AN ANN-BASED MULTILEVEL CLASSIFICATION APPROACH USING DECOMPOSED INPUT SPACE FOR TRANSIENT STABILITY ASSESSMENT

This paper proposes an ANN-based multilevel classification approach fo r fast transient stability assessment of large power systems. Based on input space decomposition, a two-level classifier incorporating two f eed-forward ANNs is built to obtain a stability index for security cla ssification using some general abstract post-fault attributes as its i nputs. The ANNs are trained by a newly developed semi-supervised learn ing algorithm. The proposed approach can not only distinguish whether a power system is stable or unstable based on the specific post-fault attributes, but also provide a relative stability indicator. The numer ical results of applying the approach to the ten-unit New England powe r system demonstrate its validity for transient stability assessment. (C) 1998 Elsevier Science S.A. All rights reserved.