New Load Modeling Approaches Based on Field Tests for Fast Transient Stability Calculations

The load models play an important role in the simulation and evaluation of power systems performance. This paper first proposes a new load model, which is based on a particular form of artificial neural networks we denote as adaptive back-propagation (ABP) network for nonparametric models. ABP can overcome some shortcomings of common back-propagation (BP), and the ABP load models offer several advantages over traditional load models as they are nonstructural and can be derived quickly. The application of the method is illustrated using actual field test data from Northeast China to Shanghai, one of the biggest cities in China. The load models so obtained are shown to replicate the test measurements more closely than those based on traditional load models. Second, extension of the method to the determination of the parameters of the traditional load models is also proposed. It is based on a linear back-propagation (LBP) network. The proposed LBP for parametric load model is incorporated in a transient stability program to show that not only the computational time is significantly reduced, but also the accuracy of identification is improved