Online dynamic safety assessment method for power system based on integrated classification model

Abstract

The invention discloses an online dynamic safety assessment method for a power system based on an integrated classification model. The method comprises the steps: 1, establishing an initial sample setfor safety assessment of the power system; 2, constructing an efficient sample set containing key variables and corresponding dynamic security classification labels through feature selection; 3, obtaining a dynamic safety evaluation model capable of accurately predicting the operation state of the power system; and 4, taking the real-time data as the input of the dynamic safety assessment model to realize the online dynamic safety assessment of the power system. The objective of the invention is to solve the problem of imbalance of evaluation data and evaluation errors caused by misclassification in the DSA process of a power system.

Description

technical field [0001] The invention relates to the field of dynamic security assessment of electric power systems, in particular to an online dynamic security assessment method of electric power systems based on an integrated classification model. Background technique [0002] With the gradual increase in the scale of the power system and the continuous expansion of the grid-connected scale of new energy, it has brought huge challenges to the safe and stable operation of the system. How to ensure the safe and stable operation of the system under more economical conditions has become more and more important. important. Therefore, the dynamic security analysis of power system has become an important research hotspot. The data of the power system has the characteristics of large data volume and mixed data types. It is more difficult and extremely important to quickly and accurately capture the accident safety alarm signal of the power system. There are always the following t...

AI Technical Summary

Problems solved by technology

[0003] First, there are often two misclassifications in the classification of data samples in the system, that is, misjudging the stable state as an unstable state and misjudging the unstable state as a stable state. The degree of harm to the power system is not the same as the wrong classification Similarly, there is an urgent need for methods that can effectively reduce classification errors to improve the stability of power systems;

[0004] Second, the classification effect of unbalanced data sets in the power system is often not very ideal, and the unbalanced sampling of data may make the classification results not in line with the actual situation. Therefore, new methods are urgently needed to solve the problems caused by unbalanced data sampling. Improve the accuracy of system dynamic security and stability prediction

The disadvantage of this invention is that it does not consider the impact of unbalanced data and misclassification of sample data on the evaluation results, resulting in insufficient confidence in the evaluation results

[0007] To sum up, the current safety assessment methods cannot meet the high adaptability and high precision requirements of the modern power system for the DSA method.

Images