一种配电网承载能力的评估方法及系统
By constructing a sample library and a neural network model based on transfer learning, and combining multi-layer constraint features and user behavior profiles, the computational complexity and timeliness issues of assessing the renewable energy carrying capacity of distribution networks are solved, enabling rapid and accurate planning decision support.
Patent Information
- Authority / Receiving Office
- CN · China
- Patent Type
- Applications(China)
- Current Assignee / Owner
- STATE GRID SHANDONG ELECTRIC POWER CO
- Filing Date
- 2026-04-23
- Publication Date
- 2026-07-17
AI Technical Summary
Existing technologies are computationally complex and time-consuming when assessing the renewable energy carrying capacity of distribution networks, making it difficult to meet the timeliness requirements of planning decisions. They also lack rapid dynamic evaluation methods, and are particularly inefficient when comparing and iterating incremental planning schemes.
A feature-carrying capacity index mapping sample library of historical power grid planning schemes is constructed, and a neural network model is trained through transfer learning to quickly evaluate the carrying capacity index of incremental schemes. Multi-layer constraint features and constraint relaxation vectors are introduced, and combined with multi-task learning and user behavior profiling, collaborative optimization schemes are generated.
It has reduced the assessment time from hours to seconds, made the assessment results more accurate, quantified the potential and implementation difficulty of different transformation measures, provided dynamic planning suggestions, and improved the efficiency and reliability of the assessment.
Smart Images
Figure CN122414869A_ABST