Method for predicting medium and long term power load based on cluster analysis and target theory

Abstract

The invention discloses a method for predicting medium and long term power load based on cluster analysis and the target theory, which is characterized by fully considering dependency among influencing factors and eliminating the dependency, solving the problem about decline of the forecasting accuracy caused by the dependency, correctly analyzing the degree of influence of all factors on the power load, and improving the forecasting accuracy of power load. The method has higher adaptability, and can be used for predicting indexes of characteristic of power load including annual maximum load, annual electricity consumption and the like.

Description

technical field [0001] The invention relates to a medium- and long-term electric load forecasting method based on cluster analysis and gray target theory, which can be used for medium- and long-term forecasting of electric load characteristic indicators such as annual maximum load and annual electricity consumption. Background technique [0002] Carrying out power load forecasting is an important task for power grid enterprises. Improving the technical level of power load forecasting is conducive to formulating reasonable power supply construction plans, rationally arranging power grid operation modes and unit maintenance plans, and helping to save coal, fuel and Reducing the cost of power generation is conducive to planned power consumption management, and is conducive to improving the economic and social benefits of the power system. [0003] The research on power load forecasting has gone through a long process, and some traditional forecasting methods have been formed. H...

AI Technical Summary

Problems solved by technology

[0003] The research on power load forecasting has gone through a long process, and some traditional forecasting methods have been formed. However, with the improvement of forecasting accuracy requirements and the influence of the uncertainty characteristics of the load itself, it is difficult for traditional forecasting methods to make higher accuracy. Prediction

There are many relevant factors that affect the power load, and they have strong uncertainty and randomness, and there is also a certain correlation between each factor. Therefore, when using traditional methods for power load forecasting, when determining the influence In terms of the degree of influence, due to the strong correlation between the influencing factors is likely to lead to information overlap, the accuracy of the prediction model will decrease

So far, there have been no literature reports and practical applications on medium and long-term power load forecasting methods based on cluster analysis and gray target theory

Images