Hybrid supervised and unsupervised neural network approach to voltage stability analysis

This paper presents a hybrid neural network approach to voltage stability analysis. Essentially, the proposed hybrid neural network consists of a Kohonen network and a multi-layer feed-forward network. By using voltage collapse margin method (VCM) and singular value decomposition method (SVD), the hybrid neural network is trained to identify voltage weak buses/areas and to evaluate the loadability of power systems in terms of voltage stability. Moreover, the Kohonen neural network works as a front end to cluster input patterns with similar features of operating conditions and hence the generalization capability of the multi-layer feed-forward network has been improved significantly. The effectiveness of the proposed network has been demonstrated on the IEEE 57-bus test system and the results are very encouraging.

[1]  T.V. Cutsem,et al.  A method to compute reactive power margins with respect to v , 1991, IEEE Power Engineering Review.

[2]  Benjamin Jeyasurya.  Artificial neural networks for power system steady-state voltage instability evaluation , 1994 .

[3]  F. L. Pagola,et al.  Estimating the loading limit margin taking into account voltage collapse areas , 1995 .

[4]  M.J.H. Sterling,et al.  Voltage collapse proximity indicator: behaviour and implications , 1992 .

[5]  Y.-Y. Hong,et al.  Voltage stability indicator for identification of the weakest bus/area in power systems , 1994 .

[6]  B. Gao,et al.  Voltage Stability Evaluation Using Modal Analysis , 1992, IEEE Power Engineering Review.

[7]  A. T. Johns,et al.  Kohonen neural network based approach to voltage weak buses/areas identification , 1997 .

[8]  O. Crisan,et al.  Voltage collapse prediction using an improved sensitivity approach , 1994 .

[9]  Danny Sutanto,et al.  Application of an optimisation method for determining the reactive margin from voltage collapse in reactive power planning , 1996 .

[10]  B. J. Cory,et al.  Towards a Neural Network Based Voltage Stability Assessment , 1994 .

[11]  Venkataramana Ajjarapu,et al.  The continuation power flow: a tool for steady state voltage stability analysis , 1991 .

[12]  N. D. Reppen,et al.  Integrated approach to transfer limit calculations , 1995 .

[13]  Alberto Berizzi,et al.  System-area operating margin assessment and security enhancement against voltage collapse , 1996 .

[14]  Claudio A. Canizares,et al.  Point of collapse and continuation methods for large AC/DC systems , 1993 .

[15]  G. J. Berg,et al.  Identifying electrically weak and strong segments of a power system from a voltage stability viewpoint , 1990 .

[16]  L. L. Freris,et al.  Investigation of the load-flow problem , 1967 .

[17]  Thomas J. Overbye,et al.  Q-V curve interpretations of energy measures for voltage security , 1994 .

[18]  T. Carlsen,et al.  Voltage stability condition in a power transmission system calculated by sensitivity methods , 1990 .

[19]  D. Hill,et al.  Voltage stability indices for stressed power systems , 1993 .

[20]  Chun-Chang Liu,et al.  Efficient methods for identifying weak nodes in electrical power networks , 1995 .

[21]  N. D. Rao,et al.  Artificial neural networks and their applications to power systems—a bibliographical survey , 1993 .