Fast eigenvalue assessment for large interconnected powers systems

This paper deals with methods for fast eigenvalue prediction in large interconnected power systems. The methods can be used for on-line oscillatory stability assessment. Special interest is focused on the prediction of critical inter-area oscillatory modes. Instead of eigenvalue computation using the complete power system model, the proposed approach is based on computational intelligence such as neural networks and decision trees. Computational intelligence methods need only a small set of selected system information. These methods do not require the entire system model and therefore, they are highly applicable in Europe's liberalized and competitive energy market.