Prediction method and device for material requirements for construction of power distribution network

Abstract

The invention relates to a prediction method for material requirements for construction of a power distribution network. The prediction method comprises the following steps of: acquiring parameters of preset attributes of historical items and using quantity of materials of the various historical items, and standardizing the using quality of the materials of the various historical items into a preset range; adopting an extreme learning mechanism to construct a prediction model according to the parameters of the preset attributes of the historical items, the standardized using quality of the materials of the various historical items and a preset number of hidden nodes, and determining a weight parameter matrix of the hidden nodes according to the prediction model; and acquiring the parameters of the preset attributes of the item to be predicted, adopting the prediction model to determine a predicted value corresponding to the using quality of the materials of the item to be predicted according to the weight parameter matrix of the hidden nodes and the parameters of the preset attributes of the item to be predicted, reducing the predicted value according to the proportion corresponding to standardization, and determining the using quality of the materials, which corresponds to the item to be predicted. A corresponding device is provided according to the method. According to the scheme, the using quantity of the various materials can be simultaneously predicted, the model is simple, and relevance is also considered.

Description

technical field [0001] The invention relates to a forecasting method, in particular to a forecasting method and device for materials demand for power distribution network construction. Background technique [0002] As the third profit source of modern enterprises, material management has increasingly become an important part of enterprise strategy, and an important force to improve enterprise operating efficiency and enhance core competitiveness. For material-intensive enterprises (such as power companies), the importance and urgency of material management are even more prominent. Material demand forecasting is based on historical material use data, using data mining methods, to discover the inherent laws of material use, to guide enterprises in the future material input and use (such as procurement, logistics, storage, requisition, etc.), to reduce manpower, material resources, and financial resources It is an important method to improve the efficiency of enterprises, and ...

AI Technical Summary

Problems solved by technology

[0006] Based on this, it is necessary to provide a method and device for forecasting the demand of power distribution network construction materials for the problem of realizing simultaneous forecasting of multiple materials

Images