Dynamic Load Modeling for Power System Based on GD-FNN

Considering the characteristics of time-varying, diversity and randomness for electric power load, this paper puts forward a generalized dynamic fuzzy neural network (GD-FNN) load model to describe dynamic characteristics of electric power load. The learning algorithm takes fuzzy -completeness as a standard to adjust parameters, and the algorithm can make a comment on the fuzzy rules and the importance of input variables, ensuring that input variable width of every rule will be auto-adapted adjustment according to its contribution to the system, thus synchronous identification for the load model structure and parameters could be achieved. The simulation from a substation measurement data indicates that the generalized dynamic fuzzy neural network load model has a good fitting degree and strong generalization capability.