Transient stability screening using artificial neural networks within a dynamic security assessment system

Abstract

Accurate assessment of transient and dynamic stability provided by an online dynamic security assessor allows the power system to be operated closer to its stability limits with considerable economic benefit through the running of less out-of-merit generation. As part of such assessors, contingency screens are used to filter out those contingencies which pose no stability problems. Those contingencies which pass through these filters are evaluated in detail to determine their effects on the system stability. The paper describes an approach where an artificial neural network is successfully used to provide a fast transient stability screen within a dynamic security assessment system. Results are presented for a number of test networks based on a reduced model of the UK National Grid System.