UUxL_HdsLHwsBmebF0Z_vd2ffeAVyajIwka2NJXHpRbRkbyjDm5DaDQVmQoNBsQk0mxWympz1ZPXBhEDEUn-GVH4a_fNvUG_9U5k641w_PswEMlMo7slavJMQTfX1X3mYOXX3BVup1SxPf8fhXz5QAGePdfy62B9EP-Y5Nv2FlH7ZweQAPj6HoEVmvh_rC-vCRtQ1zMRx7WmHnS9YQ83nlB3t219i7Z0axUSD4sV6dPIJyPCpv7uO-D0K84Fy3McecrBCpIJ5USqYVGV1rIwslKuX1VhykC2M5CpIu-nEmqFxeS1rXSlqTi0MYLpslHgHTNaWFza0DpTRzkWBB5Ad1Lg2ZBO0xRN4Q81WndDH_ssHJH_OnsONt3RUAnsGwXW_wHLbrt3bxur4I_vkEaW6S_g |
| linkProvider | IEEE |
| linkToHtml | http://cvtisr.summon.serialssolutions.com/2.0.0/link/0/eLvHCXMwlV09T8MwED1BQYIJEEV844E1EMd2Es_QUtQ2VChDtyqOfahLU5UUxL_HdsLHwsBmebF0Z_vd2ffeAVwrjkqg1oFAKpyotggUchNQtJtBGZEiQ99sIsmydDqVk5as7rkwxhhffGZu3ND_5euqXLunMnvCnX54zDdhS3AehQ1dq9USoqG8fcjvucVXV7IVOeXS0PU8_tU1xYNGf--fy-1D94d-RybfwHIAG2ZxCMOxL3s0pFVEfSFtAEnqitgojjwtTeNNUiFxmeUHebYX2bvjRpGep_iRVp-8C3m_l98NgrYTQjCnVNYBNTFqxiKGNCwSERWoZCmVSBNWJE5xxYI6U5oahsLGP9YEhc1sUcoyEVrF7Ag6i2phjoHIEqNUx9rCUsRtLJgiukEZC4UqNPoEus4Qs2WjdTH7ssHpH_NXsDPIx6PZ6DEbnsGus3tTDngOnXq1NhewXb7V89fVpffVJ0DIlkU |
| 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=2023+IEEE+PES+GTD+International+Conference+and+Exposition+%28GTD%29&rft.atitle=Machine+Learning+Applied+to+the+Operation+of+Fully+Renewable+Energy+Systems&rft.au=Chaer%2C+Ruben&rft.au=Ramirez%2C+Ignacio&rft.au=Casaravilla%2C+Gonzalo&rft.date=2023-05-01&rft.pub=IEEE&rft.spage=139&rft.epage=143&rft_id=info:doi/10.1109%2FGTD49768.2023.00053&rft.externalDocID=10261764 |