Real-Time Short-Term Voltage Stability Assessment Using Combined Temporal Convolutional Neural Network and Long Short-Term Memory Neural Network

บทความในวารสาร

ผู้เขียน/บรรณาธิการ

กลุ่มสาขาการวิจัยเชิงกลยุทธ์

รายละเอียดสำหรับงานพิมพ์

รายชื่อผู้แต่ง: dhikari, Ananta; Naetiladdanon, Sumate; Sangswang, Anawach;

ผู้เผยแพร่: MDPI

ปีที่เผยแพร่ (ค.ศ.): 2022

Volume number: 12

Issue number: 13

นอก: 2076-3417

eISSN: 2076-3417

URL: https://www.scopus.com/inward/record.uri?eid=2-s2.0-85133189441&doi=10.3390%2fapp12136333&partnerID=40&md5=dbb506261ef5a6928c55eeb5f0ec237d

ภาษา: English-Great Britain (EN-GB)

ดูในเว็บของวิทยาศาสตร์ | ดูบนเว็บไซต์ของสำนักพิมพ์ | บทความในเว็บของวิทยาศาสตร์

บทคัดย่อ

This research presents a new method based on a combined temporal convolutional neural network and long-short term memory neural network for the real-time assessment of short-term voltage stability to keep the electric grid in a secure state. The assessment includes both the voltage instability (stable state or unstable state) and the fault-induced delayed voltage recovery phenomenon subjected to disturbance. The trained model uses the time series post-disturbance bus voltage trajectories as the input in order to predict the stability state of the power system in a computationally efficient manner. The proposed method also utilizes a transfer learning approach that acclimates to the pre-trained model using only a few labeled samples, which assesses voltage instability under unseen network topology change conditions. Finally, the performance evaluated on the IEEE 9 Bus and New England 39 Bus test systems shows that the proposed method gives superior accuracy with higher efficacy and thus is suitable for online application. © 2020 by the authors. Licensee MDPI, Basel, Switzerland.

คำสำคัญ

fault-induced delayed voltage recovery, observation time window, short-term voltage stability, temporal convolutional neural network