With the increasing penetration of renewable energy resources and other forms of dispersed generation, more and more uncertainties will be brought to the dynamic security assessment (DSA) of power systems. This paper proposes an approach that uses ensemble decision trees (EDT) for online DSA. Fed with online wide-area measurement data, it is capable of not only predicting the security states of current operating conditions (OC) with high accuracy, but also indicating the confidence of the security states 1 minute ahead of the real time by an outlier identification method. The results of EDT together with outlier identification show high accuracy in the presence of variance and uncertainties due to wind power generation and other dispersed generation units.The performance of this approach is demonstrated on the operational model of western Danish power system with the scale of around 200 lines and 400 buses.
展开▼