STEADY-STATE SECURITY EVALUATION OF ELECTRICAL-POWER SYSTEMS BY MEANSOF ARTIFICIAL NEURAL-NETWORK

An artificial-neural-network (ANN) application for steady-state securi ty evaluation of electrical power systems is presented. Such applicati on is based upon a combined use of a multilayer back-propagation neura l network and of an opportune electrical system model, previously prop osed by some of the authors. In the paper; the definition of steady-st ate security and the problems arising from its on-line evaluation are briefly recalled Then, the ANN utilized is described with particular r eference to the solutions adopted by the authors. Afterwards, some rem arks on the system model utilized are reported. Finally, numerical app lications on the AEP-14 bus system are presented and the results obtai ned with different ANN configurations are analyzed.