Collaborative acceleration of CPU/GPU for electric power digital twin applications

Positioning and navigation functions are often required in grid design and operation and maintenance, general grid model building, and power plant operation. GDOP (Geometric Dilution of Position Precision) is often used to evaluate positioning accuracy. The smaller the GDOP value, the higher the positioning accuracy, and vice versa. Through the calculation and analysis of GDOP, it can help the positioning and navigation functions in the power digital twin application to more accurately locate equipment or monitoring points. This is of great significance to the operation and maintenance of the power system. In order to improve the calculation of DOP value using CPU/GPU collaborative acceleration in this paper, this paper uses GPU to optimize the core operator in GDOP calculation, and proposes a CPU/GPU collaborative computing solution. The experimental results show that the GDOP value calculation time is reduced from the original 3753 seconds to 232 seconds, and the performance is improved by 16.18x.