Locational marginal price forecasting using svr-based multi-output regression in electricity markets
Electricity markets provide valuable data for regulators, operators, and investors. The use of machine learning methods for electricity market data could provide new insights about the market, and this information could be used for decision-making. This paper proposes a tool based on multi-output re...
- Autores:
-
Moreno Chuquen, Ricardo
Chamorro, Harold R.
Riquelme Domínguez, José Miguel
González Longatt, Francisco
Cantillo Luna, Sergio Alejandro
- Tipo de recurso:
- Article of journal
- Fecha de publicación:
- 2022
- Institución:
- Universidad Autónoma de Occidente
- Repositorio:
- RED: Repositorio Educativo Digital UAO
- Idioma:
- eng
- OAI Identifier:
- oai:red.uao.edu.co:10614/14654
- Acceso en línea:
- https://hdl.handle.net/10614/14654
https://red.uao.edu.co/
- Palabra clave:
- Aprendizaje profundo (Aprendizaje automático)
Deep learning (Machine learning)
Electricity markets
Llocational marginal price (LMP)
Machine learning
Multi-output regression
- Rights
- openAccess
- License
- Derechos Reservados Revista Energies MDPI
| id |
REPOUAO2_d1b41ac55f185c4f565fa86f3c020af7 |
|---|---|
| oai_identifier_str |
oai:red.uao.edu.co:10614/14654 |
| network_acronym_str |
REPOUAO2 |
| network_name_str |
RED: Repositorio Educativo Digital UAO |
| repository_id_str |
|
| dc.title.eng.fl_str_mv |
Locational marginal price forecasting using svr-based multi-output regression in electricity markets |
| title |
Locational marginal price forecasting using svr-based multi-output regression in electricity markets |
| spellingShingle |
Locational marginal price forecasting using svr-based multi-output regression in electricity markets Aprendizaje profundo (Aprendizaje automático) Deep learning (Machine learning) Electricity markets Llocational marginal price (LMP) Machine learning Multi-output regression |
| title_short |
Locational marginal price forecasting using svr-based multi-output regression in electricity markets |
| title_full |
Locational marginal price forecasting using svr-based multi-output regression in electricity markets |
| title_fullStr |
Locational marginal price forecasting using svr-based multi-output regression in electricity markets |
| title_full_unstemmed |
Locational marginal price forecasting using svr-based multi-output regression in electricity markets |
| title_sort |
Locational marginal price forecasting using svr-based multi-output regression in electricity markets |
| dc.creator.fl_str_mv |
Moreno Chuquen, Ricardo Chamorro, Harold R. Riquelme Domínguez, José Miguel González Longatt, Francisco Cantillo Luna, Sergio Alejandro |
| dc.contributor.author.none.fl_str_mv |
Moreno Chuquen, Ricardo Chamorro, Harold R. Riquelme Domínguez, José Miguel González Longatt, Francisco Cantillo Luna, Sergio Alejandro |
| dc.subject.armarc.spa.fl_str_mv |
Aprendizaje profundo (Aprendizaje automático) |
| topic |
Aprendizaje profundo (Aprendizaje automático) Deep learning (Machine learning) Electricity markets Llocational marginal price (LMP) Machine learning Multi-output regression |
| dc.subject.armarc.eng.fl_str_mv |
Deep learning (Machine learning) |
| dc.subject.proposal.eng.fl_str_mv |
Electricity markets Llocational marginal price (LMP) Machine learning Multi-output regression |
| description |
Electricity markets provide valuable data for regulators, operators, and investors. The use of machine learning methods for electricity market data could provide new insights about the market, and this information could be used for decision-making. This paper proposes a tool based on multi-output regression method using support vector machines (SVR) for LMP forecasting. The input corresponds to the active power load of each bus, in this case obtained through Monte Carlo simulations, in order to forecast LMPs. The LMPs provide market signals for investors and regulators. The results showed the high performance of the proposed model, since the average prediction error for fitting and testing datasets of the proposed method on the dataset was less than 1%. This provides insights into the application of machine learning method for electricity markets given the context of uncertainty and volatility for either real-time and ahead markets |
| publishDate |
2022 |
| dc.date.issued.none.fl_str_mv |
2022 |
| dc.date.accessioned.none.fl_str_mv |
2023-04-10T20:30:40Z |
| dc.date.available.none.fl_str_mv |
2023-04-10T20:30:40Z |
| dc.type.spa.fl_str_mv |
Artículo de revista |
| dc.type.coar.fl_str_mv |
http://purl.org/coar/resource_type/c_2df8fbb1 |
| dc.type.coarversion.fl_str_mv |
http://purl.org/coar/version/c_970fb48d4fbd8a85 |
| dc.type.coar.eng.fl_str_mv |
http://purl.org/coar/resource_type/c_6501 |
| dc.type.content.eng.fl_str_mv |
Text |
| dc.type.driver.eng.fl_str_mv |
info:eu-repo/semantics/article |
| dc.type.redcol.eng.fl_str_mv |
http://purl.org/redcol/resource_type/ART |
| dc.type.version.eng.fl_str_mv |
info:eu-repo/semantics/publishedVersion |
| format |
http://purl.org/coar/resource_type/c_6501 |
| status_str |
publishedVersion |
| dc.identifier.issn.spa.fl_str_mv |
1996-1073 |
| dc.identifier.uri.none.fl_str_mv |
https://hdl.handle.net/10614/14654 |
| dc.identifier.instname.spa.fl_str_mv |
Universidad Autónoma de Occidente |
| dc.identifier.reponame.spa.fl_str_mv |
Repositorio Educativo Digital |
| dc.identifier.repourl.spa.fl_str_mv |
https://red.uao.edu.co/ |
| identifier_str_mv |
1996-1073 Universidad Autónoma de Occidente Repositorio Educativo Digital |
| url |
https://hdl.handle.net/10614/14654 https://red.uao.edu.co/ |
| dc.language.iso.spa.fl_str_mv |
eng |
| language |
eng |
| dc.relation.citationendpage.spa.fl_str_mv |
14 |
| dc.relation.citationissue.spa.fl_str_mv |
1 |
| dc.relation.citationstartpage.spa.fl_str_mv |
1 |
| dc.relation.citationvolume.spa.fl_str_mv |
15 |
| dc.relation.cites.spa.fl_str_mv |
Cantillo Luna, S.,; Moreno Chuquen, R.; Chamorro, H.R.; Riquelme Domínguez, J.M;, González Longatt, F. (2022). Locational marginal price forecasting using svr-based multi-output regression in electricity markets. Energies. 15 (1), 1-14. https://hdl.handle.net/10614/14654 |
| dc.relation.ispartofjournal.eng.fl_str_mv |
Energies |
| dc.relation.references.none.fl_str_mv |
Orfanogianni, T.; Gross, G. A General Formulation for LMP Evaluation. IEEE Trans. Power Syst. 2007, 22, 1163–1173 Zheng, K.; Wang, Y.; Liu, K.; Chen, Q. Locational Marginal Price Forecasting: A Componential and Ensemble Approach. IEEE Trans. Smart Grid 2020, 11, 4555–4564 Nesti, T.; Moriarty, J.; Zocca, A.; Zwart, B. Large fluctuations in locational marginal prices. Philos. Trans. R. Soc. A 2021, 379, 20190438. Yang, Y.; Tan, Z.; Yang, H.; Ruan, G.; Zhong, H. Short-Term Electricity Price Forecasting based on Graph Convolution Network and Attention Mechanism. arXiv 2021, arXiv:2107.12794. Moreno, R.; Obando, J.; Gonzalez, G. An integrated OPF dispatching model with wind power and demand response for day-ahead markets. Int. J. Electr. Comput. Eng. 2019, 9, 2794–2802. Moreno-Chuquen, R.; Cantillo, S. Assessment of a Multiperiod Optimal Power Flow for Power System Operation. Int. Rev. Electr. Eng. 2020, 15, 484–492. Lago, J.; Ridder, F.D.; Vrancx, P.; Schuttera, B.D. Forecasting day-ahead electricity prices in Europe: The importance of considering market integration. Appl. Energy 2018, 211, 890–903. Cheng, H.; Ding, X.; Zhou, W.; Ding, R. A hybrid electricity price forecasting model with Bayesian optimization for German energy exchange. Int. J. Electr. Power Energy Syst. 2019, 100, 653–666. Wang, D.; Yue, C.; ElAmraouid, A. Multi-step-ahead electricity load forecasting using a novel hybrid architecture with decomposition-based error correction strategy. Chaos Solitons Fractals 2021, 152, 111453 Hong, Y.Y.; Taylar, J.V.; Fajardo, A.C. Locational marginal price forecasting in a day-ahead power market using spatiotemporal deep learning network. Sustain. Energy Grids Netw. 2020, 24, 100406 Bernardi, M.; Lisi, F. Point and Interval Forecasting of Zonal Electricity Prices and Demand Using Heteroscedastic Models: The IPEX Case. Energies 2020, 13, 6191 Colella, P.; Mazza, A.; Bompard, E.; Chicco, G.; Russo, A.; Carlini, E.M.; Caprabianca, M.; Quaglia, F.; Luzi, L.; Nuzzo, G. Model-Based Identification of Alternative Bidding Zones: Applications of Clustering Algorithms with Topology Constraints. Energies 2021, 14, 2763 Chuquen, R.M.; Chamorro, H.R. Graph Theory Applications to Deregulated Power Systems; Springer International Publishing: Berlin, Germany, 2021 Germany, 2021. [CrossRef] 25. Ahmad, W.; Ayub, N.; Ali, T.; Irfan, M.; Awais, M.; Shiraz, M.; Glowacz, A. Towards Short Term Electricity Load Forecasting Using Improved Support Vector Machine and Extreme Learning Machine. Energies 2020, 13, 2907. [ Ma, Z.; Zhong, H.; Xie, L.; Xia, Q.; Kang, C. Month ahead average daily electricity price profile forecasting based on a hybrid nonlinear regression and SVM model: An ERCOT case study. J. Mod. Power Syst. Clean Energy 2018, 6, 281–291. Atef, S.; Eltawil, A.B. A Comparative Study Using Deep Learning and Support Vector Regression for Electricity Price Forecasting in Smart Grids; IEEE: Piscataway, NJ, USA, 2019. Zhang, Z.; Wu, M. Real-time Locational Marginal Price Forecasting Using Generative Adversarial Network. In Proceedings of the 2020 IEEE International Conference on Communications, Control, and Computing Technologies for Smart Grids, Tempe, AZ, USA, 11–13 November 2020 Pedregosa, F.; Varoquaux, G.; Gramfort, A.; Michel, V.; Thirion, B.; Grisel, O.; Blondel, M.; Prettenhofer, P.; Weiss, R.; Dubourg, V.; et al. Scikit-learn: Machine Learning in Python. J. Mach. Learn. Res. 2011, 12, 2825–2830. Department of Electrical Engineering, University of Washington. Power Systems Test Case Archive; Department of Electrical Engineering, University of Washington: Washington, DC, USA, 2021. Available online: http://labs.ece.uw.edu/pstca/ (accessed on 15 October 2021) |
| dc.rights.eng.fl_str_mv |
Derechos Reservados Revista Energies MDPI Derechos reservados - MDPI, 2022 |
| dc.rights.coar.fl_str_mv |
http://purl.org/coar/access_right/c_abf2 |
| dc.rights.uri.eng.fl_str_mv |
https://creativecommons.org/licenses/by-nc-nd/4.0/ |
| dc.rights.accessrights.eng.fl_str_mv |
info:eu-repo/semantics/openAccess |
| dc.rights.creativecommons.spa.fl_str_mv |
Atribución-NoComercial-SinDerivadas 4.0 Internacional (CC BY-NC-ND 4.0) |
| rights_invalid_str_mv |
Derechos Reservados Revista Energies MDPI Derechos reservados - MDPI, 2022 https://creativecommons.org/licenses/by-nc-nd/4.0/ Atribución-NoComercial-SinDerivadas 4.0 Internacional (CC BY-NC-ND 4.0) http://purl.org/coar/access_right/c_abf2 |
| eu_rights_str_mv |
openAccess |
| dc.format.extent.spa.fl_str_mv |
14 páginas |
| dc.format.mimetype.eng.fl_str_mv |
application/pdf |
| dc.publisher.spa.fl_str_mv |
MDPI |
| dc.publisher.place.spa.fl_str_mv |
Basel, Switzerland |
| institution |
Universidad Autónoma de Occidente |
| bitstream.url.fl_str_mv |
https://red.uao.edu.co/bitstreams/509c558b-2a91-49ec-a8de-4ffd4b5b2cfd/download https://red.uao.edu.co/bitstreams/9a486336-73b9-46b2-97ba-0f9e61413b94/download https://red.uao.edu.co/bitstreams/c2d17b29-de5d-4c11-9a58-6843ef102692/download https://red.uao.edu.co/bitstreams/8bcca521-3d2b-4463-85c4-0f758be88a72/download |
| bitstream.checksum.fl_str_mv |
1611b9bc3dbe3ffe244ca3321ba71f69 20b5ba22b1117f71589c7318baa2c560 f4fa4602b46f2b949dd6284b89b2f9d5 fd896f6f7069f1e9f3d0c84b6f7cfbc2 |
| bitstream.checksumAlgorithm.fl_str_mv |
MD5 MD5 MD5 MD5 |
| repository.name.fl_str_mv |
Repositorio Digital Universidad Autonoma de Occidente |
| repository.mail.fl_str_mv |
repositorio@uao.edu.co |
| _version_ |
1828230004203323392 |
| spelling |
Moreno Chuquen, Ricardo1ba55dc18211144016950d3899f50db9Chamorro, Harold R.4b08e14f56fb217874cde66f1d371352Riquelme Domínguez, José Miguelde4850f9f87bb692d72e823dce067e78González Longatt, Franciscoec8bc0be4b0326276b38da3c5b3de173Cantillo Luna, Sergio Alejandro 2023-04-10T20:30:40Z2023-04-10T20:30:40Z20221996-1073https://hdl.handle.net/10614/14654Universidad Autónoma de OccidenteRepositorio Educativo Digitalhttps://red.uao.edu.co/Electricity markets provide valuable data for regulators, operators, and investors. The use of machine learning methods for electricity market data could provide new insights about the market, and this information could be used for decision-making. This paper proposes a tool based on multi-output regression method using support vector machines (SVR) for LMP forecasting. The input corresponds to the active power load of each bus, in this case obtained through Monte Carlo simulations, in order to forecast LMPs. The LMPs provide market signals for investors and regulators. The results showed the high performance of the proposed model, since the average prediction error for fitting and testing datasets of the proposed method on the dataset was less than 1%. This provides insights into the application of machine learning method for electricity markets given the context of uncertainty and volatility for either real-time and ahead markets 14 páginasapplication/pdfengMDPIBasel, SwitzerlandDerechos Reservados Revista Energies MDPIDerechos reservados - MDPI, 2022https://creativecommons.org/licenses/by-nc-nd/4.0/info:eu-repo/semantics/openAccessAtribución-NoComercial-SinDerivadas 4.0 Internacional (CC BY-NC-ND 4.0)http://purl.org/coar/access_right/c_abf2Locational marginal price forecasting using svr-based multi-output regression in electricity marketsArtículo de revistahttp://purl.org/coar/resource_type/c_6501http://purl.org/coar/resource_type/c_2df8fbb1Textinfo:eu-repo/semantics/articlehttp://purl.org/redcol/resource_type/ARTinfo:eu-repo/semantics/publishedVersionhttp://purl.org/coar/version/c_970fb48d4fbd8a85Aprendizaje profundo (Aprendizaje automático)Deep learning (Machine learning)Electricity marketsLlocational marginal price (LMP)Machine learningMulti-output regression141115Cantillo Luna, S.,; Moreno Chuquen, R.; Chamorro, H.R.; Riquelme Domínguez, J.M;, González Longatt, F. (2022). Locational marginal price forecasting using svr-based multi-output regression in electricity markets. Energies. 15 (1), 1-14. https://hdl.handle.net/10614/14654EnergiesOrfanogianni, T.; Gross, G. A General Formulation for LMP Evaluation. IEEE Trans. Power Syst. 2007, 22, 1163–1173Zheng, K.; Wang, Y.; Liu, K.; Chen, Q. Locational Marginal Price Forecasting: A Componential and Ensemble Approach. IEEE Trans. Smart Grid 2020, 11, 4555–4564Nesti, T.; Moriarty, J.; Zocca, A.; Zwart, B. Large fluctuations in locational marginal prices. Philos. Trans. R. Soc. A 2021, 379, 20190438.Yang, Y.; Tan, Z.; Yang, H.; Ruan, G.; Zhong, H. Short-Term Electricity Price Forecasting based on Graph Convolution Network and Attention Mechanism. arXiv 2021, arXiv:2107.12794.Moreno, R.; Obando, J.; Gonzalez, G. An integrated OPF dispatching model with wind power and demand response for day-ahead markets. Int. J. Electr. Comput. Eng. 2019, 9, 2794–2802.Moreno-Chuquen, R.; Cantillo, S. Assessment of a Multiperiod Optimal Power Flow for Power System Operation. Int. Rev. Electr. Eng. 2020, 15, 484–492.Lago, J.; Ridder, F.D.; Vrancx, P.; Schuttera, B.D. Forecasting day-ahead electricity prices in Europe: The importance of considering market integration. Appl. Energy 2018, 211, 890–903.Cheng, H.; Ding, X.; Zhou, W.; Ding, R. A hybrid electricity price forecasting model with Bayesian optimization for German energy exchange. Int. J. Electr. Power Energy Syst. 2019, 100, 653–666.Wang, D.; Yue, C.; ElAmraouid, A. Multi-step-ahead electricity load forecasting using a novel hybrid architecture with decomposition-based error correction strategy. Chaos Solitons Fractals 2021, 152, 111453Hong, Y.Y.; Taylar, J.V.; Fajardo, A.C. Locational marginal price forecasting in a day-ahead power market using spatiotemporal deep learning network. Sustain. Energy Grids Netw. 2020, 24, 100406Bernardi, M.; Lisi, F. Point and Interval Forecasting of Zonal Electricity Prices and Demand Using Heteroscedastic Models: The IPEX Case. Energies 2020, 13, 6191Colella, P.; Mazza, A.; Bompard, E.; Chicco, G.; Russo, A.; Carlini, E.M.; Caprabianca, M.; Quaglia, F.; Luzi, L.; Nuzzo, G. Model-Based Identification of Alternative Bidding Zones: Applications of Clustering Algorithms with Topology Constraints. Energies 2021, 14, 2763Chuquen, R.M.; Chamorro, H.R. Graph Theory Applications to Deregulated Power Systems; Springer International Publishing: Berlin, Germany, 2021Germany, 2021. [CrossRef] 25. Ahmad, W.; Ayub, N.; Ali, T.; Irfan, M.; Awais, M.; Shiraz, M.; Glowacz, A. Towards Short Term Electricity Load Forecasting Using Improved Support Vector Machine and Extreme Learning Machine. Energies 2020, 13, 2907. [Ma, Z.; Zhong, H.; Xie, L.; Xia, Q.; Kang, C. Month ahead average daily electricity price profile forecasting based on a hybrid nonlinear regression and SVM model: An ERCOT case study. J. Mod. Power Syst. Clean Energy 2018, 6, 281–291.Atef, S.; Eltawil, A.B. A Comparative Study Using Deep Learning and Support Vector Regression for Electricity Price Forecasting in Smart Grids; IEEE: Piscataway, NJ, USA, 2019.Zhang, Z.; Wu, M. Real-time Locational Marginal Price Forecasting Using Generative Adversarial Network. In Proceedings of the 2020 IEEE International Conference on Communications, Control, and Computing Technologies for Smart Grids, Tempe, AZ, USA, 11–13 November 2020Pedregosa, F.; Varoquaux, G.; Gramfort, A.; Michel, V.; Thirion, B.; Grisel, O.; Blondel, M.; Prettenhofer, P.; Weiss, R.; Dubourg, V.; et al. Scikit-learn: Machine Learning in Python. J. Mach. Learn. Res. 2011, 12, 2825–2830.Department of Electrical Engineering, University of Washington. Power Systems Test Case Archive; Department of Electrical Engineering, University of Washington: Washington, DC, USA, 2021. Available online: http://labs.ece.uw.edu/pstca/ (accessed on 15 October 2021)Comunidad generalPublicationORIGINALLocational marginal price forecasting using svr-based multi-output regression in electricity markets.pdfLocational marginal price forecasting using svr-based multi-output regression in electricity markets.pdfTexto archivo completo del artículo de revista, PDFapplication/pdf6198259https://red.uao.edu.co/bitstreams/509c558b-2a91-49ec-a8de-4ffd4b5b2cfd/download1611b9bc3dbe3ffe244ca3321ba71f69MD51LICENSElicense.txtlicense.txttext/plain; charset=utf-81665https://red.uao.edu.co/bitstreams/9a486336-73b9-46b2-97ba-0f9e61413b94/download20b5ba22b1117f71589c7318baa2c560MD52TEXTLocational marginal price forecasting using svr-based multi-output regression in electricity markets.pdf.txtLocational marginal price forecasting using svr-based multi-output regression in electricity markets.pdf.txtExtracted texttext/plain36633https://red.uao.edu.co/bitstreams/c2d17b29-de5d-4c11-9a58-6843ef102692/downloadf4fa4602b46f2b949dd6284b89b2f9d5MD53THUMBNAILLocational marginal price forecasting using svr-based multi-output regression in electricity markets.pdf.jpgLocational marginal price forecasting using svr-based multi-output regression in electricity markets.pdf.jpgGenerated Thumbnailimage/jpeg15875https://red.uao.edu.co/bitstreams/8bcca521-3d2b-4463-85c4-0f758be88a72/downloadfd896f6f7069f1e9f3d0c84b6f7cfbc2MD5410614/14654oai:red.uao.edu.co:10614/146542024-04-01 09:48:21.279https://creativecommons.org/licenses/by-nc-nd/4.0/Derechos Reservados Revista Energies MDPIopen.accesshttps://red.uao.edu.coRepositorio Digital Universidad Autonoma de Occidenterepositorio@uao.edu.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 |