Voltage issue and very fast flexibility in the low-voltage grid using energy storage and artificial intelligence
Artykuł w czasopiśmie
MNiSW
0
brak dyscyplin
| Status: | |
| Autorzy: | Mroczek Bartłomiej, Pijarski Paweł, Gęca Jakub |
| Dyscypliny: | |
| Aby zobaczyć szczegóły należy się zalogować. | |
| Rok wydania: | 2026 |
| Wersja dokumentu: | Elektroniczna |
| Język: | angielski |
| Wolumen/Tom: | 157 |
| Numer artykułu: | 121669 |
| Strony: | 1 - 14 |
| Impact Factor: | 9,8 |
| Web of Science® Times Cited: | 0 |
| Bazy: | Web of Science |
| Efekt badań statutowych | NIE |
| Materiał konferencyjny: | NIE |
| Publikacja OA: | NIE |
| Abstrakty: | angielski |
| Currently, one of the main challenges faced by Distribution System Operators (DSOs) is the optimal procurement of network flexibility services, both for individual nodes of the power system and for entire grid areas. This paper introduces an original definition of a new concept — Grid Capacity PV for Low Voltage (GPPV) — an indicator enabling DSOs to assess the applicability of Very Fast Flexibility (VFF) services. Furthermore, the paper presents calculations for VFF within a selected research area that exhibits voltage issues resulting from the lack of fine- tuning of Renewable Energy Sources (RES). The obtained results, together with a description of the algorithm quantifying the amount of power required to balance a given MV/LV node, reflect the adopted architecture of the VFF service. The service was developed based on the principle of local control of an AC/DC power converter, functioning as a controllable load in terms of active power P and reactive power Q. The converter control is implemented using a convolutional neural network (AI1 net 1.1), while the control of the transformer tap po- sition (MV/LV) is performed using a decision tree (AI2 net 2.1). Subsequently, edge computing was applied by implementing the AI1 and AI2 networks in the Battery Energy Storage System (BESS) microcontroller on an ST platform (model: STM32F407G Discovery). The VFF service is also represented in block-diagram form using the Matlab/Simulink environment. |
