Energy short-term load prediction method and system based on SE-Block improved Transform

By using the SE-Block improved Transformer model, which combines channel independence and cross-scale interactive patching, the problem of long-distance dependence and local feature consideration in integrated energy systems of traditional models is solved, and efficient and accurate load forecasting is achieved.

CN121765658AActive Publication Date: 2026-03-31SHANDONG UNIV
5 Cites 5 Cited by

Patent Information

Application Number
CN202610254895.4
Authority / Receiving Office
CN · China
Patent Type
Applications(China)
Current Assignee / Owner
Filing Date
2026-03-04
Publication Date
2026-03-31
Estimated Expiration
2046-03-04

AI Technical Summary

Technical Problem

Traditional deep learning methods for load forecasting of integrated energy systems suffer from problems such as difficulty in simultaneously addressing long-distance dependencies and transient abrupt changes, multivariate coupling noise, and high computational complexity. Traditional Transformer models also suffer from high computational complexity and loss of local semantic features when dealing with long historical windows.

Method used

We adopt an improved Transformer model based on SE-Block, eliminate noise interference through a channel-independent strategy, combine cross-scale interactive patching with frequency domain-aware SE-Block modules, and use a dual-path attention mechanism to fuse features, thereby reducing computational complexity and accurately capturing temporal dependencies.

Benefits of technology

The model accurately captures the extreme points of peaks and troughs and details of rapid transitions, suppresses high-frequency noise interference, and achieves accurate prediction of the load curve, improving the robustness and accuracy of the prediction results.

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

Abstract

The invention relates to the technical field of energy prediction, in particular to an energy short-term load prediction method and system based on SE-Block improved Transform. The method comprises the steps of performing reversible normalization preprocessing based on acquired multi-element load sequence data; carrying out feature extraction and fusion on the preprocessed data by utilizing improved cross-scale interaction Patching, wherein the feature extraction and fusion comprise multi-scale feature extraction, cross-scale interaction alignment, residual error correction and dynamic fusion; and performing feature screening on the fused features based on a channel attention mechanism, wherein the feature screening comprises feature response based on improved SE-Block and non-linear interaction of context vectors. Aiming at the non-stationarity of the actual load caused by the influence of meteorological conditions and user behaviors, the model accurately depicts the fluctuation details of the load curve by automatically eliminating the noise interference among multiple variables, and the robustness of the model in the multi-element load prediction of the integrated energy system is reflected.
Need to check novelty before this filing date? Find Prior Art