Power demand prediction method and device

Through the correlation analysis of historical power demand data and related data and multi-module prediction methods, the problem of low power demand prediction accuracy in the prior art is solved, and higher prediction accuracy and robustness are achieved.

CN119250299APending Publication Date: 2025-01-03SHENZHEN POWER SUPPLY BUREAU
View PDF 0 Cites 0 Cited by

Patent Information

Application Number
CN202411449619.0
Authority / Receiving Office
CN · China
Patent Type
Applications(China)
Current Assignee / Owner
Filing Date
2024-10-16
Publication Date
2025-01-03

AI Technical Summary

Technical Problem

The existing power demand forecasting methods rely on a large amount of human identification data, resulting in low correlation and affecting the prediction accuracy.

Method used

By performing correlation analysis on historical power demand data and related data, selecting data with high correlation for model training, combining time series feature extraction, regression analysis and neural network prediction modules, the prediction accuracy of the model is improved.

Benefits of technology

It improves the accuracy and reliability of power demand prediction, enhances the robustness of the model to data fluctuations and anomalies, and maintains the stability and accuracy of the prediction.

✦ Generated by Eureka AI based on patent content.

Smart Images

  • Figure CN119250299A_ABST
    Figure CN119250299A_ABST
Patent Text Reader

Abstract

The invention provides a power demand prediction method and device, and the method comprises the steps: obtaining first training data which comprises historical power demand data and historical power demand related data; performing correlation analysis on the first training data, and determining a correlation coefficient between each piece of data in the historical power demand related data and the historical power demand data; determining second training data, wherein the second training data comprises data of which the absolute value of a correlation coefficient is greater than a preset coefficient in historical power demand related data; performing model training on the initial model based on historical power demand data and second training data to obtain a power demand prediction model; and obtaining first data, and inputting the first data into the power demand prediction model to obtain predicted power demand data. Therefore, the prediction precision of the power demand prediction model can be improved.
Need to check novelty before this filing date? Find Prior Art