A method for mining a weak reliability link of a power distribution system based on multi-dimensional analysis

Abstract

There is provided a method for mining a weak reliability link of a power distribution system based on multi-dimensional analysis. The method comprises the steps of power distribution network power failure event data collecting and cleansing, power distribution network power failure event data CUBE modeling, mined target-based power failure event data CUBE reconstructing, single-dimensional analysis on power failure event data CUBE, multi-dimensional comprehensive analysis on power failure event data CUBE and the like. The method for mining a weak reliability link of a power distribution system based on multi-dimensional analysis breaks through the limitation that the power failure event data is only used for reliability index statistics in the traditional management of reliability of the power distribution network, establishes a multi-dimensional model for the power failure event data itself to execute analysis, and mines the weak reliability link of the power distribution system from multiple perspectives and different hierarchies, thus enabling to effectively find regular features of influence factors on the power failure event of the power distribution network and where the weak reliability link of the power distribution network is, which can not only provide direct guidance for a production-management work of the power distribution network, such as grass-roots operation-maintenance and the like, but also provide a valuable decision basis for each level of management unit of the power distribution system.

Description

technical field [0001] The invention belongs to the technical field of urban power distribution system analysis, management and maintenance, and in particular relates to a multidimensional analysis-based method for mining weak links in power distribution system reliability; Background technique [0002] Research on power reliability mostly focuses on proposing new reliability indicators and calculation methods of indicators, and now a mature index system and evaluation method have been formed; in terms of reliability application and management, the current power supply reliability management of domestic power companies The system collects a large amount of power outage event data, and records every power outage event in the distribution network in detail, covering the responsible department, power outage time, equipment where the power outage occurred, responsibility reasons, technical reasons, power outage scope, protection actions, etc.; However, for a long time, the role of...

AI Technical Summary

Problems solved by technology

[0002] Research on power reliability mostly focuses on proposing new reliability indicators and calculation methods of indicators, and now a mature index system and evaluation method have been formed; in terms of reliability application and management, the current power supply reliability management of domestic power companies The system collects a large amount of power outage event data, and records every power outage event in the distribution network in detail, covering the responsible department, power outage time, equipment where the power outage occurred, responsibility reasons, technical reasons, power outage scope, protection actions, etc.; However, for a long time, the role of these large power outage event data is limited to the statistics of various distribution network reliability indicators and used for the assessment of each unit, but lacks the means to analyze and mine its deep-seated laws, which has virtually caused data corruption. Waste, but also bound the improvement of the reliability of my country's power distribution system;

Images