Transformer early warning method and system based on consensus FLS + + and trajectory optimization
CN119004158AInactive Publication Date: 2024-11-22STATE GRID SHANDONG ELECTRIC POWER CO MARKETING SERVICE CENT (MEASURING CENT)
-1 Cites -1 Cited by
Patent Information
- Application Number
- CN202411479393.9
- Authority / Receiving Office
- CN · China
- Patent Type
- Applications(China)
- Current Assignee / Owner
- Filing Date
- 2024-10-23
- Publication Date
- 2024-11-22
- Estimated Expiration
- Not applicable · inactive patent
Smart Images

Figure CN119004158A_ABST
Abstract
The invention discloses a transformer early warning method and system based on consensus FLS + + and trajectory optimization, and relates to the technical field of power systems, a power prediction model based on a neural network is constructed, and a training data set is input into the power prediction model for training; adopting a consensus FLS + + search to obtain a plurality of consensus areas; constructing a dynamic system corresponding to the neural network; integrating the trajectory of the dynamic system to obtain a plurality of candidate prediction models with optimal neural network weights and structures, and combining the plurality of candidate prediction models by adopting a linear integration method to obtain a final power prediction model; and predicting power load data of the power system according to the final power prediction model to obtain a prediction result. The method is based on a consensus FLS + + and a unified trajectory optimization method, and solves the problem that the existing model is inaccurate in load prediction and photovoltaic power generation prediction in photovoltaic access distribution transformer overload prediction.
Need to check novelty before this filing date? Find Prior Art
