A power distribution network load decomposition prediction method and system based on a physical information neural network
By constructing a physical information neural network in the distribution network and combining the constraints of power grid physical laws and meteorological data, the problem of low load restoration accuracy caused by the lack of distributed power source data was solved, and high-precision load decomposition and restoration were achieved.
Patent Information
- Application Number
- CN202610903859.6
- Authority / Receiving Office
- CN · China
- Patent Type
- Applications(China)
- Current Assignee / Owner
- Filing Date
- 2026-06-23
- Publication Date
- 2026-07-24
AI Technical Summary
In the absence of distributed generation data, traditional methods cannot effectively utilize meteorological data to reasonably constrain and infer the output of distributed generation, resulting in low accuracy of distribution network load restoration.
A load decomposition prediction method based on physical information neural networks is constructed. By embedding power grid physical laws and meteorological data, physical constraints are constructed using power grid physical laws such as node power balance and meteorological data, generating electrical and meteorological causal consistency constraints, thereby improving the load decomposition accuracy in scenarios with missing data.
In the absence of distributed power generation output data, the accuracy of load decomposition was significantly improved, ensuring that the model output conforms to the physical laws of the power grid and meteorological causal relationships, and improving the accuracy of natural load reconstruction.