CN109767051A - Transformer based on big data analysis, which has a power failure, plans arrangement method - Google Patents

Transformer based on big data analysis, which has a power failure, plans arrangement method Download PDF

Info

Publication number
CN109767051A
CN109767051A CN201811255048.1A CN201811255048A CN109767051A CN 109767051 A CN109767051 A CN 109767051A CN 201811255048 A CN201811255048 A CN 201811255048A CN 109767051 A CN109767051 A CN 109767051A
Authority
CN
China
Prior art keywords
power failure
transformer
main transformer
data
plan
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.)
Granted
Application number
CN201811255048.1A
Other languages
Chinese (zh)
Other versions
CN109767051B (en
Inventor
马占军
梁刚
刘明
田圳
王钰
任肖久
李海科
梁伟
戚艳
陈文福
韩晨曦
李丛林
杨要中
赵玲玲
郭丰瑞
梁程
潘海泉
王琳
张超雄
田中亮
蔚鑫栋
党旭鑫
徐坤
虎挺昊
何欣志
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
State Grid Tianjin Electric Power Co Ltd
Original Assignee
State Grid Corp of China SGCC
State Grid Tianjin 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, State Grid Tianjin Electric Power Co Ltd filed Critical State Grid Corp of China SGCC
Priority to CN201811255048.1A priority Critical patent/CN109767051B/en
Publication of CN109767051A publication Critical patent/CN109767051A/en
Application granted granted Critical
Publication of CN109767051B publication Critical patent/CN109767051B/en
Active legal-status Critical Current
Anticipated expiration legal-status Critical

Links

Classifications

    • 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
    • Y02—TECHNOLOGIES OR APPLICATIONS FOR MITIGATION OR ADAPTATION AGAINST CLIMATE CHANGE
    • Y02E—REDUCTION OF GREENHOUSE GAS [GHG] EMISSIONS, RELATED TO ENERGY GENERATION, TRANSMISSION OR DISTRIBUTION
    • Y02E40/00—Technologies for an efficient electrical power generation, transmission or distribution
    • Y02E40/70—Smart grids as climate change mitigation technology in the energy generation sector
    • 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

Landscapes

  • Supply And Distribution Of Alternating Current (AREA)

Abstract

The invention discloses a kind of, and arrangement method is planned in the transformer power failure based on big data analysis, belongs to network system technical field, comprising: Step 1: transformer power failure related data is extracted；It is fitted Step 2: carrying out main transformer N-1 indicatrix using K-means method；Step 3: carrying out cluster fitting using main transformer N-1 load data of the K-means algorithm in Matlab software to many years, the matched curve of transforming plant main transformer N-1 is obtained；Step 4: extracting is suitable for substation transformer interruption maintenance time section；Step 5: user-defined counter " the reasonable rate of maintenance plan ", the planning work executive condition having a power failure to quantization signifying transformer；Step 6: being optimized using particle swarm algorithm to main transformer typical case's service work power failure duration；Step 7: transformer power failure planning optimization waiting.

Description

Transformer based on big data analysis, which has a power failure, plans arrangement method
Technical field
Have a power failure the invention belongs to network system technical field more particularly to a kind of transformer based on big data analysis and plans Arrangement method.
Background technique
In recent years, deepening continuously with " digital road " construction, power supply quality of the people to large size city power distribution network It is required that increasingly improving, since 35kV and the above rack are fairly perfect, master network equipment scheduled overhaul, which has a power failure, seldom brings direct load Loss, the safe operation of electric network risk for overhauling generation become most important evaluation criterion.How transformer power failure plan row is optimized Phase, the comprehensive critical issue for reducing the security risk that transformer has a power failure and being managed as power grid security.
Summary of the invention
In view of the problems of the existing technology, the present invention proposes a kind of transformer power failure plan peace based on big data analysis Discharge method excavates transformer station high-voltage side bus and overhaul data rule and value using the tool method of big data, comprehensive to show that one kind is comprehensive Close the power failure planning optimization scheduling method in optimization transformer power failure period and duration.Using K-means algorithm to dispatching automation Transformer load data carry out cluster curve matching in system, obtain the year indicatrix of transforming plant main transformer N-1, choose trough area Section, so that the long scale safety of power failure be contemplated, recycles particle swarm algorithm to history maintenance plan to be suitable for overhauling section Middle typical case's power failure work execution time optimizes, and show that duration is suggested in typical service work, so that transformer power failure be contemplated Short-scale safety, the finally comprehensive suitable turn(a)round and power failure duration for obtaining substation transformer instruct related fortune inspection, base It departments' reasonable arrangement project progress such as builds, market, changing traditional transformer power failure plan arrangement mode, realizing to transformer The digitlization for the safety that has a power failure, intelligent control.
One of the objects of the present invention is to provide a kind of, and arrangement method, packet are planned in the transformer power failure based on big data analysis Include following steps:
Step 1: transformer power failure related data is extracted；
It is fitted Step 2: carrying out main transformer N-1 indicatrix using K-means method；Wherein: N-1 is indicated one in substation After platform main transformer has a power failure, the load factor of other main transformers；
Step 3: it is quasi- to carry out cluster using main transformer N-1 load data of the K-means algorithm in Matlab software to many years It closes, obtains the matched curve of transforming plant main transformer N-1；
Step 4: extracting is suitable for substation transformer interruption maintenance time section；Specifically:
According to the rule of transformer lines interruption maintenance, after obtaining transforming plant main transformer N-1 annual gas load fit characteristic curve, Choosing the smooth valley regions of waveform to be is suitable for repair time section, which is not more than 60 days, if choosing it less than 60 days He fills up trough section；
Step 5: user-defined counter " the reasonable rate of maintenance plan ", the planning work having a power failure to quantization signifying transformer is held Market condition, reasonable rate is higher, and to represent power failure duration more reasonable；
Reasonable rate=the running time of maintenance plan/plan application time * 100%；
Step 6: being optimized using particle swarm algorithm to main transformer typical case's service work power failure duration；Specifically:
The history main transformer power failure power failure plan duration that test class works in the works and in actual work long data are extracted, is utilized Particle swarm algorithm calculate typical duration, a typical plan duration is obtained, so that history main transformer interruption maintenance meter Reasonable rate highest is drawn, and rationally rate value is not more than 100%, the typical of type is overhauled using the optimization duration as the quasi-representative and is had a power failure Duration；
Step 7: transformer power failure planning optimization waiting；
It is suitable for having a power failure section and transformer that particle swarm algorithm obtains is typical by the transformer obtained using K-means algorithm It overhauls typical power failure duration to be integrated, obtains transformer power failure planning optimization waiting result.
Further, in the step 1: transformer power failure related data includes main transformer power failure planning data and main transformer N-1, Wherein: main transformer power failure planning data obtains 1 data of cycle T in 5 years, the number of cycle T 1 by the way of collecting on line from OMS The moon is unit accordingly；Main transformer N-1 obtains the number of the cycle T 2 in 5 years by the way of collecting on line from dispatch automated system According to 1 data of cycle T are as unit of day.OMS refers to State Grid Corporation of China's management and running applied business process.
Further, the step 2 specifically:
The first step, initialization, input gene expression matrix input specified cluster class number N as object set X, and in object N number of object is randomly selected in collection X as initial cluster center, sets iteration termination condition, above-mentioned iteration termination condition is maximum Cycle-index or cluster centre convergence error tolerance；
Second step is iterated, and data object is assigned to immediate cluster centre according to similarity criteria, thus shape At one kind；Subordinated-degree matrix is initialized, cluster centre is updated, then using the average vector of every one kind as new cluster centre, Redistribute data object；
Third step repeats second step until meeting suspension condition.
The second object of the present invention is to provide a kind of transformer power failure plan arrangement side realized based on big data analysis The computer program of method.
The third object of the present invention is to provide a kind of transformer power failure plan arrangement side realized based on big data analysis The information data processing terminal of method.
The fourth object of the present invention is to provide a kind of computer readable storage medium, including instruction, when it is in computer When upper operation, so that computer executes the transformer power failure plan arrangement method based on big data analysis.
In conclusion advantages of the present invention and good effect are as follows:
The present invention utilizes the tool method of big data, excavates transformer station high-voltage side bus and overhaul data rule and is worth, comprehensive A kind of power failure planning optimization scheduling method in complex optimum transformer power failure period and duration out.It is exchanged using K-means algorithm Transformer load data carry out cluster curve matching in degree automated system, obtain the year indicatrix of transforming plant main transformer N-1, select Trough section is taken to be suitable for overhauling section, so that the long scale safety of power failure be contemplated, recycles particle swarm algorithm to history The typical power failure work execution time optimizes in maintenance plan, show that duration is suggested in typical service work, so that change be contemplated The short-scale safety that depressor has a power failure finally the comprehensive suitable turn(a)round and power failure duration for obtaining substation transformer, instructs phase The departments such as Guan Yunjian, capital construction, marketing reasonable arrangement project progress changes traditional transformer power failure plan arrangement mode, real Now to the digitlization of transformer power failure safety, intelligent control.
Detailed description of the invention
Fig. 1 is K-means algorithm cluster in the preferred embodiment of the present invention；
Fig. 2 is main transformer N-1 lotus fit characteristic curve in the preferred embodiment of the present invention.
Specific embodiment
In order to make the objectives, technical solutions, and advantages of the present invention clearer, with reference to embodiments, to the present invention It is further elaborated.It should be appreciated that the specific embodiments described herein are merely illustrative of the present invention, it is not used to Limit the present invention.
Fig. 1 to Fig. 2, a kind of transformer power failure plan arrangement method based on big data analysis are please referred to, including is walked as follows It is rapid:
1, transformer power failure related data is extracted.Extraction demand mainly see the table below 1:
Table 1 extracts demand schedule
2, original data processing
Main transformer road load data is handled using excle software programming formula, is repeated by correcting mistake, deleting Item, correction logic, transformed structure, data compression, supplies incompleteness/null value, abandons data/variable unified specification, realizes data The verification of integrality, uniqueness, authority, legitimacy and consistency.
3, main transformer N-1 indicatrix is carried out using K-means method to be fitted
(1) K-means principle:
The first step, initialization.Input gene expression matrix and be used as object set X, input is specified to cluster class number N, and in X with Machine chooses N number of object as initial cluster center.Iteration termination condition is set, for example maximum cycle or cluster centre are received Hold back error margin.
Second step is iterated.Data object is assigned to immediate cluster centre according to similarity criteria, thus shape At one kind.Initialize subordinated-degree matrix.Update cluster centre.Then using the average vector of every one kind as new cluster centre, Redistribute data object.
Third step executes second step repeatedly until meeting suspension condition.
(2) cluster is carried out to the main transformer N-1 load data of many years using the K-means algorithm carried in Matlab software to intend It closes, obtains the matched curve of transforming plant main transformer N-1.
(3) extract is suitable for substation transformer interruption maintenance time section.
According to the rule of transformer lines interruption maintenance, the power failure window phase for needing to have 60 days or so in 1 year accounts for about complete The 16.7% of year.After obtaining transforming plant main transformer N-1 annual gas load fit characteristic curve, it is suitable for choosing the smooth valley regions of waveform Suitable repair time section, the section are not more than 60 days.If can choose other trough sections less than 60 days and be filled up.
Design limitation condition simultaneously, if valley section N-1 value is respectively less than 90%, then it is assumed that be suitable for, while utilizing degree of certainty Winter, aestivate, the boundaries Conditions On The Results such as great guarantor's electricity are screened, obtain the suitable turn(a)round of each transforming plant main transformer, and compile " Repair of Transformer calendar " is made.
4, transformer power failure duration optimizes
4.1 user-defined counters " the reasonable rate of maintenance plan ", the planning work having a power failure to quantization signifying transformer execute feelings Condition, reasonable rate is higher, and to represent power failure duration more reasonable.(being not more than 100% in principle, if too short beyond planned time is represented)
Reasonable rate=the running time of maintenance plan/plan application time * 100%
2 maintenance plan of table is rationally classified
4.2 particle swarm algorithms (PSO) iteration optimization
(1) basic principle
The basic thought of PSO algorithm is that random initializtion a group does not have volume not have the particle of quality, with each particle Solution of the position as optimization problem, and the quality of the fitness function measurement particle by reflection optimization aim.Particle is with certain Speed scanned in the solution space of setting, by remembering and learning, by successive ignition search finally obtain most Excellent solution.In each iterative process, particle will " memory " itself history optimal solution, the history optimal solution of " study " entire group.
The basic principle of particle swarm algorithm is as follows:
In the target search space of N-dimensional, m particle is wherein being flown with certain speed, when t moment, the operation of particle i State can be arranged as follows:
Position: Xi=(xi1,,...xid)TI=1,2 ..., m
Speed: Vi=(vi1,,...vid)TI=1,2 ..., m
Adaptive value are as follows: fitnessi=f (X1)
Its d ties up component (1≤d≤D) and changes according to the following formula:
wt=wmax-(wmax-wmin)t/tmax
In formula:Component is tieed up for the d of velocity vector of the particle i in the t times iteration；
Component is tieed up for the d of position vector of the particle i in the t times iteration；
The individual optimal value of component is tieed up for the d of position vector of the particle i in the t times iteration；
For global optimum of the particle group in the t times iteration in solution space；
r1, r2It is uniformly distributed at random between 0~1；c1, c2For the Studying factors of particle, c is generally taken1=c2=2.wtIt is used Property weight；
On the one hand population remembers the experience accumulation of itself in searching process, on the other hand learn the warp of other particles It tests, when the value of information of some particle is preferable, will be learnt by other particles, and be adjusted correspondingly, to improve particle Optimizing ability, by the cooperation and competition between particle, direction that entire population is constantly become better is evolved.
(2) calculating is optimized to main transformer typical case's service work power failure duration using particle swarm algorithm.
The history main transformer power failure power failure plan duration that test class works in the works and in actual work long data are extracted, is utilized Particle swarm algorithm calculate typical duration, a typical plan duration is obtained, so that history main transformer interruption maintenance meter Reasonable rate highest is drawn, and rationally rate value is not more than 100%, the typical of type is overhauled using the optimization duration as the quasi-representative and is had a power failure Duration.
5, transformer power failure planning optimization waiting
It is suitable for having a power failure section and transformer that particle swarm algorithm obtains is typical by the transformer obtained using K-means algorithm It overhauls typical power failure duration to be integrated, obtains transformer power failure planning optimization waiting result.To instruct relevant fortune inspection, base It departments' reasonable arrangement project progress such as builds, market, changing traditional transformer power failure plan arrangement mode, realizing to transformer The digitlization for the safety that has a power failure, intelligent control.
A kind of realization above preferred embodiment, i.e., the transformer based on big data analysis, which has a power failure, plans the calculating of arrangement method Machine program.
A kind of realization above preferred embodiment, i.e., the transformer based on big data analysis, which has a power failure, plans the information of arrangement method Data processing terminal.
A kind of computer readable storage medium, including instruction, when run on a computer, so that computer executes Preferred embodiment is stated, i.e., the transformer based on big data analysis, which has a power failure, plans arrangement method.
In the above-described embodiments, can come wholly or partly by software, hardware, firmware or any combination thereof real It is existing.When using entirely or partly realizing in the form of a computer program product, the computer program product include one or Multiple computer instructions.When loading on computers or executing the computer program instructions, entirely or partly generate according to Process described in the embodiment of the present invention or function.The computer can be general purpose computer, special purpose computer, computer network Network or other programmable devices.The computer instruction may be stored in a computer readable storage medium, or from one Computer readable storage medium is transmitted to another computer readable storage medium, for example, the computer instruction can be from one A web-site, computer, server or data center pass through wired (such as coaxial cable, optical fiber, Digital Subscriber Line (DSL) Or wireless (such as infrared, wireless, microwave etc.) mode is carried out to another web-site, computer, server or data center Transmission).The computer-readable storage medium can be any usable medium or include one that computer can access The data storage devices such as a or multiple usable mediums integrated server, data center.The usable medium can be magnetic Jie Matter, (for example, floppy disk, hard disk, tape), optical medium (for example, DVD) or semiconductor medium (such as solid state hard disk Solid State Disk (SSD)) etc..
The foregoing is merely illustrative of the preferred embodiments of the present invention, is not intended to limit the invention, all in essence of the invention Made any modifications, equivalent replacements, and improvements etc., should all be included in the protection scope of the present invention within mind and principle.

Claims (6)

  1. The plan arrangement method 1. a kind of transformer based on big data analysis has a power failure, it is characterised in that: include at least following steps:
    Step 1: transformer power failure related data is extracted；
    It is fitted Step 2: carrying out main transformer N-1 indicatrix using K-means method；
    Step 3: cluster fitting is carried out using main transformer N-1 load data of the K-means algorithm in Matlab software to many years, Obtain the matched curve of transforming plant main transformer N-1；
    Step 4: extracting is suitable for substation transformer interruption maintenance time section；Specifically:
    According to the rule of transformer lines interruption maintenance, after obtaining transforming plant main transformer N-1 annual gas load fit characteristic curve, choose The smooth valley regions of waveform are suitable repair time section, which is not more than 60 days, if choosing other waves less than 60 days Paddy section is filled up；
    Step 5: user-defined counter " the reasonable rate of maintenance plan ", the planning work having a power failure to quantization signifying transformer executes feelings Condition, reasonable rate is higher, and to represent power failure duration more reasonable；
    Reasonable rate=the running time of maintenance plan/plan application time * 100%；
    Step 6: being optimized using particle swarm algorithm to main transformer typical case's service work power failure duration；Specifically:
    The history main transformer power failure power failure plan duration that test class works in the works and in actual work long data are extracted, particle is utilized Group's algorithm calculate typical duration, a typical plan duration is obtained, so that history main transformer interruption maintenance plan is closed Reason rate highest, and rationally rate value is not more than 100%, when overhauling the typical power failure of type using the optimization duration as the quasi-representative It is long；
    Step 7: transformer power failure planning optimization waiting；
    It is suitable for having a power failure section and transformer typical case maintenance that particle swarm algorithm obtains by the transformer obtained using K-means algorithm Typical power failure duration is integrated, and obtains transformer power failure planning optimization waiting result.
  2. 2. being had a power failure based on the transformer described in claim 1 based on big data analysis plans arrangement method, it is characterised in that: institute State in step 1: transformer power failure related data includes main transformer power failure planning data and main transformer N-1, in which: main transformer, which has a power failure, to be planned Data obtain 1 data of cycle T in 5 years by the way of collecting on line from OMS, and 1 data of cycle T are as unit of the moon；Main transformer N-1 obtains 2 data of cycle T in 5 years by the way of collecting on line from dispatch automated system, and 1 data of cycle T are with day For unit.
  3. 3. being had a power failure based on the transformer described in claim 1 based on big data analysis plans arrangement method, it is characterised in that: institute State step 2 specifically:
    The first step, initialization, input gene expression matrix input specified cluster class number N as object set X, and in object set X N number of object is randomly selected as initial cluster center, sets iteration termination condition, above-mentioned iteration termination condition is largest loop time Several or cluster centre convergence error tolerance；
    Second step is iterated, and data object is assigned to immediate cluster centre according to similarity criteria, to form one Class；Subordinated-degree matrix is initialized, updates cluster centre, then using the average vector of every one kind as new cluster centre, again Distribute data object；
    Third step repeats second step until meeting suspension condition.
  4. 4. a kind of realize described in claim any one of 1-3 based on the transformer of big data analysis power failure plan arrangement method Calculation machine program.
  5. 5. a kind of letter for realizing the power failure plan arrangement method of the transformer described in claim any one of 1-3 based on big data analysis Cease data processing terminal.
  6. 6. a kind of computer readable storage medium, including instruction, when run on a computer, so that computer is executed as weighed The benefit transformer power failure plan arrangement method based on big data analysis that requires 1-3 described in any item.
CN201811255048.1A 2018-10-26 2018-10-26 Transformer power failure planning method based on big data analysis Active CN109767051B (en)

Priority Applications (1)

Application Number Priority Date Filing Date Title
CN201811255048.1A CN109767051B (en) 2018-10-26 2018-10-26 Transformer power failure planning method based on big data analysis

Applications Claiming Priority (1)

Application Number Priority Date Filing Date Title
CN201811255048.1A CN109767051B (en) 2018-10-26 2018-10-26 Transformer power failure planning method based on big data analysis

Publications (2)

Publication Number Publication Date
CN109767051A true CN109767051A (en) 2019-05-17
CN109767051B CN109767051B (en) 2022-12-09

Family

ID=66449447

Family Applications (1)

Application Number Title Priority Date Filing Date
CN201811255048.1A Active CN109767051B (en) 2018-10-26 2018-10-26 Transformer power failure planning method based on big data analysis

Country Status (1)

Country Link
CN (1) CN109767051B (en)

Citations (5)

* Cited by examiner, † Cited by third party
Publication number Priority date Publication date Assignee Title
CN104252646A (en) * 2013-06-29 2014-12-31 贵州黔驰信息股份有限公司 Method for automatically formulating daily power grid maintenance plans
CN105740977A (en) * 2016-01-28 2016-07-06 福州大学 Multi-target particle swarm-based power outage management optimization method
CN105913177A (en) * 2016-04-08 2016-08-31 江苏省电力公司苏州供电公司 Scheduling power failure plan information processing method based on cloud
WO2017071230A1 (en) * 2015-10-30 2017-05-04 南京南瑞集团公司 Method for short-term optimal scheduling of multi-agent hydropower station group
US20170220594A1 (en) * 2016-02-02 2017-08-03 Sap Se Machine maintenance optimization with dynamic maintenance intervals

Patent Citations (5)

* Cited by examiner, † Cited by third party
Publication number Priority date Publication date Assignee Title
CN104252646A (en) * 2013-06-29 2014-12-31 贵州黔驰信息股份有限公司 Method for automatically formulating daily power grid maintenance plans
WO2017071230A1 (en) * 2015-10-30 2017-05-04 南京南瑞集团公司 Method for short-term optimal scheduling of multi-agent hydropower station group
CN105740977A (en) * 2016-01-28 2016-07-06 福州大学 Multi-target particle swarm-based power outage management optimization method
US20170220594A1 (en) * 2016-02-02 2017-08-03 Sap Se Machine maintenance optimization with dynamic maintenance intervals
CN105913177A (en) * 2016-04-08 2016-08-31 江苏省电力公司苏州供电公司 Scheduling power failure plan information processing method based on cloud

Also Published As

Publication number Publication date
CN109767051B (en) 2022-12-09

Similar Documents

Publication Publication Date Title
Eghbal et al. Transmission expansion planning by meta-heuristic techniques: a comparison of shuffled frog leaping algorithm, PSO and GA
CN110298574B (en) Convolutional neural network-based electricity user payment risk rating method
Zeng et al. A learning framework based on weighted knowledge transfer for holiday load forecasting
Gomes et al. A two-stage strategy for security-constrained AC dynamic transmission expansion planning
Muralikrishnan et al. A comprehensive review on evolutionary optimization techniques applied for unit commitment problem
CN106022614A (en) Data mining method of neural network based on nearest neighbor clustering
CN109670650A (en) The method for solving of Cascade Reservoirs scheduling model based on multi-objective optimization algorithm
CN109768540B (en) Power distribution network power failure optimization scheduling method based on big data analysis
CN108596242A (en) Power grid meteorology load forecasting method based on wavelet neural network and support vector machines
CN109447344A (en) Based on the repairing stationary point of Distribution Network Failure big data and method for optimizing route and system
Hinojosa et al. A simulated rebounding algorithm applied to the multi-stage security-constrained transmission expansion planning in power systems
Galvani et al. Data clustering based probabilistic optimal power flow in power systems
CN105243449A (en) Method and device for correcting prediction result of electricity selling amount
CN111415049A (en) Power failure sensitivity analysis method based on neural network and clustering
CN114065634A (en) Data-driven power quality monitoring and stationing optimization method and device
Hinojosa et al. Stochastic security-constrained generation expansion planning based on linear distribution factors
Hamdan et al. On the performance of artificial neural network with sine-cosine algorithm in forecasting electricity load demand
CN115860694A (en) Business expansion process management and control method and system based on instant message technology
Shaghaghi et al. Proposing a new optimized forecasting model for the failure rate of power distribution network thermal equipment for educational centers
Yang et al. The short-term economical operation problem for hydropower station using chaotic normal cloud model based discrete shuffled frog leaping algorithm
Sun et al. Scheduling model of power system based on forecasting error of wind power plant output
CN109767051A (en) Transformer based on big data analysis, which has a power failure, plans arrangement method
Xiong et al. PSO algorithm‐based scenario reduction method for stochastic unit commitment problem
Yeh et al. Application of simplified swarm optimization algorithm in deteriorate supply chain network problem
Ermoliev et al. Linking distributed sectorial and regional optimization models under asymmetric information: towards robust food-water-energy-environmental nexus

Legal Events

Date Code Title Description
PB01 Publication
PB01 Publication
SE01 Entry into force of request for substantive examination
SE01 Entry into force of request for substantive examination
GR01 Patent grant
GR01 Patent grant