A data augmentation methodology for machine learning modelling of distribution power grid: Application on optimal storage sizing and control
| Publicatietype: | Artikel |
| Citatie: | |
| Tijdschrift: | CIRED 2021 |
| Jaar: | 2021 |
| Maand: | September |
| Pagina's: | 5 |
| URL: | https://www.cired2021.org/... |
| Samenvatting: | The growth of distributed energy generations and electric vehicle charging stations in the low voltage grid brings out new challenges for distribution system operators. Actual methods of distribution network modelling are computationally expensive and omit aging of network physical components. This paper proposes a method of data augmentation for data-driven modelling. The methodology is divided into four parts: data generation, data-driven modelling, power flow boundaries estimation, and finally the application on optimal energy storage sizing and control. |
| Trefwoorden: | machine learning, modeling, optimization, Simulation, VOLTAGE PREDICTION |
| Auteurs | |
| Toegevoegd door: | [] |
| Totaalscore: | 0 |
|
Bestanden
|
|
|
|
|
Aantekeningen
|
|
|
|
|
|
Onderwerpen
|
|
|
|
|
