Dynamic voltage stability assessment of power transmission systems using neural networks

With increased loading and exploitation of power transmission systems, voltage stability has become a growing concern in electric power utilities. Static analysis methods, such as power flow based methods, have difficulty in evaluating voltage stability due to using simple models for the system components. On the other hand, dynamic modeling and evaluation of voltage stability are complex, expensive and time consuming. In this paper, a neural network (NN) approach is presented for this purpose. This NN can establish a mapping between the operating conditions and the dynamic voltage stability margin (VSM) of each bus. This analysis gives an insight about the robustness of various buses and dynamic voltage security status of the power system. The method is examined on Iran's North-West Transmission Network, and a mean absolute estimation error of 2.3% and a response time less than 0.1 s are obtained. By comparing the results obtained through different methods, it is concluded that the NN approach provides a compromise between accuracy and speed of calculations. Hence, for operational purposes, for which having fast response is vital, using the NN approach is recommended. On the other hand, for the design and development of power systems, using dynamic simulation seems a better approach due to its higher accuracy