Skip to main content

ELIMINANDO BARRERAS TECNICAS EN REDES CON ALTA PENETRACION DE RENOVABLES Y ELECTRONICA DE POTENCIA MEDIANTE DISPOSITIVOS STATCOM Y ENLACES HVDC BASADOS EN GRID-FORMING

PID2021-127788OA-I00

•
Funding agency name Agencia Estatal de Investigación
Funding agency acronym AEI
Program Programa Estatal para Impulsar la Investigación Científico-Técnica y su Transferencia
Subprogram Subprograma Estatal de Generación de Conocimiento
Call Proyectos de I+D+i (Generación de Conocimiento y Retos Investigación)
Call year 2021
State Plan 2021-2023 Plan Estatal de Investigación Científica y Técnica y de Innovación
Beneficiary centre UNIVERSITAT POLITECNICA DE CATALUNYA

Resultados relacionados

Resultados totales (Incluyendo duplicados): 4
Encontrada(s) 1 página(s)

UPCommons. Portal del coneixement obert de la UPC
Publication Contribución de congreso (ConferenceOutput)

Data generation methodology for machine learning-based power system stability studies

  • Rossi, Francesca
  • Prieto Araujo, Eduardo|||0000-0003-4349-5923
  • Cheah Mañé, Marc|||0000-0002-0942-661X
  • Gomis Bellmunt, Oriol|||0000-0002-9507-8278
© 2022 IEEE. Personal use of this material is permitted. Permission from IEEE must be obtained for all other uses, in any current or future media, including reprinting/republishing this material for advertising or promotional purposes, creating new collective works, for resale or redistribution to servers or lists, or reuse of any copyrighted component of this work in other works., This paper proposes a methodology for database generation for Machine Learning-based power system stability studies. Power system operable region is a high-multidimensional space, therefore, creating a good quality database for training accurate predictive ML models is a challenging task. A sampling strategy aimed to explore high-multidimensional spaces avoiding curse-of-dimensionality is proposed. The strategy is based on sampling into the whole operating region ,detecting the region of the space with high information content and biasing the sampling toward that space. The computing of the entropy function is used for the stability margin detection and information content quantification. Latin Hypercube Sampling is adopted for sampling in the multidimensional space.The study is presented through the application to a small-signal stability problem. An essential power system, representing a grid with low synchronous generation rated power and high penetration of converter interfaced generation technologies, is used as case study to validate the methodology. Data are generated with the proposed methodology and with a conventional brute force approach. The two databases are compared and used for ML models training. Both the possibility to train regression and classification models is tested., This work was supported by FEDER / Ministerio de Ciencia e Innovación - Agencia Estatal de Investigación, under the project REFORMING (PID2021-127788OA-I00). The work of O. Gomis was supported by the ICREA Academia program. The work of E. Prieto and M. Cheah was supported by Serra Húnter Program., Peer Reviewed
UPCommons. Portal del coneixement obert de la UPC
Publication Contribución de congreso (ConferenceOutput)

Converters control roles selection for operating hybrid AC/DC grids with enhanced small-signal stability performance

  • Rossi, Francesca
  • Costa Dilmé, Sergi|||0009-0007-6479-8671
  • Arévalo Soler, Josep
  • Gomis Bellmunt, Oriol|||0000-0002-9507-8278
  • Prieto Araujo, Eduardo|||0000-0003-4349-5923
© 2024 IEEE. Personal use of this material is permitted. Permission from IEEE must be obtained for all other uses, in any current or future media, including reprinting/republishing this material for advertising or promotional purposes, creating new collective works, for resale or redistribution to servers or lists, or reuse of any copyrighted component of this work in other works., In hybrid AC/DC grids, Interconnecting Power Converters (IPCs) can assume different control roles, mainly among grid-following and grid-forming. The various possibilities of roles assignment are in this study indicated as Converter Control Roles Configurations (CCRCs). Their number can become large, as it grows both with the number of considered control roles and the number of IPCs in the system. This adds complexity to the studies aimed at assessing the stability of hybrid AC/DC grids operation, as all the possible CCRCs have to be considered. This paper presents a methodology for selecting a subset of the CCRCs that allows the operation of the system with enhanced small-signal stability performance. Data mining techniques are employed for clustering the CCRCs according to their stability performance behavior in the system operable space and revealing explicitly the discovered pattern through a knowledge extraction process. To exemplify the proposed methodology, a test system made of three AC sub-grids and two DC sub-grids is used and a small-signal stability performance indicator measuring the voltage deviation in the DC grids is considered., This work was supported by FEDER / Ministerio de Ciencia e Innovación- Agencia Estatal de Investigación, under the project REFORMING (PID2021-127788OA-I00). The work of O. Gomis was supported by the ICREA Academia program. The work of E. Prieto and M. Cheah was supported by Serra Húnter Program.
Recercat. Dipósit de la Recerca de Catalunya
Publication Contribución de congreso (ConferenceOutput)

Data generation methodology for machine learning-based power system stability studies

  • Rossi, Francesca
  • Prieto Araujo, Eduardo
  • Cheah Mañé, Marc
  • Gomis Bellmunt, Oriol
© 2022 IEEE. Personal use of this material is permitted. Permission from IEEE must be obtained for all other uses, in any current or future media, including reprinting/republishing this material for advertising or promotional purposes, creating new collective works, for resale or redistribution to servers or lists, or reuse of any copyrighted component of this work in other works., This paper proposes a methodology for database generation for Machine Learning-based power system stability studies. Power system operable region is a high-multidimensional space, therefore, creating a good quality database for training accurate predictive ML models is a challenging task. A sampling strategy aimed to explore high-multidimensional spaces avoiding curse-of-dimensionality is proposed. The strategy is based on sampling into the whole operating region ,detecting the region of the space with high information content and biasing the sampling toward that space. The computing of the entropy function is used for the stability margin detection and information content quantification. Latin Hypercube Sampling is adopted for sampling in the multidimensional space.The study is presented through the application to a small-signal stability problem. An essential power system, representing a grid with low synchronous generation rated power and high penetration of converter interfaced generation technologies, is used as case study to validate the methodology. Data are generated with the proposed methodology and with a conventional brute force approach. The two databases are compared and used for ML models training. Both the possibility to train regression and classification models is tested., This work was supported by FEDER / Ministerio de Ciencia e Innovación - Agencia Estatal de Investigación, under the project REFORMING (PID2021-127788OA-I00). The work of O. Gomis was supported by the ICREA Academia program. The work of E. Prieto and M. Cheah was supported by Serra Húnter Program., Peer Reviewed, Postprint (author's final draft)
Recercat. Dipósit de la Recerca de Catalunya
Publication Contribución de congreso (ConferenceOutput)

Converters control roles selection for operating hybrid AC/DC grids with enhanced small-signal stability performance

  • Rossi, Francesca
  • Costa Dilmé, Sergi
  • Arévalo Soler, Josep
  • Gomis Bellmunt, Oriol
  • Prieto Araujo, Eduardo
© 2024 IEEE. Personal use of this material is permitted. Permission from IEEE must be obtained for all other uses, in any current or future media, including reprinting/republishing this material for advertising or promotional purposes, creating new collective works, for resale or redistribution to servers or lists, or reuse of any copyrighted component of this work in other works., In hybrid AC/DC grids, Interconnecting Power Converters (IPCs) can assume different control roles, mainly among grid-following and grid-forming. The various possibilities of roles assignment are in this study indicated as Converter Control Roles Configurations (CCRCs). Their number can become large, as it grows both with the number of considered control roles and the number of IPCs in the system. This adds complexity to the studies aimed at assessing the stability of hybrid AC/DC grids operation, as all the possible CCRCs have to be considered. This paper presents a methodology for selecting a subset of the CCRCs that allows the operation of the system with enhanced small-signal stability performance. Data mining techniques are employed for clustering the CCRCs according to their stability performance behavior in the system operable space and revealing explicitly the discovered pattern through a knowledge extraction process. To exemplify the proposed methodology, a test system made of three AC sub-grids and two DC sub-grids is used and a small-signal stability performance indicator measuring the voltage deviation in the DC grids is considered., This work was supported by FEDER / Ministerio de Ciencia e Innovación- Agencia Estatal de Investigación, under the project REFORMING (PID2021-127788OA-I00). The work of O. Gomis was supported by the ICREA Academia program. The work of E. Prieto and M. Cheah was supported by Serra Húnter Program., Preprint