Contingency ranking for voltage collapse using parallel self-organizing hierarchical neural network

On-line monitoring of the power system voltage security has become a vital factor for electric utilities. This paper proposes a voltage contingency ra nking approach based on parallel self-organizing hierarchical neural networ k (PSHNN). Loadability margin to voltage collapse following a contingency h as been used to rank the contingencies. PSHNN is a multi-stage neural netwo rk where the stages operate in parallel rather than in series during testin g. The number of ANNs required is drastically reduced by adopting a cluster ing technique to group contingencies of similar severity into one cluster. Entropy based feature selection has been employed to reduce the dimensional ity of the ANN. Once trained, the proposed ANN model is capable of ranking the voltage contingencies under varying load conditions, on line. The effec tiveness of the proposed method has been demonstrated by applying it for co ntingency ranking of IEEE 30-bus system and a practical 75-bus Indian syste m. (C) 2001 Elsevier Science Ltd. All rights reserved.