POWER-SYSTEM STABILIZATION BASED ON MODULAR NEURAL-NETWORK ARCHITECTURE

Backpropagation neural networks have recently been applied to problems in power system stabilizer modeling. When trained to respond differen tly to different operating conditions, these networks tend to produce interference between conflicting solutions. in recent years, modular n eural network architectures have been used for problems in system iden tification and control. These networks learn different aspects of a pr oblem by partitioning the data space into several different regions an d are less susceptible to interference than backpropagation networks. This paper investigates the use of modular neural networks for power s ystem stabilizer modeling. Simulation studies are performed to compare the modular neural network model of a power system stabilizer against a backpropagation model and a conventional power system stabilizer mo del. (C) 1997 Elsevier Science Ltd.