An ANN-based multilevel classification approach using decomposed input space for transient stability assessment

Abstract

Abstract This paper proposes an ANN-based multilevel classification approach for fast transient stability assessment of large power systems. Based on input space decomposition, a two-level classifier incorporating two feed-forward ANNs is built to obtain a stability index for security classification using some general abstract post-fault attributes as its inputs. The ANNs are trained by a newly developed semi-supervised learning 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 numerical results of applying the approach to the ten-unit New England power system demonstrate its validity for transient stability assessment.