A Voltage Tracing Method Based on Data-Driven Power Flow

With the rapid growth of highly stochastic renewable energy sources, the number of uncertainty sources in power systems has significantly increased. This intensifies the operating pressure on power systems, makes the operating state of the power grid complex and variable, threatens the reliable and economical operation of the power grid and poses new challenges to voltage stability. In response to this issue, researchers are gradually focusing on quickly and accurately tracing the sources of voltage fluctuations. This paper analyzes the uncertainty issues in the current new power system, highlighting the advantages and shortcomings of existing research methods. Subsequently, a voltage tracing method based on data-driven power flow calculation is proposed. Finally, based on the actual two-machine five-node system, an example analysis is carried out to verify the feasibility of the method. This approach utilizes neural networks for precise and rapid power flow computations. Based on the flow results, it quantifies the influence of each node on the voltage of a specific node to trace voltage fluctuations, thereby enhancing voltage stability and improving power quality.