DNN-Based Distributed Voltage Stability Online Monitoring Method for Large-Scale Power Grids

Abstract

With the increase of power load demand and the complexity of power grid structure, the problem of voltage stability is becoming more serious, and it is urgent to study the countermeasures. In this paper, a DNN-based distributed voltage stability online monitoring method for large-scale power grids is proposed. Unlike the traditional load margin methods, the proposed method uses a local index load impedance modulus margin (LIMM) index to determine the optimal installation locations of PMUs, which is more efficiently. Moreover, the DNN is applied to learn the nonlinear relationship between the power system operation state and its corresponding LIMM. By this way, the corresponding LIMM value can be predicted through the state variables of nodes from the installed PMUs. This method can greatly improve the calculation speed of LIMM and assess the system voltage stability level in real-time, which help the system operator to judge the operating state and take measures in time. Finally, the proposed method is tested on the 14-bus system and then on the 118-bus system respectively, and the simulation results verify the effectiveness and correctness of the proposed method.