论文信息 - A novel discretization scheme combined entropy with rough set theory for transient stability assessment based on ANN

A novel discretization scheme combined entropy with rough set theory for transient stability assessment based on ANN

Transient stability assessment (TSA) is of great importance to power system operation and control. In recent years, a large amount of research work has been devoted to the TSA approach based on artificial neural networks (TSAANN). The TSAANN has shown much promise. Noticeably, existing research has focused mainly on the ANN construction and training algorithm design. However, the data pretreatment, as an inevitable and important step of TSAANN, has not attracted much attention for a long time. In this paper, the data discretization, the kernel of the data pretreatment of TSAANN is studied. A new discretization scheme combined entropy with rough sets theory (RST) for TSAANN is proposed. Simulation results indicate the validity of the proposed scheme for TSAANN.

[1] S. K. Tso,et al. Applying rough-set concept to neural-network-based transient-stability classification of power systems , 2000 .

[2] Gu Xue. A NEW FRAMEWORK FOR TRANSIENT STABILITY ASSESSMENT BASED ON NEURAL NETWORKS , 2000 .

[3] E. Z. Zhou. Functional sensitivity concept and its application to power system damping analysis , 1994 .

[4] Dejan J. Sobajic,et al. Artificial Neural-Net Based Dynamic Security Assessment for Electric Power Systems , 1989, IEEE Power Engineering Review.

[5] Shiu Kit Tso,et al. Deriving a transient stability index by neural networks for power-system security assessment , 1998 .

[6] A. A. Fouad,et al. Application of artificial neural networks in power system security and vulnerability assessment , 1994 .

[7] Jerzy W. Grzymala-Busse,et al. Rough Sets , 1995, Commun. ACM.

[8] Hong-Yeop Song,et al. A New Criterion in Selection and Discretization of Attributes for the Generation of Decision Trees , 1997, IEEE Trans. Pattern Anal. Mach. Intell..