Estimation of frequency-dependent impedances in power grids by deep lstm autoencoder and random forest
Gespeichert in:
| Titel: | Estimation of frequency-dependent impedances in power grids by deep lstm autoencoder and random forest |
|---|---|
| Autoren: | Bagheri, Azam, 1982, Bongiorno, Massimo, 1976, Gu, Irene Yu-Hua, 1953, Svensson, Jan |
| Quelle: | Energies. 14(13) |
| Schlagwörter: | Random forest regres-sion, Frequency-dependent grid impedance, LSTM autoencoder, Time-series analysis, PRBS, Unsupervised deep learning |
| Beschreibung: | This paper proposes a deep-learning-based method for frequency-dependent grid impedance estimation. Through measurement of voltages and currents at a specific system bus, the estimate of the grid impedance was obtained by first extracting the sequences of the time-dependent features for the measured data using a long short-term memory autoencoder (LSTM-AE) followed by a random forest (RF) regression method to find the nonlinear map function between extracted features and the corresponding grid impedance for a wide range of frequencies. The method was trained via simulation by using time-series measurements (i.e., voltage and current) for different system parameters and verified through several case studies. The obtained results show that: (1) extracting the time-dependent features of the voltage/current data improves the performance of the RF regression method; (2) the RF regression method is robust and allows grid impedance estimation within 1.5 grid cycles; (3) the proposed method can effectively estimate the grid impedance both in steady state and in case of large transients like electrical faults. |
| Dateibeschreibung: | electronic |
| Zugangs-URL: | https://research.chalmers.se/publication/524893 https://research.chalmers.se/publication/524893/file/524893_Fulltext.pdf |
| Datenbank: | SwePub |
Full Text Finder 
Nájsť tento článok vo Web of Science | Abstract: | This paper proposes a deep-learning-based method for frequency-dependent grid impedance estimation. Through measurement of voltages and currents at a specific system bus, the estimate of the grid impedance was obtained by first extracting the sequences of the time-dependent features for the measured data using a long short-term memory autoencoder (LSTM-AE) followed by a random forest (RF) regression method to find the nonlinear map function between extracted features and the corresponding grid impedance for a wide range of frequencies. The method was trained via simulation by using time-series measurements (i.e., voltage and current) for different system parameters and verified through several case studies. The obtained results show that: (1) extracting the time-dependent features of the voltage/current data improves the performance of the RF regression method; (2) the RF regression method is robust and allows grid impedance estimation within 1.5 grid cycles; (3) the proposed method can effectively estimate the grid impedance both in steady state and in case of large transients like electrical faults. |
|---|---|
| ISSN: | 19961073 19961073 |
| DOI: | 10.3390/en14133829 |