Transient stability assessment on China Southern Power Grid system with an improved pattern discovery-based method

Intelligent systems (IS) have been widely adopted to facilitate very fast transient stability assessment (TSA) to prevent blackouts. More recently, a TSA model based on pattern discovery (PD) method has been proposed and demonstrated on several IEEE standard test systems. It has exhibited many attractive features, including high accuracy, ability to provide classification rules and system weak-points information, etc. In this paper, the PD-based TSA method is further improved by use an alternative feature selection method which is very computational efficient and tend to result in better performance. The improved model is examined on China Southern Power Grid dynamic equivalent system and compared with state-of-art IS methods. The simulation results show that the improved model has been significantly improved in modelling efficiency and its accuracy is competitive with state-of-the-art IS techniques.