A carbon emission flow tracking method based on graph neural network

Through the carbon emission flow tracking method based on graph neural network, the proportional equalization principle and training and fine-tuning of graph neural networks are used to solve the problems of low carbon flow tracking efficiency and poor model mobility in the existing technology, and efficient and accurate Carbon flow tracking and adaptability of grids of different sizes.

CN114741956BActive Publication Date: 2024-11-08STATE GRID ZHEJIANG ELECTRIC POWER CO LTD +1
View PDF 0 Cites 2 Cited by

Patent Information

Application Number
CN202210319858.9
Authority / Receiving Office
CN · China
Patent Type
Patents(China)
Current Assignee / Owner
Filing Date
2022-03-29
Publication Date
2024-11-08
Estimated Expiration
2042-03-29

AI Technical Summary

Technical Problem

The prior art is difficult to achieve efficient and low-information demand carbon flow tracking, and lacks deep learning models that can be migrated to different scale power grids, which cannot meet the needs of frequent changes in power system topology.

Method used

The carbon emission flow tracking method based on graph neural network is adopted, and the graph neural network is constructed by collecting grid topological information and historical data, and the carbon flow tracking results are obtained using the principle of proportional equalization, and the model is suitable for power grids of different sizes through training and fine-tuning.

Benefits of technology

It realizes efficient and accurate carbon flow tracking, has good mobility, is suitable for power grids of different sizes, and meets the carbon emission tracking needs of the power system.

✦ Generated by Eureka AI based on patent content.

Smart Images

  • Figure CN114741956B_ABST
    Figure CN114741956B_ABST
Patent Text Reader

Abstract

The present invention discloses a carbon emission flow tracking method based on graph neural network. The tracking method randomly simulates the operation state of the power grid according to the topological information of the target power transmission and distribution network, the transmission and distribution lines and equipment parameters, the user locations in the power grid, the locations of each power generation facility and the carbon-electricity efficiency of the facility, generates a carbon flow tracking result sample that meets the actual situation, and trains the bus-line neural network. The neural network can be migrated between network samples of different sizes. Therefore, the method of the present invention has strong versatility and scalability; it can calculate the carbon emissions indirectly generated by each user in the power grid and the carbon emissions generated by the energy loss of the transmission and distribution lines and equipment in real time according to the power consumption data of users in the power grid and the real-time power generation of the power plant. The method of the present invention can effectively reduce the calculation speed required for carbon flow tracking and the data used in the calculation process, and can provide a more efficient and energy-saving operation basis for the effective operation of the carbon power market.
Need to check novelty before this filing date? Find Prior Art

Citation Information

Cited By

  • Carbon emission evaluation method considering external clean energy

    CN116663945A

  • A carbon emission evaluation method considering out-of-zone clean energy

    CN116663945B