TY - GEN
T1 - Enhancing Situational Awareness
T2 - 2021 North American Power Symposium, NAPS 2021
AU - Vakili, Ramin
AU - Khorsand, Mojdeh
N1 - Publisher Copyright:
© 2021 IEEE.
PY - 2021
Y1 - 2021
N2 - This paper proposes a machine-learning-based method to enhance online situational awareness in power systems by predicting under frequency load shedding (UFLS) and under voltage load shedding (UVLS) relay operations for several seconds after a disturbance. Voltage magnitudes/angles of electrically closest high voltage buses to the relay locations along with the relay settings are used as the input features to train random forest (RF) classifiers that predict UVLS/UFLS relay operations, respectively. A variety of contingencies considering different operation conditions and topologies of the Western Electricity Coordinating Council (WECC) system data representing the 2018 summer-peak load are studied offline using the GE positive sequence load flow analysis (PSLF) software. The results are used to create a comprehensive dataset for training and testing the classifiers. A comparison between the performances of RF models trained with different periods of input data is conducted in the presence of measurement errors.
AB - This paper proposes a machine-learning-based method to enhance online situational awareness in power systems by predicting under frequency load shedding (UFLS) and under voltage load shedding (UVLS) relay operations for several seconds after a disturbance. Voltage magnitudes/angles of electrically closest high voltage buses to the relay locations along with the relay settings are used as the input features to train random forest (RF) classifiers that predict UVLS/UFLS relay operations, respectively. A variety of contingencies considering different operation conditions and topologies of the Western Electricity Coordinating Council (WECC) system data representing the 2018 summer-peak load are studied offline using the GE positive sequence load flow analysis (PSLF) software. The results are used to create a comprehensive dataset for training and testing the classifiers. A comparison between the performances of RF models trained with different periods of input data is conducted in the presence of measurement errors.
KW - Machine learning
KW - online situational awareness
KW - protection relays
KW - random forest classifier
KW - under frequency load shedding
KW - under voltage load shedding
UR - http://www.scopus.com/inward/record.url?scp=85124365589&partnerID=8YFLogxK
UR - http://www.scopus.com/inward/citedby.url?scp=85124365589&partnerID=8YFLogxK
U2 - 10.1109/NAPS52732.2021.9654768
DO - 10.1109/NAPS52732.2021.9654768
M3 - Conference contribution
AN - SCOPUS:85124365589
T3 - 2021 North American Power Symposium, NAPS 2021
BT - 2021 North American Power Symposium, NAPS 2021
PB - Institute of Electrical and Electronics Engineers Inc.
Y2 - 14 November 2021 through 16 November 2021
ER -