Assessment of transient voltage stability based on critical operating time of emergency control using neural networks

Since unstable phenomena that load bus voltages collapse rapidly after a large disturbance occurred in a bulk power system, it is becoming necessary to develop a fast and precise evaluation method of what is called transient voltage stability. Although many indices have so far been proposed for static voltage stability assessment, there are few evaluation methods, digital simulation analysis for example, for the transient voltage stability assessment that deals with the dynamic characteristics of generators, loads, etc. This paper presents the transient voltage stability evaluation system that consists of two artificial neural networks (NNs). The first NN judges whether the system is stable or not under a given operating condition, load composition and fault location from the viewpoint of the transient voltage stability. If it is judged to be unstable, the second NN estimates critical operating time of emergency control action as a severity index of the transient voltage instability. Here, closing of a bus tie that is switched off in the normal state is adopted as the emergency control for voltage stabilization. Numerical examples for a 26-bus model system are shown in order to check the effectiveness of the proposed evaluation system.