Short-term load prediction method and apparatus

Abstract

The invention relates to a short-term load prediction method. The method comprises: acquiring historical data of a cool-thermal power load and corresponding weather data thereof; carrying out a correlation analysis on the historical data of the cool-thermal power load and the corresponding weather data to obtain relevant weather data affecting the cool-thermal power load; selecting historical feature dates based on predicted date features and determining an error absolute value vector between relevant weather data, affecting the cool-thermal power load, of all historical feature dates and relevant weather data, affecting the cool-thermal power load, of the predicted date; determining weights of all elements in the error absolute value vector by using an improved entropy method and determining a similar error between the relevant weather data, affecting the cool-thermal power load, of all historical feature dates and the relevant weather data, affecting the cool-thermal power load, of the predicted date; and selecting a similar date of the predicted date based on the similar error and determining a load of the predicted date according to the similar error corresponding to the similar date. Therefore, a problem of slow operation speed of the existing short-term load prediction method is solved.

Description

technical field [0001] The invention relates to the technical field of load forecasting, in particular to a short-term load forecasting method and device. Background technique [0002] With the rapid growth of the national economy and the improvement of people's living standards, the situation of energy utilization in the world today is becoming increasingly severe, and the resulting environmental problems cannot be ignored. How to achieve efficient and environmentally friendly utilization of energy has become a global hot issue. The use of distributed energy supply system has become an important way and effective means to realize the coordinated development of economy and energy. [0003] Load forecasting is an important part of distributed energy system planning, and it plays an important role in understanding user load changes and formulating reasonable development strategies. The accuracy of load forecasting ensures the economical and safe operation of distributed ener...

AI Technical Summary

Problems solved by technology

[0007] The present invention provides a short-term load forecasting method and device, the purpose of which is to solve the problem of slow calculation speed existing in the current short-term load forecasting method

Images