Volltext-Downloads (blau) und Frontdoor-Views (grau)
  • search hit 1 of 3
Back to Result List

Artificial neural network based decision support system for the present power grid accounting for the successful integration of renewable energy sources such as PV systems

  • We present an alternative approach to grid management in low voltage grids by the use of artificial intelligence. The developed decision support system is based on an artificial neural network (ANN). Due to the fast reaction time of our system, real time grid management will be possible. Remote controllable switches and tap changers in transformer stations are used to actively manage the grid infrastructure. The algorithm can support the distribution system operators to keep the grid in a safe state at any time. Its functionality is demonstrated by a case study using a virtual test grid. The ANN achieves a prediction rate of around 90% for the different grid management strategies. By considering the four most likely solutions proposed by the ANN, the prediction rate increases to 98.8%, with a 0.1 second increase in the running time of the model.

Export metadata

Additional Services

Search Google Scholar

Statistics

frontdoor_oas
Metadaten
Author:Manuela Linke, Tobias Messmer, Gabriel Micard, Adrian Wenzel, Gunnar Schubert, Matthias Kindl, Adrian Minde
DOI:https://doi.org/10.4229/EUPVSEC20192019-6CV.1.21
ISBN:3-936338-60-4
Parent Title (English):36th European Photovoltaic Solar Energy Conference and Exhibition (EU PVSEC 2019), 9-13 September, Marseille, France
Document Type:Conference Proceeding
Language:English
Year of Publication:2019
Release Date:2020/01/28
Tag:Grid Management; Distributed System Operators (DSO); Grid Integration; Smart Grids; Artificial Neural Networks
First Page:1895
Last Page:1898
Institutes:Fakultät Elektrotechnik und Informationstechnik
Relevance:Keine peer reviewed Publikation (Wissenschaftlicher Artikel und Aufsatz, Proceeding, Artikel in Tagungsband)
Open Access?:Nein