TY - GEN
T1 - Earlier detection of risk of blackout by real-time dynamic security assessment based on extreme learning machines
AU - Xu, Y.
AU - Dong, Z. Y.
AU - Meng, K.
AU - Xu, Z.
AU - Zhang, R.
AU - Wu, Andrew Y.
AU - Wong, K. P.
PY - 2010
Y1 - 2010
N2 - The lack of real-time tools capable of detecting risk of blackouts is one of the contribution factors to the recent large blackouts occurred around the world. In terms of dynamic security assessment (DSA), artificial intelligence and data mining techniques have been widely applied to facilitate very fast DSA for enhanced situational awareness of insecurity. However, many of the current state-of-the-art models usually sutTer from excessive training time and complex parameters tuning problems, leading to their inefficiency for real-time implementation. In this paper, a new DSA method using Extreme Learning Machine (ELM) is proposed, which has significantly improved the learning speed and can therefore provide earlier detection of the risk of blackout. The proposed method is examined on the New England 39-bus test system, and compared with other state-of-the-art methods in terms of computation time and accuracy. The simulation results show that the ELM-based DSA method possesses superior computation speed and acceptably high accuracy.
AB - The lack of real-time tools capable of detecting risk of blackouts is one of the contribution factors to the recent large blackouts occurred around the world. In terms of dynamic security assessment (DSA), artificial intelligence and data mining techniques have been widely applied to facilitate very fast DSA for enhanced situational awareness of insecurity. However, many of the current state-of-the-art models usually sutTer from excessive training time and complex parameters tuning problems, leading to their inefficiency for real-time implementation. In this paper, a new DSA method using Extreme Learning Machine (ELM) is proposed, which has significantly improved the learning speed and can therefore provide earlier detection of the risk of blackout. The proposed method is examined on the New England 39-bus test system, and compared with other state-of-the-art methods in terms of computation time and accuracy. The simulation results show that the ELM-based DSA method possesses superior computation speed and acceptably high accuracy.
KW - Blackout prevention
KW - Dynamic security assessment
KW - Extreme learning machine (ELM)
KW - Intelligent system
UR - http://www.scopus.com/inward/record.url?scp=78751505413&partnerID=8YFLogxK
U2 - 10.1109/POWERCON.2010.5666055
DO - 10.1109/POWERCON.2010.5666055
M3 - Conference contribution
AN - SCOPUS:78751505413
SN - 9781424459407
T3 - 2010 International Conference on Power System Technology: Technological Innovations Making Power Grid Smarter, POWERCON2010
BT - 2010 International Conference on Power System Technology
T2 - 2010 International Conference on Power System Technology: Technological Innovations Making Power Grid Smarter, POWERCON2010
Y2 - 24 October 2010 through 28 October 2010
ER -