一种基于模型-数据混合驱动的综合能源系统区间状态估计方法
By employing a model-data hybrid approach, utilizing the artificial fish swarm method and long short-term memory neural networks, combined with kernel density estimation, the uncertainty problem in data transmission and equipment measurement in integrated energy systems was solved. This resulted in highly accurate and efficient interval state estimation, ensuring stable system operation.
Patent Information
- Authority / Receiving Office
- CN · China
- Patent Type
- Patents(China)
- Current Assignee / Owner
- CHANGSHA UNIVERSITY OF SCIENCE AND TECHNOLOGY
- Filing Date
- 2022-07-28
- Publication Date
- 2026-07-17
AI Technical Summary
Existing technologies lack consideration for the uncertainties in data transmission and equipment measurement in integrated energy systems, resulting in a lack of reliability in point state estimation and affecting the safe and reliable operation of the system.
A model-data hybrid approach is adopted, which uses the artificial fish swarm method to solve the point state estimation model and obtains the direct mapping relationship between the measurement data and the interval state estimation results through the long short-term memory neural network. Combined with kernel density estimation to fit the error probability distribution, the interval state estimation is realized.
It improves the accuracy and timeliness of interval state estimation for integrated energy systems, reduces the computation time for online applications, and ensures the safe and reliable operation of the system.
Smart Images
Figure CN115271443B_ABST