Neural networks for the calculation of the minimum frequency during forced outage of a generating unit

摘要

Dynamic security assessment is of special importance to island power systems. The CPU time required in order to apply conventional methods for those calculations does not allow real-time application. An important advantage of artificial neural networks compared with other methods, is the fast calculation time. This paper presents a neural-network model which was designed to calculate the minimum frequency during forced outage of a generating unit. The minimum frequency is a strong indication of the severity of the fault. Hence, it is a significant part of the dynamic security assessment procedure. In the future, we plan to incorporate neural-network models into other aspects of the dynamic security assessment process.