Research on Hybrid Measurement Data Fusion Method based on Double-layer Multi-head Graph Attention Network for New Energe Power System

In the new energe power system, there are multiple measurement information sources such as synchronous phasor measurement unit (PMU) and supervisory control and data acquisition (SCADA) to realize the rapid capture of the system running state. In this paper, a method on hybrid measurement data fusion method based on Double-layer Multi-head Graph Attention Network (DMGAT) is proposed for the new energe power system. Considering the measurement difference and timing synchronicity of PMU and SCADA, the synchronization and difference of PMU and SCADA are captured adaptively by double-layer attention mechanism, and the network topology of new energe power system is integrated. The multi-angle and multisource measurement data are fused by DMGAT from precision, synchronization and operating state. An improved New England 10 -machine 39 -node system is taken as an example to verify the feasibility and effectiveness of the method. Experiments show that the proposed algorithm can improve the measurement data accuracy of SCADA node and PMU node in various new energe power system data fusion scenarios, and give full play to the advantages of hybrid measurement.