Research on Dynamic Perception and Simulation Technology of Power Grid State Based on UAV

This paper proposes a dynamic perception and simulation technology framework for power grid state based on UAV, combined with the extended Kalman filter algorithm for data processing and state estimation. The system uses sensors carried by UAVs to conduct real-time inspections of key power grid facilities, obtain multi-dimensional data including voltage, current, temperature, etc., and use the extended Kalman filter algorithm to dynamically estimate and update the power grid state to ensure the accuracy and timeliness of the data. The simulation results show that the adoption of this technical solution can effectively improve the accuracy and real-time performance of power grid state perception. In the simulated complex power grid environment, the system can respond to power grid emergencies with a delay of 0.2 seconds per second, significantly shortening the reaction time of traditional manual monitoring and decision-making processes (reduced by about 35<sup xmlns:mml="http://www.w3.org/1998/Math/MathML" xmlns:xlink="http://www.w3.org/1999/xlink">%</sup>). Specific analysis shows that the mean square error (MSE) of the extended Kalman filter algorithm in power grid state estimation is less than 2%, the voltage fluctuation prediction accuracy reaches 98.6%, and the real-time estimation errors of temperature and current are less than 5%. In addition, the system can also dynamically track and predict the power grid state, accurately warn of potential faults, and provide decision support.