Electric power system equivalent inertia probability prediction method and device, product and storage medium

Abstract

The invention discloses a power system equivalent inertia probability prediction method and device, a product and a storage medium, and the method comprises the steps: building a point prediction model of system equivalent inertia through employing a CatBoost integrated learning algorithm, and building a nonlinear mapping relation between an input feature and the system equivalent inertia; and establishing a prediction error probability density function of each time period by adopting nonparametric kernel density estimation, and combining a system equivalent inertia point prediction result to obtain a probability density function of system equivalent inertia at a to-be-predicted moment and a prediction interval under any confidence level, thereby realizing dynamic estimation of an inertia change uncertainty interval. More comprehensive probability statistical information is provided for power grid operation mode personnel, and the method is of great significance to arrangement of power system operation and regulation and control plans under a reasonable risk level.

Description

technical field [0001] The invention relates to the technical field of power system scheduling operation, in particular to a power system equivalent inertia probability prediction method, device, product and medium. Background technique [0002] Inertia evaluation has become a hot research issue in high-proportion new energy power systems. In recent years, scholars at home and abroad have carried out a lot of research work in this field, but it is only used to evaluate the inertia level of the system at the current operating moment or after the disturbance occurs. For future moments The research on system inertia change trend prediction is still rare. In fact, due to the rapid and short-lived inertia response, for the planning and dispatching operation department, the system inertia level may not be predicted in advance, which may increase the risk of frequency instability when a large disturbance event occurs in the low-inertia operation scenario. [0003] At present, the ...

AI Technical Summary

Problems solved by technology

Due to the strong randomness and intermittent nature of wind turbine output affected by meteorological factors, the operation mode of the system is complex and changeable, the equivalent inertia of the system will show large fluctuations on the time scale, and there is a high degree of uncertainty in the prediction results

Images