614 / 2019-03-17 19:43:26

Study on Online Recognition Method of Cascading Trip-off Evaluation of the Renewable Energy Based on Machine Learning

support vector machine,trip-off of the renewable energy,online Recognition,cascading failure

Machine learning has been extensively studied in power system safety and stability evaluation. Considering that there are many factors affecting cascading trip-off of the renewable energy, it has both accuracy and speed to identify cascading tripping of the renewable energy by machine learning。A method of cascading trip-off evaluation based on support vector machine considering conservatism is proposed. The method combines causal analysis and statistical theory to extract key feature quantities, and establishes the mapping relationship between system feature quantities and trip-off by training, identifies cascading tripping of the renewable energy under pre-faults, and updates the prediction model rolling with simulation results to avoid the occurrence of misjudgement to a great extent.The validity of the proposed method is verified by an example of actual power system, which shows that the proposed method is practical.