A rule-based fuzzy power system stabilizer tuned by a neural network

A fuzzy logic power system stabilizer (FPSS) has been developed using speed and active power deviations as the controller input variables. The inference mechanism of the fuzzy logic controller is represented by a (7×7) decision table, i.e. 49 if-then rules. There is no need for a plant model to design the FPSS. Two scaling parameters have been introduced to tune the FPSS. These scaling parameters are the outputs of a neural network which gets the operating conditions of the power system as inputs. This mechanism of tuning the FPSS by the neural network, makes the FPSS adaptive to changes in the operating conditions. Therefore, the degradation of the system response, under a wide range of operating conditions, is less compared to the system response with a fixed-parameter FPSS. The tuned stabilizer has been tested by performing nonlinear simulations using a synchronous machine-infinite bus model. The responses are compared with the fixed-parameter FPSS and a conventional (linear) power system stabilizer. It is shown that the neuro-fuzzy stabilizer is superior to both of them