Photovoltaic load clustering method and device based on coupling meteorological factors and medium

By co-clustering the photovoltaic output, load and meteorological data of the distributed photovoltaic access grid, the joint clustering problem of difficult to effectively consider meteorology, photovoltaic and load in the existing technology is solved, and the distributed photovoltaic access grid is realized Accurate clustering and comprehensive impact assessment of scenarios.

CN119474928APending Publication Date: 2025-02-18STATE GRID SHANGHAI MUNICIPAL ELECTRIC POWER CO
View PDF 0 Cites -1 Cited by

Patent Information

Application Number
CN202411298183.X
Authority / Receiving Office
CN · China
Patent Type
Applications(China)
Current Assignee / Owner
Filing Date
2024-09-18
Publication Date
2025-02-18

AI Technical Summary

Technical Problem

The prior art is difficult to effectively consider the combined clustering of meteorology, photovoltaics and loads, resulting in increased fluctuations in the system's net load when distributed photovoltaics are connected to the power grid and difficult to balance the scheduling.

Method used

By collecting photovoltaic output data, load data and multi-dimensional meteorological data from distributed photovoltaic connection power grids, we conduct correlation analysis and screen the meteorological factors, conduct principal component analysis and combine them into coupled meteorological factors, and use hierarchical clustering algorithm to divide the coupled meteorological factors. The clustered photovoltaic and load data are obtained.

Benefits of technology

Accurate clustering and comprehensive impact assessment of distributed photovoltaic access grid scenarios are realized, and more accurate system net load prediction and scheduling balance support are provided.

✦ Generated by Eureka AI based on patent content.

Smart Images

  • Figure CN119474928A_ABST
    Figure CN119474928A_ABST
Patent Text Reader

Abstract

The invention relates to a photovoltaic load clustering method and device based on coupling meteorological factors and a medium. The method comprises the following steps: collecting hourly photovoltaic output data, load data and multi-dimensional meteorological data in a distributed photovoltaic access power grid; correlation analysis is carried out on the multi-dimensional meteorological data, and first K meteorological factors with the highest correlation with photovoltaic output and load are screened out; performing principal component analysis on the screened K meteorological factors to extract principal components with high contribution rates, and combining the K meteorological factors according to the principal components with high contribution rates to obtain coupled meteorological factors; dividing the coupling meteorological factor set by adopting a hierarchical clustering algorithm to obtain clustered photovoltaic and load data; wherein the clustering number in the hierarchical clustering algorithm is obtained through comprehensive calculation by an elbow method and a contour coefficient method. Compared with the prior art, the method is more accurate and reliable.
Need to check novelty before this filing date? Find Prior Art