Transferable electric power system dominant instability mode discrimination method
A power system and pattern category technology, applied in character and pattern recognition, biological neural network models, instruments, etc., can solve the problems of untargeted sample labeling requirements in the target domain, affecting the efficiency of model adaptation, and not helping model adaptation. , to ensure safe and stable operation, reduce time costs, and improve model applicability
Pending Publication Date: 2022-04-12
HUAZHONG UNIV OF SCI & TECH
View PDF0 Cites 0 Cited by
- Summary
- Abstract
- Description
- Claims
- Application Information
AI Technical Summary
Problems solved by technology
However, the required number of samples is large, and the cost of manual labeling is high, which affects the efficiency of model adaptation
Moreover, the labeling requirements for the target domain samples are not targeted, and labeling some target domain samples may not be very helpful for model adaptation
Method used
the structure of the environmentally friendly knitted fabric provided by the present invention; figure 2 Flow chart of the yarn wrapping machine for environmentally friendly knitted fabrics and storage devices; image 3 Is the parameter map of the yarn covering machine
View moreImage
Smart Image Click on the blue labels to locate them in the text.
Smart ImageViewing Examples
Examples
Experimental program
Comparison scheme
Effect test
Embodiment Construction
[0041] In order to make the object, technical solution and advantages of the present invention clearer, the present invention will be further described in detail below in conjunction with the accompanying drawings and embodiments. It should be understood that the specific embodiments described here are only used to explain the present invention, not to limit the present invention. In addition, the technical features involved in the various embodiments of the present invention described below can be combined with each other as long as they do not constitute a conflict with each other.
[0042]The embodiment of the present invention provides a method for discriminating the dominant instability mode of the power system that can be migrated, such as Figure 1-2 shown, including:
[0043] S1, training the first deep neural network model M based on the source domain sample set 0 .
[0044] Specifically, the mapping relationship from the simulation data to the dominant instability...
the structure of the environmentally friendly knitted fabric provided by the present invention; figure 2 Flow chart of the yarn wrapping machine for environmentally friendly knitted fabrics and storage devices; image 3 Is the parameter map of the yarn covering machine
Login to View More PUM
Login to View More Abstract
The invention discloses a migratable electric power system dominant instability mode discrimination method, and belongs to the field of electric power system stability analysis. The invention provides a method for enabling an electric power system dominant instability mode discrimination model based on deep learning to quickly adapt to the change of an operation mode of the electric power system. In the sample level, a small number of most uncertain samples are selected from target domain unlabeled samples through forward active learning to be delivered to experts for labeling, source domain samples distributed deviating from a target domain are deleted from a source domain sample set through reverse active learning, and the selected labeled target domain samples and the remaining source domain samples form a mixed sample set. In the model level, a fine-tuning transfer learning method is adopted to train a source domain model based on the mixed sample set. Thus, the model can be migrated to the target domain through fewer target domain labeling samples, the efficiency of adapting to the power grid operation mode change by the dominant instability mode discrimination model is improved, the safety of a power system is improved, and the applicability is high.
Description
technical field [0001] The invention belongs to the field of power system stability analysis, and more specifically relates to a method for discriminating the dominant instability mode of a transferable power system. Background technique [0002] The safe and stable operation of the power system is crucial to energy security and economic and social development, and its security and stability issues are the key concerns of system planning, operation, and protection workers. Quickly and accurately judging the stability and instability of the power system and the dominant instability mode (voltage instability, power angle instability) after the power system is subject to a large disturbance will buy time for emergency control measures and provide a basis for which measures to take , so as to effectively ensure the security and stability of the system. [0003] Time-domain simulation, energy function, bifurcation analysis, etc. are commonly used methods to identify the dominant...
Claims
the structure of the environmentally friendly knitted fabric provided by the present invention; figure 2 Flow chart of the yarn wrapping machine for environmentally friendly knitted fabrics and storage devices; image 3 Is the parameter map of the yarn covering machine
Login to View More Application Information
Patent Timeline
Login to View More Patent Type & Authority Applications(China)
IPC IPC(8): G06K9/62G06N3/04
Inventor 姚伟石重托张润丰文劲宇
Owner HUAZHONG UNIV OF SCI & TECH