Flexible management of power flows in the low-voltage grid using energy storage & artificial intelligence
Artykuł w czasopiśmie
MNiSW
100
Lista 2024
| Status: | |
| Autorzy: | Mroczek Bartłomiej, Pijarski Paweł |
| Dyscypliny: | |
| Aby zobaczyć szczegóły należy się zalogować. | |
| Rok wydania: | 2025 |
| Wersja dokumentu: | Drukowana | Elektroniczna |
| Język: | angielski |
| Numer czasopisma: | Pt B |
| Wolumen/Tom: | 139 |
| Numer artykułu: | 118878 |
| Strony: | 1 - 15 |
| Impact Factor: | 9,8 |
| Web of Science® Times Cited: | 0 |
| Scopus® Cytowania: | 0 |
| Bazy: | Web of Science | Scopus |
| Efekt badań statutowych | NIE |
| Materiał konferencyjny: | NIE |
| Publikacja OA: | NIE |
| Abstrakty: | angielski |
| One of the main challenges of the energy sector at the moment is to be able to absorb maximum power and electricity from RES (Renewable energy sources), without applying constraints for them on the grid at any voltage level. This paper presents the proprietary Block model of the Low Voltage (LV) grid control system enabling full control of the power flow in the LV grid using BESS (Battery Energy System Storage). The block system of LV grid control is built on the basis of four dedicated algorithms within three logic blocks, described later in this article. The first two algorithms of the four run offline for optimal power selection and BESS location and for building the training database. The other two algorithms are the procedure for starting BESS operation and maintaining its continuity. The execution device (GPU microcontroller) responsible for the current BESS control is a deep learning convolutional machine, while a statistical shallow learning regression machine (mdl) is responsible for controlling the MV/LV transformer ratio settings. The research was carried out in a real LV grid with high-RES saturation. The model was implemented in the environment: Power Word Simulator, MATLAB and SIMULINK. |
