Power distribution station construction material demand prediction method based on support vector

Abstract

The invention discloses a power distribution station construction material demand prediction method based on a support vector, and the method is characterized in that the method comprises the steps: obtaining a power distribution attribute parameter of a historical construction power distribution station and the material consumption corresponding to the power distribution attribute parameter; noise reduction processing is performed on the power distribution attribute parameters and the material consumption, and a noise reduction data set is obtained after irrelevant features are removed; performing normalization processing on the noise reduction data set to obtain a standardized data set; performing parameter optimization processing on the standardized data set by adopting a support vector regression model to obtain a power distribution station construction material demand prediction model; and according to the power distribution station construction material demand prediction model and the to-be-tested project power distribution attribute parameters, determining a predicted value corresponding to the to-be-tested project material demand, thereby reducing the situation that a traditional machine learning algorithm is easy to cause overfitting and influences the power distribution station construction material demand prediction effect, effectively utilizing and managing construction materials, and improving the power distribution station construction material demand prediction efficiency. The power distribution station construction process is ensured to be smooth.

Description

technical field [0001] The present application relates to the field of power grid material demand forecasting, in particular to a support vector-based method, system, and storage medium for forecasting material demand for power distribution station construction. Background technique [0002] In the process of conventional distribution station construction, it is often necessary to estimate the material demand for distribution station construction through manpower statistical evaluation. In the early stage of construction, it takes a huge amount of manpower and material resources to collect data and summarize them to ensure that the material reserves meet the needs of power distribution. The demand for materials in the process of substation construction enables the distribution station to be completed as planned, but the efficiency of manpower statistics is low, and construction materials cannot be effectively used and managed. [0003] The traditional regression algorithm is...

AI Technical Summary

Problems solved by technology

[0002] In the process of conventional distribution station construction, it is often necessary to estimate the material demand for distribution station construction through manpower statistical evaluation. In the early stage of construction, it takes a huge amount of manpower and material resources to collect data and summarize them to ensure that the material reserves meet the needs of power distribution. The demand for materials in the process of substation construction, so that the substation can be completed as planned, but the efficiency of manpower statistics is low, and the construction materials cannot be effectively used and managed

[0003] The traditional regression algorithm is used to construct a mathematical model based on historical construction data over the years, and then predict the demand for distribution station construction materials according to the preset attribute parameters of the project to be tested. The prediction is considered to be correct only when the value is high, which is likely to cause overfitting and affect the forecasting effect of material demand for distribution station construction.

Images