Vulnerability assessment of a large sized power system using neural network considering various feature extraction methods

Vulnerability assessment of power systems is important so as to determine their ability to continue to provide service in case of any unforeseen catastrophic contingency such as power system component failures, communication system failures, human operator error, and natural calamity. An approach towards the development of on-line power system vulnerability assessment is by means of using an artificial neural network (ANN), which is being used successfully in many areas of power systems because of its ability to handle the fusion of multiple sources of data and information. An important consideration when applying ANN in power system vulnerability assessment is the proper selection and dimension reduction of training features. This paper aims to investigate the effect of using various feature extraction methods on the performance of ANN as well as to evaluate and compare the efficiency of the proposed feature extraction method named as neural network weight extraction. For assessing vulnerability of power systems, a vulnerability index based on power system loss is used and considered as the ANN output. To illustrate the effectiveness of ANN considering various feature extraction methods for vulnerability assessment on a large sized power system, it is verified on the IEEE 300-bus test system.

[1]  Mohamed A. El-Sharkawi,et al.  Application of computational intelligence to power system vulnerability assessment and adaptive protection using high-speed communication , 2002 .

[2]  Claire Cardie,et al.  Proceedings of the Eighteenth International Conference on Machine Learning, 2001, p. 577–584. Constrained K-means Clustering with Background Knowledge , 2022 .

[3]  M. Delimar,et al.  Artificial neural networks in power system topology recognition , 2003, The IEEE Region 8 EUROCON 2003. Computer as a Tool..

[4]  M. Bilginer Gülmezoglu,et al.  The common vector approach and its relation to principal component analysis , 2001, IEEE Trans. Speech Audio Process..

[5]  Marcos J. Rider,et al.  Artificial neural networks for solving the power flow problem in electric power systems , 2002 .

[6]  Azah Mohamed,et al.  Vulnerability assessment of a large sized power system considering a new index based on power system loss , 2007 .

[7]  Melanie Hilario,et al.  Stability of feature selection algorithms , 2005, Fifth IEEE International Conference on Data Mining (ICDM'05).

[8]  Chee Peng Lim,et al.  Application of an adaptive neural network with symbolic rule extraction to fault detection and diagnosis in a power generation plant , 2004 .

[9]  C. Jensen,et al.  Power System Security Assessment Using Neural Networks: Feature Selection Using Fisher Discrimination , 2001, IEEE Power Engineering Review.

[10]  B. Jeyasurya,et al.  On-line transient stability assessment using artificial neural network , 2004, 2004 Large Engineering Systems Conference on Power Engineering (IEEE Cat. No.04EX819).

[11]  Sung-Hun Lim.  Fault Current Waveform Analysis of a Flux-Lock Type SFCL According to LC Resonance Condition of Third Winding , 2008 .

[12]  Kamel Mohamed Faraoun,et al.  Neural Networks Learning Improvement using the K-Means Clustering Algorithm to Detect Network Intrusions , 2007 .

[13]  Chang Seop Koh,et al.  A Robust and Computationally Efficient Optimal Design Algorithm of Electromagnetic Devices Using Adaptive Response Surface Method , 2008 .

[14]  Simon Patrick Teeuwsen.  Oscillatory Stability Assessment of Power Systems Using Computational Intelligence , 2005 .