Planning optimization method combining electricity price distribution scene clustering and graph network analysis

By combining electricity price distribution scenario clustering and graph network analysis, the problems of electricity price prediction errors and lack of representativeness in scenario division caused by the uncertainty of new energy sources and load fluctuations in power grid planning are solved. This achieves multi-objective optimization of power grid planning and improves the economy, security and reliability of the power grid.

CN121616341APending Publication Date: 2026-03-06YUNNAN POWER GRID CO LTD
View PDF 0 Cites 0 Cited by

Patent Information

Application Number
CN202511779803.6
Authority / Receiving Office
CN · China
Patent Type
Applications(China)
Current Assignee / Owner
Filing Date
2025-11-28
Publication Date
2026-03-06

AI Technical Summary

Technical Problem

Existing power grid planning methods fail to effectively address the uncertainties in renewable energy output, the volatility of load demand, and the dynamic changes in the electricity market. This results in large errors in nodal price predictions, a lack of representativeness in scenario clustering, difficulty in balancing nodal price fairness, power flow stability, and line utilization, and insufficient economic efficiency and security in the optimization results.

Method used

By combining electricity price distribution scenario clustering and graph network analysis, a node electricity price prediction model is constructed through probabilistic production simulation. Dynamic time warping algorithm and graph convolutional neural network are used for scenario clustering. An improved multi-objective genetic algorithm is combined to optimize power grid planning and optimize the grid structure to improve the accuracy of electricity price prediction and the overall performance of the planning scheme.

Benefits of technology

It significantly improves the accuracy of nodal price forecasting, enhances the representativeness of scenario segmentation results, and achieves a balance between nodal price fairness, power flow stability, and line utilization, thereby improving the economy, security, and reliability of power grid planning.

✦ Generated by Eureka AI based on patent content.

Smart Images

  • Figure CN121616341A_ABST
    Figure CN121616341A_ABST
Patent Text Reader

Abstract

The invention provides a planning optimization method combining electricity price distribution scene clustering and graph network analysis, and relates to the technical field of power system planning optimization, and the method comprises the steps: building a node electricity price prediction model through obtaining generator set parameters and historical electricity load data of a target region, and obtaining typical daily electricity price data; the method comprises the steps of extracting time distribution characteristics of typical daily electricity price data, performing scene clustering by adopting a dynamic time warping algorithm to obtain a typical electricity price scene set, constructing a multi-voltage-class power transmission network frame planning model, analyzing node electricity price differences, power flow stability and line utilization rates under different network frame structures, calculating evaluation indexes, and optimizing the network frame planning model. And carrying out global optimization search on the net rack planning scheme by adopting an improved multi-target genetic algorithm, and selecting an optimal net rack scheme. According to the method, comprehensive optimization of node electricity price fairness, power flow stability and line utilization rate balance is realized, and the economical efficiency, safety and reliability of a power grid planning scheme are improved.
Need to check novelty before this filing date? Find Prior Art