CN112085333B - Power distribution network construction control index incidence relation research method based on incidence algorithm - Google Patents

Power distribution network construction control index incidence relation research method based on incidence algorithm Download PDF

Info

Publication number
CN112085333B
CN112085333B CN202010785079.9A CN202010785079A CN112085333B CN 112085333 B CN112085333 B CN 112085333B CN 202010785079 A CN202010785079 A CN 202010785079A CN 112085333 B CN112085333 B CN 112085333B
Authority
CN
China
Prior art keywords
index
power distribution
distribution network
data
degree
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.)
Active
Application number
CN202010785079.9A
Other languages
Chinese (zh)
Other versions
CN112085333A (en
Inventor
于昊正
陈鹏浩
何永秀
郁晋雄
潘肇伦
孙慧君
王可蕙
李科
周鹏
郭新志
杨卓
李会涛
王利利
贾书艳
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.)
North China Electric Power University
Economic and Technological Research Institute of State Grid Henan Electric Power Co Ltd
Original Assignee
North China Electric Power University
Economic and Technological Research Institute of State Grid Henan 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 North China Electric Power University, Economic and Technological Research Institute of State Grid Henan Electric Power Co Ltd filed Critical North China Electric Power University
Priority to CN202010785079.9A priority Critical patent/CN112085333B/en
Publication of CN112085333A publication Critical patent/CN112085333A/en
Application granted granted Critical
Publication of CN112085333B publication Critical patent/CN112085333B/en
Active legal-status Critical Current
Anticipated expiration legal-status Critical

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
    • 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
    • Y—GENERAL TAGGING OF NEW TECHNOLOGICAL DEVELOPMENTS; GENERAL TAGGING OF CROSS-SECTIONAL TECHNOLOGIES SPANNING OVER SEVERAL SECTIONS OF THE IPC; TECHNICAL SUBJECTS COVERED BY FORMER USPC CROSS-REFERENCE ART COLLECTIONS [XRACs] AND DIGESTS
    • Y04—INFORMATION OR COMMUNICATION TECHNOLOGIES HAVING AN IMPACT ON OTHER TECHNOLOGY AREAS
    • Y04S—SYSTEMS INTEGRATING TECHNOLOGIES RELATED TO POWER NETWORK OPERATION, COMMUNICATION OR INFORMATION TECHNOLOGIES FOR IMPROVING THE ELECTRICAL POWER GENERATION, TRANSMISSION, DISTRIBUTION, MANAGEMENT OR USAGE, i.e. SMART GRIDS
    • Y04S10/00—Systems supporting electrical power generation, transmission or distribution
    • Y04S10/50—Systems or methods supporting the power network operation or management, involving a certain degree of interaction with the load-side end user applications

Abstract

The invention relates to a power distribution network construction management and control index incidence relation research method based on an incidence algorithm, which comprises the following steps: step 1: collecting and controlling key index data in the whole process of a power distribution network construction project to form an index system; step 2: preprocessing data; and step 3: finding out association rules by using an Apriori algorithm; and 4, step 4: and analyzing the calculated association rule, and combing the association relation among the indexes in the index system. The construction data of the power distribution network has the characteristics of large volume, complex attributes, difficult collection and the like, is lack of data overall analysis, has low decision level, and disperses a large amount of data in different works, processes and systems. The relation between the determined power distribution network construction control indexes is difficult to determine, and the relation between the indexes is likely to have larger deviation only by experience judgment.

Description

Power distribution network construction control index incidence relation research method based on incidence algorithm
Technical Field
The invention belongs to the field of overall management and control of power distribution network construction, is suitable for finding out the incidence relation among key management and control indexes, and particularly relates to a power distribution network construction management and control index incidence relation research method based on an incidence algorithm.
Background
The power distribution network has huge construction projects and different types, and a large amount of complex data relations are generated in the construction process. And forming a management and control index system of each stage of the project by combing key management and control indexes of the power distribution network construction project. And mining the incidence relation among all key indexes based on an Apriori algorithm so as to better realize the project group management of the power distribution network.
At present, the theory of the method for mining association rules based on the association algorithm is relatively mature, such as DHP algorithm and FP-Growth algorithm. However, when the DHP algorithm needs to spend a lot of time building the hash table and uses the number recorded by the hash hierarchy to estimate the support of the candidate item set, the support of some item sets is overestimated, resulting in a high false positive rate in the initial stage; the excavated result of the FP-Growth algorithm is too detailed, sometimes the result is not required to be so detailed, and in addition, the algorithm requires much time and space to construct an FP-tree in the excavating process; the Apriori algorithm uses the prior property, so that the efficiency of the layer-by-layer generation of the frequent item set is greatly improved. The number of power distribution network construction projects is huge, the types of the power distribution network construction projects are different, a large amount of complex data are generated in the construction process, and if the projects are managed one by one, a large amount of manpower is consumed, so that the cleaning of the association relation among key indexes of the power distribution network construction projects is very necessary for the management of the power distribution network construction projects, and no technology relates to the field at present.
Disclosure of Invention
Aiming at the defects in the prior art, the invention provides a power distribution network construction management and control index association relation research method based on an association algorithm, and aims to analyze key management and control indexes of the whole process of construction of a plurality of power distribution network projects by using an Apriori algorithm, calculate the support degree, the confidence degree and the promotion degree among the indexes, compare the support degree, the confidence degree and the promotion degree with a set threshold value, mine the association relation in the indexes and provide reference for power distribution network construction project management.
In order to achieve the above purposes, the technical scheme adopted by the invention is as follows:
a power distribution network construction management and control index association relation research method based on an association algorithm comprises the following steps:
step 1: collecting control key index data of the whole process of a power distribution network construction project to form an index system;
and 2, step: preprocessing data;
and 3, step 3: finding out association rules by using an Apriori algorithm;
and 4, step 4: and analyzing the found association rule, and combing the association relation among the indexes in the index system.
On the basis of the scheme, the specific steps of the step 2 are as follows:
(1) Deleting invalid records in the management and control key index data:
the data of the management and control key indexes is 0 or 1,0, which indicates that the management and control key indexes have no deviation, 1 indicates that the management and control key indexes have deviation, and the data which is not 0 or 1 is deleted;
(2) Deleting the management and control key index data with missing values:
27 pieces of control key index data are drawn, and data with missing values are deleted in an index system.
On the basis of the scheme, the specific steps of the step 3 are as follows:
supposing that n power distribution network construction project data are collected, wherein each project data comprises the completion conditions of m control key indexes, and each of the n power distribution network construction project data records that at least one control key index in m control key indexes has deviation;
Figure BDA0002621648800000021
in the formula: x is the number of ij The implementation condition of the jth index of the ith power distribution network construction project is shown; i =1,2, …, n; j =1,2, …, m;
calculating the support degree between the jth index and the kth index
Figure BDA0002621648800000031
Confidence level
Figure BDA0002621648800000032
Degree of lifting
Figure BDA0002621648800000033
As shown in formulas (2) to (6):
Figure BDA0002621648800000034
Figure BDA0002621648800000035
Figure BDA0002621648800000036
Figure BDA0002621648800000037
Figure BDA0002621648800000038
in the formula: sigma jk The number of items of which the jth index is deviated when the jth index is deviated in n power distribution network construction projects is k =1,2, …, m; sigma k 、σ j Respectively representing the number of items with deviation of the kth index and the jth index in n power distribution network construction items; support (j) represents the support of the jth index; support (k) indicates the support of the kth index.
If the calculated support degree between the jth index and the kth index
Figure BDA0002621648800000039
Confidence level
Figure BDA00026216488000000310
Degree of lifting
Figure BDA00026216488000000311
If the three conditions of the equations (7) - (9) are satisfied simultaneously, the probability that the k-th index has deviation is increased when the j-th index has deviation, so that the k-th index is considered to be associated with the j-th index; otherwise, the k index and the j index are considered to have no association relation;
Figure BDA00026216488000000312
Figure BDA00026216488000000313
Figure BDA00026216488000000314
in the formula, T 1 ，T 2 ，T 3 Respectively threshold values of support degree, confidence degree and promotion degree;
in the first iteration, calculating the support degree, the confidence degree and the promotion degree of each item in an index system, comparing the support degree, the confidence degree and the promotion degree with a set threshold value, and recording all found frequent item sets as 1-; in the 2 nd iteration, taking the 1-frequent item set as a seed item set of the 2 nd iteration so as to generate a candidate 2-item set; in the 2 nd iteration, in order to mine all 2-frequent item sets as seed item sets of the next iteration, the actual support degree, confidence degree and promotion degree of each candidate 2-item set need to be calculated and compared with a set threshold value, and the 2-frequent item sets are found out; the iterative process continues until a new set of frequent items cannot be generated.
The invention has the beneficial effects that:
the construction data of the power distribution network has the characteristics of large volume, complex attributes, difficult collection and the like, is lack of data overall analysis, has low decision level, and disperses a large amount of data in different works, processes and systems. The relation between the determined power distribution network construction control indexes is difficult to determine, and the relation between the indexes is likely to have larger deviation only by experience judgment.
Drawings
The invention has the following drawings:
FIG. 1 is a flow chart of the present invention.
FIG. 2 shows a raw index data preprocessing process.
Fig. 3Apriori algorithm flow chart.
FIG. 4 is a diagram of a power distribution network construction project management and control key index association relationship.
Detailed Description
The invention is described in further detail below with reference to figures 1-4.
A power distribution network construction management and control index incidence relation research method based on an incidence algorithm comprises the following steps:
step 1:
in the step 1, collecting management and control data of a power distribution network construction project to form an index system;
the remarks are as follows:
when collecting load data, the integrity and accuracy of the data are guaranteed as much as possible.
Step 2:
in step 2, the data preprocessing method is as follows, and the specific process is as shown in fig. 2:
during data preprocessing, the correctness of the calculation result is affected by the absence or the mistiming of the index data, so the index data should be preprocessed before calculation, and the method is as follows:
(1) Deleting invalid records in index data
The control key index data required by the research is 0 or 1.0 indicates that the index has no deviation, and 1 indicates that the index has deviation. Data other than 0 or 1 is deleted.
(2) Deleting missing data
27 key management and control indexes are drawn up, and data with missing indexes are deleted in an index system.
And step 3:
in step 3, the method for determining the power distribution network construction project management and control index association relationship comprises the following steps:
assuming that n power distribution network construction project data are collected, each project data comprises the completion condition of m key indexes, and each piece of n power distribution network construction project data records that at least one control key index in m has deviation;
Figure BDA0002621648800000051
in the formula: x is a radical of a fluorine atom ij The implementation condition of the jth index of the ith power distribution network construction project is shown; i =1,2, …, n; j =1,2, …, m.
Calculating the support degree between the jth index and the kth index
Figure BDA0002621648800000052
Confidence level
Figure BDA0002621648800000053
Degree of lifting
Figure BDA0002621648800000054
As shown in formulas (2) to (6).
Figure BDA0002621648800000055
Figure BDA0002621648800000056
Figure BDA0002621648800000061
Figure BDA0002621648800000062
Figure BDA0002621648800000063
In the formula: sigma jk The number of items of which the jth index is deviated when the jth index is deviated in n power distribution network construction projects is k =1,2, …, m; sigma k 、σ j Respectively representing the number of items with deviation of the kth index and the jth index in n power distribution network construction items; support (j) represents the support of the jth index; support (k) indicates the support of the kth index.
If the calculated support degree between the jth index and the kth index
Figure BDA0002621648800000064
Confidence level
Figure BDA0002621648800000065
Degree of lifting
Figure BDA0002621648800000066
Is full at the same timeIf the three conditions of equations (7) to (9) are satisfied, the probability of the deviation of the kth index is increased when the jth index is considered to be deviated, and therefore the kth index is considered to be associated with the jth index; otherwise, the k index and the j index are not associated.
Figure BDA0002621648800000067
Figure BDA0002621648800000068
Figure BDA0002621648800000069
In the formula, T 1 ，T 2 ，T 3 Respectively, support degree, confidence degree and lifting degree.
In the first iteration, the support degree, the confidence degree and the promotion degree of each item in the index system are calculated and compared with the set threshold value, and all the frequent items found are set as 1-. In the 2 nd iteration, the 1-frequent item set is taken as a seed item set of the 2 nd iteration, so as to generate a candidate 2-item set. In the 2 nd iteration, in order to mine all 2-frequent item sets as the seed item set of the next iteration, the actual support degree, confidence degree and promotion degree of each candidate 2-item set need to be calculated and compared with the set threshold value to find out the 2-frequent item set. The iterative process continues until a new set of frequent items cannot be generated. The algorithmic process is shown in fig. 3.
And 4, step 4:
in step 4, the incidence relation between the key control indexes of the whole process of the power distribution network construction project is analyzed according to the incidence relation result calculated in the step 3. Finally, the relationship between indexes mined according to the mining is shown in FIG. 4.
Detailed description of the preferred embodiment
1528 records of management and control key index data of a power distribution network construction project are collected firstly in the research. And secondly, deleting invalid data samples from the index data samples. After data processing, 94 invalid sample records and 1434 valid sample records exist in the sample data.
And inputting the sample records after data processing into an Apriori algorithm model. According to a set threshold value (T) 1 ＝0.3、T 2 ＝0.6、T 3 = 1) the correlation between the indices is obtained, and since the calculated correlation is large, the correlation including two indices associated with the rationality of the addressing is shown here as shown in table 1.
TABLE 1 address selection rationality association
Figure BDA0002621648800000071
It can be seen that in the association relation of item 1,
Figure BDA0002621648800000072
Figure BDA0002621648800000073
the records of 38% in the project set are the records with deviation in the rationality of the site selection and the design progress, and the confidence coefficient of 0.79 indicates that the records of the project with deviation in the rationality of the site selection of 79% also have deviation in the design progress. A boost of greater than 1 indicates that the two are positively correlated, with larger values being more correlated.
The examination and approval progress, labor cost, mechanical cost, equipment operation efficiency and constructor efficiency are also related to the rationality of the site selection, and when deviation occurs in the rationality of the site selection, indexes related to the rationality of the site selection are prone to deviation.
When a power distribution network construction project is managed in the future, if a certain index has deviation, the associated index can be managed and controlled in advance, the influence on project implementation is reduced, and the effect of prior control is achieved.
The technical key points and points to be protected of the invention are as follows:
1. a power distribution network construction management and control index association relation research method based on an Apriori algorithm is provided. According to the determined control indexes of the power distribution network construction project, the Apriori association algorithm can dig out association relations among the control indexes from massive power distribution network construction data.
2. And excavating the association relation between the control indexes based on an Apriori algorithm, comparing and analyzing the association relation with the association relation existing in the experience, and judging whether the excavated association relation is reasonable or making up for the defects of the past experience. And a reference is provided for the future power distribution network construction project management and control.
Those not described in detail in this specification are well within the skill of the art.

Claims (2)

1. A power distribution network construction management and control index incidence relation research method based on an incidence algorithm is characterized by comprising the following steps:
step 1: collecting control key index data of the whole process of a power distribution network construction project, and forming an index system;
step 2: preprocessing data;
and step 3: finding out association rules by using an Apriori algorithm;
and 4, step 4: analyzing the found association rule, and combing out the association relation among all indexes in the index system;
the specific steps of the step 3 are as follows:
assuming that n power distribution network construction project data are collected, each project data comprises the completion condition of m control key indexes, and each of the n power distribution network construction project data records that at least one control key index in m control key indexes has deviation;
Figure FDA0003867994600000011
in the formula: x is the number of ij The implementation condition of the jth index of the ith power distribution network construction project is shown; i =1,2, …, n; j =1,2, …, m;
calculating the support degree between the jth index and the kth index
Figure FDA0003867994600000012
Confidence level
Figure FDA0003867994600000013
Degree of lifting
Figure FDA0003867994600000014
As shown in formulas (2) to (6):
Figure FDA0003867994600000015
Figure FDA0003867994600000016
Figure FDA0003867994600000017
Figure FDA0003867994600000018
Figure FDA0003867994600000019
in the formula: sigma jk The number of items of which the jth index is deviated when the jth index is deviated in n power distribution network construction projects is k =1,2, …, m; sigma k 、σ j Respectively representing the number of items with deviation of the kth index and the jth index in n power distribution network construction items; support (j) represents the support of the jth index; support (k) represents the support of the kth index;
if the calculated support degree between the jth index and the kth index
Figure FDA0003867994600000021
Confidence level
Figure FDA0003867994600000022
Degree of lifting
Figure FDA0003867994600000023
If the three conditions of the formulas (7) - (9) are satisfied simultaneously, the possibility that the k index has deviation is increased when the j index has deviation, so that the k index is considered to be associated with the j index; otherwise, the k index and the j index are considered to have no association relation;
Figure FDA0003867994600000024
Figure FDA0003867994600000025
Figure FDA0003867994600000026
in the formula, T 1 ，T 2 ，T 3 Respectively threshold values of support degree, confidence degree and promotion degree;
in the first iteration, calculating the support degree, the confidence degree and the promotion degree of each item in an index system, comparing the support degree, the confidence degree and the promotion degree with a set threshold value, and recording all found frequent item sets as 1-; in the 2 nd iteration, taking the 1-frequent item set as a seed item set of the 2 nd iteration so as to generate a candidate 2-item set; in the 2 nd iteration, in order to mine all 2-frequent item sets as seed item sets of the next iteration, the actual support degree, confidence degree and promotion degree of each candidate 2-item set need to be calculated and compared with a set threshold value, and the 2-frequent item sets are found out; the iterative process continues until a new set of frequent items cannot be generated.
2. The method for researching the association relationship of the construction management and control indexes of the power distribution network based on the association algorithm as claimed in claim 1, wherein the specific steps in step 2 are as follows:
(1) Deleting invalid records in the management and control key index data:
the data of the control key indexes is 0 or 1,0, which indicates that the control key indexes have no deviation, 1 indicates that the control key indexes have deviation, and the data which is not 0 or 1 is deleted;
(2) Deleting the management and control key index data with missing values:
27 pieces of control key index data are drawn, and data with missing values are deleted in an index system.
CN202010785079.9A 2020-08-06 2020-08-06 Power distribution network construction control index incidence relation research method based on incidence algorithm Active CN112085333B (en)

Priority Applications (1)

Application Number Priority Date Filing Date Title
CN202010785079.9A CN112085333B (en) 2020-08-06 2020-08-06 Power distribution network construction control index incidence relation research method based on incidence algorithm

Applications Claiming Priority (1)

Application Number Priority Date Filing Date Title
CN202010785079.9A CN112085333B (en) 2020-08-06 2020-08-06 Power distribution network construction control index incidence relation research method based on incidence algorithm

Publications (2)

Publication Number Publication Date
CN112085333A CN112085333A (en) 2020-12-15
CN112085333B true CN112085333B (en) 2023-01-17

Family

ID=73734884

Family Applications (1)

Application Number Title Priority Date Filing Date
CN202010785079.9A Active CN112085333B (en) 2020-08-06 2020-08-06 Power distribution network construction control index incidence relation research method based on incidence algorithm

Country Status (1)

Country Link
CN (1) CN112085333B (en)

Family Cites Families (7)

* Cited by examiner, † Cited by third party
Publication number Priority date Publication date Assignee Title
CN103700029A (en) * 2013-12-16 2014-04-02 国家电网公司 Establishing method for post-evaluation index system for power grid construction project
CN106681882A (en) * 2015-11-06 2017-05-17 上海瑞致软件有限公司 IT-service concentrated monitoring and managing system based on Apriori algorithm
CN105843210B (en) * 2016-03-22 2018-11-09 清华大学 Power transformer defect information data digging method
CN107451708A (en) * 2017-04-26 2017-12-08 国家电网公司 A kind of grid equipment monitoring information confidence association analysis method based on Apriori algorithm
US10430898B2 (en) * 2017-12-06 2019-10-01 NAD Grid Corp Method and system for facilitating electricity services
CN108629528A (en) * 2018-06-20 2018-10-09 国网江苏省电力有限公司电力科学研究院 Quality of Transformer problem analysis method based on Apriori algorithm
CN110298056A (en) * 2019-03-27 2019-10-01 国网浙江海盐县供电有限公司 A kind of power distribution network contact efficiency assessment method

Also Published As

Publication number Publication date
CN112085333A (en) 2020-12-15

Similar Documents

Publication Publication Date Title
CN107169628B (en) Power distribution network reliability assessment method based on big data mutual information attribute reduction
CN111105332B (en) Highway intelligent pre-maintenance method and system based on artificial neural network
CN111046341A (en) Unconventional natural gas fracturing effect evaluation and capacity prediction method based on principal component analysis
CN115564114B (en) Airspace carbon emission short-term prediction method and system based on graph neural network
CN110210169B (en) LSTM-based shield tunneling machine fault prediction method
CN106815652A (en) A kind of distribution network reliability Forecasting Methodology based on big data correlation analysis
CN112949202A (en) Bayesian network-based rockburst probability prediction method
CN112990500A (en) Transformer area line loss analysis method and system based on improved weighted gray correlation analysis
CN111709668A (en) Power grid equipment parameter risk identification method and device based on data mining technology
CN115049124A (en) Deep and long tunnel water inrush prediction method based on Bayesian network
CN115310361A (en) Method and system for predicting underground dust concentration of coal mine based on WGAN-CNN
CN113609770A (en) Rolling bearing RUL prediction method based on piecewise linear fitting HI and LSTM
CN116384700A (en) Energy efficiency optimization method for central air conditioning system based on data mining
CN104317794A (en) Chinese feature word association pattern mining method based on dynamic project weight and system thereof
CN116226103A (en) Method for detecting government data quality based on FPGrow algorithm
CN116796403A (en) Building energy saving method based on comprehensive energy consumption prediction of commercial building
CN110781206A (en) Method for predicting whether electric energy meter in operation fails or not by learning meter-dismantling and returning failure characteristic rule
CN112085333B (en) Power distribution network construction control index incidence relation research method based on incidence algorithm
CN114548493A (en) Method and system for predicting current overload of electric energy meter
CN107977727B (en) Method for predicting blocking probability of optical cable network based on social development and climate factors
CN111210147B (en) Sintering process operation performance evaluation method and system based on time sequence feature extraction
CN114492996A (en) Water taking tunnel progress risk analysis method considering emotion factors
CN111625525A (en) Environmental data repairing/filling method and system
CN113743453A (en) Population quantity prediction method based on random forest
CN112052277A (en) Voltage sag severity assessment method and device based on big data

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
GR01 Patent grant
GR01 Patent grant