Power load long time sequence prediction method and related device

Through the method of mobile decomposition and multi-layer network extraction, the problem of insufficient data time change trend capture in long-term prediction of power load is solved, and higher prediction accuracy and response ability to external factors are achieved.

CN120016482APending Publication Date: 2025-05-16XIANGJIANG LAB
9 Cites 9 Cited by

Patent Information

Application Number
CN202510490167.9
Authority / Receiving Office
CN · China
Patent Type
Applications(China)
Current Assignee / Owner
Filing Date
2025-04-18
Publication Date
2025-05-16

AI Technical Summary

Technical Problem

The prior art has limitations in the prediction of long-term power loads, it is difficult to fully capture the time-changing trend of data, and it is insufficient to respond to complex external factors.

Method used

The mobile decomposition method is used to decompose the power load timing data into seasonal components and trend components, and input the trend cluster enhancement network and seasonal causal attention network respectively. The long-term trend characteristics and short-term seasonal characteristics are extracted through the K-means clustering and causal masking mechanism, and the prediction results are generated after fusion.

Benefits of technology

It improves the prediction accuracy of long sequences of power loads, enhances the response ability to complex external factors, and significantly improves the accuracy and robustness of prediction.

✦ Generated by Eureka AI based on patent content.
Patent Text Reader

Abstract

The invention provides a power load long time sequence prediction method and a related device, and relates to the technical field of power load prediction. The method comprises the steps of collecting power load time sequence data; preprocessing the power load time sequence data; decomposing the preprocessed power load time sequence data into a seasonal component and a trend component through a mobile decomposition method; inputting the trend components into a trend clustering enhancement network, performing channel clustering on the trend components through a K-means clustering algorithm, applying independent linear transformation to each clustering group, and extracting long-term trend features; inputting the seasonal components into a seasonal causal attention network, and extracting short-term seasonal features through a causal mask mechanism and a multi-head attention mechanism; fusing the long-term trend features and the short-term seasonal features to generate fused features; and inputting the fusion features into a decoder, and outputting a power load prediction result through a full connection layer. The change trend of the power load data is fully considered, and the prediction precision of the power load long sequence is improved.
Need to check novelty before this filing date? Find Prior Art