Power material purchasing demand prediction system for distribution network

Abstract

The invention provides a power material purchasing demand prediction system for a distribution network, and belongs to the field of prediction systems. The system employs a method which comprises the steps: obtaining yearly investment plan data and historical monthly delivery data from a data layer, carrying out the data cleaning of the data in an application layer, transmitting the data to a prediction model in a modeling layer for prediction after cleaning, obtaining a prediction result, determining an optimal weight value combination and an optimal parameter combination according to the comparison of the prediction result with an actual demand so as to determine a final prediction result, and carrying out the subsequent processing of the final prediction result in the application layer. The data obtained from the data layer is cleaned through the application layer, and the data is transmitted to the prediction model in the modeling layer for prediction, thereby obtaining the prediction result. The optimal weight value combination is determined according to the comparison between the prediction result and the actual demands, and the optimal parameter combination is determined according to a deviation percentage, thereby determining the final prediction result. The difference between the final prediction result and the actual demand is very small, thereby improving the accuracy of the prediction result.

Description

technical field [0001] The invention belongs to the field of forecasting systems, and in particular relates to a demand forecasting system for distribution network power material procurement. Background technique [0002] With the increasing demand for electricity in urban and rural areas, the development of the power grid is also following up, so there are many types of power grid materials and complex standards. [0003] At present, the power demand of each region predicted based on human experience or imperfect forecasting system is often inaccurate and the error is too large, and it is impossible to allocate the power demand of each region most reasonably. Contents of the invention [0004] In order to solve the shortcomings and deficiencies existing in the prior art, the present invention provides a distribution network electric power material procurement demand forecasting system, which can improve the accuracy of forecasting electricity demand. [0005] In order to...

AI Technical Summary

Problems solved by technology

[0003] At present, the power demand of each region predicted based on human experience or imperfect forecasting system is often inaccurate and the error is too large, and it is impossible to allocate the power demand of each region in the most reasonable way.

Images