Security evaluation of interconnected systems with large wind power production using artificial intelligence systems

Abstract

This paper presents a new methodology to evaluate, within the framework of on-line security assessment, the dynamic behavior of interconnected power systems having an increased penetration of wind power production. This approach exploits functional knowledge generated off-line, the Regression Tree (RT) automatic learning method to perform Feature Subset Selection (FSS) and Artificial Neural Networks (ANN) to provide a way for fast evaluation of the security degree.