Power grid operation safety evaluation method based on particle swarm algorithm and gradient boosting tree

Abstract

The invention discloses a power grid operation safety evaluation method based on a particle swarm algorithm and a gradient boosting tree. The method comprises the following steps: collecting the operation data of a power system, carrying out the simulation based on an anticipated accident set, obtaining a fault sample, and forming a sample set; performing feature selection on the sample set to obtain a key variable capable of being used for predicting the state of the power system; constructing an online dynamic safety evaluation model by combining a gradient boosting tree and ensemble learning, carrying out offline training and updating on the model by utilizing key variables, and carrying out regression prediction on the state of the power system; and inputting the real-time power systemoperation data into the constructed online dynamic safety evaluation model, and carrying out real-time dynamic safety evaluation on the power grid. The power system online dynamic safety evaluation model provided by the invention can provide quick and efficient evaluation for the power grid, is beneficial to system maintenance and safety measure prevention work of power personnel, and has great significance for improving the safety and quality of power grid operation.

Description

technical field [0001] The invention belongs to the field of power system safety evaluation, and in particular relates to a power grid operation safety evaluation method based on particle swarm algorithm and gradient boosting tree. Background technique [0002] On the one hand, with the continuous decarbonization of modern power systems, especially the large-scale integration of renewable energy generation, and the potential electrification of the transport and heating sectors, the operating state space of power systems is being greatly expanded, and the number of possible operating points The expansion necessitates the development of novel safety assessment methods; on the other hand, the liberalization of electricity markets has greatly decentralized distribution and supply services in many regions, reducing the controllability of the system by system operators. The above aspects have brought unprecedented challenges to the stable and reliable operation of the power system...

AI Technical Summary

Problems solved by technology

[0008] The technical problem of the present invention is that the existing power system dynamic security assessment method has more or less overestimation or underestimation problems when performing correlation detection, so that the selected features are not accurate enough; the existing power system transient stability analysis method does not well meet the requirements of online dynamic security evaluation

Images