CN111008759A - Power distribution network state evaluation method based on information fusion - Google Patents

Power distribution network state evaluation method based on information fusion Download PDF

Info

Publication number
CN111008759A
CN111008759A CN201911098218.4A CN201911098218A CN111008759A CN 111008759 A CN111008759 A CN 111008759A CN 201911098218 A CN201911098218 A CN 201911098218A CN 111008759 A CN111008759 A CN 111008759A
Authority
CN
China
Prior art keywords
evaluation
power distribution
distribution network
weight
index
Prior art date
Legal status (The legal status is an assumption and is not a legal conclusion. Google has not performed a legal analysis and makes no representation as to the accuracy of the status listed.)
Pending
Application number
CN201911098218.4A
Other languages
Chinese (zh)
Inventor
陈冉
杨超
纪坤华
周健
沈冰
杨凌辉
袁晓明
Current Assignee (The listed assignees may be inaccurate. Google has not performed a legal analysis and makes no representation or warranty as to the accuracy of the list.)
Shanghai Runpower Information Technology Co ltd
State Grid Shanghai Electric Power Co Ltd
Original Assignee
Shanghai Runpower Information Technology Co ltd
State Grid Shanghai Electric Power Co Ltd
Priority date (The priority date is an assumption and is not a legal conclusion. Google has not performed a legal analysis and makes no representation as to the accuracy of the date listed.)
Filing date
Publication date
Application filed by Shanghai Runpower Information Technology Co ltd, State Grid Shanghai Electric Power Co Ltd filed Critical Shanghai Runpower Information Technology Co ltd
Priority to CN201911098218.4A priority Critical patent/CN111008759A/en
Publication of CN111008759A publication Critical patent/CN111008759A/en
Pending legal-status Critical Current

Links

Images

Classifications

    • G—PHYSICS
    • G06—COMPUTING; CALCULATING OR COUNTING
    • G06Q—INFORMATION AND COMMUNICATION TECHNOLOGY [ICT] SPECIALLY ADAPTED FOR ADMINISTRATIVE, COMMERCIAL, FINANCIAL, MANAGERIAL OR SUPERVISORY PURPOSES; SYSTEMS OR METHODS SPECIALLY ADAPTED FOR ADMINISTRATIVE, COMMERCIAL, FINANCIAL, MANAGERIAL OR SUPERVISORY PURPOSES, NOT OTHERWISE PROVIDED FOR
    • G06Q10/00—Administration; Management
    • G06Q10/06—Resources, workflows, human or project management; Enterprise or organisation planning; Enterprise or organisation modelling
    • G06Q10/063—Operations research, analysis or management
    • G06Q10/0639—Performance analysis of employees; Performance analysis of enterprise or organisation operations
    • G06Q10/06393—Score-carding, benchmarking or key performance indicator [KPI] analysis
    • G—PHYSICS
    • G06—COMPUTING; CALCULATING OR COUNTING
    • G06F—ELECTRIC DIGITAL DATA PROCESSING
    • G06F18/00—Pattern recognition
    • G06F18/20—Analysing
    • G06F18/25—Fusion techniques
    • G—PHYSICS
    • G06—COMPUTING; CALCULATING OR COUNTING
    • G06Q—INFORMATION AND COMMUNICATION TECHNOLOGY [ICT] SPECIALLY ADAPTED FOR ADMINISTRATIVE, COMMERCIAL, FINANCIAL, MANAGERIAL OR SUPERVISORY PURPOSES; SYSTEMS OR METHODS SPECIALLY ADAPTED FOR ADMINISTRATIVE, COMMERCIAL, FINANCIAL, MANAGERIAL OR SUPERVISORY PURPOSES, NOT OTHERWISE PROVIDED FOR
    • G06Q50/00—Systems or methods specially adapted for specific business sectors, e.g. utilities or tourism
    • G06Q50/06—Electricity, gas or water supply
    • G—PHYSICS
    • G06—COMPUTING; CALCULATING OR COUNTING
    • G06F—ELECTRIC DIGITAL DATA PROCESSING
    • G06F18/00—Pattern recognition
    • G06F18/20—Analysing
    • G06F18/25—Fusion techniques
    • G06F18/259—Fusion by voting

Abstract

The invention relates to a power distribution network state evaluation method based on information fusion, which comprises the following steps: s1: determining a target index of the power distribution network and a plurality of sub-level indexes which belong to the target index; s2: voting for each sublevel index by a plurality of expert groups, and obtaining an evaluation table by each expert group; s3: solving fuzzy weight vectors of each evaluation table about the sublevel indexes; s4: fusing all the fuzzy weight vectors obtained in the step S3 through a D-S fusion criterion to obtain an evaluation weight vector, and obtaining probability distribution results of each evaluation result about the target index according to the evaluation weight vector; the voting options and the evaluation results of the target indexes are divided into a plurality of degree levels with the same number. Compared with the prior art, the method has the advantages of objectivity, accuracy and the like.

Description

Power distribution network state evaluation method based on information fusion
Technical Field
The invention relates to a power distribution network evaluation method, in particular to a power distribution network state evaluation method based on information fusion.
Background
The power distribution system is used as a terminal link directly facing a user, and is directly related to the quality and reliability of power consumption of the user. The power distribution network has the advantages of complex station types, wide distribution, changeable geographic environment, easy interference and damage, and large operation, maintenance and overhaul workload. With the rapid development of economy and the rapid expansion of power distribution networks, the development of power distribution automation and intelligent power distribution networks are the practical requirements of adapting to the personalized power supply requirements of users, supporting the access of distributed power supplies and realizing the intelligent operation management of power grids, and are the main directions of power distribution network development and construction. Urban power distribution networks of industrially developed countries are formed, the power distribution basic data management and power distribution first-aid repair management are very important, the power distribution operation management working efficiency is improved by advanced tools and means, and finally the advanced tools and means are used for providing high-quality service for customers; however, many countries do not implement feeder automation over a large area, but only in some load-intensive and sensitive areas.
The management level of power distribution networks at home and abroad is improved, one of the important technical means is the construction and application of power distribution automation, and the construction of the power distribution automation is in three stages of 'on-site' power distribution automation, power distribution monitoring automation and comprehensive power distribution automation. Along with the importance of the application of the power distribution network and the increasing level of power distribution network management, the importance of the application of the power distribution network and the increasing level of the power distribution network management are required to be correspondingly improved, and relevant researches are carried out by scholars at home and abroad for researching the power distribution network management from respective angles. The comprehensive evaluation method is characterized in that an analytic hierarchy process is adopted for comprehensive evaluation of operation management of the power distribution network in more research, the weight directly influences the scientific rationality of a comprehensive evaluation result for the problem of comprehensive evaluation, and a plurality of effective methods are provided for the problem of comprehensive evaluation of the power distribution network at present, but most of the effective methods have the following problems:
firstly, the weight is determined only by adopting a subjective or objective method, the subjective or objective single factor has a large shadow on the weighting result, the weight is determined by depending on the expert experience, and the objectivity is relatively poor;
and the other is dependent on data samples, information loss exists, and the weighting result has a certain gap with the actual situation.
Disclosure of Invention
The invention aims to overcome the defects of the prior art and provide a power distribution network state evaluation method based on information fusion, which integrates evaluation results obtained by grading of different expert groups and provides relatively objective comprehensive evaluation aiming at the subjectivity of the grading of the experts.
The purpose of the invention can be realized by the following technical scheme:
a power distribution network state evaluation method based on information fusion comprises the following steps:
s1: determining a target index of the power distribution network and a plurality of sub-level indexes belonging to the target index according to a power distribution network management comprehensive evaluation index selection principle;
s2: voting for each sublevel index by a plurality of expert groups, and obtaining an evaluation table by each expert group;
s3: solving fuzzy weight vectors of each evaluation table about the sublevel indexes;
s4: fusing all the fuzzy weight vectors obtained in the step S3 through a D-S fusion criterion to obtain an evaluation weight vector, and obtaining probability distribution results of each evaluation result about the target index according to the evaluation weight vector;
further, the target indexes of the power distribution network comprise automatic management, safety management, visual management, standardized management, cooperative management and efficient management;
the method quantifies the sub-level indexes with the target index characteristics, quantifies and describes the target index states through the evaluation result probability distribution of the states of the target indexes, further guides the planning targets and directions of the power distribution network, and can be applied to comparing and planning the power distribution network with the current power distribution network, visually quantificationally describing the implementation effect of power distribution network planning measures and evaluating and comparing various power distribution network planning schemes.
The evaluation results of the voting options and the target indexes are divided into a plurality of degree levels with the same number, each expert group comprises a plurality of experts, and the number of the experts in each group is the same.
Further, the calculation process of the D-S fusion criterion is:
the calculation formula of the D-S fusion criterion is as follows:
Figure BDA0002269014080000021
wherein, the fuzzy weight vector m: 2Θ→[0，1]Satisfy the following requirements
Figure BDA0002269014080000022
And m (Φ) ═ 0, the recognition frame Θ ═ H1，H2…HN}，H1，H2…HNRepresenting N voting choices or evaluation results arranged in order of degree,
Figure BDA0002269014080000024
for evaluating weight vectors, M is the number of expert groups, M1，m2…mMThe fuzzy weight vector of each evaluation table about the sublevel indexes, k size reflects evidence conflict degree, coefficient
Figure BDA0002269014080000023
Referred to as a normalization factor, to avoid assigning non-zero probabilities to the null set at the time of synthesis.
Further, the step S3 specifically includes:
s301: all expert groups score the sub-level indexes according to a 1-9 scale method, compare every two sub-level indexes, construct a weight judgment matrix which passes consistency test and is about the sub-level indexes, calculate the characteristic vector of the weight judgment matrix, normalize the characteristic vector to obtain the judgment weight vector of the weight judgment matrix, normalize the statistical result of the group expert votes in each evaluation table, and obtain the fuzzy evaluation matrix of each evaluation table;
s302: and multiplying the judgment weight vector of the sub-level index and the fuzzy evaluation matrix of each evaluation table to obtain the fuzzy weight vector of the evaluation table.
Further, the consistency check process specifically comprises:
sequentially calculating the maximum characteristic root lambda of the weight judgment matrixmaxJudging whether CR is less than 0.1 or not according to the consistency index CI and the consistency ratio CR, if so, continuing to adopt the detected primary index weight judgment matrix table and the detected secondary index weight judgment matrix, and otherwise, recollecting;
the calculation formula for CI and CR is:
Figure BDA0002269014080000031
where n is the matrix order.
Compared with the prior art, the invention has the following beneficial effects:
(1) according to the method, a plurality of expert groups are adopted to vote together aiming at the subjectivity of expert scoring, each expert group obtains one evaluation table, the fuzzy weight vector of each evaluation table about the sublevel index is solved, then all the fuzzy weight vectors are fused through a D-S fusion rule to obtain the evaluation weight vector of the probability distribution result of each evaluation result containing the target index, the evaluation results obtained by scoring of different expert groups are fused, the influence of artificial subjective factors is reduced, the level of a power distribution network can be reflected more truly, and the comprehensive evaluation is closer to the actual situation;
(2) according to the evaluation of an expert group, every two sub-level indexes are compared according to a 1-9 scale method, a weight judgment matrix which passes consistency test and is about the sub-level indexes is constructed, the importance degree among the sub-level indexes is fuzzy and uncertain, the importance degree number among the sub-level indexes is quantized through the 1-9 scale method, the uncertain events become more deterministic events, the influence degree of the sub-level indexes on the comprehensive evaluation result is more objective, and the evaluation result is more accurate;
(3) the target index, the number and the composition of the expert groups, the sub-level indexes and the number of the sub-level indexes can be flexibly selected, and the method has wide application range.
Drawings
FIG. 1 is a flow chart of a method of the present invention;
FIG. 2 is a frame diagram of an evaluation index system under M groups of experts and N sub-level indexes;
fig. 3 is a frame diagram of the evaluation index system of the present embodiment.
Detailed Description
The invention is described in detail below with reference to the figures and specific embodiments. The present embodiment is implemented on the premise of the technical solution of the present invention, and a detailed implementation manner and a specific operation process are given, but the scope of the present invention is not limited to the following embodiments.
A power distribution network state evaluation method based on information fusion, as shown in fig. 1, includes:
s1: as shown in fig. 2, a target index of the power distribution network and a plurality of sub-level indexes belonging to the target index are determined according to a power distribution network management comprehensive evaluation index selection principle, in this embodiment, an automatic management level of the power distribution network is selected as the target index, and the sub-level indexes are data extraction efficiency, data quality and an automation ratio, as shown in fig. 3;
s2: voting for each sublevel index by an expert group with 10 people to obtain 2 evaluation tables;
s3: solving fuzzy weight vectors of each evaluation table about the sublevel indexes;
s4: fusing all the fuzzy weight vectors obtained in the step S3 through a D-S fusion criterion to obtain an evaluation weight vector, and obtaining probability distribution results of each evaluation result about the target index according to the evaluation weight vector;
the following principles are followed when determining the sublevel indexes of the target indexes of the power distribution network:
the number of evaluation indexes is properly reduced and distributed in parallel according to the operability principle;
the objectivity principle respects objective history, fully utilizes the inherent information of original data and reduces artificial influence;
selecting qualitative and quantitative evaluation factors simultaneously according to a qualitative and quantitative combination principle;
the rationality principle is adopted, and the evaluation indexes are scientifically demonstrated, so that the development current situation of the power distribution network is comprehensively reflected, and the main characteristics of the power distribution network are comprehensively reflected;
scientific principle, mathematical model, evaluation index system and evaluation method keep strict logic;
the independence principle keeps independence among all evaluation indexes and reduces the correlation as much as possible;
and (4) systematic principle, and the target correlation among the related factors and the correlation and integrity among the factors are considered at the same time.
The voting options are classified into good, good and general 5 degree levels, namely, poor and poor, and the evaluation result of the automation management level of the power distribution network is classified into 5 degree levels, namely, excellent, good, qualified, basically qualified and unqualified.
Correspondingly acquiring two evaluation tables of the table 1 and the table 2 after voting by the expert group 1 and the expert group 2:
TABLE 1 automated management level expert group 1 scoring
A1 Good taste Is preferably used In general Is poor Difference (D)
Efficiency of data extraction 1 3 4 2 0
Quality of data 3 2 4 1 0
Automated ratio 1 2 4 2 1
TABLE 2 automated management level expert group 2 Scoring
A2 Good taste Is preferably used In general Is poor Difference (D)
Efficiency of data extraction 1 4 3 2 0
Quality of data 3 3 3 1 0
Automated ratio 2 2 3 2 1
The specific process of step S3 is:
s301: all expert groups score the sub-level indexes according to a 1-9 scale method, compare every two sub-level indexes and construct a weight judgment matrix which passes consistency test and is about the sub-level indexes;
the consistency checking process specifically comprises the following steps:
sequentially calculating the maximum characteristic root lambda of the weight judgment matrixmaxJudging whether CR is less than 0.1 or not according to the consistency index CI and the consistency ratio CR, if so, continuing to adopt the detected primary index weight judgment matrix table and the detected secondary index weight judgment matrix, and otherwise, recollecting;
the calculation formula for CI and CR is:
Figure BDA0002269014080000051
where n is the matrix order.
The weight determination matrix is shown in table 3:
TABLE 3 automated management weight determination matrix
A B1 B2 B3
B1 1 1 2
B2 1 1 3
B3 1/2 1/3 1
Wherein, a represents the automation management level, B1, B2 and B3 respectively represent the data extraction efficiency, the data quality and the automation proportion, and the construction of the judgment matrix under the 1-9 scale method is shown in table 4:
TABLE 4 judgment matrix construction basis
Figure BDA0002269014080000052
Figure BDA0002269014080000061
Calculating the characteristic vector of the weight judgment matrix, normalizing the characteristic vector to obtain the weight vector of the weight judgment matrix, and normalizing the intra-group expert voting statistical results of each evaluation table to obtain the fuzzy evaluation matrix of each evaluation table;
s302: multiplying the judgment weight vector of the sub-level index and the fuzzy evaluation matrix of each evaluation table to obtain the fuzzy weight vector of the evaluation table, as shown in table 5:
table 5 fuzzy weight vectors of table 1 and table 2
Figure BDA0002269014080000062
Wherein a1 represents the automation management level under the evaluation of the expert group 1, and a2 represents the automation management level under the evaluation of the expert group 2, as can be seen from table 5, when different experts rate, the evaluation of the automation management level of the power distribution network has great difference, if the first group of experts is adopted, 31.8% of experts consider the management level to be excellent, and when the second group of experts is adopted, only 18.9% of experts consider the management level to be excellent, the evaluation of the management level is not objective enough, and certain subjective influence exists.
The calculation formula of the D-S fusion criterion is as follows:
Figure BDA0002269014080000063
wherein, the fuzzy weight vector m: 2Θ→[0，1]Satisfy the following requirements
Figure BDA0002269014080000064
And m (Φ) ═ 0, the recognition frame Θ ═ H1，H2，H3，H4，H5}，H1，H2，H3，H4And H5Representing 5 voting choices or evaluation results arranged in order of degree,
Figure BDA0002269014080000065
for evaluating weight vectors, M is the number of expert groups, M1And m2The fuzzy weight vector of each evaluation table about the sublevel indexes, k size reflects evidence conflict degree, coefficient
Figure BDA0002269014080000066
Referred to as a normalization factor, to avoid assigning non-zero probabilities to the null set at the time of synthesis.
Calculations were performed according to table 1 and table 2:
k＝m1(H1)*m2(H2)+m1(H1)*m2(H3)+m1(H1)*m2(H4)+m1(H1)*m2(H5)+m2(H1)*m1(H2)+m2(H1)*m1(H3)+m2(H1)*m1(H4)+m2(H1)*m1(H5)+m1(H2)*m2(H3)+m1(H2)*m2(H4)+m1(H2)*m2(H5)+m2(H2)*m1(H3)+m2(H2)*m1(H4)+m2(H2)*m1(H5)+m1(H3)*m2(H4)m1(H3)*m2(H5)+m2(H3)*m1(H4)+m2(H3)*m1(H5)+m1(H4)*m2(H5)+m2(H4)*m1(H5)＝0.7712
m(H1)＝m1(H1)*m2(H1)/(1-k)＝0.2618
in the same way canTo obtain m (H)2)、m(H3)、m(H4) And m (H)5) As shown in Table 6:
table 6 integrated results of comprehensive evaluation of power distribution network automation management level after integration
H1 H2 H3 H4 H5
m 0.2618 0.1528 0.4446 0.1299 0.0077
As can be seen from the probability distribution of the evaluation results in table 6, the evaluation results after the fusion are integrated with the evaluation of two groups of experts, so that the evaluation of the automatic management level of the urban distribution network is more objective, wherein 26.5% and 15.3% of the experts respectively consider that the improvement of the automatic management level in the management mode of the urban distribution network is very obvious, 44.5% of the experts consider that the improvement of the automatic management level is more general, and 14% of the experts consider that the automatic management level is not substantially improved.
The method has important significance for strengthening the specialization and lean management of the power distribution network, the method quantifies sub-level indexes with target index characteristics according to the method, quantifies the target index state through the evaluation result probability distribution of the state of the target index, further guides the planning target and the direction of the power distribution network, and can be applied to comparing and planning the power grid with the current power grid, and visually and quantitatively describing the implementation effect of power grid planning measures and evaluating and comparing various power distribution network planning schemes.
The foregoing detailed description of the preferred embodiments of the invention has been presented. It should be understood that numerous modifications and variations could be devised by those skilled in the art in light of the present teachings without departing from the inventive concepts. Therefore, the technical solutions available to those skilled in the art through logic analysis, reasoning and limited experiments based on the prior art according to the concept of the present invention should be within the scope of protection defined by the claims.

Claims (9)

1. A power distribution network state evaluation method based on information fusion is characterized by comprising the following steps:
s1: determining a target index of the power distribution network and a plurality of sub-level indexes which belong to the target index;
s2: voting for each sublevel index by a plurality of expert groups, and obtaining an evaluation table by each expert group;
s3: solving fuzzy weight vectors of each evaluation table about the sublevel indexes;
s4: fusing all the fuzzy weight vectors obtained in the step S3 through a D-S fusion criterion to obtain an evaluation weight vector, and obtaining probability distribution results of each evaluation result about the target index according to the evaluation weight vector;
the voting options and the evaluation results of the target indexes are divided into a plurality of degree levels with the same number.
2. The power distribution network state evaluation method based on information fusion of claim 1, wherein each expert group comprises a plurality of experts and the number of experts in each group is the same.
3. The method for evaluating the state of the power distribution network based on the information fusion, according to claim 1, is characterized in that the calculation formula of the D-S fusion criterion is as follows:
Figure FDA0002269014070000011
Figure FDA0002269014070000012
wherein, the fuzzy weight vector m: 2Θ→[0，1]Satisfy the following requirements
Figure FDA0002269014070000013
And m (Φ) ═ 0, the recognition frame Θ ═ H1，H2…HN}，H1，H2…HNRepresenting N voting choices or evaluation results arranged in order of degree,
Figure FDA0002269014070000014
for evaluating weight vectors, M is the number of expert groups, M1，m2…mMFuzzy weight vector of each evaluation table about the sub-level index.
4. The method for evaluating the state of the power distribution network based on the information fusion as claimed in claim 1, wherein the step S3 specifically comprises the steps of:
s301: all expert groups evaluate and obtain a weight judgment matrix about the sublevel indexes passing consistency test, obtain a judgment weight vector of the weight judgment matrix, and calculate a fuzzy evaluation matrix of each evaluation table;
s302: and calculating to obtain the fuzzy weight vector of the evaluation table according to the judgment weight vector of the weight judgment matrix of the sublevel index and the fuzzy evaluation matrix of each evaluation table.
5. The power distribution network state evaluation method based on information fusion of claim 4, wherein the weight judgment matrix of the sub-level indexes is constructed according to a 1-9 scaling method.
6. The power distribution network state evaluation method based on information fusion according to claim 4, wherein the consistency check process specifically comprises:
sequentially calculating the maximum characteristic root lambda of the weight judgment matrixmaxJudging whether CR is less than 0.1 or not according to the consistency index CI and the consistency ratio CR, if so, continuing to adopt the detected primary index weight judgment matrix table and the detected secondary index weight judgment matrix, and otherwise, recollecting;
the calculation formula for CI and CR is:
Figure FDA0002269014070000021
Figure FDA0002269014070000022
where n is the matrix order.
7. The power distribution network state evaluation method based on information fusion according to claim 4, wherein the calculation process of the judgment weight vector is as follows:
and calculating the eigenvector of the weight judgment matrix, and normalizing the eigenvector to obtain the weight vector of the weight judgment matrix.
8. The power distribution network state evaluation method based on information fusion according to claim 4, wherein the fuzzy evaluation matrix calculation process of the evaluation table is as follows:
and normalizing the intra-group expert voting statistical results of the evaluation table to obtain a fuzzy evaluation matrix.
9. The method according to claim 1, wherein the target indexes of the power distribution network include automation management, security management, visualization management, standardization management, coordination management, and high efficiency management.
CN201911098218.4A 2019-11-12 2019-11-12 Power distribution network state evaluation method based on information fusion Pending CN111008759A (en)

Priority Applications (1)

Application Number Priority Date Filing Date Title
CN201911098218.4A CN111008759A (en) 2019-11-12 2019-11-12 Power distribution network state evaluation method based on information fusion

Applications Claiming Priority (1)

Application Number Priority Date Filing Date Title
CN201911098218.4A CN111008759A (en) 2019-11-12 2019-11-12 Power distribution network state evaluation method based on information fusion

Publications (1)

Publication Number Publication Date
CN111008759A true CN111008759A (en) 2020-04-14

Family

ID=70111944

Family Applications (1)

Application Number Title Priority Date Filing Date
CN201911098218.4A Pending CN111008759A (en) 2019-11-12 2019-11-12 Power distribution network state evaluation method based on information fusion

Country Status (1)

Country Link
CN (1) CN111008759A (en)

Citations (3)

* Cited by examiner, † Cited by third party
Publication number Priority date Publication date Assignee Title
CN106997489A (en) * 2017-03-09 2017-08-01 国家电网公司 New variable impedance transformer state evaluating method based on evidence theory
CN107563601A (en) * 2017-08-08 2018-01-09 中国计量科学研究院 A kind of intelligent electric energy meter evaluation of running status method
CN109685340A (en) * 2018-12-11 2019-04-26 国网山东省电力公司青岛供电公司 A kind of controller switching equipment health state evaluation method and system

Patent Citations (3)

* Cited by examiner, † Cited by third party
Publication number Priority date Publication date Assignee Title
CN106997489A (en) * 2017-03-09 2017-08-01 国家电网公司 New variable impedance transformer state evaluating method based on evidence theory
CN107563601A (en) * 2017-08-08 2018-01-09 中国计量科学研究院 A kind of intelligent electric energy meter evaluation of running status method
CN109685340A (en) * 2018-12-11 2019-04-26 国网山东省电力公司青岛供电公司 A kind of controller switching equipment health state evaluation method and system

Non-Patent Citations (1)

* Cited by examiner, † Cited by third party
Title
刘子潇;: "基于模糊综合评价法的电动汽车充电站选址决策" *

Similar Documents

Publication Publication Date Title
Sun et al. Using Bayesian deep learning to capture uncertainty for residential net load forecasting
CN109409628B (en) Acquisition terminal manufacturer evaluation method based on metering big data clustering model
CN110222991B (en) Metering device fault diagnosis method based on RF-GBDT
CN112054943B (en) Traffic prediction method for mobile network base station
CN104376413A (en) Power grid planning scheme evaluation system based on analytic hierarchy process and data envelopment analysis
CN104331773A (en) Comprehensive assessment method for power network planning schemes
CN105373894A (en) Inspection data-based power marketing service diagnosis model establishing method and system
CN103617447B (en) The evaluation system of intelligent substation and evaluation methodology
CN105046582A (en) Convenient power grid security risk evaluation method
CN105956788A (en) Dynamic management control method for cost of power transmission and transformation project
CN111080101A (en) AHP-based multi-dimensional evaluation method for service efficiency of power supply channel
CN108549907A (en) A kind of data verification method based on multi-source transfer learning
CN114386884B (en) Lean evaluation method for power grid dispatching operation
CN114266289A (en) Complex equipment health state assessment method
CN116011827A (en) Power failure monitoring analysis and early warning system and method for key cells
CN112101785A (en) Method for analyzing comprehensive benefits of power and communication sharing iron tower
CN115829145A (en) Photovoltaic power generation capacity prediction system and method
CN115660170A (en) Multidimensional index weight collaborative optimization data asset management effect differentiation evaluation method and system
CN115358437A (en) Power supply load prediction method based on convolutional neural network
Lin et al. An online data-driven risk assessment method for resilient distribution systems
CN111091223A (en) Distribution transformer short-term load prediction method based on Internet of things intelligent sensing technology
CN114553671A (en) Diagnosis method for power communication network fault alarm
Qu et al. Research on short‐term output power forecast model of wind farm based on neural network combination algorithm
CN115905319B (en) Automatic identification method and system for abnormal electricity fees of massive users
CN111160719A (en) Two-network fused multi-index evaluation method

Legal Events

Date Code Title Description
PB01 Publication
PB01 Publication
SE01 Entry into force of request for substantive examination
SE01 Entry into force of request for substantive examination