Short-term power load prediction method and device based on spatio-temporal neural network model

CN119109039BActive Publication Date: 2026-06-26ZHEJIANG UNIV OF FINANCE & ECONOMICS +1
View PDF 2 Cites 0 Cited by

Patent Information

Authority / Receiving Office
CN · China
Patent Type
Patents(China)
Current Assignee / Owner
ZHEJIANG UNIV OF FINANCE & ECONOMICS
Filing Date
2024-09-09
Publication Date
2026-06-26

AI Technical Summary

Technical Problem

Existing power load forecasting methods are insufficient in handling non-Euclidean spatial relationships between adjacent areas in the power grid, especially GNN-based models which struggle to represent the spatial relationships between power loads in real time.

Method used

A spatiotemporal neural network model based on adaptive graph convolutional branches and gated recurrent units is adopted. Combined with an improved learnable adjacency matrix, the model captures non-Euclidean spatial features through adaptive graph convolutional branches and extracts temporal features by combining them with gated recurrent units, thus obtaining spatiotemporal features.

Benefits of technology

It improves the accuracy of short-term power load forecasting, and can more accurately reflect the non-Euclidean spatial relationship of power load data, thus enhancing the accuracy of forecasting.

✦ Generated by Eureka AI based on patent content.

Smart Images

  • Figure CN119109039B_ABST
    Figure CN119109039B_ABST
Patent Text Reader

Abstract

The application discloses a short-term power load prediction method and device based on a space-time neural network model, adopts a novel space-time neural network model, and the space-time neural network model comprises a preset number of adaptive space-time feature extraction modules; in the adaptive space-time feature extraction modules, space features and time features are respectively extracted through adaptive graph convolution branches and gated recurrent unit branches, and are fused to obtain space-time features. Through the preset number of adaptive space-time feature extraction modules, the features output by the last adaptive space-time feature extraction module are connected in residual connection with input features, linear transformation is performed, and a prediction result is obtained. The model disclosed by the application can extract potential non-Euclidean space features by using an improved learnable adjacency matrix, and does not need to use a predetermined adjacency matrix as prior knowledge, so that the precision of short-term power load prediction can be further improved.
Need to check novelty before this filing date? Find Prior Art