CN106529786A - Power distribution network load calibration method and power distribution network load calibration device based on big data analysis - Google Patents
Power distribution network load calibration method and power distribution network load calibration device based on big data analysis Download PDFInfo
- Publication number
- CN106529786A CN106529786A CN201610951489.XA CN201610951489A CN106529786A CN 106529786 A CN106529786 A CN 106529786A CN 201610951489 A CN201610951489 A CN 201610951489A CN 106529786 A CN106529786 A CN 106529786A
- Authority
- CN
- China
- Prior art keywords
- data
- load
- distribution network
- power distribution
- network load
- 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
- 238000000034 method Methods 0.000 title claims abstract description 35
- 238000007405 data analysis Methods 0.000 title claims abstract description 7
- 230000002159 abnormal effect Effects 0.000 claims description 19
- 230000008859 change Effects 0.000 claims description 13
- 238000012795 verification Methods 0.000 claims description 6
- 238000004458 analytical method Methods 0.000 claims description 5
- 230000004069 differentiation Effects 0.000 claims description 5
- 230000001131 transforming effect Effects 0.000 claims description 4
- 238000009434 installation Methods 0.000 claims description 3
- 238000006243 chemical reaction Methods 0.000 claims 1
- 238000010561 standard procedure Methods 0.000 claims 1
- 238000005516 engineering process Methods 0.000 abstract description 3
- 238000012937 correction Methods 0.000 abstract description 2
- 238000001914 filtration Methods 0.000 abstract description 2
- 238000012545 processing Methods 0.000 abstract description 2
- 240000002853 Nelumbo nucifera Species 0.000 description 5
- 235000006508 Nelumbo nucifera Nutrition 0.000 description 5
- 235000006510 Nelumbo pentapetala Nutrition 0.000 description 5
- 238000004364 calculation method Methods 0.000 description 3
- 230000006872 improvement Effects 0.000 description 3
- 238000012423 maintenance Methods 0.000 description 3
- 230000035772 mutation Effects 0.000 description 3
- 241001269238 Data Species 0.000 description 2
- 238000010276 construction Methods 0.000 description 2
- 238000001514 detection method Methods 0.000 description 2
- 238000010586 diagram Methods 0.000 description 2
- 230000000694 effects Effects 0.000 description 2
- 238000007726 management method Methods 0.000 description 2
- 238000012544 monitoring process Methods 0.000 description 2
- 238000005457 optimization Methods 0.000 description 2
- 241001453233 Doodia media Species 0.000 description 1
- 230000009286 beneficial effect Effects 0.000 description 1
- 238000004891 communication Methods 0.000 description 1
- 238000013480 data collection Methods 0.000 description 1
- 230000001419 dependent effect Effects 0.000 description 1
- 238000006073 displacement reaction Methods 0.000 description 1
- 238000007689 inspection Methods 0.000 description 1
- 238000005259 measurement Methods 0.000 description 1
- 238000012986 modification Methods 0.000 description 1
- 230000004048 modification Effects 0.000 description 1
- 238000013439 planning Methods 0.000 description 1
- 230000008569 process Effects 0.000 description 1
- 230000009467 reduction Effects 0.000 description 1
- 238000012552 review Methods 0.000 description 1
- 238000007363 ring formation reaction Methods 0.000 description 1
- 230000003068 static effect Effects 0.000 description 1
- 238000010937 topological data analysis Methods 0.000 description 1
- 230000009466 transformation Effects 0.000 description 1
- 238000012384 transportation and delivery Methods 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
-
- 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—Information and communication technology [ICT] specially adapted for implementation of business processes of specific business sectors, e.g. utilities or tourism
- G06Q50/06—Energy or water supply
Landscapes
- Business, Economics & Management (AREA)
- Engineering & Computer Science (AREA)
- Human Resources & Organizations (AREA)
- Economics (AREA)
- Strategic Management (AREA)
- Theoretical Computer Science (AREA)
- Entrepreneurship & Innovation (AREA)
- Health & Medical Sciences (AREA)
- Marketing (AREA)
- General Physics & Mathematics (AREA)
- General Business, Economics & Management (AREA)
- Tourism & Hospitality (AREA)
- Physics & Mathematics (AREA)
- Public Health (AREA)
- Primary Health Care (AREA)
- Water Supply & Treatment (AREA)
- Development Economics (AREA)
- Educational Administration (AREA)
- General Health & Medical Sciences (AREA)
- Game Theory and Decision Science (AREA)
- Operations Research (AREA)
- Quality & Reliability (AREA)
- Supply And Distribution Of Alternating Current (AREA)
Abstract
The invention discloses a power distribution network load calibration method based on big data analysis. The method comprises the steps of acquiring basic data based on a power distribution automatic system; filtering distortion load curves which are affected by a specific event through associated data analysis; eliminating load curved with severe shape distortion by means of an average per-unit value method; processing burr data according to a 3sigma principle; and completing lost data through an interpolation method. The invention further provides a power distribution network load calibration device based on big data analysis, wherein the power distribution network load calibration device comprises a data acquiring module and a data calibration module. According to the power distribution network load calibration method and the power distribution network load calibration device, big data analysis technology is utilized; intelligent identification and abnormity correction are performed on power distribution network load data in multiple dimensions, thereby ensuring high effectiveness of the load data and improving quality and efficiency in load calibration. Furthermore the power distribution network load calibration method is concise and effective and is suitable for engineering practical application.
Description
Technical field
The present invention relates to distribution network load collimation technique field, more particularly to a kind of born based on the power distribution network that big data is analyzed
The method and apparatus of lotus calibration.
Background technology
Load data in operation of power networks has various important uses, such as load prediction, can open capacity management, operation
Method optimizing, economic operation analysis, planning and designing etc..At present, there is weakness to some extent in the grid structure of each department distribution
Link, load data it is second-rate, it is to the calibration of Distribution Network Load Data data typically using carrying out by the way of multidimentional system analysis, several
According to grasping not comprehensively, person works measure big, inefficiency and less effective.
Based on distribution automation system, the potentiality that its big data is used fully are excavated, using the grid structure in system, is set
The various informations such as standby parameter, load data, develop a set of efficiently easy-to-use automatic Load calibration steps, be significant and
Value:Can be Distribution Network Frame construction, Operation Mode Optimization, lifting power supply capacity, raising correspondence managerial skills and operating efficiency
Etc. aspect formed important support.
In the prior art, typically distribution network load management is carried out by dimensional analytic system, wherein substantial amounts of data are received
Collection housekeeping and analysis decision work are dependent on manually carrying out.Calculate the data for adopting inaccurate, or rely on artificial nucleus couple;
Caused load variations of distribution method of operation adjustment etc. are not considered.In general, distribution network load calibration is usually manually to be situated between
Under entering, limited utilization distribution historic load, is even estimated with static datas such as cut-off currents roughly in some cases,
It is difficult to embody the dynamic change of operation of power networks, result of calculation belongs to outline calculating, and accuracy is low;Person works' amount is big, efficiency compared with
Low and easy error.
The content of the invention
The present invention carries out big data analysis using the model data and history data of power distribution network, and controller switching equipment is born
Lotus curve data is calibrated automatically, it is ensured that the reasonability and availability of distribution network load data.
On the one hand the technical solution used in the present invention is a kind of distribution network load calibration steps analyzed based on big data, bag
Include following steps:A, the basic data for load verification is obtained based on electrical power distribution automatization system;B, in the basic data
Abnormal load data recognized and corrected using one or more data analysing methods of differentiation, wherein, the exception
Load data includes causing load curve shape that shape distortion data of abnormal change, unexpected between adjacent time interval data occur
Load burr data of change and by least one of Deletional data three caused by failure.
The basic data includes in step:Substation equipment data, medium voltage distribution network device data, power distribution network
Topological connection relation data, transformer station's historical data, the historical load of medium voltage distribution network historical data and Medium voltage switch or circuit breaker and distribution transforming
Curve.
As a further improvement on the present invention, step B includes:Analyzed to by particular event shadow by associated data
Loud distorting loads curve is filtered, according to the historical data of switch division state transformation, to non-standard fortune in sampled data
Data under line mode are filtered.
Preferably, step B also includes:Further power network topology is carried out according to the historical data that switch division shape becomes
Analyze to determine the region affected by the particular event.
As a further improvement on the present invention, step B includes:The shape distortion is rejected using average perunit value method
Load curve.
Preferably, step B also includes:The mean value for calculating the load per-unit curve in each day first obtains average perunit
Curve, then calculates the load per-unit curve in each day and the distance of average per-unit curve, according to apart from the distortion of size Ordination
Degree determines shape distortion load curve.Preferably, step B also includes, obtains during calculated load per-unit curve
Sample must be investigated.
As a further improvement on the present invention, step B includes:Load burr data are rejected using 3 σ Criterion Methods;It is logical
Cross the Deletional data of interpolation method completion.
Another aspect of the present invention provides a kind of distribution network load calibrating installation analyzed based on big data, including:Data are obtained
Delivery block, obtains the basic data for load verification based on electrical power distribution automatization system;Data calibration module, for the base
Abnormal load data in plinth data are recognized and are corrected using one or more data analysing methods of differentiation, wherein institute
State abnormal load data include causing load curve shape that the shape distortion data of abnormal change occur, between adjacent time interval data
Suddenly change load burr data and by least one of Deletional data three caused by failure.
Beneficial effects of the present invention are:For Distribution Network Frame construction, Operation Mode Optimization, lift power supply capacity, improve correspondence
The aspect such as managerial skills and operating efficiency forms important support;It is with big data analytical technology, negative to power distribution network from multiple dimensions
Lotus data carry out INTELLIGENT IDENTIFICATION and abnormal amendment, it is ensured that the validity of load data, improve the quality and effect of load verification
Rate.The method of the present invention succinctly effectively, is suitable for being engineered practical application.
Description of the drawings
Fig. 1 show the overall procedure block diagram of the method according to the invention.
Specific embodiment
The overall procedure of the distribution network load calibration steps analyzed based on big data of the invention with reference to shown in Fig. 1
Block diagram.
In step, the acquisition of basic data is carried out based on electrical power distribution automatization system (DAS).Electrical power distribution automatization system is
It is a kind of can make distribution enterprise in the distance in real time fashion monitoring, coordinate and operate controller switching equipment automated system;Its content
It is several with monitoring (SCADA system), distribution GIS-Geographic Information System (GIS) and dsm (DSM) including electric distribution network data collection
Individual part.
Basic data needed for distribution network load calibration is all extracted from electrical power distribution automatization system automatically, it is not necessary to
Artificial data maintenance is carried out, system maintenance cost is reduced.Mass data information, load verification master are included in electrical power distribution automatization system
Need to utilize data below:A. substation equipment data:Main transformer, bus, device parameter (model, capacity, the cut-off current of outlet
Deng);B. medium voltage distribution network device data:Each part of path, Medium voltage switch or circuit breaker, the equipment (model, capacity, cut-off current etc.) of distribution transforming;c.
The topological connection relation of power distribution network;D. transformer station's historical data:Main transformer, bus, the historical load curve of outlet;E. medium-voltage distribution
Net historical data:Medium voltage switch or circuit breaker, the historical load curve of distribution transforming.
In real data system, the generation of abnormal load data is often random, mainly with shape distortion data, load
Various Exception Types such as burr data, missing data are present in database.The present invention adopts differentiation to various abnormal datas
Data processing.
In stepb, analyzed by associated data and filter the distorting loads curve affected by particular event, wherein shape is abnormal
Become data and refer to measurement system under normal circumstances, as particular event causes load curve shape that abnormal change occurs
Situation, the load distortion for showing as the normal data load fluctuation that causes of superposition particular event and producing.
The particular event for causing load distortion is probably line fault, overhaul of the equipments, large user's switching, extreme weather situation
(such as high temperature, typhoon etc.), or other can cause the situation of electric load unusual fluctuations.This kind of event is often adjoint when occurring
The change (being mainly shown as the change of switch conjunction point state and network topology structure on circuit) of power system operating mode.Therefore,
The analysis of power distribution network topological data is introduced, according to the historical data that switch division shape becomes, can be non-standard operation in sampled data
Data (causing the data of load distortion because of particular event impact) under mode are filtered out.Such as certain circuit is a certain
It performs interruption maintenance operation, and the switch of the circuit can produce the historical events such as separating brake/combined floodgate record on the same day.So, lead to
Cross and review panel switches history displacement logout, and power network topology when occurring to event is analyzed, it is possible to it is determined which
The load in a little regions receives the impact of the event, so as to realize the filtration treatment on the distorting loads affected by particular event.
In a preferred embodiment, shape Severe distortion load curve is rejected using average perunit value method.According to aforementioned step
The method of rapid B, may filter that most of shape distortion data by the switch events record and topological analysis that associate.In order to
It is perfectly safe to the identification of shape distortion data to guarantee, the present invention is on this basis, negative to distortion using " average perunit value " method
Lotus curve is implemented secondary identification and is rejected.
Generally electric load has the following properties that:Electric load is not only regular but also has randomness, over a period to come, together
The load of one moment point is substantially in normal distribution.Load between adjacent time interval has viscosity, i.e., will not undergo mutation, and this is
Carry out the basis of abnormal load data check.Part throttle characteristics in the case of identical or approximate correlative factor (such as weather) is identical or phase
Seemingly.According to these characteristics of electric load, rejecting of the average perunit value method to shape Severe distortion load curve can be adopted.
In practical engineering application, the mean value for first calculating each day load per-unit curve obtains average per-unit curve, then counts
Calculate the distance of each day per-unit curve and average per-unit curve, according to apart from size Ordination distortion degree, this be a kind of row it
Effective method.Specific algorithm is as follows:
It is assumed that the number of days for needing detection load data is d, there is t period daily, investigate sample and obtain as the following formula:
In formula:L is load sample vector;Ld is the load sample of the d days;L* d,tFor the perunit load of the d days t periods;
Ld,tFor the load of the d days t periods;Lmax, d are the peak load of the d days;L*Avg is the average of each day load per-unit curve
Value;L*Avg_t is the average perunit load of t periods;D*Avg_d is the distance of the d days per-unit curves and average per-unit curve.D*
Avg_d is bigger, it is meant that it is more remote that the load curve of this day deviates average load curve.In Practical Project, can be according to D*avg_d
Sequence, D*Avg_d maximum a collection of load sample is rejected.
Load burr data can numerically show as unexpected increase or the reduction between adjacent time interval data, follow-up numerical value
It is returned near normal value again.Mutation amplitude is changeable, and the Min-max in load data typically belongs to mutation amplitude mistake
Big burr.It is because the generation of burr data that acquisition system is subject to of short duration disturbance etc. to occur abnormal more, or is subject to impact negative
The impact of the factors such as lotus (such as cyclization dash current).After the load curve for rejecting shape Severe distortion, to remaining curve
Implement deburring operation.
For the Min-max that normal range (NR) is measured more than equipment, can simply be known by valid value range inspection
Not.For the exceptional data point of burr class more generally, the statistical law based on sampled data is entered using " 3 σ criterions "
Row identification and correction.3 σ criterions are also called Pauta criterion, and it is first to assume that one group of detection data comprises only random error, to which
Carry out calculating and process obtaining standard deviation, it is interval by certain determine the probability one, it is believed that all more than this interval error, just not
Belong to random error but gross error, the data containing the error should give rejecting.
In an embodiment according to the present invention, the method for optimizing based on " 3 σ criterions " deburring is as follows:
For observation data sequence { y1,y2,…,yj-1, the variation characteristic for describing the sequence data is
dj=2yj-(yj+1+yj-1) (j=2,3 ..., N-1) (7)
So, N-2 d can be obtained by N number of observation dataj.At this moment, by djValue can sequence of calculation data variation average statisticalAnd mean square deviation
According to djThe absolute value of deviation and the ratio of mean square deviation
Usually, work as qj>When 3, then it is assumed that yiIt is exceptional value (i.e. so-called " 3 σ criterions ").
Work as yiIt is identified for exceptional value when, can using interpolation method to yiIt is corrected.Simplest linear interpolation formula is such as
Under:
yi=(yi-1+i+1)/2 (11)
In a preferred embodiment, by interpolation method completion missing data, performance of this kind of abnormal data in database
For null value, the mostly reason such as acquisition system/communication device failure causes.Row interpolation can be entered using formula (11) in missing number strong point
Completion.
In a further embodiment, the distribution network load calibrating installation analyzed based on big data is also provided, the device can be with
Based on existing computing device hardware, such as personal computer, calculation server etc., prestoring in non-transitory medium is performed
Instruct to implement above-mentioned method.
The above, simply presently preferred embodiments of the present invention, the invention is not limited in above-mentioned embodiment, as long as
Which reaches the technique effect of the present invention with identical means, should all belong to protection scope of the present invention.In the protection model of the present invention
In enclosing, its technical scheme and/or embodiment can have a variety of modifications and variations.
Claims (10)
1. it is a kind of based on big data analyze distribution network load calibration steps, it is characterised in that comprise the following steps:
A, the basic data for load verification is obtained based on electrical power distribution automatization system;
B, the abnormal load data in the basic data are distinguished using one or more data analysing methods of differentiation
Know and amendment, wherein, the abnormal load data include causing load curve shape occur abnormal change shape distortion data,
The load burr data of the suddenly change between adjacent time interval data and by failure caused by Deletional data three extremely
Few one.
2. the distribution network load calibration steps analyzed based on big data according to claim 1, wherein, institute in step
Stating basic data includes:Substation equipment data, medium voltage distribution network device data, the topological connection relation data of power distribution network, change
The historical load curve of power station historical data, medium voltage distribution network historical data and Medium voltage switch or circuit breaker and distribution transforming.
3. the distribution network load calibration steps analyzed based on big data according to claim 1, step B includes:
The distorting loads curve affected by particular event is filtered by associated data analysis, according to switch division state
Data under the non-standard method of operation in sampled data are filtered by the historical data of conversion.
4. the distribution network load calibration steps analyzed based on big data according to claim 3, step B also includes:
The historical data become according to switch division shape is further analyzed to determine by the particular event to power network topology
The region of impact.
5. the distribution network load calibration steps analyzed based on big data according to claim 1, step B includes:
The shape distortion load curve is rejected using average perunit value method.
6. the distribution network load calibration steps analyzed based on big data according to claim 5, step B also includes:
The mean value for calculating the load per-unit curve in each day first obtains average per-unit curve, then calculates the load perunit in each day
Curve and the distance of average per-unit curve, determine shape distortion load curve according to apart from size Ordination distortion degree.
7. the distribution network load calibration steps analyzed based on big data according to claim 6, step B also includes,
Obtained by below equation during calculated load per-unit curve and investigate sample:
Wherein, L is load sample vector;LdFor the load sample of the d days;L* d,tFor the perunit load of the d days t periods;Ld,tFor
The load of the d days t periods;Lmax,dFor the peak load of the d days;L* avgIt is the mean value of each day load per-unit curve;L* avg_tIt is
The average perunit load of t periods;D* avg_dIt is the distance of the d days per-unit curves and average per-unit curve.
8. the distribution network load calibration steps analyzed based on big data according to claim 1, step B includes:
Load burr data are rejected using 3 σ Criterion Methods.
9. the distribution network load calibration steps analyzed based on big data according to claim 1, step B includes:
By the Deletional data of interpolation method completion.
10. it is a kind of based on big data analyze distribution network load calibrating installation, it is characterised in that include:
Data acquisition module, obtains the basic data for load verification based on electrical power distribution automatization system;
Data calibration module, for the abnormal load data in the basic data are adopted with one or more data of differentiation
Analysis method is recognized and is corrected,
Wherein described abnormal load data include causing load curve shape that the shape distortion data of abnormal change occur, adjacent
Load burr data of the suddenly change between period data and by least one of Deletional data three caused by failure.
Priority Applications (1)
Application Number | Priority Date | Filing Date | Title |
---|---|---|---|
CN201610951489.XA CN106529786A (en) | 2016-10-26 | 2016-10-26 | Power distribution network load calibration method and power distribution network load calibration device based on big data analysis |
Applications Claiming Priority (1)
Application Number | Priority Date | Filing Date | Title |
---|---|---|---|
CN201610951489.XA CN106529786A (en) | 2016-10-26 | 2016-10-26 | Power distribution network load calibration method and power distribution network load calibration device based on big data analysis |
Publications (1)
Publication Number | Publication Date |
---|---|
CN106529786A true CN106529786A (en) | 2017-03-22 |
Family
ID=58326858
Family Applications (1)
Application Number | Title | Priority Date | Filing Date |
---|---|---|---|
CN201610951489.XA Pending CN106529786A (en) | 2016-10-26 | 2016-10-26 | Power distribution network load calibration method and power distribution network load calibration device based on big data analysis |
Country Status (1)
Country | Link |
---|---|
CN (1) | CN106529786A (en) |
Cited By (9)
Publication number | Priority date | Publication date | Assignee | Title |
---|---|---|---|---|
CN107665402A (en) * | 2017-09-18 | 2018-02-06 | 安徽蓝杰鑫信息科技有限公司 | A kind of transformer station that discrete sudden load change point is removed based on mean square deviation can access capability assessment method |
CN107944654A (en) * | 2017-10-13 | 2018-04-20 | 国网山东省电力公司青岛供电公司 | A kind of electricity characteristic analysis method and device |
CN110415382A (en) * | 2018-04-27 | 2019-11-05 | 云丁网络技术(北京)有限公司 | A kind of door lock state detection method, device, system and storage medium |
CN110599060A (en) * | 2019-09-20 | 2019-12-20 | 南方电网科学研究院有限责任公司 | Method, device and equipment for determining operation efficiency of power distribution network |
CN110726625A (en) * | 2019-11-14 | 2020-01-24 | 中北大学 | Method for determining length of rock material fracture process area |
CN111027835A (en) * | 2019-12-02 | 2020-04-17 | 国网宁夏电力有限公司经济技术研究院 | Power grid planning decision data noise identification and reduction method and system |
CN112417363A (en) * | 2020-11-11 | 2021-02-26 | 深圳供电局有限公司 | Load analysis method and system for transformer substation |
CN112884042A (en) * | 2021-02-23 | 2021-06-01 | 新疆大学 | Power transmission and distribution line maximum load identification method based on relevance vector machine |
CN113515512A (en) * | 2021-06-22 | 2021-10-19 | 国网辽宁省电力有限公司鞍山供电公司 | Quality control and improvement method for industrial internet platform data |
Citations (2)
Publication number | Priority date | Publication date | Assignee | Title |
---|---|---|---|---|
CN103198437A (en) * | 2013-04-18 | 2013-07-10 | 国家电网公司 | Power grid measurement data and power grid model correction method and device |
CN105069525A (en) * | 2015-07-30 | 2015-11-18 | 广西大学 | All-weather 96-point daily load curve prediction and optimization correction system |
-
2016
- 2016-10-26 CN CN201610951489.XA patent/CN106529786A/en active Pending
Patent Citations (2)
Publication number | Priority date | Publication date | Assignee | Title |
---|---|---|---|---|
CN103198437A (en) * | 2013-04-18 | 2013-07-10 | 国家电网公司 | Power grid measurement data and power grid model correction method and device |
CN105069525A (en) * | 2015-07-30 | 2015-11-18 | 广西大学 | All-weather 96-point daily load curve prediction and optimization correction system |
Non-Patent Citations (1)
Title |
---|
陈建华等: "确定性合同分解中异常负荷数据的识别与修正", 《电力系统自动化》 * |
Cited By (11)
Publication number | Priority date | Publication date | Assignee | Title |
---|---|---|---|---|
CN107665402A (en) * | 2017-09-18 | 2018-02-06 | 安徽蓝杰鑫信息科技有限公司 | A kind of transformer station that discrete sudden load change point is removed based on mean square deviation can access capability assessment method |
CN107944654A (en) * | 2017-10-13 | 2018-04-20 | 国网山东省电力公司青岛供电公司 | A kind of electricity characteristic analysis method and device |
CN110415382A (en) * | 2018-04-27 | 2019-11-05 | 云丁网络技术(北京)有限公司 | A kind of door lock state detection method, device, system and storage medium |
CN110415382B (en) * | 2018-04-27 | 2021-12-24 | 云丁网络技术(北京)有限公司 | Door lock state detection method, device and system and storage medium |
CN110599060A (en) * | 2019-09-20 | 2019-12-20 | 南方电网科学研究院有限责任公司 | Method, device and equipment for determining operation efficiency of power distribution network |
CN110726625A (en) * | 2019-11-14 | 2020-01-24 | 中北大学 | Method for determining length of rock material fracture process area |
CN111027835A (en) * | 2019-12-02 | 2020-04-17 | 国网宁夏电力有限公司经济技术研究院 | Power grid planning decision data noise identification and reduction method and system |
CN112417363A (en) * | 2020-11-11 | 2021-02-26 | 深圳供电局有限公司 | Load analysis method and system for transformer substation |
CN112417363B (en) * | 2020-11-11 | 2022-06-24 | 深圳供电局有限公司 | Load analysis method and system for transformer substation |
CN112884042A (en) * | 2021-02-23 | 2021-06-01 | 新疆大学 | Power transmission and distribution line maximum load identification method based on relevance vector machine |
CN113515512A (en) * | 2021-06-22 | 2021-10-19 | 国网辽宁省电力有限公司鞍山供电公司 | Quality control and improvement method for industrial internet platform data |
Similar Documents
Publication | Publication Date | Title |
---|---|---|
CN106529786A (en) | Power distribution network load calibration method and power distribution network load calibration device based on big data analysis | |
CN109146093B (en) | Power equipment field investigation method based on learning | |
CN107609569B (en) | Power distribution network ground fault positioning method based on multi-dimensional feature vectors | |
CN102495952B (en) | Isolating switch risk evaluating system and methods of risk assessment thereof | |
CN108551166B (en) | Power grid equipment and section ultra-short-term load prediction, alarm and stability control method | |
CN108695846B (en) | Unit distribution power grid operation risk assessment method | |
AU2019388238B2 (en) | System and method for controlling photovoltaic balancing | |
CN110750760B (en) | Abnormal theoretical line loss detection method based on situation awareness and control diagram | |
CN110954782B (en) | Distribution network instantaneous fault identification method and system based on density peak clustering | |
CN116993329B (en) | Communication equipment operation maintenance decision management system based on data analysis | |
Jia et al. | Defect prediction of relay protection systems based on LSSVM-BNDT | |
CN109390937B (en) | Electrical parameter identification method and system based on power system operation data | |
CN104834305B (en) | Distribution automation terminal remote measurement exception analysis system and method based on DMS systems | |
CN109191007A (en) | A kind of method and system that grid equipment N-1 consequence grade determines automatically | |
CN104766183A (en) | Power grid real time fault event flow management system and adopted management method thereof | |
CN116882595A (en) | Comprehensive performance prediction method and system for transformer substation | |
CN117117780A (en) | Circuit breaker anti-blocking method and system based on secondary information fusion of transformer substation | |
CN114693186B (en) | Method and system for analyzing and processing multiple fault events of differentiated combined type transformer substation | |
CN107785875B (en) | Method and system for calculating line operation overvoltage generated in case of single-pole ground fault | |
CN115619098A (en) | Intelligent electric power material data processing method based on grading monitoring and early warning | |
CN104036433A (en) | Method for evaluating running management level of power distribution network | |
CN114236308A (en) | Feeder line information-based power distribution network fault detection and positioning method | |
CN114545097A (en) | Lightning early warning studying and judging method based on multi-factor dynamic weight algorithm | |
CN112001073A (en) | Reliability analysis research method of traction power supply system | |
CN110826179A (en) | Intelligent substation relay protection real-time reliability prediction method |
Legal Events
Date | Code | Title | Description |
---|---|---|---|
C06 | 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 |
Application publication date: 20170322 |
|
RJ01 | Rejection of invention patent application after publication |