A source-load time series scenario construction method, device and equipment

By constructing source-load time series scenarios using multivariate joint probability distribution and density clustering algorithms, the problems of insufficient feature dimensions and inadequate evaluation indicators in existing technologies are solved, enabling more efficient and accurate generation and prediction of power system scenarios.

CN121233984BActive Publication Date: 2026-06-09EAST CHINA BRANCH OF STATE GRID CORP
View PDF 2 Cites 0 Cited by

Patent Information

Authority / Receiving Office
CN · China
Patent Type
Patents(China)
Current Assignee / Owner
EAST CHINA BRANCH OF STATE GRID CORP
Filing Date
2025-08-06
Publication Date
2026-06-09

AI Technical Summary

Technical Problem

Existing technologies for constructing time-series power system scenarios suffer from insufficient feature dimensions and limited scenario rationality evaluation indicators, and lack a systematic and comprehensive multi-dimensional verification system.

Method used

The power output data is sampled using a multivariate joint probability distribution wind-solar-load scenario sampling function. The overall and local evaluations are performed in conjunction with a pre-constructed evaluation index system. Target samples are screened using density clustering algorithm to construct source-load time series scenarios, and the results are verified using probability density function, inverse cumulative distribution function, etc.

Benefits of technology

The generated source-load time series scenarios are more accurate, reflecting the actual characteristics of the power system, improving the efficiency and accuracy of scenario generation, and effectively predicting future power transmission status.

✦ Generated by Eureka AI based on patent content.

Smart Images

  • Figure CN121233984B_ABST
    Figure CN121233984B_ABST
Patent Text Reader

Abstract

The application provides a source-load time sequence scene construction method, device and equipment, the method comprises the following steps: calling a wind-light-load scene sampling function of a multivariate joint probability distribution to sample in output data distribution of a first power transmission system, to obtain a candidate sample, the wind-light-load scene sampling function is constructed by historical output data of a second power transmission system and a multivariate joint probability distribution algorithm; calling a pre-constructed evaluation index system, the candidate sample is used to evaluate the first power transmission system from the overall level and the local level, the overall level pays attention to the output performance of the first power transmission system in the whole time period, and the local level pays attention to the output performance of the first power transmission system in the local time period; the candidate sample is clustered based on the obtained evaluation result, and the target sample is obtained based on the clustering result; and the source-load time sequence scene corresponding to the first power transmission system is constructed based on the target sample.
Need to check novelty before this filing date? Find Prior Art