基于联邦学习与差分隐私保护的智能电网调度方法
By combining federated learning and differential privacy-preserving smart grid scheduling methods with deep causal inference and game theory learning, the problems of data privacy and efficient scheduling in smart grids are solved, and efficient and secure grid resource management and scheduling are achieved.
Patent Information
- Authority / Receiving Office
- CN · China
- Patent Type
- Patents(China)
- Current Assignee / Owner
- NORTHEAST GASOLINEEUM UNIV
- Filing Date
- 2025-11-19
- Publication Date
- 2026-07-17
AI Technical Summary
In smart grids, how to achieve efficient resource scheduling and data sharing while ensuring data privacy, especially how to balance data privacy protection and scheduling efficiency in multi-stakeholder scenarios, is a key challenge.
A smart grid scheduling method based on federated learning and differential privacy protection is adopted. Through local data training of intelligent agent nodes, differential privacy processing, model aggregation of central aggregation server, deep causal inference and game learning, data sharing and resource optimization are achieved.
It has improved the accuracy, flexibility, security and robustness of power grid dispatch while ensuring data privacy, enabling rapid response to sudden changes in power load and environmental changes, optimizing resource allocation and ensuring the stable operation of the power grid.
Smart Images
Figure CN121526205B_ABST