CN108665181A - A kind of appraisal procedure and device of distribution network reliability - Google Patents
A kind of appraisal procedure and device of distribution network reliability Download PDFInfo
- Publication number
- CN108665181A CN108665181A CN201810478810.6A CN201810478810A CN108665181A CN 108665181 A CN108665181 A CN 108665181A CN 201810478810 A CN201810478810 A CN 201810478810A CN 108665181 A CN108665181 A CN 108665181A
- Authority
- CN
- China
- Prior art keywords
- distribution network
- index
- network equipment
- failure rate
- indicate
- 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
Links
- 238000009826 distribution Methods 0.000 title claims abstract description 323
- 238000000034 method Methods 0.000 title claims abstract description 50
- 238000012937 correction Methods 0.000 claims abstract description 182
- 230000008439 repair process Effects 0.000 claims abstract description 66
- 238000013528 artificial neural network Methods 0.000 claims abstract description 54
- 230000005611 electricity Effects 0.000 claims description 44
- 238000012545 processing Methods 0.000 claims description 18
- 230000008676 import Effects 0.000 claims description 16
- 238000012216 screening Methods 0.000 claims description 12
- 230000032683 aging Effects 0.000 claims description 11
- 230000008569 process Effects 0.000 claims description 11
- 238000011156 evaluation Methods 0.000 claims description 10
- 230000004888 barrier function Effects 0.000 claims description 5
- 230000007613 environmental effect Effects 0.000 claims description 5
- 230000035945 sensitivity Effects 0.000 claims description 2
- 210000004218 nerve net Anatomy 0.000 claims 1
- 210000002569 neuron Anatomy 0.000 description 28
- 230000006870 function Effects 0.000 description 20
- 230000004913 activation Effects 0.000 description 8
- 238000004590 computer program Methods 0.000 description 7
- 238000004422 calculation algorithm Methods 0.000 description 6
- 238000011161 development Methods 0.000 description 6
- 230000018109 developmental process Effects 0.000 description 6
- 238000010586 diagram Methods 0.000 description 6
- 238000010801 machine learning Methods 0.000 description 6
- 238000004364 calculation method Methods 0.000 description 5
- 238000005457 optimization Methods 0.000 description 5
- 230000005540 biological transmission Effects 0.000 description 3
- 238000003066 decision tree Methods 0.000 description 3
- 238000007637 random forest analysis Methods 0.000 description 3
- 238000010206 sensitivity analysis Methods 0.000 description 3
- 238000012706 support-vector machine Methods 0.000 description 3
- 240000002853 Nelumbo nucifera Species 0.000 description 2
- 235000006508 Nelumbo nucifera Nutrition 0.000 description 2
- 235000006510 Nelumbo pentapetala Nutrition 0.000 description 2
- 230000001133 acceleration Effects 0.000 description 2
- 238000003483 aging Methods 0.000 description 2
- 238000004458 analytical method Methods 0.000 description 2
- 230000008859 change Effects 0.000 description 2
- 238000010276 construction Methods 0.000 description 2
- 230000001066 destructive effect Effects 0.000 description 2
- 238000005516 engineering process Methods 0.000 description 2
- 238000009434 installation Methods 0.000 description 2
- 238000012423 maintenance Methods 0.000 description 2
- 238000005259 measurement Methods 0.000 description 2
- 238000003860 storage Methods 0.000 description 2
- 239000003643 water by type Substances 0.000 description 2
- 238000005303 weighing Methods 0.000 description 2
- 244000131316 Panax pseudoginseng Species 0.000 description 1
- 235000005035 Panax pseudoginseng ssp. pseudoginseng Nutrition 0.000 description 1
- 235000003140 Panax quinquefolius Nutrition 0.000 description 1
- 238000013459 approach Methods 0.000 description 1
- 230000015572 biosynthetic process Effects 0.000 description 1
- 238000012217 deletion Methods 0.000 description 1
- 230000037430 deletion Effects 0.000 description 1
- 230000000694 effects Effects 0.000 description 1
- JEIPFZHSYJVQDO-UHFFFAOYSA-N ferric oxide Chemical compound O=[Fe]O[Fe]=O JEIPFZHSYJVQDO-UHFFFAOYSA-N 0.000 description 1
- 235000008434 ginseng Nutrition 0.000 description 1
- 238000007689 inspection Methods 0.000 description 1
- 238000004519 manufacturing process Methods 0.000 description 1
- 238000012986 modification Methods 0.000 description 1
- 230000004048 modification Effects 0.000 description 1
- 230000003287 optical effect Effects 0.000 description 1
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 present invention provides a kind of appraisal procedure of distribution network reliability and devices, first obtain Fisrt fault repair time index set and Fisrt fault rate index set, then the second fault correction time index set and the second failure rate index set are obtained, finally predict the fault correction time and failure rate of Distribution Network Equipment, and distribution network reliability is assessed, the present invention deletes the technical indicator for being unsatisfactory for neural network bulk sample this local derviation susceptibility requirement, alleviate the complexity of prediction model index, also filter out the socioeconomic environment indicator for meeting that fault correction time and the failure rate degree of correlation require from preset socioeconomic environment indicator respectively by Pearson correlation coefficients method, improve the confidence level of evaluating reliability of distribution network result, ensure the accuracy of evaluating reliability of distribution network result, it is more in line with reality and business demand.
Description
Technical field
The present invention relates to distribution network technology fields, and in particular to a kind of appraisal procedure and device of distribution network reliability.
Background technology
Dependability parameter needed for evaluating reliability of distribution network mainly includes Distribution Network Equipment failure rate, Distribution Network Equipment event
Hinder repair time and switching time, from the point of view of fault outage angle, the parameter master that is affected to reliability assessment result
There are the fault correction time and failure rate of Distribution Network Equipment.And influence Distribution Network Equipment fault correction time and failure rate because
Element is more, can be regarded as an index set, is typically reliable according to expert's offer or generally acknowledged power distribution network in the prior art
Property assessment parameter index collection establish model evaluating reliability of distribution network parameter predicted, ignore evaluating reliability of distribution network
Index is the existing information redundancy in terms of data modeling and disturbance degree the problem of, and traditional evaluating reliability of distribution network parameter
Index set, which is considered, is limited only to service technique level, and then causes distribution network reliability parameter evaluation credible result degree low.
Invention content
In order to overcome the shortcomings of that the above-mentioned parameter evaluation of distribution network reliability in the prior art credible result degree is low, the present invention carries
For the appraisal procedure and device of a kind of distribution network reliability, first obtains Fisrt fault repair time index set and Fisrt fault rate refers to
Mark collection, then obtains the second fault correction time index set and the second failure rate index set, finally predicts the event of Distribution Network Equipment
Hinder repair time and failure rate, and distribution network reliability is assessed, it is inclined that present invention deletion is unsatisfactory for neural network bulk sample sheet
The technical indicator for leading susceptibility requirement alleviates the complexity of prediction model index, is also distinguished by Pearson correlation coefficients method
The social economy for meeting that fault correction time and the failure rate degree of correlation require is filtered out from preset socioeconomic environment indicator
Environmental index improves the confidence level of evaluating reliability of distribution network result, ensures the accuracy of evaluating reliability of distribution network result,
It is more in line with reality and business demand.
In order to achieve the above-mentioned object of the invention, the present invention adopts the following technical scheme that：
On the one hand, the present invention provides a kind of appraisal procedure of distribution network reliability, including：
It is unsatisfactory for god from being deleted in the primary fault repair time index set and primary fault rate index set of Distribution Network Equipment
The technical indicator required through network bulk sample this local derviation susceptibility, obtains Fisrt fault repair time index set and Fisrt fault rate refers to
Mark collection；
It is filtered out from preset socioeconomic environment indicator respectively by Pearson correlation coefficients method and meets fault restoration
The socioeconomic environment indicator that time and the failure rate degree of correlation require, and it is separately added into Fisrt fault repair time index set and the
One failure rate index set obtains the second fault correction time index set and the second failure rate index set；
It is set according to target value prediction power distribution network is respectively referred in the second fault correction time index set and the second failure rate index set
Standby fault correction time and failure rate, and distribution network reliability is commented by the fault correction time and failure rate of prediction
Estimate.
Technical indicator in the primary fault repair time index set of the Distribution Network Equipment includes influencing on-load switch event
Hinder the technical indicator of repair time and influences the technical indicator of other Distribution Network Equipment fault correction times；
The technical indicator for influencing on-load switch fault correction time includes new input on-load switch quantity, put into operation the time limit
Less than or equal to 5 years quantity accountings, the time limit that puts into operation are more than 5 years and are more than 15 years less than or equal to 15 years quantity accountings, the time limit that puts into operation
Amount accounting, import volume accounting, joint quantity accounting, domestic quantity accounting, for indoor on-load switch quantity accounting, be used for
Outdoor on-load switch quantity accounting；
The technical indicator for influencing other Distribution Network Equipment fault correction times include new input Distribution Network Equipment quantity/
New input line length, the time limit that puts into operation are less than or equal to 5 years quantity accountings, the time limit that puts into operation is more than 5 years and is less than or equal to 15 years quantity
Accounting, the time limit that puts into operation are more than 15 years quantity accountings, import volume accounting, joint quantity accounting and domestic quantity accounting.
Technical indicator in the primary fault rate index set of the Distribution Network Equipment includes putting into operation the time limit less than or equal to 5 years
Amount accounting, the time limit that puts into operation are more than 5 years and are more than 15 years quantity accountings less than or equal to 15 years quantity accountings, the time limit that puts into operation, bad lead
Have a power failure caused by frequency of power cut, operational management caused by frequency of power cut, low pressure facility failure caused by the frequency of power cut of cause, aging
Number and new input Distribution Network Equipment quantity newly put into line length.
Described deleted from the primary fault repair time index set and primary fault rate index set of Distribution Network Equipment is discontented with
The technical indicator that sufficient neural network bulk sample this local derviation susceptibility requires, including：
Using deviation standardization to influencing the index of Distribution Network Equipment fault correction time and influencing Distribution Network Equipment failure
The index of rate carries out nondimensionalization processing respectively, obtains nondimensionalization treated to influence Distribution Network Equipment fault correction time
Index and the index for influencing Distribution Network Equipment failure rate；
Calculated separately by BP neural network influence Distribution Network Equipment fault correction time the bulk sample of index this local derviation it is quick
Sensitivity and the bulk sample of index this local derviation susceptibility for influencing Distribution Network Equipment failure rate；
If influencing neural network this local derviation of bulk sample susceptibility of the index of Distribution Network Equipment fault correction time or influencing to match
Neural network bulk sample this local derviation susceptibility of the index of grid equipment failure rate is less than neural network bulk sample this local derviation susceptibility threshold
Value, then deleting corresponding nondimensionalization treated influences the index of Distribution Network Equipment fault correction time or influences power distribution network to set
The index of standby failure rate, otherwise retaining corresponding nondimensionalization treated influences the index of Distribution Network Equipment fault correction time
Or influence the index of Distribution Network Equipment failure rate.
The preset socioeconomic environment indicator includes that GNP per capita, the density of population, bad weather number account for
Than, traffic congestion delay index and electricity consumption speedup.
The GNP per capita is calculated as follows：
Wherein, rGDPpc indicates that GNP per capita, GDP indicate the output total value of national product and service, popu
Indicate total number of people；
The density of population is calculated as follows：
Wherein, dp indicates that the density of population, area indicate area sum；
The bad weather number accounting is calculated as follows：
Wherein, t indicates bad weather number accounting, TeIndicate that total number of days that bad weather occurs, Y indicate 1 year number of days；
The traffic congestion delay index is calculated as follows：
Wherein, a indicates that traffic congestion delay index, z indicate vehicular traffic type number, TzIndicate traffic congestion by
Time, T 'zIndicate free flow by time, αzIndicate z kind vehicular traffic type amount of flow accountings, andez
Indicate z kind vehicular traffic type amount of flow；
The electricity consumption speedup is calculated as follows：
Wherein, v indicates electricity consumption speedup, GNIndicate N electricity consumptions, GN-1Indicate N-1 electricity consumptions.
Described filtered out from preset socioeconomic environment indicator respectively by Pearson correlation coefficients method meets failure
The socioeconomic environment indicator that repair time and the failure rate degree of correlation require, and it is separately added into Fisrt fault repair time index set
With Fisrt fault rate index set, including：
It is calculate by the following formula the pearson correlation system of all socioeconomic environment indicators and fault correction time and failure rate
Number：
Wherein, εyAnd ελIndicate fault correction time yiWith failure rate λiPearson correlation coefficients,Indicate the θ society
Meeting economic environment index, yi、λiThe fault correction time and failure rate of i-th kind of Distribution Network Equipment are indicated respectively；
Select εyFisrt fault repair time index set is added in socioeconomic environment indicator not less than correlation coefficient threshold,
Select ελThe second failure rate index set is added in socioeconomic environment indicator not less than correlation coefficient threshold.
On the other hand, the present invention also provides a kind of apparatus for evaluating of distribution network reliability, including：
Removing module, for from the primary fault repair time index set and primary fault rate index set of Distribution Network Equipment
Delete and be unsatisfactory for the technical indicator of neural network bulk sample this local derviation susceptibility requirement, obtain Fisrt fault repair time index set and
Fisrt fault rate index set；
Screening module is filtered out from preset socioeconomic environment indicator respectively for passing through Pearson correlation coefficients method
When meeting the socioeconomic environment indicator that fault correction time and the failure rate degree of correlation require, and being separately added into Fisrt fault reparation
Between index set and Fisrt fault rate index set, obtain the second fault correction time index set and the second failure rate index set；
Evaluation module, for respectively referring to target value according in the second fault correction time index set and the second failure rate index set
Predict the fault correction time and failure rate of Distribution Network Equipment, and by the fault correction time and failure rate of prediction to power distribution network
Reliability is assessed.
Technical indicator in the primary fault repair time index set of the Distribution Network Equipment includes influencing on-load switch event
Hinder the technical indicator of repair time and influences the technical indicator of other Distribution Network Equipment fault correction times；
The technical indicator for influencing on-load switch fault correction time includes new input on-load switch quantity, put into operation the time limit
Less than or equal to 5 years quantity accountings, the time limit that puts into operation are more than 5 years and are more than 15 years less than or equal to 15 years quantity accountings, the time limit that puts into operation
Amount accounting, import volume accounting, joint quantity accounting, domestic quantity accounting, for indoor on-load switch quantity accounting, be used for
Outdoor on-load switch quantity accounting；
The technical indicator for influencing other Distribution Network Equipment fault correction times include new input Distribution Network Equipment quantity/
New input line length, the time limit that puts into operation are less than or equal to 5 years quantity accountings, the time limit that puts into operation is more than 5 years and is less than or equal to 15 years quantity
Accounting, the time limit that puts into operation are more than 15 years quantity accountings, import volume accounting, joint quantity accounting and domestic quantity accounting.
Technical indicator in the primary fault rate index set of the Distribution Network Equipment includes putting into operation the time limit less than or equal to 5 years
Amount accounting, the time limit that puts into operation are more than 5 years and are more than 15 years quantity accountings less than or equal to 15 years quantity accountings, the time limit that puts into operation, bad lead
Have a power failure caused by frequency of power cut, operational management caused by frequency of power cut, low pressure facility failure caused by the frequency of power cut of cause, aging
Number and new input Distribution Network Equipment quantity newly put into line length.
The removing module includes：
Nondimensionalization processing unit, for the index using deviation standardization to influence Distribution Network Equipment fault correction time
Nondimensionalization processing is carried out respectively with the index for influencing Distribution Network Equipment failure rate, obtains nondimensionalization treated to influence distribution
The index of net equipment fault repair time and the index for influencing Distribution Network Equipment failure rate；
First computing unit, for calculating separately the finger for influencing Distribution Network Equipment fault correction time by BP neural network
Target this local derviation of bulk sample susceptibility and the bulk sample of index this local derviation susceptibility for influencing Distribution Network Equipment failure rate；
First selecting unit, if the neural network bulk sample sheet of the index for influencing Distribution Network Equipment fault correction time is inclined
Neural network bulk sample this local derviation susceptibility led susceptibility or influence the index of Distribution Network Equipment failure rate is complete less than neural network
Sample local derviation susceptibility threshold, then deleting corresponding nondimensionalization treated influences the finger of Distribution Network Equipment fault correction time
Mark or the index for influencing Distribution Network Equipment failure rate, otherwise retain corresponding nondimensionalization treated influence Distribution Network Equipment therefore
Hinder the index of repair time or influences the index of Distribution Network Equipment failure rate.
The preset socioeconomic environment indicator includes that GNP per capita, the density of population, bad weather number account for
Than, traffic congestion delay index and electricity consumption speedup.
The GNP per capita is calculated as follows：
Wherein, rGDPpc indicates that GNP per capita, GDP indicate the output total value of national product and service, popu
Indicate total number of people；
The density of population is calculated as follows：
Wherein, dp indicates that the density of population, area indicate area sum；
The bad weather number accounting is calculated as follows：
Wherein, t indicates bad weather number accounting, TeIndicate that total number of days that bad weather occurs, Y indicate 1 year number of days；
The traffic congestion delay index is calculated as follows：
Wherein, a indicates that traffic congestion delay index, z indicate vehicular traffic type number, TzIndicate traffic congestion by
Time, T 'zIndicate free flow by time, αzIndicate z kind vehicular traffic type amount of flow accountings, andezTable
Show z kind vehicular traffic type amount of flow；
The electricity consumption speedup is calculated as follows：
Wherein, v indicates electricity consumption speedup, GNIndicate N electricity consumptions, GN-1Indicate N-1 electricity consumptions.
The screening module includes：
Second computing unit, for being calculate by the following formula all socioeconomic environment indicators and fault correction time and failure
The Pearson correlation coefficients of rate：
Wherein, εyAnd ελIndicate fault correction time yiWith failure rate λiPearson correlation coefficients,Indicate the θ society
Meeting economic environment index, yi、λiThe fault correction time and failure rate of i-th kind of Distribution Network Equipment are indicated respectively；
Second selecting unit, for selecting εyThe first event is added in socioeconomic environment indicator not less than correlation coefficient threshold
Hinder repair time index set, selects ελThe second failure rate index is added in socioeconomic environment indicator not less than correlation coefficient threshold
Collection.
Compared with the immediate prior art, technical solution provided by the invention has the advantages that：
In the appraisal procedure of distribution network reliability provided by the invention, first from the primary fault repair time of Distribution Network Equipment
The technical indicator for being unsatisfactory for neural network bulk sample this local derviation susceptibility requirement is deleted in index set and primary fault rate index set, is obtained
To Fisrt fault repair time index set and Fisrt fault rate index set, then by Pearson correlation coefficients method respectively from default
Socioeconomic environment indicator in filter out and meet the social economic environment that fault correction time and the failure rate degree of correlation require and refer to
Mark, and it is separately added into Fisrt fault repair time index set and Fisrt fault rate index set, it obtains the second fault correction time and refers to
Mark collection and the second failure rate index set, finally respectively refer to according in the second fault correction time index set and the second failure rate index set
Target value predicts the fault correction time and failure rate of Distribution Network Equipment, and the fault correction time and failure rate pair for passing through prediction
Distribution network reliability is assessed, and the present invention deletes the technical indicator for being unsatisfactory for neural network bulk sample this local derviation susceptibility requirement,
The complexity of prediction model index is alleviated, also by Pearson correlation coefficients method respectively from preset socioeconomic environment indicator
In filter out and meet the socioeconomic environment indicator that fault correction time and the failure rate degree of correlation require, it is reliable to improve power distribution network
The confidence level of property assessment result；
The apparatus for evaluating of distribution network reliability provided by the invention includes removing module, screening module and evaluation module, is deleted
Except module is unsatisfactory for for being deleted from the primary fault repair time index set and primary fault rate index set of Distribution Network Equipment
The technical indicator that neural network bulk sample this local derviation susceptibility requires, obtains Fisrt fault repair time index set and Fisrt fault rate
Index set；Screening module is used to filter out from preset socioeconomic environment indicator respectively by Pearson correlation coefficients method full
The socioeconomic environment indicator that sufficient fault correction time and the failure rate degree of correlation require, and it is separately added into Fisrt fault repair time
Index set and Fisrt fault rate index set, obtain the second fault correction time index set and the second failure rate index set；Assess mould
Block be used for according to respectively refer in the second fault correction time index set and the second failure rate index set target value predict Distribution Network Equipment
Fault correction time and failure rate, and distribution network reliability is commented by the fault correction time and failure rate of prediction
Estimate, alleviate the complexity of prediction model index, improves the confidence level of evaluating reliability of distribution network result；
The present invention is by neural network this local derviation of bulk sample susceptibility from the primary fault repair time index of Distribution Network Equipment
The technical indicator for being unsatisfactory for neural network bulk sample this local derviation susceptibility requirement is deleted in collection and primary fault rate index set, is led to simultaneously
It crosses Pearson correlation coefficients method and is filtered out from preset socioeconomic environment indicator respectively and meet fault correction time and failure
The socioeconomic environment indicator that the rate degree of correlation requires ensures the accuracy of evaluating reliability of distribution network result, is more in line with reality
Situation and business demand.
Description of the drawings
Fig. 1 is the appraisal procedure flow chart of distribution network reliability in the embodiment of the present invention 1.
Specific implementation mode
Invention is further described in detail below in conjunction with the accompanying drawings.
Embodiment 1
The embodiment of the present invention 1 provides a kind of appraisal procedure of distribution network reliability, and particular flow sheet is as shown in Figure 1, specific
Process is as follows：
S101：It is discontented from being deleted in the primary fault repair time index set and primary fault rate index set of Distribution Network Equipment
The technical indicator that sufficient neural network bulk sample this local derviation susceptibility requires, obtains Fisrt fault repair time index set and Fisrt fault
Rate index set；
S102：It is filtered out from preset socioeconomic environment indicator respectively by Pearson correlation coefficients method and meets failure
The socioeconomic environment indicator that repair time and the failure rate degree of correlation require, and it is separately added into Fisrt fault repair time index set
With Fisrt fault rate index set, the second fault correction time index set and the second failure rate index set are obtained；
S103：Distribution is predicted according to target value is respectively referred in the second fault correction time index set and the second failure rate index set
The fault correction time and failure rate of net equipment, and by the fault correction time of prediction and failure rate to distribution network reliability into
Row assessment.
Above-mentioned Distribution Network Equipment includes distribution transformer, cable run, overhead transmission line, breaker, on-load switch, fuse
And disconnecting switch, wherein distribution transformer, cable run, overhead transmission line, breaker, fuse and disconnecting switch belong to except negative
Other Distribution Network Equipments other than lotus switch, indicate the code name of Distribution Network Equipment with i, i=1,2,3 ... ..., 7.
The fault correction time of Distribution Network Equipment can be calculate by the following formula：
Wherein, yiIndicate the fault correction time of Distribution Network Equipment i,Indicate the jth kind power off time of Distribution Network Equipment i
(unit：Hour)；njIndicate the frequency of power cut (unit that jth kind power off time occurs：It is secondary).
The failure rate of Distribution Network Equipment can be calculate by the following formula：
Wherein, λiIndicate the failure rate of Distribution Network Equipment i, NiIndicate Distribution Network Equipment i because failure cannot execute predetermined function
Number (unit：It is secondary)；TiIndicate Distribution Network Equipment i run times (i=1, when 4,5,6,7, unit：100 year；I=2,
When 3, unit：100 km years).
Technical indicator in the primary fault repair time index set of above-mentioned Distribution Network Equipment includes influencing on-load switch event
Hinder the technical indicator of repair time and influences the technical indicator of other Distribution Network Equipment fault correction times；
The technical indicator for influencing on-load switch fault correction time includes that newly input on-load switch quantity, the time limit that puts into operation are less than
Equal to 5 years quantity accountings, the time limit that puts into operation are more than 5 years and are accounted for more than 15 years quantity less than or equal to 15 years quantity accountings, the time limit that puts into operation
Than, import volume accounting, joint quantity accounting, domestic quantity accounting, for indoor on-load switch quantity accounting, for open air
On-load switch quantity accounting；
The technical indicator for influencing other Distribution Network Equipment fault correction times includes new input Distribution Network Equipment quantity/new throwing
Enter line length, the time limit that puts into operation be less than or equal to 5 years quantity accountings, the time limit that puts into operation be more than 5 years and less than or equal to 15 years quantity accountings,
The time limit that puts into operation is more than 15 years quantity accountings, import volume accounting, joint quantity accounting and domestic quantity accounting.
Technical indicator in the primary fault rate index set of Distribution Network Equipment is accounted for including the time limit that puts into operation less than or equal to 5 years quantity
Than, the time limit that puts into operation be more than 5 years and less than or equal to 15 years quantity accountings, the time limit that puts into operation be more than 15 years quantity accountings, it is bad caused by
Frequency of power cut caused by frequency of power cut, aging, frequency of power cut caused by frequency of power cut, operational management caused by low pressure facility failure
And it newly puts into Distribution Network Equipment quantity or newly puts into line length.
Can set influence Distribution Network Equipment fault correction time index formed index set as
R indicates MiMiddle index number, the index set for influencing the index formation of Distribution Network Equipment failure rate areP tables
Show OiMiddle index number, MiInIndicate the new used device quantity of Distribution Network Equipment i or the line length of Distribution Network Equipment,
Wherein i=1, when 4,5,6,7,Indicate the new used device quantity (units of Distribution Network Equipment i：Platform), i=2, when 3,It indicates
Line length (the unit of Distribution Network Equipment i：KM)；Indicate that Distribution Network Equipment i puts into operation the time limit less than or equal to 5 respectively
Year quantity accounting, the time limit that puts into operation are more than 5 years and are more than 15 years quantity accountings less than or equal to 15 years quantity accountings, the time limit that puts into operation, andWherein ST2The expression time limit that puts into operation is small
In equal to 5 years number of devices, ST3Expression put into operation the time limit more than 5 years be less than or equal to 15 years number of devices, ST4The expression time limit that puts into operation is big
In 15 years number of devices；Distribution Network Equipment i bad caused frequency of power cut, Distribution Network Equipment i are indicated respectively
Frequency of power cut caused by aging, frequency of power cut caused by the management of frequency of power cut row, fortune caused by low pressure facility failure.Because each
The mounting means and running environment of Distribution Network Equipment have differences, so the corresponding O of each Distribution Network EquipmentiThere is also difference,
The wherein corresponding O of on-load switch5It has moreThe two is indicated respectively for indoor on-load switch quantity accounting, for open air
On-load switch quantity accounting, andWherein DE5Expression is opened for indoor load
Close quantity, FO5It indicates for outdoor on-load switch quantity；OiInWith MiInOne is a pair of
It answers,Import volume accounting, joint quantity accounting, domestic quantity accounting in Distribution Network Equipment i are indicated respectively, andWherein FRiIndicate umber of feed inlet
Amount, FXiQuantity, HO are produced in expression jointlyiIndicate domestic quantity.
Then, above-mentioned S101 is from the primary fault repair time index set and primary fault rate index set of Distribution Network Equipment
Delete and be unsatisfactory for the technical indicator of neural network bulk sample this local derviation susceptibility requirement, detailed process it is as follows：
1) using deviation standardization to influencing the index of Distribution Network Equipment fault correction time and influencing Distribution Network Equipment event
The index of barrier rate carries out nondimensionalization processing respectively, obtains nondimensionalization treated to influence Distribution Network Equipment fault correction time
Index and influence Distribution Network Equipment failure rate index；
2) being calculated separately by BP neural network influences the bulk sample of index this local derviation of Distribution Network Equipment fault correction time
Susceptibility and the bulk sample of index this local derviation susceptibility for influencing Distribution Network Equipment failure rate；
Specifically by fault correction time yiAndIt is updated to BP neural network, and uses bulk sample this local derviation susceptibility point
Analysis method calculatesTo fault correction time yiSusceptibility, i.e. this local derviation of the bulk sample of Distribution Network Equipment fault correction time is sensitive
Degree；And by failure rate λiAndIt is brought into BP neural network, and uses bulk sample this local derviation sensitivity analysis method, is calculatedPair therefore
Barrier rate λiSusceptibility, i.e. the bulk sample of Distribution Network Equipment failure rate this local derviation susceptibility；
The specific calculating process of the bulk sample of Distribution Network Equipment fault correction time this local derviation susceptibility is as follows：
Wherein, g-th of sample hidden layer, h-th of neuron, which inputs, is
G-th of sample hidden layer, h-th of neuron, which exports, is
G-th of sample output layer, k-th of neuron, which inputs, is
G-th of sample output layer, k-th of neuron, which exports, is
And then r-th of index of g-th of sample is to output variableLocal derviation susceptibility beWherein, w indicates input layer and hidden layer connection weight；V indicate hidden layer with it is defeated
Go out a layer connection weight；L indicates hidden layer neuron number；F (x) indicates hidden layer neuron activation function；G (x) indicates output
Layer neuron activation functions.
When it is implemented, single sample g cannot reflect input pointer to on-load switch failure rate λ5Susceptibility, so need
Want function by single sample local derviation susceptibilityIt integrates, this local derviation of the bulk sample of last Distribution Network Equipment fault correction time
Susceptibility calculation formula is：
Wherein, Sr,kIndicate that bulk sample this local derviation susceptibility of Distribution Network Equipment failure rate, r indicate that index number, k indicate god
Through first number, G indicates sample size size.
The specific calculating process of the bulk sample of Distribution Network Equipment failure rate this local derviation susceptibility is as follows：
Wherein, g-th of sample hidden layer, h-th of neuron, which inputs, is
G-th of sample hidden layer, h-th of neuron, which exports, is
G-th of sample output layer, k-th of neuron, which inputs, is
G-th of sample output layer, k-th of neuron, which exports, is
And then p-th of index of g-th of sample is to output variableLocal derviation susceptibility beWherein, w indicates input layer and hidden layer connection weight；V indicate hidden layer with it is defeated
Go out a layer connection weight；L indicates hidden layer neuron number；F (x) indicates hidden layer neuron activation function；G (x) indicates output
Layer neuron activation functions.
When it is implemented, single sample g cannot reflect input pointer to on-load switch failure rate λ5Susceptibility, so need
Want function by single sample local derviation susceptibilityIt integrates, bulk sample this local derviation susceptibility of last Distribution Network Equipment failure rate
Calculation formula is：
Wherein, Sp,kIndicate that bulk sample this local derviation susceptibility of Distribution Network Equipment failure rate, p indicate that index number, k indicate god
Through first number, G indicates sample size size.
If 3) influence neural network this local derviation of bulk sample susceptibility or the influence of the index of Distribution Network Equipment fault correction time
Neural network bulk sample this local derviation susceptibility of the index of Distribution Network Equipment failure rate is less than neural network bulk sample this local derviation susceptibility
Threshold value (can be set as 0.2) in this example, then delete corresponding nondimensionalization treated when influencing Distribution Network Equipment fault restoration
Between index or influence the index of Distribution Network Equipment failure rate, otherwise retaining corresponding nondimensionalization treated influences power distribution network
The index of equipment fault repair time or the index for influencing Distribution Network Equipment failure rate.
Conventional electrical distribution net reliability assessment selecting index is based on service logic and expert opinion, and selected index is from architecture
On belong to and Distribution Network Equipment runs relevant operational indicator.Some are difficult to happen variation and (such as put into operation in the operational indicator short time
The time limit is more than 5 years and is less than or equal to 15 years quantity accountings), it is limited to evaluating reliability of distribution network parametric variations.In reality
It is typically also to be caused by extraneous factor to cause Distribution Network Equipment to break down or cause fault time elongated, as strong wind and heavy rain,
Damage to crops caused by thunder, traffic etc..These extraneous factors change in real time again, and the influence to reliability assessment parameter may be more than
The influence of business variable, so need to take into account social economic environment factor in index set structure；When it is implemented, to influencing to be somebody's turn to do
The selection of the socioeconomic environment indicator of regional fault correction time and failure rate need to be closely related with on-load switch business.This
From the level of economic development, population, weather conditions, the angle of traffic and electricity consumption is analyzed for invention, then, what S102 chose
Socioeconomic environment indicator includes GNP per capita, the density of population, bad weather number accounting, traffic congestion delay index
With electricity consumption speedup；
In conjunction with actually considering, an Economic Developing Standard of Cities is higher, and infrastructure is more perfect, service quality is higher.
So the city that the level of economic development is high, to do more timely of Distribution Network Equipment installation and maintenance work and in place, power distribution network
The number that equipment breaks down is fewer, and the time that fault restoration is spent is shorter.It usually will state's people's livelihood per capita in development economics
Total value is produced as the efficiency index for weighing the huge collection sight Economic Status in a country.GNP per capita is pressed
Formula calculates：
Wherein, rGDPpc indicates that GNP per capita, GDP indicate the output total value of national product and service, popu
Indicate total number of people；
From the point of view of population and social environment relationship, the density of population is an important factor for influencing social resources supply.People
Mouth density increases, and from basic eco-environmental elements such as empty gas and waters, arrives house, public space, public service etc., all tends to tighten, and
The bearing capacity of social resources can also become fragile.So the area that the density of population is big, the possibility that Distribution Network Equipment breaks down
Property can also increase, and fault correction time also can be elongated.The density of population is calculated as follows：
Wherein, dp indicates that the density of population, area indicate area sum；
Relationship by studying weather conditions and on-load switch finds that Changes in weather is that Distribution Network Equipment is caused to break down
Immediate cause, such as strong wind, heavy rain bad weather can acceleration equipment agings.Bad weather is chosen in measurement to weather conditions
Number accounting is as the important indicator for influencing Distribution Network Equipment fault correction time and equipment failure rate.Bad weather is to occur to dash forward
So, mobile rapid, violent, the great diastrous weather of destructive power or the weather for severe temperature occur, including thunderstorm gale, ice
Hail, cyclone, local heavy showers, severe snow.Wherein severe temperature refers to being higher than 35 DEG C, or the temperature less than 0 DEG C.Bad weather
Occurrence number is frequent, easily leads to device fails.Bad weather number accounting is higher, and distribution network failure power failure frequency is got over
More, the time for handling distribution network failure is longer.Bad weather number accounting is calculated as follows：
Wherein, t indicates bad weather number accounting, TeIndicate that total number of days that bad weather occurs, Y indicate 1 year number of days；
Traffic becomes in multiple fields such as tourism trip, the processing of hospital's accessibility, fire emergency influences flow of personnel
The key factor of efficiency, therefore using traffic as an important factor for influence on-load switch fault correction time, it chooses traffic and gathers around
Stifled delay index is as the socio-economic indicator for influencing on-load switch fault correction time.The value of traffic delay index is bigger, says
It is bright go out line delay bigger, the traffic more congestion that accounts for the ratio of travel time, the time spent in business personnel reaches fault point, is longer,
Traffic congestion delay index is calculated as follows：
Wherein, a indicates that traffic congestion delay index, z indicate vehicular traffic type number, TzIndicate traffic congestion by
Time, T 'zIndicate free flow by time, αzIndicate z kind vehicular traffic type amount of flow accountings, andezTable
Show z kind vehicular traffic type amount of flow；
From the perspective of electricity consumption, electricity consumption growth rate is faster under normal circumstances, illustrates the local demand to electric power
Bigger, the construction or newer demand to Distribution Network Equipment are bigger.And newly put into or newer Distribution Network Equipment initial stage fortune
Row less stable needs to carry out professional debugging, is easy to happen failure.So the present invention is using electricity consumption speedup as influence failure rate
Socio-economic indicator.Electricity consumption speedup is calculated as follows：
Wherein, v indicates electricity consumption speedup, GNIndicate N electricity consumptions, GN-1Indicate N-1 electricity consumptions.
In above-mentioned S102, the socioeconomic environment indicator of Distribution Network Equipment is sieved by Pearson correlation coefficients method
Choosing, and the social economic environment variable by degree of correlation less than 0.6 is cast out.Pearson correlation coefficients therein are calculated as follows：
Wherein, εyAnd ελIndicate fault correction time yiWith failure rate λiPearson correlation coefficients,Indicate the θ society
It can economic environment index.
In above-mentioned S102, filtered out from preset socioeconomic environment indicator respectively by Pearson correlation coefficients method full
The socioeconomic environment indicator that sufficient fault correction time and the failure rate degree of correlation require, and it is separately added into Fisrt fault repair time
Index set and Fisrt fault rate index set, detailed process are as follows：
1) it is calculate by the following formula the pearson correlation of all socioeconomic environment indicators and fault correction time and failure rate
Coefficient：
Wherein, εyAnd ελIndicate fault correction time yiWith failure rate λiPearson correlation coefficients,Indicate the θ society
Meeting economic environment index, yi、λiThe fault correction time and failure rate of i-th kind of Distribution Network Equipment are indicated respectively；
2) ε is selectedyFisrt fault repair time index is added in socioeconomic environment indicator not less than correlation coefficient threshold
Collection selects ελThe second failure rate index set is added in socioeconomic environment indicator not less than correlation coefficient threshold.
In S103, the second fault correction time index set and the second failure rate that can be provided with through the embodiment of the present invention 1
Respectively refer to the fault correction time and failure rate of target value prediction Distribution Network Equipment, and the failure for passing through Distribution Network Equipment in index set
Repair time and failure rate assess the reliability of Distribution Network Equipment.Specific steps may include：
Respectively refer to target value according in the second fault correction time index set and the second failure rate index set, passes through machine learning
Regression algorithm is predicted to obtain the fault correction time and failure rate of various Distribution Network Equipments；
The fault correction time of Distribution Network Equipment is smaller and failure rate is lower, illustrates that the reliability of Distribution Network Equipment is higher；
Conversely, lower；
The reliability of various Distribution Network Equipments in overall power distribution net realizes the assessment to distribution network reliability.
Wherein, decision tree, random forest, neural network, support vector machines etc. may be used in machine learning regression algorithm.
Embodiment 2
Based on 1 same inventive concept of embodiment, the embodiment of the present invention 2 provides a kind of assessment dress of distribution network reliability
It sets, specifically includes removing module, screening module and evaluation module, it is specific as follows：
On the other hand, the present invention also provides a kind of apparatus for evaluating of distribution network reliability, including removing module, screening module
And evaluation module, the function of above-mentioned module is illustrated separately below：
Removing module therein, for from Distribution Network Equipment primary fault repair time index set and primary fault rate refer to
Mark, which is concentrated to delete, is unsatisfactory for the technical indicator of neural network bulk sample this local derviation susceptibility requirement, obtains Fisrt fault repair time and refers to
Mark collection and Fisrt fault rate index set；
Screening module therein, for by Pearson correlation coefficients method respectively from preset socioeconomic environment indicator
The socioeconomic environment indicator for meeting that fault correction time and the failure rate degree of correlation require is filtered out, and is separately added into Fisrt fault
Repair time index set and Fisrt fault rate index set, obtain the second fault correction time index set and the second failure rate index
Collection；
Evaluation module therein, for respectively referring to according in the second fault correction time index set and the second failure rate index set
Target value predicts the fault correction time and failure rate of Distribution Network Equipment, and the fault correction time and failure rate pair for passing through prediction
Distribution network reliability is assessed.
Technical indicator in the primary fault repair time index set of above-mentioned Distribution Network Equipment includes influencing on-load switch event
Hinder the technical indicator of repair time and influences the technical indicator of other Distribution Network Equipment fault correction times；
The technical indicator of above-mentioned influence on-load switch fault correction time includes new input on-load switch quantity, put into operation the time limit
Less than or equal to 5 years quantity accountings, the time limit that puts into operation are more than 5 years and are more than 15 years less than or equal to 15 years quantity accountings, the time limit that puts into operation
Amount accounting, import volume accounting, joint quantity accounting, domestic quantity accounting, for indoor on-load switch quantity accounting, be used for
Outdoor on-load switch quantity accounting；
The technical indicator of other Distribution Network Equipment fault correction times of above-mentioned influence include new input Distribution Network Equipment quantity/
New input line length, the time limit that puts into operation are less than or equal to 5 years quantity accountings, the time limit that puts into operation is more than 5 years and is less than or equal to 15 years quantity
Accounting, the time limit that puts into operation are more than 15 years quantity accountings, import volume accounting, joint quantity accounting and domestic quantity accounting.
Technical indicator in the primary fault rate index set of above-mentioned Distribution Network Equipment includes putting into operation the time limit less than or equal to 5 years
Amount accounting, the time limit that puts into operation are more than 5 years and are more than 15 years quantity accountings less than or equal to 15 years quantity accountings, the time limit that puts into operation, bad lead
Have a power failure caused by frequency of power cut, operational management caused by frequency of power cut, low pressure facility failure caused by the frequency of power cut of cause, aging
Number and new input Distribution Network Equipment quantity newly put into line length.
Above-mentioned removing module specifically includes following several units：
Nondimensionalization processing unit, for the index using deviation standardization to influence Distribution Network Equipment fault correction time
Nondimensionalization processing is carried out respectively with the index for influencing Distribution Network Equipment failure rate, obtains nondimensionalization treated to influence distribution
The index of net equipment fault repair time and the index for influencing Distribution Network Equipment failure rate；
First computing unit, for calculating separately the finger for influencing Distribution Network Equipment fault correction time by BP neural network
Target this local derviation of bulk sample susceptibility and the bulk sample of index this local derviation susceptibility for influencing Distribution Network Equipment failure rate；
First selecting unit, if the neural network bulk sample sheet of the index for influencing Distribution Network Equipment fault correction time is inclined
Neural network bulk sample this local derviation susceptibility led susceptibility or influence the index of Distribution Network Equipment failure rate is complete less than neural network
Sample local derviation susceptibility threshold, then deleting corresponding nondimensionalization treated influences the finger of Distribution Network Equipment fault correction time
Mark or the index for influencing Distribution Network Equipment failure rate, otherwise retain corresponding nondimensionalization treated influence Distribution Network Equipment therefore
Hinder the index of repair time or influences the index of Distribution Network Equipment failure rate.
Above-mentioned preset socioeconomic environment indicator includes that GNP per capita, the density of population, bad weather number account for
Than, traffic congestion delay index and electricity consumption speedup.
GNP per capita is calculated as follows：
Wherein, rGDPpc indicates that GNP per capita, GDP indicate the output total value of national product and service, popu
Indicate total number of people；
The density of population is calculated as follows：
Wherein, dp indicates that the density of population, area indicate area sum；
Bad weather number accounting is calculated as follows：
Wherein, t indicates bad weather number accounting, TeIndicate that total number of days that bad weather occurs, Y indicate 1 year number of days；
Traffic congestion delay index is calculated as follows：
Wherein, a indicates that traffic congestion delay index, z indicate vehicular traffic type number, TzIndicate traffic congestion by
Time, T 'zIndicate free flow by time, αzIndicate z kind vehicular traffic type amount of flow accountings, andEz tables
Show z kind vehicular traffic type amount of flow；
Electricity consumption speedup is calculated as follows：
Wherein, v indicates electricity consumption speedup, GNIndicate N electricity consumptions, GN-1Indicate N-1 electricity consumptions.
Above-mentioned screening module specifically includes：
Second computing unit, for being calculate by the following formula all socioeconomic environment indicators and fault correction time and failure
The Pearson correlation coefficients of rate：
Wherein, εyAnd ελIndicate fault correction time yiWith failure rate λiPearson correlation coefficients,Indicate the θ society
Meeting economic environment index, yi、λiThe fault correction time and failure rate of i-th kind of Distribution Network Equipment are indicated respectively；
Second selecting unit, for selecting εyThe first event is added in socioeconomic environment indicator not less than correlation coefficient threshold
Hinder repair time index set, selects ελThe second failure rate index is added in socioeconomic environment indicator not less than correlation coefficient threshold
Collection.
In the second fault correction time index set and the second failure rate index set that evaluation module is obtained by screening module
Respectively refer to the fault correction time and failure rate of target value prediction Distribution Network Equipment, and the fault correction time for passing through Distribution Network Equipment
The reliability of Distribution Network Equipment is assessed with failure rate.Evaluation module is specifically used for：
Respectively refer to target value according in the second fault correction time index set and the second failure rate index set, passes through machine learning
Regression algorithm is predicted to obtain the fault correction time and failure rate of various Distribution Network Equipments；
The fault correction time of Distribution Network Equipment is smaller and failure rate is lower, illustrates that the reliability of Distribution Network Equipment is higher；
Conversely, lower；
The reliability of various Distribution Network Equipments in overall power distribution net realizes the assessment to distribution network reliability.
Wherein, decision tree, random forest, neural network, support vector machines etc. may be used in machine learning regression algorithm.
Embodiment 3
The embodiment of the present invention 3 provides a kind of appraisal procedure of distribution network reliability, and detailed process is as follows：
S301：It is discontented from being deleted in the primary fault repair time index set and primary fault rate index set of Distribution Network Equipment
The technical indicator that sufficient neural network bulk sample this local derviation susceptibility requires, obtains Fisrt fault repair time index set and Fisrt fault
Rate index set；
S302：It is filtered out from preset socioeconomic environment indicator respectively by Pearson correlation coefficients method and meets failure
The socioeconomic environment indicator that repair time and the failure rate degree of correlation require, and it is separately added into Fisrt fault repair time index set
With Fisrt fault rate index set, the second fault correction time index set and the second failure rate index set are obtained；
S303：Distribution is predicted according to target value is respectively referred in the second fault correction time index set and the second failure rate index set
The fault correction time and failure rate of net equipment, and by the fault correction time of prediction and failure rate to distribution network reliability into
Row assessment.
Above-mentioned Distribution Network Equipment includes distribution transformer, cable run, overhead transmission line, breaker, on-load switch, with i tables
Show the code name of Distribution Network Equipment, i=1,2,3 ... ..., 5.
The fault correction time of Distribution Network Equipment can be calculate by the following formula：
Wherein, yiIndicate the fault correction time of Distribution Network Equipment i,Indicate the jth kind power off time of Distribution Network Equipment i
(unit：Hour)；njIndicate the frequency of power cut (unit that jth kind power off time occurs：It is secondary).
The failure rate of Distribution Network Equipment can be calculate by the following formula：
Wherein, λiIndicate the failure rate of Distribution Network Equipment i, NiIndicate Distribution Network Equipment i because failure cannot execute predetermined function
Number (unit：It is secondary)；TiIndicate Distribution Network Equipment i run times (i=1, when 4,5,6,7, unit：100 year；I=2,
When 3, unit：100 km years).
Technical indicator in the primary fault repair time index set of above-mentioned Distribution Network Equipment includes influencing on-load switch event
Hinder the technical indicator of repair time and influences the technical indicator of other Distribution Network Equipment fault correction times；
The technical indicator of above-mentioned influence on-load switch fault correction time includes new input on-load switch quantity, put into operation the time limit
Less than or equal to 5 years quantity accountings, the time limit that puts into operation are more than 5 years and are more than 15 years less than or equal to 15 years quantity accountings, the time limit that puts into operation
Amount accounting, import volume accounting, joint quantity accounting, domestic quantity accounting, for indoor on-load switch quantity accounting, be used for
Outdoor on-load switch quantity accounting；
The technical indicator of other Distribution Network Equipment fault correction times of above-mentioned influence include new input Distribution Network Equipment quantity/
New input line length, the time limit that puts into operation are less than or equal to 5 years quantity accountings, the time limit that puts into operation is more than 5 years and is less than or equal to 15 years quantity
Accounting, the time limit that puts into operation are more than 15 years quantity accountings, import volume accounting, joint quantity accounting and domestic quantity accounting.
Technical indicator in the primary fault rate index set of above-mentioned Distribution Network Equipment includes putting into operation the time limit less than or equal to 5 years
Amount accounting, the time limit that puts into operation are more than 5 years and are more than 15 years quantity accountings less than or equal to 15 years quantity accountings, the time limit that puts into operation, bad lead
Have a power failure caused by frequency of power cut, operational management caused by frequency of power cut, low pressure facility failure caused by the frequency of power cut of cause, aging
Number and new input Distribution Network Equipment quantity newly put into line length.
Can set influence Distribution Network Equipment fault correction time index formed index set as
Influence Distribution Network Equipment failure rate index formed index set beM5InIndicate on-load switch number
Measure (unit：Platform)；It indicates respectively；Indicate that the on-load switch time limit that puts into operation puts into operation less than or equal to 5 years respectively
The time limit is more than 5 years and is more than 15 years quantity accountings less than or equal to 15 years quantity accountings, the time limit that puts into operation, and Wherein ST2Indicate that the on-load switch time limit that puts into operation was set less than or equal to 5 years
Standby quantity, ST3Indicate on-load switch put into operation the time limit more than 5 years be less than or equal to 15 years number of devices, ST4Indicate that on-load switch puts into operation
The time limit is more than 15 years number of devices；On-load switch bad caused frequency of power cut, on-load switch are indicated respectively
Frequency of power cut caused by aging, frequency of power cut caused by frequency of power cut, operational management caused by low pressure facility failure.O5InWith MiInIt corresponds,Respectively indicate import on-load switch quantity accounting,
Joint on-load switch quantity accounting, domestic on-load switch quantity accounting, Wherein FR5Indicate on-load switch quantity, the FX of import5Indicate the on-load switch number produced jointly
Amount, HO5Indicate domestic on-load switch quantity；WithThe two is indicated respectively for indoor on-load switch quantity accounting, is used
On-load switch quantity accounting in open air,Wherein DE5It indicates to bear for indoor
Lotus number of switches, FO5It indicates for outdoor on-load switch quantity.
Then, above-mentioned S101 is from the primary fault repair time index set and primary fault rate index set of Distribution Network Equipment
The technical indicator for being unsatisfactory for neural network bulk sample this local derviation susceptibility requirement is deleted, detailed process is as follows：
1) using deviation standardization to influencing the index of Distribution Network Equipment fault correction time and influencing Distribution Network Equipment event
The index of barrier rate carries out nondimensionalization processing respectively, obtains nondimensionalization treated to influence Distribution Network Equipment fault correction time
Index and influence Distribution Network Equipment failure rate index, i.e., to M5,O5Nondimensionalization processing is carried out, is obtainedWithIt calculates
Formula is respectivelyWherein 1≤r≤8,1≤p≤9。
2) being calculated separately by BP neural network influences the bulk sample of index this local derviation of Distribution Network Equipment fault correction time
Susceptibility and the bulk sample of index this local derviation susceptibility for influencing Distribution Network Equipment failure rate；
Specifically by on-load switch repair time y5AndIt is updated to BP neural network, and this local derviation is sensitive using bulk sample
Analytic approach is spent, is calculatedTo fault correction time y5Susceptibility, i.e. this local derviation of the bulk sample of Distribution Network Equipment fault correction time
Susceptibility；And load is closed into switch fault rate λ5AndIt is brought into BP neural network, and uses bulk sample this local derviation susceptibility point
Analysis method calculatesTo failure rate λ5Susceptibility, i.e. the bulk sample of Distribution Network Equipment failure rate this local derviation susceptibility, whereinWithRespectively as y5And λ5Input layer, y5And λ5For the defeated of neural network
Go out layer；
The specific calculating process of the bulk sample of Distribution Network Equipment fault correction time this local derviation susceptibility is as follows：
Wherein, g-th of sample hidden layer, h-th of neuron, which inputs, is
G-th of sample hidden layer, h-th of neuron, which exports, is
G-th of sample output layer, k-th of neuron, which inputs, is
G-th of sample output layer, k-th of neuron, which exports, is
And then r-th of index of g-th of sample is to output variableLocal derviation susceptibility beWherein, w indicates input layer and hidden layer connection weight；V indicate hidden layer with it is defeated
Go out a layer connection weight；L indicates hidden layer neuron number；F (x) indicates hidden layer neuron activation function；G (x) indicates output
Layer neuron activation functions.
When it is implemented, single sample g cannot reflect input pointer to on-load switch failure rate y5Susceptibility, so need
Want function by single sample local derviation susceptibilityIt integrates, this local derviation of the bulk sample of last Distribution Network Equipment fault correction time
Susceptibility calculation formula is：
Wherein, Sr,kIndicate that bulk sample this local derviation susceptibility of Distribution Network Equipment failure rate, r indicate that index number, k indicate god
Through first number, G indicates sample size size.
The specific calculating process of the bulk sample of Distribution Network Equipment failure rate this local derviation susceptibility is as follows：
Wherein, g-th of sample hidden layer, h-th of neuron, which inputs, is
G-th of sample hidden layer, h-th of neuron, which exports, is
G-th of sample output layer, k-th of neuron, which inputs, is
G-th of sample output layer, k-th of neuron, which exports, is
And then p-th of index of g-th of sample is to output variableLocal derviation susceptibility beWherein, w indicates input layer and hidden layer connection weight；V indicate hidden layer with it is defeated
Go out a layer connection weight；L indicates hidden layer neuron number；F (x) indicates hidden layer neuron activation function；G (x) indicates output
Layer neuron activation functions.
When it is implemented, single sample g cannot reflect input pointer to on-load switch failure rate λ5Susceptibility, so need
Want function by single sample local derviation susceptibilityIt integrates, bulk sample this local derviation susceptibility of last Distribution Network Equipment failure rate
Calculation formula is：
Wherein, Sp,kIndicate that bulk sample this local derviation susceptibility of Distribution Network Equipment failure rate, p indicate that index number, k indicate god
Through first number, G indicates sample size size.
If 3) influence neural network this local derviation of bulk sample susceptibility or the influence of the index of Distribution Network Equipment fault correction time
Neural network bulk sample this local derviation susceptibility of the index of Distribution Network Equipment failure rate is less than neural network bulk sample this local derviation susceptibility
Threshold value (can be set as 0.2), then deleting corresponding nondimensionalization treated influences the finger of Distribution Network Equipment fault correction time
Mark or the index for influencing Distribution Network Equipment failure rate, otherwise retain corresponding nondimensionalization treated influence Distribution Network Equipment therefore
Hinder the index of repair time or influences the index of Distribution Network Equipment failure rate.Compared by calculating, when on-load switch fault restoration
Between y5It is obtained by neural network bulk sample this local derviation sensitivity analysisOn-load switch failure rate λ5Through
It crosses bulk sample this local derviation sensitivity analysis and obtains O5Index of middle neural network bulk sample this local derviation susceptibility more than 0.2 is o1、o3、o5、
o9, four kinds of indexs composition O '5=(o1, o3, o5, o9)。
Conventional electrical distribution net reliability assessment selecting index is based on service logic and expert opinion, and selected index is from architecture
On belong to and Distribution Network Equipment runs relevant operational indicator.Some are difficult to happen variation and (such as put into operation in the operational indicator short time
The time limit is more than 5 years and is less than or equal to 15 years quantity accountings), it is limited to evaluating reliability of distribution network parametric variations.In reality
It is typically also to be caused by extraneous factor to cause Distribution Network Equipment to break down or cause fault time elongated, as strong wind and heavy rain,
Damage to crops caused by thunder, traffic etc..These extraneous factors change in real time again, and the influence to reliability assessment parameter may be more than
The influence of business variable, so need to take into account social economic environment factor in index set structure；When it is implemented, to influencing to be somebody's turn to do
The selection of the socioeconomic environment indicator of regional fault correction time and failure rate need to be closely related with on-load switch business.This
From the level of economic development, population, weather conditions, the angle of traffic and electricity consumption is analyzed for invention, and then, 102 choose
Socioeconomic environment indicator includes GNP per capita, the density of population, bad weather number accounting, traffic congestion delay index
With electricity consumption speedup；
In conjunction with actually considering, an Economic Developing Standard of Cities is higher, and infrastructure is more perfect, service quality is higher.
So the city that the level of economic development is high, to do more timely of Distribution Network Equipment installation and maintenance work and in place, power distribution network
The number that equipment breaks down is fewer, and the time that fault restoration is spent is shorter.It usually will state's people's livelihood per capita in development economics
Total value is produced as the efficiency index for weighing the huge collection sight Economic Status in a country.GNP per capita is pressed
Formula calculates：
Wherein, rGDPpc indicates that GNP per capita, GDP indicate the output total value of national product and service, popu
Indicate total number of people；
From the point of view of population and social environment relationship, the density of population is an important factor for influencing social resources supply.People
Mouth density increases, and from basic eco-environmental elements such as empty gas and waters, arrives house, public space, public service etc., all tends to tighten, and
The bearing capacity of social resources can also become fragile.So the area that the density of population is big, the possibility that Distribution Network Equipment breaks down
Property can also increase, and fault correction time also can be elongated.The density of population is calculated as follows：
Wherein, dp indicates that the density of population, area indicate area sum；
Relationship by studying weather conditions and on-load switch finds that Changes in weather is that Distribution Network Equipment is caused to break down
Immediate cause, such as strong wind, heavy rain bad weather can acceleration equipment agings.Bad weather is chosen in measurement to weather conditions
Number accounting is as the important indicator for influencing Distribution Network Equipment fault correction time and equipment failure rate.Bad weather is to occur to dash forward
So, mobile rapid, violent, the great diastrous weather of destructive power or the weather for severe temperature occur, including thunderstorm gale, ice
Hail, cyclone, local heavy showers, severe snow.Wherein severe temperature refers to being higher than 35 DEG C, or the temperature less than 0 DEG C.Bad weather
Occurrence number is frequent, easily leads to device fails.Bad weather number accounting is higher, and distribution network failure power failure frequency is got over
More, the time for handling distribution network failure is longer.Bad weather number accounting is calculated as follows：
Wherein, t indicates bad weather number accounting, TeIndicate that total number of days that bad weather occurs, Y indicate 1 year number of days；
Traffic becomes in multiple fields such as tourism trip, the processing of hospital's accessibility, fire emergency influences flow of personnel
The key factor of efficiency, therefore using traffic as an important factor for influence on-load switch fault correction time, it chooses traffic and gathers around
Stifled delay index is as the socio-economic indicator for influencing on-load switch fault correction time.The value of traffic delay index is bigger, says
It is bright go out line delay bigger, the traffic more congestion that accounts for the ratio of travel time, the time spent in business personnel reaches fault point, is longer,
Traffic congestion delay index is calculated as follows：
Wherein, a indicates that traffic congestion delay index, z indicate vehicular traffic type number, TzIndicate traffic congestion by
Time, T 'zIndicate free flow by time, αzIndicate z kind vehicular traffic type amount of flow accountings, andez
Indicate z kind vehicular traffic type amount of flow；
From the perspective of electricity consumption, electricity consumption growth rate is faster under normal circumstances, illustrates the local demand to electric power
Bigger, the construction or newer demand to Distribution Network Equipment are bigger.And newly put into or newer Distribution Network Equipment initial stage fortune
Row less stable needs to carry out professional debugging, is easy to happen failure.So the present invention is using electricity consumption speedup as influence failure rate
Socio-economic indicator.Electricity consumption speedup is calculated as follows：
Wherein, v indicates electricity consumption speedup, GNIndicate N electricity consumptions, GN-1Indicate N-1 electricity consumptions.
In above-mentioned S102, filtered out from preset socioeconomic environment indicator respectively by Pearson correlation coefficients method full
The socioeconomic environment indicator that sufficient fault correction time and the failure rate degree of correlation require, and it is separately added into Fisrt fault repair time
Index set and Fisrt fault rate index set, detailed process are as follows：
1) it is calculate by the following formula the pearson correlation of all socioeconomic environment indicators and fault correction time and failure rate
Coefficient：
Wherein, εyAnd ελIndicate fault correction time yiWith failure rate λiPearson correlation coefficients,Indicate the θ society
Meeting economic environment index, yi、λiThe fault correction time and failure rate of i-th kind of Distribution Network Equipment are indicated respectively；
2) ε is selectedyFisrt fault repair time index is added in socioeconomic environment indicator not less than correlation coefficient threshold
Collection selects ελThe second failure rate index set is added in socioeconomic environment indicator not less than correlation coefficient threshold.Specifically work as society
Meeting economic environment index and the absolute value of the Pearson correlation coefficients of on-load switch fault correction time and failure rate are more than 0.6
When, then socioeconomic environment indicator is added to on-load switch fault correction time index set on-load switch failure rate index set
O′5.By calculating Pearson correlation coefficients, bad weather accounting t, traffic congestion delay index a and on-load switch fault restoration
Time y5Related coefficient be respectively 0.77,0.88, so adding it to on-load switch index set M '5In, finally formBy calculating Pearson correlation coefficients, bad weather accounting t, electricity consumption speedup v and load
The related coefficient of switch fault rate λ 5 is respectively 0.78,0.84, so adding it to O '5In, finally form O "5=(o1, o3,
o5, o9, t, v)；
In above-mentioned S103, each index in the second fault correction time index set and the second failure rate index set can be passed through
The fault correction time and failure rate of value prediction Distribution Network Equipment, and the fault correction time and failure rate for passing through Distribution Network Equipment
The reliability of Distribution Network Equipment is assessed.Specific steps may include：
Respectively refer to target value according in the second fault correction time index set and the second failure rate index set, passes through machine learning
Regression algorithm is predicted to obtain the fault correction time and failure rate of various Distribution Network Equipments；
The fault correction time of Distribution Network Equipment is smaller and failure rate is lower, illustrates that the reliability of Distribution Network Equipment is higher；
Conversely, lower；
The reliability of various Distribution Network Equipments in overall power distribution net realizes the assessment to distribution network reliability.
Wherein, decision tree, random forest, neural network, support vector machines etc. may be used in machine learning regression algorithm.
For the standard of the second fault correction time index set and the second failure rate index set that the inspection embodiment of the present invention 3 provides
True rate, respectively by on-load switch fault correction time y5With failure rate λ5Input of the front and back index set of optimization as respective model
Variable, by fault correction time y5With failure rate λ5Prediction model is established as target variable.By comparing index set before and after optimization
The prediction effect of generated model finds the index set M " using optimization5The accuracy rate ratio of generated model uses M5It is generated
The accuracy rate of model averagely improves 25.5%；Use the index set O " of optimization5The accuracy rate ratio of generated model uses O5It gives birth to
At the accuracy rate of model averagely improve 25.2%.Illustrate the index set optimization method to improving evaluating reliability of distribution network ginseng
The predictive ability of exponential model is effective, can be used for the management work to evaluating reliability of distribution network parameter.Specific index set screening
Front and back model accuracy rate contrast table such as table 1：
Table 1
For convenience of description, each section of apparatus described above is divided into various modules with function or unit describes respectively.
Certainly, each module or the function of unit can be realized in same or multiple softwares or hardware when implementing the application.
It should be understood by those skilled in the art that, embodiments herein can be provided as method, system or computer program
Product.Therefore, complete hardware embodiment, complete software embodiment or reality combining software and hardware aspects can be used in the application
Apply the form of example.Moreover, the application can be used in one or more wherein include computer usable program code computer
The computer program production implemented in usable storage medium (including but not limited to magnetic disk storage, CD-ROM, optical memory etc.)
The form of product.
The application is with reference to method, the flow of equipment (system) and computer program product according to the embodiment of the present application
Figure and/or block diagram describe.It should be understood that can be realized by computer program instructions every first-class in flowchart and/or the block diagram
The combination of flow and/or box in journey and/or box and flowchart and/or the block diagram.These computer programs can be provided
Instruct the processor of all-purpose computer, special purpose computer, Embedded Processor or other programmable data processing devices to produce
A raw machine so that the instruction executed by computer or the processor of other programmable data processing devices is generated for real
The device for the function of being specified in present one flow of flow chart or one box of multiple flows and/or block diagram or multiple boxes.
These computer program instructions, which may also be stored in, can guide computer or other programmable data processing devices with spy
Determine in the computer-readable memory that mode works so that instruction generation stored in the computer readable memory includes referring to
Enable the manufacture of device, the command device realize in one flow of flow chart or multiple flows and/or one box of block diagram or
The function of being specified in multiple boxes.
These computer program instructions also can be loaded onto a computer or other programmable data processing device so that count
Series of operation steps are executed on calculation machine or other programmable devices to generate computer implemented processing, in computer or
The instruction executed on other programmable devices is provided for realizing in one flow of flow chart or multiple flows and/or block diagram one
The step of function of being specified in a box or multiple boxes.
Finally it should be noted that：The above embodiments are merely illustrative of the technical scheme of the present invention and are not intended to be limiting thereof, institute
The those of ordinary skill in category field with reference to above-described embodiment still can to the present invention specific implementation mode modify or
Equivalent replacement, these are applying for this pending hair without departing from any modification of spirit and scope of the invention or equivalent replacement
Within bright claims.
Claims (14)
1. a kind of appraisal procedure of distribution network reliability, which is characterized in that including：
It is unsatisfactory for nerve net from being deleted in the primary fault repair time index set and primary fault rate index set of Distribution Network Equipment
The technical indicator that network bulk sample this local derviation susceptibility requires, obtains Fisrt fault repair time index set and Fisrt fault rate index
Collection；
It is filtered out from preset socioeconomic environment indicator respectively by Pearson correlation coefficients method and meets fault correction time
The socioeconomic environment indicator required with the failure rate degree of correlation, and it is separately added into Fisrt fault repair time index set and the first event
Barrier rate index set obtains the second fault correction time index set and the second failure rate index set；
Distribution Network Equipment is predicted according to target value is respectively referred in the second fault correction time index set and the second failure rate index set
Fault correction time and failure rate, and distribution network reliability is assessed by the fault correction time and failure rate of prediction.
2. the appraisal procedure of distribution network reliability according to claim 1, which is characterized in that the original of the Distribution Network Equipment
Technical indicator in beginning fault correction time index set includes influencing technical indicator and the influence of on-load switch fault correction time
The technical indicator of other Distribution Network Equipment fault correction times；
The technical indicator for influencing on-load switch fault correction time includes that newly input on-load switch quantity, the time limit that puts into operation are less than
Equal to 5 years quantity accountings, the time limit that puts into operation are more than 5 years and are accounted for more than 15 years quantity less than or equal to 15 years quantity accountings, the time limit that puts into operation
Than, import volume accounting, joint quantity accounting, domestic quantity accounting, for indoor on-load switch quantity accounting, for open air
On-load switch quantity accounting；
The technical indicator of other Distribution Network Equipment fault correction times of influence includes new input Distribution Network Equipment quantity/new throwing
Enter line length, the time limit that puts into operation be less than or equal to 5 years quantity accountings, the time limit that puts into operation be more than 5 years and less than or equal to 15 years quantity accountings,
The time limit that puts into operation is more than 15 years quantity accountings, import volume accounting, joint quantity accounting and domestic quantity accounting.
3. the appraisal procedure of distribution network reliability according to claim 2, which is characterized in that the original of the Distribution Network Equipment
Technical indicator in beginning failure rate index set is more than 5 years and small less than or equal to 5 years quantity accountings, the time limit that puts into operation including the time limit that puts into operation
Have a power failure caused by equal to 15 years quantity accountings, the time limit that puts into operation are more than 15 years quantity accountings, bad caused frequency of power cut, aging
Frequency of power cut caused by frequency of power cut, operational management caused by number, low pressure facility failure and new input Distribution Network Equipment number
Amount newly puts into line length.
4. the appraisal procedure of distribution network reliability according to claim 2, which is characterized in that described from Distribution Network Equipment
It is deleted in primary fault repair time index set and primary fault rate index set and is unsatisfactory for neural network bulk sample this local derviation susceptibility
It is required that technical indicator, including：
Using deviation standardization to influencing the index of Distribution Network Equipment fault correction time and influencing Distribution Network Equipment failure rate
Index carries out nondimensionalization processing respectively, obtains nondimensionalization treated to influence the index of Distribution Network Equipment fault correction time
With the index for influencing Distribution Network Equipment failure rate；
Being calculated separately by BP neural network influences the bulk sample of index this local derviation susceptibility of Distribution Network Equipment fault correction time
With the bulk sample of index this local derviation susceptibility for influencing Distribution Network Equipment failure rate；
If influencing neural network this local derviation of bulk sample susceptibility of the index of Distribution Network Equipment fault correction time or influencing power distribution network
Neural network bulk sample this local derviation susceptibility of the index of equipment failure rate is less than neural network bulk sample this local derviation susceptibility threshold, then
Delete corresponding nondimensionalization treated influence the index of Distribution Network Equipment fault correction time or influence Distribution Network Equipment therefore
The index of barrier rate, otherwise retaining corresponding nondimensionalization treated influences the index or shadow of Distribution Network Equipment fault correction time
Ring the index of Distribution Network Equipment failure rate.
5. the appraisal procedure of distribution network reliability according to claim 1, which is characterized in that the preset social economy
Environmental index includes GNP per capita, the density of population, bad weather number accounting, traffic congestion delay index and electricity consumption
Speedup.
6. the appraisal procedure of distribution network reliability according to claim 5, which is characterized in that
The GNP per capita is calculated as follows：
Wherein, rGDPpc indicates that GNP per capita, GDP indicate that the output total value of national product and service, popu indicate
Total number of people；
The density of population is calculated as follows：
Wherein, dp indicates that the density of population, area indicate area sum；
The bad weather number accounting is calculated as follows：
Wherein, t indicates bad weather number accounting, TeIndicate that total number of days that bad weather occurs, Y indicate 1 year number of days；
The traffic congestion delay index is calculated as follows：
Wherein, a indicates that traffic congestion delay index, z indicate vehicular traffic type number, TzIndicate traffic congestion by time,
T′zIndicate free flow by time, αzIndicate z kind vehicular traffic type amount of flow accountings, andezIndicate z
Kind vehicular traffic type amount of flow；
The electricity consumption speedup is calculated as follows：
Wherein, v indicates electricity consumption speedup, GNIndicate N electricity consumptions, GN-1Indicate N-1 electricity consumptions.
7. the appraisal procedure of the distribution network reliability according to claim 1,5 or 6, which is characterized in that described to pass through Pierre
Gloomy correlation coefficient process filters out that meet fault correction time related to failure rate from preset socioeconomic environment indicator respectively
Desired socioeconomic environment indicator is spent, and is separately added into Fisrt fault repair time index set and Fisrt fault rate index set,
Including：
It is calculate by the following formula the Pearson correlation coefficients of all socioeconomic environment indicators and fault correction time and failure rate：
Wherein, εyAnd ελIndicate fault correction time yiWith failure rate λiPearson correlation coefficients,Indicate the θ society's warp
Ji environmental index, yi、λiThe fault correction time and failure rate of i-th kind of Distribution Network Equipment are indicated respectively；
Select εyFisrt fault repair time index set, selection is added in socioeconomic environment indicator not less than correlation coefficient threshold
ελThe second failure rate index set is added in socioeconomic environment indicator not less than correlation coefficient threshold.
8. a kind of apparatus for evaluating of distribution network reliability, which is characterized in that including：
Removing module, for being deleted from the primary fault repair time index set of Distribution Network Equipment and primary fault rate index set
It is unsatisfactory for the technical indicator of neural network bulk sample this local derviation susceptibility requirement, obtains Fisrt fault repair time index set and first
Failure rate index set；
Screening module filters out satisfaction from preset socioeconomic environment indicator respectively for passing through Pearson correlation coefficients method
The socioeconomic environment indicator that fault correction time and the failure rate degree of correlation require, and be separately added into Fisrt fault repair time and refer to
Mark collection and Fisrt fault rate index set, obtain the second fault correction time index set and the second failure rate index set；
Evaluation module, for according to respectively refer in the second fault correction time index set and the second failure rate index set target value prediction
The fault correction time and failure rate of Distribution Network Equipment, and it is reliable to power distribution network by the fault correction time of prediction and failure rate
Property is assessed.
9. the apparatus for evaluating of distribution network reliability according to claim 8, which is characterized in that the original of the Distribution Network Equipment
Technical indicator in beginning fault correction time index set includes influencing technical indicator and the influence of on-load switch fault correction time
The technical indicator of other Distribution Network Equipment fault correction times；
The technical indicator for influencing on-load switch fault correction time includes that newly input on-load switch quantity, the time limit that puts into operation are less than
Equal to 5 years quantity accountings, the time limit that puts into operation are more than 5 years and are accounted for more than 15 years quantity less than or equal to 15 years quantity accountings, the time limit that puts into operation
Than, import volume accounting, joint quantity accounting, domestic quantity accounting, for indoor on-load switch quantity accounting, for open air
On-load switch quantity accounting；
The technical indicator of other Distribution Network Equipment fault correction times of influence includes new input Distribution Network Equipment quantity/new throwing
Enter line length, the time limit that puts into operation be less than or equal to 5 years quantity accountings, the time limit that puts into operation be more than 5 years and less than or equal to 15 years quantity accountings,
The time limit that puts into operation is more than 15 years quantity accountings, import volume accounting, joint quantity accounting and domestic quantity accounting.
10. the apparatus for evaluating of distribution network reliability according to claim 9, which is characterized in that the Distribution Network Equipment
Technical indicator in primary fault rate index set include put into operation the time limit be more than 5 years less than or equal to 5 years quantity accountings, the time limit that puts into operation and
Less than or equal to 15 years quantity accountings, the time limit that puts into operation, which are more than caused by 15 years quantity accountings, bad caused frequency of power cut, aging, to stop
Frequency of power cut caused by frequency of power cut, operational management caused by electric number, low pressure facility failure and newly put into Distribution Network Equipment
Quantity newly puts into line length.
11. the apparatus for evaluating of distribution network reliability according to claim 9, which is characterized in that the removing module includes：
Nondimensionalization processing unit, for the index and shadow using deviation standardization to influence Distribution Network Equipment fault correction time
The index for ringing Distribution Network Equipment failure rate carries out nondimensionalization processing respectively, obtains nondimensionalization treated influencing power distribution network setting
The index of standby fault correction time and the index for influencing Distribution Network Equipment failure rate；
First computing unit, for calculating separately the index for influencing Distribution Network Equipment fault correction time by BP neural network
This local derviation of bulk sample susceptibility and the bulk sample of index this local derviation susceptibility for influencing Distribution Network Equipment failure rate；
First selecting unit, if quick for influencing the neural network bulk sample of index of Distribution Network Equipment fault correction time this local derviation
Neural network bulk sample this local derviation susceptibility of the index of sensitivity or influence Distribution Network Equipment failure rate is less than neural network bulk sample sheet
Local derviation susceptibility threshold, then delete corresponding nondimensionalization treated the index for influencing Distribution Network Equipment fault correction time or
The index for influencing Distribution Network Equipment failure rate, otherwise retaining corresponding nondimensionalization treated influences Distribution Network Equipment failure and repaiies
The index of multiple time or the index for influencing Distribution Network Equipment failure rate.
12. the apparatus for evaluating of distribution network reliability according to claim 8, which is characterized in that preset society's warp
Ji environmental index includes GNP per capita, the density of population, bad weather number accounting, traffic congestion delay index and electricity consumption
Measure speedup.
13. the apparatus for evaluating of distribution network reliability according to claim 12, which is characterized in that
The GNP per capita is calculated as follows：
Wherein, rGDPpc indicates that GNP per capita, GDP indicate that the output total value of national product and service, popu indicate
Total number of people；
The density of population is calculated as follows：
Wherein, dp indicates that the density of population, area indicate area sum；
The bad weather number accounting is calculated as follows：
Wherein, t indicates bad weather number accounting, TeIndicate that total number of days that bad weather occurs, Y indicate 1 year number of days；
The traffic congestion delay index is calculated as follows：
Wherein, a indicates that traffic congestion delay index, z indicate vehicular traffic type number, TzIndicate traffic congestion by time,
T′zIndicate free flow by time, αzIndicate z kind vehicular traffic type amount of flow accountings, andezIndicate z
Kind vehicular traffic type amount of flow；
The electricity consumption speedup is calculated as follows：
Wherein, v indicates electricity consumption speedup, GNIndicate N electricity consumptions, GN-1Indicate N-1 electricity consumptions.
14. the apparatus for evaluating of the distribution network reliability according to claim 8,12 or 13, which is characterized in that the screening mould
Block includes：
Second computing unit, for being calculate by the following formula all socioeconomic environment indicators and fault correction time and failure rate
Pearson correlation coefficients：
Wherein, εyAnd ελIndicate fault correction time yiWith failure rate λiPearson correlation coefficients,Indicate the θ society's warp
Ji environmental index, yi、λiThe fault correction time and failure rate of i-th kind of Distribution Network Equipment are indicated respectively；
Second selecting unit, for selecting εySocioeconomic environment indicator's addition Fisrt fault not less than correlation coefficient threshold is repaiied
Multiple time index collection, selects ελThe second failure rate index set is added in socioeconomic environment indicator not less than correlation coefficient threshold.
Priority Applications (1)
| Application Number | Priority Date | Filing Date | Title |
|---|---|---|---|
| CN201810478810.6A CN108665181A (en) | 2018-05-18 | 2018-05-18 | A kind of appraisal procedure and device of distribution network reliability |
Applications Claiming Priority (1)
| Application Number | Priority Date | Filing Date | Title |
|---|---|---|---|
| CN201810478810.6A CN108665181A (en) | 2018-05-18 | 2018-05-18 | A kind of appraisal procedure and device of distribution network reliability |
Publications (1)
| Publication Number | Publication Date |
|---|---|
| CN108665181A true CN108665181A (en) | 2018-10-16 |
Family
ID=63776894
Family Applications (1)
| Application Number | Title | Priority Date | Filing Date |
|---|---|---|---|
| CN201810478810.6A Pending CN108665181A (en) | 2018-05-18 | 2018-05-18 | A kind of appraisal procedure and device of distribution network reliability |
Country Status (1)
| Country | Link |
|---|---|
| CN (1) | CN108665181A (en) |
Cited By (5)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN110059938A (en) * | 2019-03-29 | 2019-07-26 | 四川大学 | A kind of distribution network planning method based on correlation rule driving |
| CN110889544A (en) * | 2019-11-20 | 2020-03-17 | 贵州电网有限责任公司电力科学研究院 | Method and device for predicting operation indexes of power distribution network |
| CN111221880A (en) * | 2020-04-23 | 2020-06-02 | 北京瑞莱智慧科技有限公司 | Feature combination method, device, medium, and electronic apparatus |
| CN112070243A (en) * | 2020-07-08 | 2020-12-11 | 国网浙江杭州市富阳区供电有限公司 | Multi-channel automatic pushing method for power grid fault information |
| CN112906251A (en) * | 2021-04-16 | 2021-06-04 | 云南电网有限责任公司 | Analysis method and system for reliability influence factors of power distribution network |
Citations (6)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN102682407A (en) * | 2012-04-06 | 2012-09-19 | 广东电网公司电力科学研究院 | Comprehensive reliability assessment method for 500kV terminal substation |
| CN102968556A (en) * | 2012-11-08 | 2013-03-13 | 重庆大学 | Probability distribution-based distribution network reliability judgment method |
| CN103839187A (en) * | 2012-11-20 | 2014-06-04 | 上海昌泰求实电力新技术有限公司 | Comprehensive assessment index system for power-supplying capacity and operation level of regional power grid |
| CN106251045A (en) * | 2016-07-21 | 2016-12-21 | 中国南方电网有限责任公司电网技术研究中心 | Distribution network reliability appraisal procedure based on multiple leading factor |
| CN106980905A (en) * | 2017-03-15 | 2017-07-25 | 南方电网科学研究院有限责任公司 | Distribution network reliability Forecasting Methodology and system |
| CN107169628A (en) * | 2017-04-14 | 2017-09-15 | 华中科技大学 | A kind of distribution network reliability evaluation method based on big data mutual information attribute reduction |
-
2018
- 2018-05-18 CN CN201810478810.6A patent/CN108665181A/en active Pending
Patent Citations (6)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN102682407A (en) * | 2012-04-06 | 2012-09-19 | 广东电网公司电力科学研究院 | Comprehensive reliability assessment method for 500kV terminal substation |
| CN102968556A (en) * | 2012-11-08 | 2013-03-13 | 重庆大学 | Probability distribution-based distribution network reliability judgment method |
| CN103839187A (en) * | 2012-11-20 | 2014-06-04 | 上海昌泰求实电力新技术有限公司 | Comprehensive assessment index system for power-supplying capacity and operation level of regional power grid |
| CN106251045A (en) * | 2016-07-21 | 2016-12-21 | 中国南方电网有限责任公司电网技术研究中心 | Distribution network reliability appraisal procedure based on multiple leading factor |
| CN106980905A (en) * | 2017-03-15 | 2017-07-25 | 南方电网科学研究院有限责任公司 | Distribution network reliability Forecasting Methodology and system |
| CN107169628A (en) * | 2017-04-14 | 2017-09-15 | 华中科技大学 | A kind of distribution network reliability evaluation method based on big data mutual information attribute reduction |
Non-Patent Citations (2)
| Title |
|---|
| 冯春雨: "基于敏感性的正则RBF神经网络及其在特征选择上的应用", <中国优秀硕士学位论文全文数据库，信息科技辑>, 15 December 2011 (2011-12-15), pages 14 - 16 * |
| 罗东;胡良焕;邢玉珍;: "电网评价指标体系研究", 安徽电力, no. 03, 30 September 2009 (2009-09-30) * |
Cited By (7)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN110059938A (en) * | 2019-03-29 | 2019-07-26 | 四川大学 | A kind of distribution network planning method based on correlation rule driving |
| CN110059938B (en) * | 2019-03-29 | 2023-04-11 | 四川大学 | Power distribution network planning method based on association rule driving |
| CN110889544A (en) * | 2019-11-20 | 2020-03-17 | 贵州电网有限责任公司电力科学研究院 | Method and device for predicting operation indexes of power distribution network |
| CN110889544B (en) * | 2019-11-20 | 2022-07-01 | 贵州电网有限责任公司电力科学研究院 | Method and device for predicting operation indexes of power distribution network |
| CN111221880A (en) * | 2020-04-23 | 2020-06-02 | 北京瑞莱智慧科技有限公司 | Feature combination method, device, medium, and electronic apparatus |
| CN112070243A (en) * | 2020-07-08 | 2020-12-11 | 国网浙江杭州市富阳区供电有限公司 | Multi-channel automatic pushing method for power grid fault information |
| CN112906251A (en) * | 2021-04-16 | 2021-06-04 | 云南电网有限责任公司 | Analysis method and system for reliability influence factors of power distribution network |
Similar Documents
| Publication | Publication Date | Title |
|---|---|---|
| CN108665181A (en) | A kind of appraisal procedure and device of distribution network reliability | |
| CN109492857A (en) | A kind of distribution network failure risk class prediction technique and device | |
| US20140156031A1 (en) | Adaptive Stochastic Controller for Dynamic Treatment of Cyber-Physical Systems | |
| CN103617561A (en) | System and method for evaluating state of secondary device of power grid intelligent substation | |
| CN106022583A (en) | Electric power communication service risk calculation method and system based on fuzzy decision tree | |
| CN107123982A (en) | A kind of distribution network reliability analysis method of economic benefit based on equipment alteration | |
| CN106936127A (en) | A kind of line load regression analysis and Forecasting Methodology and system | |
| CN105740975A (en) | Data association relationship-based equipment defect assessment and prediction method | |
| CN110826228B (en) | Regional power grid operation quality limit evaluation method | |
| CN104462718A (en) | Method for evaluating economic operation year range of transformer substation | |
| CN108428063A (en) | A kind of Establishment of integrated evaluation index system of one stream distribution network construction level | |
| Protalinsky et al. | Identification of the actual state and entity availability forecasting in power engineering using neural-network technologies | |
| Wang et al. | Fast supply reliability evaluation of integrated power-gas system based on stochastic capacity network model and importance sampling | |
| CN110649627B (en) | Static voltage stability margin evaluation method and system based on GBRT | |
| Fogliatto et al. | Power distribution system interruption duration model using reliability analysis regression | |
| Huang et al. | A restoration-clustering-decomposition learning framework for aging-related failure rate estimation of distribution transformers | |
| Xu et al. | Resilience-driven post-disaster restoration of interdependent infrastructure systems under different decision-making environments | |
| Roland et al. | Reliability prediction of Port Harcourt electricity distribution network using NEPLAN | |
| WO2019140553A1 (en) | Method and device for determining health index of power distribution system and computer storage medium | |
| CN115187134A (en) | Grid-based power distribution network planning method and device and terminal equipment | |
| Taheri et al. | Toward operational resilience of smart energy networks in complex infrastructures | |
| Daraghmi et al. | Accurate and time‐efficient negative binomial linear model for electric load forecasting in IoE | |
| CN108596474B (en) | A kind of electricity power engineering on-road efficiency evaluation method and system meeting power demand | |
| Mehrtash et al. | Security-Constrained transmission expansion planning with risk index of N-1 security obtained from PMU Data | |
| Zhu et al. | Assessment method of distribution network health level based on multivariate information |
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 |