Temperature adjustment load quantifying method based on correlation analysis and meteorological factor clustering

Abstract

The invention discloses a temperature adjustment load quantifying method based on correlation analysis and meteorological factor clustering, comprising the following steps: getting the meteorological factors of temperature adjustment loads through analysis of correlation between daily maximum load and meteorological factors; after getting the meteorological factors, determining the meteorological factor intervals of the temperature adjustment loads and a benchmark load according to the variance change of a daily maximum load data subset based on meteorological factor clustering; after determining the meteorological factor intervals of the temperature adjustment loads and the benchmark load, getting corresponding temperature adjustment load days and a benchmark load day, getting the load statistics corresponding to each temperature adjustment load day and the load statistics corresponding to the benchmark load day, averaging the load statistical values in the benchmark load day to get a benchmark daily load curve, and carrying out subtraction on the daily load data of the temperature adjustment load days and the benchmark daily load curve to get a temperature adjustment load curve of the current day; and carrying out data processing on the basis of the temperature adjustment load curve of each day to get the daily, weekly, monthly, seasonally and yearly values of the cooling load in summer and heating load in winter.

Description

technical field [0001] The invention relates to a method for quantifying temperature regulation load. In particular, it relates to a quantitative method of thermoregulation load based on correlation analysis and clustering of meteorological factors. Background technique [0002] With the rapid development of the national economy and the continuous improvement of the power market, the analysis of load characteristics has gradually become an indispensable part of the operation and planning of power companies. It has an important theoretical guiding role and practical application value. Grasping the changing characteristics and development rules of load can not only improve the accuracy of load forecasting of electric power enterprises, but also help the safe and stable operation of the power system, and can also improve the quality of power supply for users, so that electric power enterprises can obtain better economic benefits. Load characteristic analysis is the process of...

AI Technical Summary

Problems solved by technology

The two algorithms have certain defects: 1) The influence weight of each meteorological factor (temperature, humidity, wind force, rainfall, etc.) on the cooling load in areas with different climatic conditions is different from the dominant factor, and the correlation coefficient of the highest weight factor is also different. In the same way, the traditional method is only applicable to the case where the high-weight influence factor of the cooling load is single and strictly changes according to the season, which has limitations; The load periods are the same, and the change of cooling load in special weather in spring, summer and autumn loads is not considered, that is, there may be no cooling load on a certain day in summer when the weather is relatively cool, but there may be cooling load on a certain day under special weather conditions in spring and autumn; 3) There are many uncertain factors in the calculation process, and the results obtained by different data selection standards are quite different, resulting in large errors

Images