A neural fuzzy power system stabilizer based on α-level sets

Abstract

A new type of fuzzy logic power system stabilizer is proposed in this paper. It is constructed using a five-layered neural fuzzy network architecture based on α - level fuzzy sets. The workability of this neural fuzzy power system stabilizer is first demonstrated using regularly spaced and triangular fuzzy sets. Then, it is shown that the fuzzy sets can be tuned so as to improve the damping performance of the stabilizer. To obtain the desired output for backpropagation to be applied, the network output is altered at a randomly chosen time instant. The altered output is then taken as the desired output if the stabilizer performs better than without the alteration. Simulation results show that the performance of the neural fuzzy network can be improved within 30 training cycles.