A reconstruction method for missing measurement data of distribution network
A technology for measuring data and power distribution network, applied in electrical components, circuit devices, AC network circuits, etc. It can enhance the generalization ability and robustness, improve the accuracy of missing reconstruction, and improve the stability.
Active Publication Date: 2021-05-07
NORTH CHINA ELECTRIC POWER UNIV (BAODING)
View PDF3 Cites 0 Cited by
- Summary
- Abstract
- Description
- Claims
- Application Information
AI Technical Summary
Problems solved by technology
[0008] The purpose of the present invention is to provide a method based on generative confrontation and A reconstruction method for missing measurement data of distribution network based on dual semantic awareness
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
[0041] Such as figure 1 As shown, the network structure of distribution network measurement data deletion reconstruction based on generative confrontation and dual semantic perception in this embodiment uses GAN to construct the main model, and builds a missing reconstruction network with two deep learning networks of generator and discriminator. build model.
[0042] Such as figure 2 As shown, in this embodiment, the generator and discriminator of game confrontation are constructed based on the idea of generative confrontation, and feature extraction is performed on measurement data, the setting of layer parameters and the type of internal neural network are determined, and feature extraction is performed through a separate and iterative training method for the first time. Model feature extraction training, using the ADAM optimizer to optimize the hyperparameters of the generator and discriminator during the training process.
[0043] Such as image 3 As shown, this emb...
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
A method for reconstruction of distribution network measurement data missing based on generative confrontation and dual semantic perception belongs to the field of electric power big data processing technology. This method uses the idea of generative adversarial network (GAN) game confrontation, independently extracts data features and spatio-temporal distribution characteristics through the model, combines context information, generates perceptual information, and reconstructs perceptual information to form a double semantic perception (Double Semantic Perception) ) missing reconstruction constraints, and find the maximum similarity data with the data to be reconstructed to realize the missing reconstruction of measurement data. The invention is completely driven by data, and overcomes the limitations in adaptability, algorithm efficiency and accuracy of establishing a mathematical reconstruction model based on business mechanism under the complex environment of distribution network. Using this method avoids the need to make distribution assumptions and feature explicit modeling of data based on a large amount of prior knowledge in the process of traditional missing reconstruction, and improves the defects of traditional GAN such as slow convergence speed and unstable training, with high data missing reconstruction accuracy.
Description
technical field [0001] The invention relates to a reconstruction method for lack of distribution network measurement data based on generative confrontation and dual semantic perception, and belongs to the technical field of electric power big data processing. Background technique [0002] In the context of energy reform and social development, distribution network, as an important infrastructure for economic and social development, plays a key role in realizing the strategic goals of smart grid and energy Internet. With the improvement of informatization, automation and interaction level of smart distribution network and the mutual penetration and integration with the Internet of Things, a large amount of data has been accumulated in the power system measurement system. Authentic and reliable data can correctly reflect the operating characteristics and objective laws of the power system. However, failures or interference may occur in all aspects of data collection, measureme...
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 Patents(China)
IPC IPC(8): H02J3/00
CPCH02J3/00H02J2203/20
Inventor 齐林海杨玉莲王红
Owner NORTH CHINA ELECTRIC POWER UNIV (BAODING)