CN105279353A - Low voltage transformer area line loss calculating method based on cluster characteristic and network vector - Google Patents
Low voltage transformer area line loss calculating method based on cluster characteristic and network vector Download PDFInfo
- Publication number
- CN105279353A CN105279353A CN201410269508.1A CN201410269508A CN105279353A CN 105279353 A CN105279353 A CN 105279353A CN 201410269508 A CN201410269508 A CN 201410269508A CN 105279353 A CN105279353 A CN 105279353A
- Authority
- CN
- China
- Prior art keywords
- loss
- backbone
- network vector
- line
- line loss
- 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
Landscapes
- Supply And Distribution Of Alternating Current (AREA)
Abstract
The invention provides a low voltage transformer area line loss calculating method based on cluster characteristics and network vectors; the method uses a typical transformer area line loss theory accumulated in years to calculate a result, and uses a cluster analysis method to calculate transformer area type loss indexes according to power supply volume and maximum power supply radius parameters; the method uses statistics parameters like transformer area power supply volume, a main line, branches, and ammeters to fast calculate transformer area theory line loss. The method can satisfy power supply company transformer area theory line loss calculating precision requirements, is fast in calculating speed, and theory line loss calculating time consumption of each transformer area is smaller than 50 millisecond; no network wiring diagram is needed, statistics parameters needed by the transformer area line loss calculation can be easily obtained from an existing system of the power supply company in real time, and artificial data maintenance workload is small, thus basically realizing maintenance-free effect.
Description
Technical field
The present invention relates to line loss calculation technical field, more specifically relate to a kind of low-voltage platform area line loss calculation method based on cluster feature and network vector.
Background technology
Line loss calculation is an important process content of electric power enterprise with analysis, and theoretical loss calculation is the line loss per unit drawn according to defeated, change, controller switching equipment parameter, load uncertainty, property calculation.Logical in a few years Shanxi Power Network theoretical line loss caluclation is analyzed, and the theory wire loss electricity of low-voltage platform area accounts for about 15% of the whole network total losses electricity, is the emphasis that damage falls in electrical network.
There are three huge difficulties in the whole network low-voltage platform area line loss calculation: one is that low-voltage platform area quantity is extremely huge, and real-time data capture difficulty, workload and cost are all quite huge; Two is that conventional table domain tyeory line loss algorithm or measuring instrument of distribution line loss device all need input table district substitutional resistance, but the calculating of substitutional resistance needs to draw platform district detailed network topological structure in systems in which, needs a large amount of manpower and materials to drop into; The transformation of three Shi Tai districts or change produce a large amount of data maintenance work, exceed the ability to bear of line loss staff.
Summary of the invention
(1) technical matters that will solve
How quick the technical problem to be solved in the present invention is, the calculating low-voltage platform area line loss that letter becomes.
(2) technical scheme
In order to solve the problems of the technologies described above, the invention provides a kind of low-voltage platform area line loss calculation method based on cluster feature and network vector, comprising the following steps:
The basic data in the existing platform district of S1, automatic acquisition or input, front-month delivery, maximum radius of electricity supply, backbone length, backbone hop count, branch line quantity, branch line length;
S2, foundation existing platform district basic data, adopt three layers of BP neural network models training to calculate, obtain platform district type loss objective;
S3, network vector calculate, and adopt equivalent current values as the network vector value of every bar branch road, and can calculate appearance district head end electric current by actual measurement or foundation delivery is I, then every section of circuit network vector is:
Backbone: backbone has n section, n section connected, first section of network vector is I, and the 2nd section of network vector is (n-1) * I/n, the like, latter end network vector is I/n;
Branch line: branch line has one or more branch, there is m section in each branch; The multi-stage series of each branch, in parallel between branch; Each branch line first section of network vector is I/n, and the 2nd section of network vector is (m-1) * I/ (m*n), the like, latter end network vector is I/ (m*n);
Subscribers feeder: subscribers feeder multistage is all in parallel, every section of network vector is 9*I/k, and wherein k is the total hop count of subscribers feeder;
S4, computational scheme loss,
(1) loss of described backbone is calculated,
Backbone loss=KC*K1*K2*Kpl*I*I*R* (n+1) * (2n+1)/(6n*n), wherein, R is backbone all-in resistance; KC is electric current conversion factor; K1 shape coefficient, is defaulted as 1; K2 platform district type loss objective; Kpl circuit types loss factor;
(2) loss of every bar branch line of described branch line is calculated,
Loss=KC*K1*K2*Kpl* (I/n) * (I/n) * r* (m+1) * (2m+1)/(6m*m) of every bar branch line; The wherein all-in resistance of this branch line of r;
(3) described subscriber's line loss is calculated,
Subscriber's line loss=KC*K1*K2*Kpl*9*I*I/ (k*k*k);
S5, reckoner damage,
Table damage=single-phase machinery table monthly loss * single-phase machinery table quantity/30+ three-phase mechanical table monthly loss * three-phase mechanical table quantity/30+ single-phase electricity sublist monthly loss * single-phase electricity sublist quantity/30+ three-phase electricity sublist monthly loss * three-phase electricity sublist quantity/30;
S6, calculating total losses and line loss per unit,
Total losses=table damage+backbone loss+branch line loss+entrance line loss;
Line loss per unit=total losses/delivery * 100%.
Preferably, the all-in resistance r of described backbone all-in resistance R and branch line is all according to wire type and length computation.
Preferably, the span of described district's type loss objective is 0 ~ 3.
(3) beneficial effect
The invention provides a kind of low-voltage platform area line loss calculation method based on cluster feature and network vector, method of the present invention is while meeting electric company's platform domain tyeory line loss calculation accuracy requirement, have the computing velocity be exceedingly fast, every platform domain tyeory line loss calculation is consuming time is less than 50 milliseconds; And without the need to drawing network connection figure, needed for platform district line loss calculation, statistical parameter is easy to Real-time Obtaining from electric company's existing system, and artificial data maintenance workload is little, substantially non-maintaining.
Accompanying drawing explanation
In order to be illustrated more clearly in the embodiment of the present invention or technical scheme of the prior art, be briefly described to the accompanying drawing used required in embodiment or description of the prior art below, apparently, accompanying drawing in the following describes is only some embodiments of the present invention, for those of ordinary skill in the art, under the prerequisite not paying creative work, other accompanying drawing can also be obtained according to these accompanying drawings.
Fig. 1 is three layers of BP neural network model figure that the present invention utilizes;
Fig. 2 is the process flow diagram of a kind of low-voltage platform area line loss calculation method based on cluster feature and network vector of the present invention.
Embodiment
Below in conjunction with drawings and Examples, the present invention is described in further detail.Following examples for illustration of the present invention, but can not be used for limiting the scope of the invention.
Fig. 2 is the process flow diagram of a kind of low-voltage platform area line loss calculation method based on cluster feature and network vector of the present invention; Method of the present invention comprises the following steps:
The basic data in the existing platform district of S1, automatic acquisition or input, front-month delivery, maximum radius of electricity supply, backbone length, backbone hop count, branch line quantity, branch line length;
S2, foundation existing platform district basic data, adopt three-layer neural network model training to calculate, obtain platform district type loss objective; Described three-layer neural network model is BP neural network model; The span of described district's type loss objective is 0 ~ 3;
Above-mentioned poly-three-layer neural network model comprises: input layer has 6 inputs, the moon delivery, maximum radius of electricity supply, backbone length, backbone hop count, branch line quantity, branch line length; Hidden layer has 6 neurons; Output layer has 1 output, and Ji Tai district type loss objective, shown in model structure Fig. 1.Interconnected all between two between 6 inputs of described three-layer neural network mode input layer and 6 neurons of hidden layer, this figure is the too complexity avoiding picture, only depict input 1 front-month delivery and the annexation of input 6 that is between branch line length and hidden layer neuron in detail, the relation object between other 4 inputs and hidden layer neuron is same.The weights of described three-layer neural network model have 42 parameters, wherein: have 36 parameter WAij (i=1 between input layer and hidden layer ... 6, j=1 ... 6) weights between input i and hidden layer neuron j, are represented respectively; 6 parameter WBj (j=1 are had between hidden layer and output layer ... 6) weights between hidden layer neuron j and output (platform district type loss objective), are represented respectively.
S3, network vector calculate, and adopt equivalent current values as the network vector value of every bar branch road, and can calculate appearance district head end electric current by actual measurement or foundation delivery is I, then every section of circuit network vector is:
Backbone: backbone has n section, n section connected, first section of network vector is I, and the 2nd section of network vector is (n-1) * I/n, the like, latter end network vector is I/n;
Branch line: branch line has one or more branch, there is m section in each branch; The multi-stage series of each branch, in parallel between branch; Each branch line first section of network vector is I/n, and the 2nd section of network vector is (m-1) * I/ (m*n), the like, latter end network vector is I/ (m*n);
Subscribers feeder: subscribers feeder multistage is all in parallel, every section of network vector is 9*I/k, and wherein k is the total hop count of subscribers feeder;
S4, computational scheme loss,
(1) loss of described backbone is calculated,
Backbone loss=KC*K1*K2*Kpl*I*I*R* (n+1) * (2n+1)/(6n*n), wherein, R is backbone all-in resistance; KC is electric current conversion factor; K1 shape coefficient, is defaulted as 1; K2 platform district type loss objective; Kpl circuit types loss factor;
(2) loss of every bar branch line of described branch line is calculated,
Loss=KC*K1*K2*Kpl* (I/n) * (I/n) * r* (m+1) * (2m+1)/(6m*m) of every bar branch line; The wherein all-in resistance of this branch line of r;
(3) described subscriber's line loss is calculated,
Subscriber's line loss=KC*K1*K2*Kpl*9*I*I/ (k*k*k)
S5, reckoner damage,
Table damage=single-phase machinery table monthly loss * single-phase machinery table quantity/30+ three-phase mechanical table monthly loss * three-phase mechanical table quantity/30+ single-phase electricity sublist monthly loss * single-phase electricity sublist quantity/30+ three-phase electricity sublist monthly loss * three-phase electricity sublist quantity/30;
S6, calculating total losses and line loss per unit,
Total losses=table damage+backbone loss+branch line loss+entrance line loss;
Line loss per unit=total losses/delivery * 100%.
The all-in resistance r of above-mentioned backbone all-in resistance R and branch line is all according to wire type and length computation.
Method disclosed by the invention, while meeting electric company's platform domain tyeory line loss calculation accuracy requirement, has the computing velocity be exceedingly fast, and every platform domain tyeory line loss calculation is consuming time is less than 50 milliseconds; And without the need to drawing network connection figure, needed for platform district line loss calculation, statistical parameter is easy to Real-time Obtaining from electric company's existing system, and artificial data maintenance workload is little, substantially non-maintaining.
Above embodiment is only for illustration of the present invention, but not limitation of the present invention.Although with reference to embodiment to invention has been detailed description, those of ordinary skill in the art is to be understood that, various combination, amendment or equivalent replacement are carried out to technical scheme of the present invention, do not depart from the spirit and scope of technical solution of the present invention, all should be encompassed in the middle of right of the present invention.
Claims (3)
1., based on a low-voltage platform area line loss calculation method for cluster feature and network vector, it is characterized in that, comprise the following steps:
The basic data in the existing platform district of S1, automatic acquisition or input, front-month delivery, maximum radius of electricity supply, backbone length, backbone hop count, branch line quantity, branch line length;
S2, foundation existing platform district basic data, adopt three layers of BP neural network models training to calculate, obtain platform district type loss objective;
S3, network vector calculate, and adopt equivalent current values as the network vector value of every bar branch road, and can calculate appearance district head end electric current by actual measurement or foundation delivery is I, then every section of circuit network vector is:
Backbone: backbone has n section, n section connected, first section of network vector is I, and the 2nd section of network vector is (n-1) * I/n, the like, latter end network vector is I/n;
Branch line: branch line has one or more branch, there is m section in each branch; The multi-stage series of each branch, in parallel between branch; Each branch line first section of network vector is I/n, and the 2nd section of network vector is (m-1) * I/ (m*n), the like, latter end network vector is I/ (m*n);
Subscribers feeder: subscribers feeder multistage is all in parallel, every section of network vector is 9*I/k, and wherein k is the total hop count of subscribers feeder;
S4, computational scheme loss,
(1) loss of described backbone is calculated,
Backbone loss=KC*K1*K2*Kpl*I*I*R* (n+1) * (2n+1)/(6n*n), wherein, R is backbone all-in resistance; KC is electric current conversion factor; K1 shape coefficient, is defaulted as 1; K2 is platform district type loss objective; Kpl is circuit types loss factor;
(2) loss of every bar branch line of described branch line is calculated,
Loss=KC*K1*K2*Kpl* (I/n) * (I/n) * r* (m+1) * (2m+1)/(6m*m) of every bar branch line; The wherein all-in resistance of this branch line of r;
(3) described subscriber's line loss is calculated,
Subscriber's line loss=KC*K1*K2*Kpl*9*I*I/ (k*k*k);
S5, reckoner damage,
Table damage=single-phase machinery table monthly loss * single-phase machinery table quantity/30+ three-phase mechanical table monthly loss * three-phase mechanical table quantity/30+ single-phase electricity sublist monthly loss * single-phase electricity sublist quantity/30+ three-phase electricity sublist monthly loss * three-phase electricity sublist quantity/30
；
S6, calculating total losses and line loss per unit,
Total losses=table damage+backbone loss+branch line loss+entrance line loss;
Line loss per unit=total losses/delivery * 100%.
2. method according to claim 1, is characterized in that, the all-in resistance r of described backbone all-in resistance R and branch line is all according to wire type and length computation.
3. method according to claim 1, is characterized in that, the span of described district's type loss objective is 0 ~ 3.
Priority Applications (1)
| Application Number | Priority Date | Filing Date | Title |
|---|---|---|---|
| CN201410269508.1A CN105279353A (en) | 2014-06-17 | 2014-06-17 | Low voltage transformer area line loss calculating method based on cluster characteristic and network vector |
Applications Claiming Priority (1)
| Application Number | Priority Date | Filing Date | Title |
|---|---|---|---|
| CN201410269508.1A CN105279353A (en) | 2014-06-17 | 2014-06-17 | Low voltage transformer area line loss calculating method based on cluster characteristic and network vector |
Publications (1)
| Publication Number | Publication Date |
|---|---|
| CN105279353A true CN105279353A (en) | 2016-01-27 |
Family
ID=55148363
Family Applications (1)
| Application Number | Title | Priority Date | Filing Date |
|---|---|---|---|
| CN201410269508.1A Pending CN105279353A (en) | 2014-06-17 | 2014-06-17 | Low voltage transformer area line loss calculating method based on cluster characteristic and network vector |
Country Status (1)
| Country | Link |
|---|---|
| CN (1) | CN105279353A (en) |
Cited By (4)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN106127387A (en) * | 2016-06-24 | 2016-11-16 | 中国电力科学研究院 | A kind of platform district based on BP neutral net line loss per unit appraisal procedure |
| CN107832855A (en) * | 2017-09-14 | 2018-03-23 | 北京中恒博瑞数字电力科技有限公司 | Line loss multi-source diagnostic method and system based on correlation analysis |
| CN108229087A (en) * | 2017-09-30 | 2018-06-29 | 国网上海市电力公司 | A kind of destructed method of low-voltage platform area typical scene |
| CN114638554A (en) * | 2022-05-18 | 2022-06-17 | 国网浙江省电力有限公司 | Marketing business health index evaluation joint control method and system |
Citations (3)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN103577679A (en) * | 2012-08-10 | 2014-02-12 | 深圳市龙电电气有限公司 | Real-time computing method for theoretical line loss of low-voltage distribution room |
| CN103617357A (en) * | 2013-11-30 | 2014-03-05 | 国网河南省电力公司南阳供电公司 | Public transformer district low-voltage line loss analysis system and using method thereof |
| CN103632235A (en) * | 2013-12-05 | 2014-03-12 | 国网上海市电力公司 | Improved forward-backward sweep algorithm based power-grid low-voltage platform area line loss information processing method |
-
2014
- 2014-06-17 CN CN201410269508.1A patent/CN105279353A/en active Pending
Patent Citations (3)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN103577679A (en) * | 2012-08-10 | 2014-02-12 | 深圳市龙电电气有限公司 | Real-time computing method for theoretical line loss of low-voltage distribution room |
| CN103617357A (en) * | 2013-11-30 | 2014-03-05 | 国网河南省电力公司南阳供电公司 | Public transformer district low-voltage line loss analysis system and using method thereof |
| CN103632235A (en) * | 2013-12-05 | 2014-03-12 | 国网上海市电力公司 | Improved forward-backward sweep algorithm based power-grid low-voltage platform area line loss information processing method |
Non-Patent Citations (4)
| Title |
|---|
| 侯其峰等: "低压线损计算的"改进竹节法"", 《农村电气化》 * |
| 刘成祥: "竹节法在低压理论线损计算中的运用", 《大众用电》 * |
| 林维莉等: "基于支持向量机的低压台区线损管理诊断模型", 《华东电力》 * |
| 陈海涵等: "低压网理论线损计算方法的探讨", 《广东输电与变电技术》 * |
Cited By (6)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN106127387A (en) * | 2016-06-24 | 2016-11-16 | 中国电力科学研究院 | A kind of platform district based on BP neutral net line loss per unit appraisal procedure |
| CN107832855A (en) * | 2017-09-14 | 2018-03-23 | 北京中恒博瑞数字电力科技有限公司 | Line loss multi-source diagnostic method and system based on correlation analysis |
| CN107832855B (en) * | 2017-09-14 | 2020-08-21 | 北京中恒博瑞数字电力科技有限公司 | Line loss multi-source diagnosis method and system based on correlation analysis |
| CN108229087A (en) * | 2017-09-30 | 2018-06-29 | 国网上海市电力公司 | A kind of destructed method of low-voltage platform area typical scene |
| CN114638554A (en) * | 2022-05-18 | 2022-06-17 | 国网浙江省电力有限公司 | Marketing business health index evaluation joint control method and system |
| CN114638554B (en) * | 2022-05-18 | 2022-08-26 | 国网浙江省电力有限公司 | Marketing business health index evaluation joint control method and system |
Similar Documents
| Publication | Publication Date | Title |
|---|---|---|
| CN107968439B (en) | Active power distribution network joint optimization algorithm based on mixed integer linear programming | |
| CN103559553B (en) | Distributing line planning and distribution transform site selection optimizing method based on load moment theory | |
| CN105279353A (en) | Low voltage transformer area line loss calculating method based on cluster characteristic and network vector | |
| CN105117560B (en) | A kind of medium-voltage distribution circuit theoretical line loss caluclation method | |
| CN106169750B (en) | A kind of active distribution network net capability computational methods based on second order cone relaxation | |
| CN105826918A (en) | Method and system for calculating theoretical line loss of power grid | |
| CN102033999A (en) | Load distribution based method for calculating recently planned annual line loss of medium-voltage distribution network | |
| CN105375477A (en) | Rural power distribution network line loss calculation method and system | |
| CN104348158B (en) | In the integrated automatism voltage control in ground county, coordinate the automatic generation method of control zone | |
| CN103746388A (en) | Electric distribution network reactive-voltage three-level coordination control method | |
| CN105046584A (en) | K-MEANS algorithm-based ideal line loss rate calculation method | |
| CN102856896B (en) | On-line analytical method for direct-current transmission loss | |
| CN105914735B (en) | A kind of power distribution network economic load tidal current computing method | |
| CN105488589A (en) | Genetic simulated annealing algorithm based power grid line loss management evaluation method | |
| CN110912137A (en) | Flexible power distribution network operation domain model construction method considering alternating current power flow | |
| CN108665133B (en) | Method and system for constructing power distribution system operation efficiency evaluation model | |
| CN110688619B (en) | Theoretical line loss calculation system and method for power distribution network | |
| CN104112237A (en) | WAMS-based genetic algorithm-improved power grid reactive capacity optimization configuration method | |
| CN114629128A (en) | User low-voltage management method and system based on marketing and distribution data fusion | |
| CN111027886A (en) | Evaluation method of low-voltage treatment scheme considering unit cost effectiveness | |
| CN108108871B (en) | Type selection method for wind power plant group power transmission equipment | |
| CN106570332B (en) | Method for improving line loss calculation result of power equipment | |
| CN104200276B (en) | A kind of intelligent distribution network reconstructing method of feature based load injection | |
| CN103679551A (en) | Method for on-line calculation of power flow of power distribution network | |
| CN105139145A (en) | Medium-voltage distribution line theory line loss analysis system |
Legal Events
| Date | Code | Title | Description |
|---|---|---|---|
| C06 | Publication | ||
| PB01 | Publication | ||
| C10 | Entry into 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: 20160127 |