一种时空融合的光伏发电预测方法、系统、设备及介质
The spatiotemporal fusion photovoltaic power generation prediction method improves the accuracy of photovoltaic power generation prediction by utilizing spatiotemporal attention layers and cluster representations, solves the problem of insufficient prediction caused by single time series modeling, and ensures the stable operation of the power grid.
CN122026338BActive Publication Date: 2026-07-17STATE GRID ZHEJIANG ELECTRIC POWER CO LTD +1
Patent Information
- Application Number
- CN202610484561.6
- Authority / Receiving Office
- CN · China
- Patent Type
- Patents(China)
- Current Assignee / Owner
- Filing Date
- 2026-04-14
- Publication Date
- 2026-07-17
- Estimated Expiration
- 2046-04-14
Smart Images
Figure CN122026338B_ABST
Abstract
本发明公开了一种时空融合的光伏发电预测方法、系统、设备及介质，涉及电力系统技术领域，所述方法包括对获取到的光伏发电数据进行时空和时间的转换，生成融合嵌入表示并进行分块处理，得到分块嵌入表示；将分块嵌入表示输入时空注意力层进行变换，得到各节点的目标表征向量，输出初始发电预测结果；计算融合时空嵌入表示的各目标节点与各个类簇中心之间的欧氏距离并进行动态调优，以确定每个目标节点对应的类簇中心；聚合各类簇中心内所有节点，得到类簇时序表示；协同类簇时序表示和时序表征向量，为各预测专家分配权重，以输出目标发电预测结果；以目标发电预测结果，确定目标电力系统的最优发电计划，提升调度的可靠性。
Need to check novelty before this filing date? Find Prior Art
Citation Information
Patent Citations
Power short-term load prediction system based on multi-source information adaptive fusion and working method thereof
CN121710198A
Energy time series data forecasting system
JP7529334B1