An adjacency matrix determination method and device, electronic equipment and storage medium
By determining the vertex set of load covariates and generating a filtered adjacency matrix, the problem of hidden correlation between load and covariates is solved, the accuracy of load forecasting is improved, and the system is adapted to the operating rules of the power grid.
CN122413360APending Publication Date: 2026-07-17INFORMATION & COMM BRANCH OF STATE GRID JIANGSU ELECTRIC POWER +2
Patent Information
- Authority / Receiving Office
- CN · China
- Patent Type
- Applications(China)
- Current Assignee / Owner
- INFORMATION & COMM BRANCH OF STATE GRID JIANGSU ELECTRIC POWER
- Filing Date
- 2026-04-10
- Publication Date
- 2026-07-17
AI Technical Summary
Technical Problem
Existing technologies struggle to effectively uncover hidden correlations between loads and between loads and covariates, impacting the accuracy of load forecasting.
Method used
By determining the set of load covariate vertices, a first adjacency matrix is generated and filtered to obtain a second adjacency matrix. This model characterizes the asymmetric correlation between load vertices and covariate vertices, eliminates redundant information, and adapts to the operating rules of the power grid.
Benefits of technology
It has enabled the determination of the influence relationships between loads and between loads and covariates, providing feature support for diversified load forecasting and improving forecast accuracy.
✦ Generated by Eureka AI based on patent content.
Smart Images
Figure CN122413360A_ABST
Abstract
本发明公开了一种邻接矩阵确定方法、装置、电子设备和存储介质。具体实施方案包括：确定负荷协变量顶点集；基于所述负荷协变量顶点集，生成第一邻接矩阵；对所述第一邻接矩阵进行过滤，得到第二邻接矩阵。通过负荷协变量顶点集生成第一邻接矩阵，刻画了负荷顶点与协变量顶点之间的非对称关联特性，适配负荷所在的电网的运行规律，通过对第一邻接矩阵进行过滤得到第二邻接矩阵，实现了图结构的稀疏化，剔除了冗余信息，实现了负荷间以及负荷和协变量间影响关系的确定，为多元化负荷预测提供特征支撑。
Need to check novelty before this filing date? Find Prior Art