Long-term load combined prediction method based on multiple linear regression and gray Verhulst model

Abstract

The invention relates to power system automation technology, in particular to a long-term load combined prediction method based on multiple linear regression and a gray Verhulst model, which comprises the following steps of: collecting load prediction data; constructing a multiple linear regression model; creating a gray Verhulst model, and the gray Verhulst model; creating a combined predictionmodel. The divergence and convergence of load curve growth are comprehensively considered;. Firstly, a multiple linear regression model capable of embodying load growth divergence is constructed, then, a gray Verhulst model capable of embodying load growth convergence is constructed, and finally, a combined prediction model is constructed by integrating two single models, so that the problem thatchange characteristics of load data are difficult to comprehensively consider in long-term load prediction is solved. The change rule of the load can be comprehensively mastered, and the accuracy of long-term load prediction is improved.

Description

technical field [0001] The invention belongs to the technical field of power system automation, in particular to a long-term load combination forecasting method based on multiple linear regression and gray Verhulst models. Background technique [0002] Accurate power load forecasting can provide support for power industry planning, power enterprise investment decision-making, and operation management. In the past few decades of long-term load forecasting development, the research on forecasting methods has been very in-depth. Many mathematical algorithms have been combined with power load forecasting. There are also many disciplines and power load forecasting that have conducted cross-research, and many research results have been achieved. . Existing studies have shown that a single long-term load forecasting method often performs better in individual aspects, but it is difficult to fully consider the changing characteristics of load data. Therefore, it is necessary to stud...

AI Technical Summary

Problems solved by technology

Existing studies have shown that a single long-term load forecasting method often performs better in individual aspects, but it is difficult to fully consider the changing characteristics of load data. Therefore, it is necessary to study a long-term load forecasting method that can comprehensively consider the changing characteristics of load in each period

Images