Nuclear power unit electric power prediction method based on clustering analysis and random forest regression

Abstract

The invention belongs to the field of power systems, and relates to a nuclear power unit electric power prediction method based on clustering analysis and random forest regression. The historical operation data of the unit is subjected to feature extraction through clustering analysis to train the random forest regression model, so that the electric power of the unit can be predicted according tothe real-time operation data of the unit. Due to the fact that data dimension reduction is achieved through clustering analysis, construction of a mechanism model is avoided by constructing a random forest regression model, and the method has the advantages of being high in prediction precision, high in prediction speed and high in generalization capacity.

Description

technical field [0001] The invention belongs to the field of electric power systems, and relates to a method for predicting electric power of nuclear power units based on cluster analysis and random forest regression. Background technique [0002] Nuclear energy occupies an important position in the world's energy structure because of its clean and stable power generation characteristics. A group of developed countries, led by France, the United States and Germany, have already vigorously developed nuclear power technology. In the face of increasingly serious resource and environmental pressures, my country's energy situation is becoming increasingly severe, and it is imperative to adjust the energy structure. The installed capacity of nuclear power is expected to reach 58 million kilowatts in 2020, and the continuously rising installed capacity has prompted people to pay attention to the problems arising from the operation of nuclear power units. [0003] In recent years,...

AI Technical Summary

Problems solved by technology

[0004] In the actual operation of nuclear power units, there are various parameters that affect the electrical power of the unit, and these parameters have strong correlation and collinearity. It is difficult for the linear regression model to achieve high fitting accuracy; compared with the traditional regression model, the random forest regression model has the advantages of strong generalization ability, fast training speed, simple implementation, and accurate prediction. It has been applied in the field of wind power prediction , but has not been applied in nuclear power units, so it is of great significance for the application research of random forest regression model in conventional islands of nuclear power plants

Images