CN109214717A - Power distribution network power grid evaluation method and its evaluation system - Google Patents

Power distribution network power grid evaluation method and its evaluation system Download PDF

Info

Publication number
CN109214717A
CN109214717A CN201811242931.7A CN201811242931A CN109214717A CN 109214717 A CN109214717 A CN 109214717A CN 201811242931 A CN201811242931 A CN 201811242931A CN 109214717 A CN109214717 A CN 109214717A
Authority
CN
China
Prior art keywords
evaluation
index
adaptability
distribution network
factor
Prior art date
Legal status (The legal status is an assumption and is not a legal conclusion. Google has not performed a legal analysis and makes no representation as to the accuracy of the status listed.)
Pending
Application number
CN201811242931.7A
Other languages
Chinese (zh)
Inventor
李映雪
朱文广
杨为群
熊宁
王伟
刘小春
周成
王敏
王丽
彭怀德
陈国华
Current Assignee (The listed assignees may be inaccurate. Google has not performed a legal analysis and makes no representation or warranty as to the accuracy of the list.)
State Grid Corp of China SGCC
Economic and Technological Research Institute of State Grid Jiangxi Electric Power Co Ltd
Original Assignee
State Grid Corp of China SGCC
Economic and Technological Research Institute of State Grid Jiangxi Electric Power Co Ltd
Priority date (The priority date is an assumption and is not a legal conclusion. Google has not performed a legal analysis and makes no representation as to the accuracy of the date listed.)
Filing date
Publication date
Application filed by State Grid Corp of China SGCC, Economic and Technological Research Institute of State Grid Jiangxi Electric Power Co Ltd filed Critical State Grid Corp of China SGCC
Priority to CN201811242931.7A priority Critical patent/CN109214717A/en
Publication of CN109214717A publication Critical patent/CN109214717A/en
Pending legal-status Critical Current

Links

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
    • 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
    • H—ELECTRICITY
    • H02—GENERATION; CONVERSION OR DISTRIBUTION OF ELECTRIC POWER
    • H02J—CIRCUIT ARRANGEMENTS OR SYSTEMS FOR SUPPLYING OR DISTRIBUTING ELECTRIC POWER; SYSTEMS FOR STORING ELECTRIC ENERGY
    • H02J3/00—Circuit arrangements for ac mains or ac distribution networks
    • H—ELECTRICITY
    • H02—GENERATION; CONVERSION OR DISTRIBUTION OF ELECTRIC POWER
    • H02J—CIRCUIT ARRANGEMENTS OR SYSTEMS FOR SUPPLYING OR DISTRIBUTING ELECTRIC POWER; SYSTEMS FOR STORING ELECTRIC ENERGY
    • H02J2203/00—Indexing scheme relating to details of circuit arrangements for AC mains or AC distribution networks
    • H02J2203/20—Simulating, e g planning, reliability check, modelling or computer assisted design [CAD]

Abstract

The invention discloses a kind of power distribution network power grid evaluation methods, including choose Adaptability Evaluation index factor；Acquire history index value, history index weights and history index grade point；Establish the first training set；Construct deep learning evaluation model；Calculate Evaluation: Current index value；Establish the Adaptability Evaluation rule of power distribution network；Establish the second training set；Construct deep learning index weights model；Calculate current criteria weighted value；Calculate the Adaptability Evaluation result of distribution network source.The invention also discloses the evaluation systems for realizing the power distribution network power grid evaluation method.The present invention can be improved the accuracy of the weight of Adaptability Evaluation index, while improve Adaptability Evaluation result precision, provide accurate Adaptability Evaluation foundation for distribution network transform.

Description

Power distribution network power grid evaluation method and its evaluation system
Technical field
Present invention relates particularly to a kind of power distribution network power grid evaluation method and its evaluation systems.
Background technique
With the development of economic technology, electric energy has become essential secondary energy sources in people's production and production, gives People's production and life brings endless convenience.
Currently, rapid growth is presented in distributed generation resource development, it has also become various circles of society's focus, however its grid-connected also can Operation of Electric Systems and stability to each province and city bring many negative effects.A large amount of distributed generation resources access power grids, will be to matching Power grid generates tremendous influence.It is mainly manifested in the following aspects: 1) to the influence of distribution power flow；2) to power distribution network electricity The influence of energy quality；3) to the influence of power distribution network short circuit calculation；4) to the influence of distribution network reliability.In addition, since management is marked Quasi- and technical specification is not comprehensive enough, clear, can operate poor, and power grid enterprises are difficult to fully assess Grid-connected Distributed Generation Power System Reliability, power quality and safety, to make the difficulty and complexity of the grid-connected change of distributed generation resource.
A kind of Distributed Generation in Distribution System allocation plan evaluation method, Patent No. CN201610888691.2, specifically Disclose: (1) building includes four layers of distributed generation resource allocation plan evaluation of destination layer, rule layer, sub- rule layer and measure layer Index system；Destination layer is top；The rule layer sets up multiple indexs；Multiple indexs of the sub- rule layer to rule layer It is further refined, each index is divided into multiple sub- indexs；The measure layer proposes that the calculating of specific evaluation index is public Formula carries out quantitative analysis；(2) each layer of relative importance is obtained using analytic hierarchy process (AHP), determines index and sub- index Weight establishes the weight model of distributed generation resource allocation plan assessment indicator system；(3) it is distributed according to the weight model The overall merit score of formula power configuration scheme.But the synthesis of distributed generation resource allocation plan is calculated using analytic hierarchy process (AHP) Evaluation score needs to rely on expertise, lacks and objectively evaluates to index, leads to the weight accuracy for calculating resulting index It is lower, from causing overall merit scores accuracy lower.
Summary of the invention
Scientific reliably power distribution network grid power source can be evaluated one of the objects of the present invention is to provide one kind Power distribution network power grid evaluation method.
The second object of the present invention is to provide a kind of evaluation system for realizing the power distribution network power grid evaluation method.
This power distribution network power grid evaluation method provided by the invention, includes the following steps:
S1. the Adaptability Evaluation index factor of power distribution network power grid evaluation is chosen；
S2. the Adaptability Evaluation index factor chosen according to step S1 acquires Adaptability Evaluation index factor in power distribution network Corresponding history index value, history index weights and history index grade point；
S3. history index value, history index weights corresponding to the Adaptability Evaluation index factor to step S2 acquisition And history index grade point carries out feature extraction, and establishes the first training set；
S4. the first training set established according to step S3 constructs deep learning evaluation model；
S5. the Evaluation: Current index value for the Adaptability Evaluation index factor that step S2 chooses is calculated；
S6. according to the deep learning evaluation model for Evaluation: Current index value and step the S4 building being calculated, foundation is matched The Adaptability Evaluation rule of power grid；
S7. history index value, history index weights corresponding to the Adaptability Evaluation index factor to step S2 acquisition And history index grade point carries out feature extraction, and establishes the second training set；
S8. the second training set established according to step S7 constructs deep learning index weights model；
S9. according to the deep learning index weights mould of the step S5 Evaluation: Current index value being calculated and step S8 building Type calculates the current criteria weighted value of Adaptability Evaluation index factor；
S10. the Adaptability Evaluation index factor that Adaptability Evaluation index factor, the step S9 chosen according to step S1 is obtained Current criteria weighted value and the obtained power distribution network of step S6 Adaptability Evaluation rule, the adaptability for calculating distribution network source comments Valence result.
The Adaptability Evaluation index factor of selection power distribution network power grid evaluation described in step S1, specially using as follows Step is chosen:
(1) according to the operating parameter of Distribution Network Equipment, iotave evaluation index factor is selected；
(2) according to the iotave evaluation index factor selected in step (1), original evaluation index factor institute in power distribution network is acquired Corresponding history index value, history index weights and history index grade calculate each original comment using correlation analysis algorithm The corresponding related coefficient of valence index factor；
(3) according to initial value evaluation index factor and its corresponding related coefficient, Adaptability Evaluation index factor is determined.
The Adaptability Evaluation index factor includes that route Rate of average load, heavy-haul line accounting, load are in most preferably Route accounting, Breaking capacity average margin, switch qualification rate, capacity-load ratio, heavily loaded transformer accounting, the load of traffic coverage are in False protection rate, protection sensitivity verification qualification rate and normal fortune under the transformer accounting in optimum operation section, fault condition False protection rate when row.
Deep learning evaluation model is constructed according to the first training set described in step S4, specially according to the first training set, Deep learning is carried out to the first algorithm set using deep neural network model, to construct deep learning index weights model.
First algorithm set includes Data Dimensionality Reduction Algorithm, association algorithm, linear regression algorithm and sorting algorithm.
Deep learning index weights model is constructed according to the second training set described in step S8, specially according to the second training Collection carries out deep learning to the second algorithm set using deep neural network model, to construct deep learning index weights mould Type.
Second algorithm set includes step analysis algorithm, Principal Component Analysis Algorithm, association algorithm, linear regression calculation Method and sorting algorithm.
According to the current criteria weight of Adaptability Evaluation index factor, Adaptability Evaluation index factor described in step S10 Value and the Adaptability Evaluation rule of power distribution network calculate Adaptability Evaluation as a result, being specially to calculate Adaptability Evaluation using following formula As a result Q:
N is the number of Adaptability Evaluation index factor, w in formulaiFor the weight of i-th of Adaptability Evaluation index factor, IiFor I-th of Adaptability Evaluation index factor.
The present invention also provides a kind of evaluation systems for realizing the power distribution network power grid evaluation method, including adaptability Evaluation index factor selection module, history value acquisition module, the first training set establishes module, deep learning evaluation model establishes mould Block, Evaluation: Current index value computing module, Adaptability Evaluation rule establish module, the second training set establishes module, deep learning Weight model establishes module, current criteria weight value calculation module and power distribution network power adaptation evaluation result computing module；It is suitable Answering property evaluation index factor selection module, history value acquisition module, the first training set establishes module, deep learning evaluation model is built Formwork erection block, Evaluation: Current index value computing module, Adaptability Evaluation rule establish module, the second training set establishes module, depth Study weight model establishes module, current criteria weight value calculation module and power distribution network power adaptation evaluation result computing module It is sequentially connected in series；Adaptability Evaluation index factor chooses the Adaptability Evaluation index that module is used to choose the evaluation of power distribution network power grid Factor；History value acquisition module is used for the Adaptability Evaluation index factor according to selection, acquires Adaptability Evaluation in power distribution network and refers to History index value, history index weights corresponding to mark factor and history index grade point；First training set establishes module For history index value, history index weights corresponding to the Adaptability Evaluation index factor to acquisition and history index etc. Grade value carries out feature extraction, and establishes the first training set；Deep learning evaluation model establishes module for according to the first of foundation Training set constructs deep learning evaluation model；Evaluation: Current index value computing module is used to calculate the Adaptability Evaluation chosen and refers to The Evaluation: Current index value of mark factor；Adaptability Evaluation rule establishes module for according to the Evaluation: Current index value that is calculated With the deep learning evaluation model of building, the Adaptability Evaluation rule of power distribution network is established；Second training set establish module for pair History index value corresponding to the Adaptability Evaluation index factor of acquisition, history index weights and history index grade point into Row feature extraction, and establish the second training set；Deep learning weight model establishes module for according to the second training set of foundation, Construct deep learning index weights model；Current criteria weight value calculation module is used for according to the Evaluation: Current index being calculated The deep learning index weights model of value and building calculates the current criteria weighted value of Adaptability Evaluation index factor；Power distribution network Power adaptation evaluation result computing module be used for according to Adaptability Evaluation index factor, Adaptability Evaluation index factor it is current The Adaptability Evaluation of index weights and power distribution network rule, calculates the Adaptability Evaluation result of distribution network source.
This power distribution network power grid evaluation method and its evaluation system provided by the invention, can be improved Adaptability Evaluation The accuracy of the weight of index, while Adaptability Evaluation result precision is improved, accurate adaptability is provided for distribution network transform Appreciation gist.
Detailed description of the invention
Fig. 1 is the method flow diagram of the method for the present invention.
Fig. 2 is the functional block diagram of present system.
Specific embodiment
It is as shown in Figure 1 the method flow diagram of the method for the present invention: this power distribution network power grid evaluation provided by the invention Method includes the following steps:
S1. the Adaptability Evaluation index factor of power distribution network power grid evaluation is chosen；Specially carried out using following steps It chooses:
(1) according to the operating parameter of Distribution Network Equipment, iotave evaluation index factor is selected；
(2) according to the iotave evaluation index factor selected in step (1), original evaluation index factor institute in power distribution network is acquired Corresponding history index value, history index weights and history index grade calculate each original comment using correlation analysis algorithm The corresponding related coefficient of valence index factor；
(3) according to initial value evaluation index factor and its corresponding related coefficient, Adaptability Evaluation index factor is determined；
In the specific implementation, optimum operation section can be in access line Rate of average load, heavy-haul line accounting, load Route accounting, Breaking capacity average margin, switch qualification rate, capacity-load ratio, heavily loaded transformer accounting, load be in optimum operation False protection rate, protection sensitivity verification qualification rate and while operating normally, are protected under the transformer accounting in section, fault condition Malfunction rate is as Adaptability Evaluation index factor；
Route Rate of average load Id1It is able to reflect the power transmission situation of distribution line, is to measure distribution line overall load The important indicator of amount:P in formulaGFor the not grid-connected net online amount of distributed generation resource, PDG For the grid-connected net online amount of distributed generation resource；IjNFor the rated current of route j, UjNFor the voltage rating of route j；
Heavy-haul line accounting Id2I.e. Rate of average load is more than that the distribution line of route rated capacity 70% accounts for the total distribution of system The specific gravity of route, for evaluate DG it is grid-connected after distribution line operation safety and determine distribution line weak link, for Net track remodelling provides foundation:M in formula5It is more than its specified load to be the grid-connected line load rate afterwards of DG The number of lines of flow 70%, NLFor the total distribution line item number of system；
Load is in the route accounting I in optimum operation sectiond3For whether evaluating the grid-connected rear distribution line operation conditions of DG It is high-quality, it is the important indicator for reflecting distribution line performance driving economy, it is preferable that route Rate of average load is its rated current-carrying capacity When 50%~60%, which is in optimum operation section；M in formula6For the grid-connected rear line of DG The number of lines of the road load factor in its rated current-carrying capacity 50%~60%；NLFor the total distribution line item number of system；
Breaking capacity average margin Id4It, can for the average value of DG all breaker Breaking capacity nargin in network after grid-connected Power distribution network switchs the confidence level correctly opened and closed after reflection DG is grid-connected；Switch qualification rate is for evaluating the grid-connected rear power distribution circuit breakers of DG Safe operation situation, reflection network switching equipment is to the adaptation situation of distributed generation resource, for verifying the conjunction of single breaker Lattice situation determines the weak link of network switching, and the transformation for power distribution network switchgear provides foundation；M in formulakK-th of breaker for being DG after grid-connected opens the light Capacity Margin, m7For the breaker number that DG can normally be cut-off after grid-connected, NsFor breaker sum；
Capacity-load ratio Id6, heavily loaded transformer accounting Id7And load is in the transformer accounting I in optimum operation sectiond8；Hold and carries Than the ratio for referring to the abundant corresponding total load of transformer equipment total capacity in a certain power supply area, for evaluating the transformation of power distribution network entirety Device utilization rate and operation nargin；Heavily loaded transformer accounting is that load factor is more than transformer rated capacity 45% under normal operation Transformer relative system transformer sum accounting；The transformer accounting that load is in optimum operation section is for evaluating DG Whether the operation conditions of network distribution transformer is high-quality after grid-connected, is the important indicator for reflecting transformer station high-voltage side bus economy, it is preferable that negative When load rate is nominal load rate 35%~45%, Transformer Operation Status is best. P in formulaTFor transformer in power distribution network Total capacity, PLFor transformer total load, m in power distribution network8For the DG change of transformer load rate more than its rated capacity 80% after grid-connected Depressor number of units, NTFor system transformer sum, m9The transformer number of units in optimum operation section is in for the grid-connected rear load of DG；
False protection rate I under fault conditiond9, protection sensitivity verification qualification rate Id10And false protection when operating normally Rate Id11；False protection rate determines net for measuring the power distribution network protective relaying device adaptation situation grid-connected to DG under fault condition The weak link of network protection provides foundation for renovating for distribution protection；Protection sensitivity verification qualification rate can embody The adaptation situation of power distribution network time limit current quick break protection, verifies single protection act sensitivity, determines protective device after DG is grid-connected Weak link, the transformation for distribution protection device provides foundation；False protection rate is able to reflect load guarantor when normal operation Protect the influence degree to the adaptability of distributed generation resource and DG to network trend. M in formula10For the grid-connected rear distribution of DG Protective relaying device malfunction number, N under net fault conditionPSum, m are installed for protective relaying device11For the grid-connected rear sensitivity of DG Protection number greater than 1.3, m12The number of malfunction occurs for protective relaying device when for DG, power distribution network is operated normally after grid-connected；
S2. the Adaptability Evaluation index factor chosen according to step S1 acquires Adaptability Evaluation index factor in power distribution network Corresponding history index value, history index weights and history index grade point；
S3. history index value, history index weights corresponding to the Adaptability Evaluation index factor to step S2 acquisition And history index grade point carries out feature extraction, and establishes the first training set；
S4. the first training set established according to step S3 constructs deep learning evaluation model；Specially according to the first training Collection carries out deep learning to the first algorithm set using deep neural network model, to construct deep learning index weights mould Type；First algorithm set includes Data Dimensionality Reduction Algorithm, association algorithm, linear regression algorithm and sorting algorithm；
S5. the Evaluation: Current index value for the Adaptability Evaluation index factor that step S2 chooses is calculated；
S6. according to the deep learning evaluation model for Evaluation: Current index value and step the S4 building being calculated, foundation is matched The Adaptability Evaluation rule of power grid；
S7. history index value, history index weights corresponding to the Adaptability Evaluation index factor to step S2 acquisition And history index grade point carries out feature extraction, and establishes the second training set；
S8. the second training set established according to step S7 constructs deep learning index weights model；Specially according to second Training set carries out deep learning to the second algorithm set using deep neural network model, to construct deep learning index power Molality type；Second algorithm set includes step analysis algorithm, Principal Component Analysis Algorithm, association algorithm, linear regression algorithm and divides Class algorithm
S9. according to the deep learning index weights mould of the step S5 Evaluation: Current index value being calculated and step S8 building Type calculates the current criteria weighted value of Adaptability Evaluation index factor；
S10. the Adaptability Evaluation index factor that Adaptability Evaluation index factor, the step S9 chosen according to step S1 is obtained Current criteria weighted value and the obtained power distribution network of step S6 Adaptability Evaluation rule, the adaptability for calculating distribution network source comments Valence result；Adaptability Evaluation result Q is specially calculated using following formula:
N is the number of Adaptability Evaluation index factor, w in formulaiFor the weight of i-th of Adaptability Evaluation index factor, IiFor I-th of Adaptability Evaluation index factor.
It is illustrated in figure 2 the functional block diagram of present system: this realization distribution network source provided by the invention The evaluation system of grid-connected evaluation method, the Adaptability Evaluation index factor including being sequentially connected in series choose module, history value acquisition mould Block, the first training set establish module, deep learning evaluation model establishes module, Evaluation: Current index value computing module, adaptability Evaluation rule establishes module, the second training set establishes module, deep learning weight model establishes module, current criteria weighted value meter Calculate module and power distribution network power adaptation evaluation result computing module；Adaptability Evaluation index factor is chosen module and is matched for choosing The Adaptability Evaluation index factor of the grid-connected evaluation of electric network source；History value acquisition module according to the Adaptability Evaluation of selection for referring to Mark factor acquires history index value, history index weights corresponding to Adaptability Evaluation index factor in power distribution network and goes through History index grade point；First training set establishes module for history index corresponding to the Adaptability Evaluation index factor to acquisition Value, history index weights and history index grade point carry out feature extraction, and establish the first training set；Deep learning evaluation Model building module is used for the first training set according to foundation, constructs deep learning evaluation model；Evaluation: Current index value calculates Module is used to calculate the Evaluation: Current index value for the Adaptability Evaluation index factor chosen；Adaptability Evaluation rule establishes module use In the deep learning evaluation model according to the Evaluation: Current index value and building being calculated, the Adaptability Evaluation of power distribution network is established Rule；Second training set establishes module for history index value, history corresponding to the Adaptability Evaluation index factor to acquisition Index weights and history index grade point carry out feature extraction, and establish the second training set；Deep learning weight model is built Formwork erection block is used for the second training set according to foundation, constructs deep learning index weights model；Current criteria weighted value calculates mould Block is used for the deep learning index weights model according to the Evaluation: Current index value and building being calculated, and calculates Adaptability Evaluation The current criteria weighted value of index factor；Power distribution network power adaptation evaluation result computing module according to Adaptability Evaluation for referring to The Adaptability Evaluation rule of mark factor, the current criteria weighted value of Adaptability Evaluation index factor and power distribution network, calculates power distribution network The Adaptability Evaluation result of power supply.

Claims (9)

1. a kind of power distribution network power grid evaluation method, includes the following steps:
S1. the Adaptability Evaluation index factor of power distribution network power grid evaluation is chosen；
S2. it is right to acquire Adaptability Evaluation index factor institute in power distribution network for the Adaptability Evaluation index factor chosen according to step S1 History index value, history index weights and the history index grade point answered；
S3. to step S2 acquisition Adaptability Evaluation index factor corresponding to history index value, history index weights and History index grade point carries out feature extraction, and establishes the first training set；
S4. the first training set established according to step S3 constructs deep learning evaluation model；
S5. the Evaluation: Current index value for the Adaptability Evaluation index factor that step S2 chooses is calculated；
S6. according to the deep learning evaluation model for Evaluation: Current index value and step the S4 building being calculated, power distribution network is established Adaptability Evaluation rule；
S7. to step S2 acquisition Adaptability Evaluation index factor corresponding to history index value, history index weights and History index grade point carries out feature extraction, and establishes the second training set；
S8. the second training set established according to step S7 constructs deep learning index weights model；
S9. the deep learning index weights model constructed according to the step S5 Evaluation: Current index value being calculated and step S8, Calculate the current criteria weighted value of Adaptability Evaluation index factor；
S10. the Adaptability Evaluation index factor that Adaptability Evaluation index factor, the step S9 chosen according to step S1 is obtained is worked as The Adaptability Evaluation rule for the power distribution network that preceding index weights and step S6 are obtained, calculates the Adaptability Evaluation knot of distribution network source Fruit.
2. power distribution network power grid evaluation method according to claim 1, it is characterised in that selection described in step S1 is matched The Adaptability Evaluation index factor of the grid-connected evaluation of electric network source is specially chosen using following steps:
(1) according to the operating parameter of Distribution Network Equipment, iotave evaluation index factor is selected；
(2) it according to the iotave evaluation index factor selected in step (1), acquires in power distribution network corresponding to original evaluation index factor History index value, history index weights and history index grade, each iotave evaluation is calculated using correlation analysis algorithm and is referred to The corresponding related coefficient of mark factor；
(3) according to initial value evaluation index factor and its corresponding related coefficient, Adaptability Evaluation index factor is determined.
3. power distribution network power grid evaluation method according to claim 2, it is characterised in that the Adaptability Evaluation refers to Mark factor includes that route Rate of average load, heavy-haul line accounting, load are in route accounting, the Breaking capacity in optimum operation section Average margin, switch qualification rate, capacity-load ratio, heavily loaded transformer accounting, load are in the transformer accounting in optimum operation section, event False protection rate when false protection rate, protection sensitivity verification qualification rate and normal operation in the case of barrier.
4. power distribution network power grid evaluation method according to claim 3, it is characterised in that according to described in step S4 One training set constructs deep learning evaluation model, specially according to the first training set, using deep neural network model to first Algorithm set carries out deep learning, to construct deep learning index weights model.
5. power distribution network power grid evaluation method according to claim 4, it is characterised in that first algorithm set Including Data Dimensionality Reduction Algorithm, association algorithm, linear regression algorithm and sorting algorithm.
6. power distribution network power grid evaluation method according to claim 5, it is characterised in that according to described in step S8 Two training sets construct deep learning index weights model, specially according to the second training set, using deep neural network model pair Second algorithm set carries out deep learning, to construct deep learning index weights model.
7. power distribution network power grid evaluation method according to claim 6, it is characterised in that second algorithm set Including step analysis algorithm, Principal Component Analysis Algorithm, association algorithm, linear regression algorithm and sorting algorithm.
8. power distribution network power grid evaluation method according to claim 7, it is characterised in that according to suitable described in step S10 The Adaptability Evaluation rule meter of answering property evaluation index factor, the current criteria weighted value of Adaptability Evaluation index factor and power distribution network Adaptability Evaluation is calculated as a result, being specially to calculate Adaptability Evaluation result Q using following formula:
N is the number of Adaptability Evaluation index factor, w in formulaiFor the weight of i-th of Adaptability Evaluation index factor, IiIt is i-th A Adaptability Evaluation index factor.
9. it is a kind of realize claim 1~one of described in power distribution network power grid evaluation method evaluation system, including adapt to Property evaluation index factor chooses module, history value acquisition module, the first training set establish module, deep learning evaluation model is established Module, Evaluation: Current index value computing module, Adaptability Evaluation rule establish module, the second training set establishes module, depth It practises weight model and establishes module, current criteria weight value calculation module and power distribution network power adaptation evaluation result computing module； Adaptability Evaluation index factor chooses module, history value acquisition module, the first training set and establishes module, deep learning evaluation model Establish that module, Evaluation: Current index value computing module, Adaptability Evaluation rule establish module, the second training set establishes module, depth Degree study weight model establishes module, current criteria weight value calculation module and power distribution network power adaptation evaluation result and calculates mould Block is sequentially connected in series；Adaptability Evaluation index factor is chosen module and is referred to for choosing the Adaptability Evaluation of power distribution network power grid evaluation Mark factor；History value acquisition module is used for the Adaptability Evaluation index factor according to selection, acquires Adaptability Evaluation in power distribution network History index value, history index weights corresponding to index factor and history index grade point；First training set establishes mould Block is for history index value, history index weights and history index corresponding to the Adaptability Evaluation index factor to acquisition Grade point carries out feature extraction, and establishes the first training set；Deep learning evaluation model establishes module for according to the of foundation One training set constructs deep learning evaluation model；Evaluation: Current index value computing module is used to calculate the Adaptability Evaluation chosen The Evaluation: Current index value of index factor；Adaptability Evaluation rule establishes module for according to the Evaluation: Current index that is calculated The deep learning evaluation model of value and building establishes the Adaptability Evaluation rule of power distribution network；Second training set is established module and is used for History index value, history index weights corresponding to Adaptability Evaluation index factor to acquisition and history index grade point Feature extraction is carried out, and establishes the second training set；Deep learning weight model establishes module for according to the second of foundation the training Collection constructs deep learning index weights model；Current criteria weight value calculation module is used for according to the Evaluation: Current being calculated The deep learning index weights model of index value and building calculates the current criteria weighted value of Adaptability Evaluation index factor；Match Electric network source Adaptability Evaluation result computing module is used for according to Adaptability Evaluation index factor, Adaptability Evaluation index factor The Adaptability Evaluation of current criteria weighted value and power distribution network rule, calculates the Adaptability Evaluation result of distribution network source.
CN201811242931.7A 2018-10-24 2018-10-24 Power distribution network power grid evaluation method and its evaluation system Pending CN109214717A (en)

Priority Applications (1)

Application Number Priority Date Filing Date Title
CN201811242931.7A CN109214717A (en) 2018-10-24 2018-10-24 Power distribution network power grid evaluation method and its evaluation system

Applications Claiming Priority (1)

Application Number Priority Date Filing Date Title
CN201811242931.7A CN109214717A (en) 2018-10-24 2018-10-24 Power distribution network power grid evaluation method and its evaluation system

Publications (1)

Publication Number Publication Date
CN109214717A true CN109214717A (en) 2019-01-15

Family

ID=64996576

Family Applications (1)

Application Number Title Priority Date Filing Date
CN201811242931.7A Pending CN109214717A (en) 2018-10-24 2018-10-24 Power distribution network power grid evaluation method and its evaluation system

Country Status (1)

Country Link
CN (1) CN109214717A (en)

Cited By (5)

* Cited by examiner, † Cited by third party
Publication number Priority date Publication date Assignee Title
CN109858799A (en) * 2019-01-26 2019-06-07 国网福建省电力有限公司 Active distribution network modification measures and route heavy duty rate relevance method for digging and device
CN110162545A (en) * 2019-04-18 2019-08-23 平安城市建设科技(深圳)有限公司 Information-pushing method, equipment, storage medium and device based on big data
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
CN112488475A (en) * 2020-11-20 2021-03-12 广西电网有限责任公司电力科学研究院 Method and system for differential evaluation of multi-level gridding reliability
CN113822536A (en) * 2021-08-26 2021-12-21 国网河北省电力有限公司邢台供电分公司 Power distribution network index evaluation method based on branch definition algorithm

Citations (4)

* Cited by examiner, † Cited by third party
Publication number Priority date Publication date Assignee Title
CN102999792A (en) * 2012-12-20 2013-03-27 诸暨市供电局 Method for comprehensive evaluation of power distribution network optimization allocation
CN103310390A (en) * 2013-07-05 2013-09-18 武汉大学 Grid security comprehensive evaluation method
CN104318339A (en) * 2014-09-15 2015-01-28 国家电网公司 Power grid investment benefit evaluation method based on comprehensive empowerment method
CN104598725A (en) * 2014-12-31 2015-05-06 国家电网公司 Evaluation method for power distribution network adaptability of distributed power supply after grid connection

Patent Citations (4)

* Cited by examiner, † Cited by third party
Publication number Priority date Publication date Assignee Title
CN102999792A (en) * 2012-12-20 2013-03-27 诸暨市供电局 Method for comprehensive evaluation of power distribution network optimization allocation
CN103310390A (en) * 2013-07-05 2013-09-18 武汉大学 Grid security comprehensive evaluation method
CN104318339A (en) * 2014-09-15 2015-01-28 国家电网公司 Power grid investment benefit evaluation method based on comprehensive empowerment method
CN104598725A (en) * 2014-12-31 2015-05-06 国家电网公司 Evaluation method for power distribution network adaptability of distributed power supply after grid connection

Non-Patent Citations (1)

* Cited by examiner, † Cited by third party
Title
姜大立: "基于神经网络的综合预测模型", 《中国系统工程学会第八届学术年会论文集》 *

Cited By (7)

* Cited by examiner, † Cited by third party
Publication number Priority date Publication date Assignee Title
CN109858799A (en) * 2019-01-26 2019-06-07 国网福建省电力有限公司 Active distribution network modification measures and route heavy duty rate relevance method for digging and device
CN109858799B (en) * 2019-01-26 2022-08-05 国网福建省电力有限公司 Active power distribution network reconstruction measure and line heavy load rate relevance mining method and device
CN110162545A (en) * 2019-04-18 2019-08-23 平安城市建设科技(深圳)有限公司 Information-pushing method, equipment, storage medium and device based on big data
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
CN112488475A (en) * 2020-11-20 2021-03-12 广西电网有限责任公司电力科学研究院 Method and system for differential evaluation of multi-level gridding reliability
CN113822536A (en) * 2021-08-26 2021-12-21 国网河北省电力有限公司邢台供电分公司 Power distribution network index evaluation method based on branch definition algorithm

Similar Documents

Publication Publication Date Title
CN109214717A (en) Power distribution network power grid evaluation method and its evaluation system
CN104579868B (en) Powerline network construction method based on pitch point importance
CN103744850B (en) A kind of electrical network disaster real-time monitoring device and method based on intuitionistic fuzzy-rough sets
CN104766185B (en) Area power grid outage information based on grid power blackout characteristic studies and judges system and method
CN102934312B (en) Energy production system and control thereof
CN109118098A (en) The cascading failure methods of risk assessment and system of high proportion wind-electricity integration
CN103310390A (en) Grid security comprehensive evaluation method
CN105117839B (en) A kind of power system weak link identification method based on cascading failure
CN103618638B (en) The method of assessment power telecom network maintenance solution
CN103996099B (en) Method for conducting intelligent evaluation on student operation in training system
CN108899904A (en) A kind of alternating current-direct current large power grid cascading failure method for fast searching and system
CN104901306B (en) Power grid operation safety margin calculating method taking cascading faults into consideration
CN106329516A (en) Typical scene recognition based dynamic reconstruction method of power distribution network
CN105069692A (en) Accurate power grid safety risk assessment method
CN106651189A (en) Transformer state evaluation method based on multilayer compound rule
CN106093713A (en) A kind of power distribution network section Fault Locating Method containing distributed power source and system
CN107256449A (en) A kind of relay protection device of intelligent substation state evaluation and appraisal procedure
CN107633320A (en) A kind of power network line importance appraisal procedure based on weather prognosis and risk assessment
CN105447618B (en) A kind of electric system subregion reliability estimation method
CN106600458A (en) Power grid risk comprehensive assessment method based on improved power betweenness
CN109917175A (en) It is a kind of for high anti-back-out when overvoltage method for quick predicting
CN103150635A (en) Operation and maintenance method of power equipment
CN104318317A (en) Black-start scheme optimization method based on distributive integrated energy supply system
CN103745267A (en) Distributed photovoltaic system grid connection influence evaluation method
CN104037760B (en) Anticipated accident selection method for electric power system with uncertain injection power

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
RJ01 Rejection of invention patent application after publication
RJ01 Rejection of invention patent application after publication

Application publication date: 20190115