Unit peak regulation capability evaluation method based on data mining, terminal and storage medium

Abstract

The invention provides a data mining-based unit peak load regulation capability evaluation method, a terminal and a storage medium. The method comprises the steps of obtaining original data; preprocessing the data; working condition division is carried out with the heating steam extraction flow as the benchmark; performing standard data screening on the preprocessed parameter sample data; constructing a working condition model; according to the principle of the least square method, the generated power serves as a dependent variable, the main steam flow and the heating steam extraction flow serve as independent variables, non-linear relation fitting is conducted, and the non-linear relation among the generated power, the main steam flow and the heating steam extraction flow is determined; a linear relation between the power generation power optimization value and the main steam flow under different working conditions is constructed, and a heat supply working condition diagram is drawn; and the interval between the generated power and the heating steam extraction flow is evaluated. On the basis of actual unit operation data, the change of the unit operation condition is followed, and the obtained condition diagram conforms to the actual condition of the unit and does not need to be corrected. The method is not influenced by unit types and unit performance differences, and has general applicability.

Description

technical field [0001] The invention relates to the field of peak regulation capability evaluation of heating units, in particular to a data mining-based peak regulation capability evaluation method of a unit, a terminal and a computer-readable storage medium. Background technique [0002] With the rapid changes in the power grid pattern and power structure, the power grid is facing a new situation. The access ratio of new energy sources is increasing year by year, and the access of random power sources brings difficulties to the adjustment of active and reactive power of the power grid. The power grid peak regulation is almost entirely undertaken by conventional thermal power units, while the proportion of adjustable units is gradually decreasing. [0003] The thermal power unit has high stability and controllability, and is a reliable support for the safe and stable operation of the power grid. However, thermal power units are faced with new situations such as environmen...

AI Technical Summary

Problems solved by technology

First of all, the method uses the clustering method to divide the working conditions, and it is difficult to guarantee the accuracy of the working conditions division.

Kmeans clustering has its inherent disadvantages: it is necessary to artificially set the number of clusters, sensitive to the initial cluster center, etc.

Secondly, whether the Gaussian distribution can be used for each working condition needs to be verified, and the reliability of the verification using the Gaussian distribution probability density function cannot be verified at present, resulting in the inability to effectively evaluate the verification results

Images