A multi-dimensional quantitative evaluation and intelligent attribution method for power grid mesh services

CN122243466APending Publication Date: 2026-06-19FOSHAN POWER SUPPLY BUREAU GUANGDONG POWER GRID
View PDF 0 Cites 0 Cited by

Patent Information

Authority / Receiving Office
CN · China
Patent Type
Applications(China)
Current Assignee / Owner
FOSHAN POWER SUPPLY BUREAU GUANGDONG POWER GRID
Filing Date
2026-03-20
Publication Date
2026-06-19

AI Technical Summary

Technical Problem

Existing technologies for evaluating power grid services suffer from problems such as single-dimensional evaluation, unfair evaluation results, low efficiency of manual attribution, and strong subjectivity. They cannot comprehensively and objectively reflect the overall capabilities of grid services and quickly locate the root causes of anomalies.

Method used

A multi-dimensional quantitative evaluation system is constructed, which combines grid-differentiated attribute labels and adaptive weight allocation. A Bayesian attribution network model is used for intelligent root cause localization, forming a closed-loop management of evaluation-attribution-improvement.

Benefits of technology

It enables a comprehensive, fair, and accurate evaluation of power grid services, quickly identifies grid shortcomings, and improves the accuracy and efficiency of root cause localization through intelligent attribution, forming a closed-loop management system and providing data support and decision-making basis.

✦ Generated by Eureka AI based on patent content.

Smart Images

  • Figure CN122243466A_ABST
    Figure CN122243466A_ABST
Patent Text Reader

Abstract

This invention discloses a multi-dimensional quantitative evaluation and intelligent attribution method for power grid grid services, belonging to the field of power grid operation management and intelligent evaluation technology. Addressing the problems of existing power grid grid service evaluations, such as single dimensions, poor weight adaptability, and low efficiency due to reliance on manual attribution, this invention constructs a three-level multi-dimensional evaluation index system covering the entire service process. Based on grid-differentiated attribute tags, it achieves adaptive allocation of index weights using a subjective and objective weighting method. Through data normalization and weighted calculation, it obtains a comprehensive quantitative score for grid services, completing evaluation grading and anomaly indicator identification. A Bayesian attribution network is used to locate the core root causes of service anomalies, forming a closed-loop management system of evaluation-attribution-improvement. This invention significantly improves the accuracy of power grid grid service evaluation and the efficiency of anomaly handling, providing effective technical support for the refined operation of power grid grids.
Need to check novelty before this filing date? Find Prior Art