Neural networks for dynamic security assessment of large-scale power systems: requirements overview

The computational requirements associated with dynamic security assessment (DSA) by conventional methods are two or three orders of magnitude more than the requirements for static security assessment. Therefore comprehensive on-line DSA is infeasible in present power system control centers. The exploitation of novel techniques to solve the problems of DSA is essential for on-line implementation. The authors set forth the requirements of DSA for a large-scale power system, followed by a description of the capabilities and limitations of neural network methods in meeting these requirements.<>