CN109725219B - Automatic identification method for electric energy meter distribution area - Google Patents
Automatic identification method for electric energy meter distribution area Download PDFInfo
- Publication number
- CN109725219B CN109725219B CN201811643294.4A CN201811643294A CN109725219B CN 109725219 B CN109725219 B CN 109725219B CN 201811643294 A CN201811643294 A CN 201811643294A CN 109725219 B CN109725219 B CN 109725219B
- Authority
- CN
- China
- Prior art keywords
- voltage
- electric energy
- energy meter
- power
- area
- 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.)
- Active
Links
Images
Landscapes
- Management, Administration, Business Operations System, And Electronic Commerce (AREA)
- Supply And Distribution Of Alternating Current (AREA)
Abstract
The invention relates to an automatic identification method for an electric energy meter area, and belongs to the field of electric parameter measurement application of a power distribution network. Firstly, a voltage loss model is established on the basis of the accurate data of the existing transformer area. And then estimating the table voltage of the station area based on the voltage loss model and the user side data. And finally, carrying out correlation analysis on the estimated voltage and the actual voltage, comprehensively deciding a station area to which the user electric energy meter belongs, and giving correlation coefficients of the estimated voltage and the actual voltage, thereby improving the management capability of the power grid and promoting the healthy and stable operation of the power grid.
Description
Technical Field
The invention belongs to the field of power distribution network electrical parameter measurement application, and relates to an automatic identification method for an electric energy meter area.
Background
In the daily management work of a power distribution network by a power company, problems related to a distribution area to which a user electric energy meter belongs are often involved, such as remote charge control, clock timing, three-phase power balance, phase sequence control, line loss calculation and the like. The accurate identification of the distribution room to which the user electric energy meter belongs can realize refined marketing and effectively reduce consumption and loss.
At present, the station area identification of users mainly depends on a power carrier technology, carrier signals need to be sent from a concentrator, and then a user side is connected with a measuring tool to measure, so that the workload is very large, and the interference of electromagnetic signals is easily caused.
According to a data exchange protocol specified in DL/T645-2007 multifunctional electric energy meter communication protocol issued in 12 months of 2007, various state information during the operation of the power grid can be collected in real time. If the collected operation data can be fully utilized to analyze the power distribution network, the distribution area of the user electric energy meter can be effectively identified, the work difficulty of power company management personnel can be greatly reduced, and the operation efficiency of the power grid is improved.
Disclosure of Invention
In view of the above, the present invention is directed to a method for automatically identifying a power meter distribution area. A voltage loss model is established on the basis of the accurate data of the existing transformer area. And then estimating the voltage value of a phase of the transformer area general table by using the voltage and the power value of the user electric energy meter and the power value of the phase of the transformer area general table at the same moment based on a voltage loss model. And finally, determining the transformer area of the user electric energy meter by calculating Spearman rank correlation coefficients of voltage estimated values and voltage actual values of the transformer area general tables at several moments.
In order to achieve the purpose, the invention provides the following technical scheme:
an automatic identification method for an electric energy meter platform area comprises the following steps:
s1: acquiring voltage and power values of a distribution area master meter and a user electric energy meter at a plurality of moments by using known correct distribution area data;
s2: establishing a voltage loss model by utilizing the collected voltage and power values;
s3: estimating the voltage of each phase of each station area general table at each moment by using the voltage loss model and the data of the user electric energy meter to be identified;
s4: calculating Spearman rank correlation coefficients of the estimated values and the actual values of the voltage of each phase of the time station area general table based on the data;
s5: and comprehensively deciding the station area to which the electric energy meter of the user to be identified belongs by using the Spearman rank correlation coefficient of the actual value and the estimated value.
Further, the step S1 specifically includes:
synchronously acquiring the voltage V of the user electric energy meter once every 1-15 minutes within a certain number of daysuPower WuAnd the voltage V of the table area general table corresponding to the user electric energy meter at the corresponding phasetPower Wt(ii) a Finally, a training data set D (W) is constructed according to the collected datau Vu,Wt,Vt)。
Further, the step S2 specifically includes:
s21: normalizing the collected training data set D by a zero-mean normalization method, eliminating dimension between the training data set D and the collected training data set D to obtain a new training data set D*The specific conversion formula is as follows:
s22: the parameters (k) of the voltage loss model are derived by locally minimizing the objective function according to the principle of the gradient descent method0,k1,k2,k3) (ii) a The objective function is:
where λ is the regularization parameter and m is the training data set D*The number of samples to be collected in (a),
are respectively training set D*The ith sample in (1).
Further, the S3 specifically includes:
s31: synchronously acquiring the voltage V of the user electric energy meter to be identified once every 1-15 minutes within a certain number of daysuxPower WuxAnd the voltage V of each station area general table in each phasetPower Wt(ii) a Finally, 3 x k data sets T are constructed according to the collected dataij(Wux Vux,Wtij,Vtij) (ii) a Wherein k is the total number of the cell, i is the number of the cell, and j is one of A, B, C phases;
s32: data set TijEach piece of data in S21 is normalized according to the mean and variance in S21;
s33: estimating the voltage value of each phase of each station area at corresponding moment according to the voltage loss model; the specific formula of the voltage loss model is as follows:
wherein, V'tijRepresenting the voltage estimate, V, of the i-th cell summary in the j-phaseux、WuxRespectively representing the voltage and power, W, of the electric energy meter of the user to be identifiedtij V′tijRepresenting the power of the ith cell summary table in the j phase.
Further, the S4 specifically includes:
s41: each data set TijRespectively sequencing the obtained estimated voltage value and actual value of the jth phase of the ith station zone from small to large, and calculating corresponding rank RiAnd Qi；
S42: according to the calculated rank, a Spearman rank correlation coefficient is calculated, and the specific formula is as follows:
further, the S5 specifically includes:
s51: taking three correlation coefficients r calculated by the ith station areaiA、riB、riCThe square of the maximum value in (b) is taken as the correlation degree r of the regioni 2；
S52: if zone correlation ri 2Less than gamma1If yes, removing the ith station zone from the alternative station zone; wherein r is more than or equal to 02≤1，ri 2The closer to 1, the stronger the correlation between the user electric energy meter and the ith station area; gamma ray1Is a threshold value, obtained empirically;
s53: in the rest of the alternative stations, r with the maximum correlation degree is searchedi 2Then, the user electric energy meter to be identified belongs to the ith station area;
s54: if the appropriate distribution area can not be matched finally, more data are obtained and then analyzed; and repeating the steps S3 to S5 to identify more user electric energy meters without constructing a voltage loss model.
The invention has the beneficial effects that:
firstly, the electric energy meter can measure the voltage and power, and a data analysis method is used for automatically identifying the station area of the user electric energy meter, so that additional special equipment is not required to be added, and the cost is reduced;
and secondly, cross-platform area identification can be realized, the problem of file entry errors of the power company is effectively solved, and the accuracy of statistics is improved.
Drawings
In order to make the object, technical scheme and beneficial effect of the invention more clear, the invention provides the following drawings for explanation:
FIG. 1 is a flow chart of a method for automatically identifying a distribution area of an electric energy meter;
fig. 2 is a comprehensive decision diagram of the station area to which the user electric energy meter belongs.
Detailed Description
Preferred embodiments of the present invention will be described in detail below with reference to the accompanying drawings.
Fig. 1 is a flow chart of an automatic identification method for a power meter region, and fig. 2 is a comprehensive decision chart of a region to which a user power meter belongs. As shown in the figure: the invention provides an automatic identification method of an electric energy meter area, which comprises the following steps:
s1: acquiring voltage and power values of a distribution area general meter and a user electric energy meter at a certain moment by using known correct distribution area data;
s2: establishing a voltage loss model by using the collected voltage and power values;
s3: estimating the voltage of each phase of each station area general table at each moment by using the voltage loss model and the data of the user electric energy meter to be identified;
s4: calculating Spearman rank correlation coefficients of estimated values and actual values of each phase voltage of a station area general table at a plurality of moments;
s5: comprehensively deciding a distribution area to which the user electric energy meter belongs by using a Spearman rank correlation coefficient of the actual value and the estimated value;
further, the specific method for acquiring the voltage and power values of the distribution area summary meter and the user electric energy meter at some time by using the known correct distribution area data in step S1 includes: synchronously acquiring the voltage V of the user electric energy meter once every 1-15 minutes within a certain number of daysuPower WuAnd the voltage V of the table area general table corresponding to the user electric energy meter at the corresponding phasetPower Wt. Finally, a training data set D (W) is constructed according to the collected datau Vu,Wt,Vt)；
Further, the step of establishing a voltage loss model by using the collected voltage and power values in S2 includes the following specific steps:
s21: normalizing the collected training data set D by a zero-mean normalization method, eliminating dimension between the training data set D and the collected training data set D to obtain a new training data set D*The specific conversion formula is as follows:
s22: the parameters (k) of the voltage loss model are derived by locally minimizing the objective function according to the principle of the gradient descent method0,k1,k2,k3)；
Further, the objective function in S22 is
Where λ is the regularization parameter and m is the training data set D*The number of samples to be collected in (a),
are respectively training set D*The ith sample in (1).
Further, in the step S3, the voltage of each phase of each distribution area summary table at each moment is estimated by using the voltage loss model and the data of the user electric energy meter to be identified, which includes the following specific steps:
s31: synchronously acquiring the voltage V of the user electric energy meter to be identified once every 15 minutes within 30 daysuxPower WuxAnd the voltage V of each station area general table in each phasetPower Wt. Finally, 3 x k data sets T are constructed according to the collected dataij(WuxVux,Wtij,Vtij). Wherein k is the total number of the cell, i is the number of the cell, and j is one of A, B, C phases;
s32: data set TijIn (1)Each piece of data was normalized by the mean and variance in S21;
s33: and estimating the voltage value of each phase of each station area at the corresponding moment according to the voltage loss model. The specific formula of the voltage loss model is as follows:
wherein, V'tijRepresenting the voltage estimate, V, of the i-th cell summary in the j-phaseux、WuxRespectively representing the voltage and power, W, of the electric energy meter of the user to be identifiedtij V′tijRepresenting the power of the ith cell summary table in the j phase.
Further, in step S4, the Spearman rank correlation coefficient is calculated based on the data of the estimated value and the actual value of each phase voltage of the total table of the station area at some time, which includes the following specific steps:
s41: each data set TijRespectively sequencing the obtained estimated voltage value and actual value of the jth phase of the ith station zone from small to large, and calculating corresponding rank RiAnd Qi；
S42: according to the calculated rank, a Spearman rank correlation coefficient is calculated, and the specific formula is as follows:
further, the step S5 of comprehensively deciding the station area to which the user electric energy meter belongs by using the Spearman rank correlation coefficient between the actual value and the estimated value includes the following specific steps:
s51: taking three correlation coefficients r calculated by the ith station areaiA、riB、riCThe square of the maximum value in (b) is taken as the correlation degree r of the regioni 2；
S52: if zone correlation ri 2(0≤r2≤1，ri 2The closer to 1, the stronger the correlation between the user electric energy meter and the ith station zone) is, the smallerAt gamma1(threshold, given empirically by the expert), then the ith cell is removed from the candidate cell;
s53: in the rest of the alternative stations, r with the maximum correlation degree is searchedi 2Then, the user electric energy meter to be identified belongs to the ith station area;
s54: and if the suitable distribution area can not be matched finally, acquiring more data and then analyzing. By repeating the steps S3 to S5, more user electric energy meters can be identified without constructing a voltage loss model.
The embodiment provides an automatic identification method for the electric energy meter region based on a ridge regression and Spearman rank correlation method, which can not only effectively identify the region to which the user electric energy meter belongs, but also provide corresponding correlation coefficients, thereby providing accurate region identification and promoting safe and effective operation of a power grid.
Finally, it is noted that the above-mentioned preferred embodiments illustrate rather than limit the invention, and that, although the invention has been described in detail with reference to the above-mentioned preferred embodiments, it will be understood by those skilled in the art that various changes in form and detail may be made therein without departing from the scope of the invention as defined by the appended claims.
Claims (6)
1. An automatic identification method for an electric energy meter platform area is characterized by comprising the following steps: the method comprises the following steps:
s1: acquiring voltage and power values of a distribution area master meter and a user electric energy meter at a plurality of moments by using known correct distribution area data;
s2: establishing a voltage loss model by utilizing the collected voltage and power values;
s3: estimating the voltage of each phase of each station area general table at each moment by using the voltage loss model and the data of the user electric energy meter to be identified;
s4: calculating Spearman rank correlation coefficients of the estimated values and the actual values of the voltage of each phase of the time station area general table based on the data;
s5: and comprehensively deciding the station area to which the electric energy meter of the user to be identified belongs by using the Spearman rank correlation coefficient of the actual value and the estimated value.
2. The automatic identification method of the electric energy meter distribution area according to claim 1, characterized in that: the step S1 specifically includes:
synchronously acquiring the voltage V of the user electric energy meter once every 1-15 minutes within a certain number of daysuPower WuAnd the voltage V of the table area general table corresponding to the user electric energy meter at the corresponding phasetPower Wt(ii) a Finally, a training data set D (W) is constructed according to the collected datau Vu,Wt,Vt)。
3. The automatic identification method of the electric energy meter distribution area according to claim 2, characterized in that: the step S2 specifically includes:
s21: normalizing the collected training data set D by a zero-mean normalization method, eliminating dimension between the training data set D and the collected training data set D to obtain a new training data set D*The specific conversion formula is as follows:
s22: the parameters (k) of the voltage loss model are derived by locally minimizing the objective function according to the principle of the gradient descent method0,k1,k2,k3) (ii) a The objective function is:
where λ is the regularization parameter and m is the training data set D*The number of samples to be collected in (a),
Wt (i),
are respectively training set D*The ith sample in (1).
4. The automatic identification method of the electric energy meter distribution area according to claim 3, characterized in that: the S3 specifically includes:
s31: synchronously acquiring the voltage V of the user electric energy meter to be identified once every 1-15 minutes within a certain number of daysuxPower WuxAnd the voltage V of each station area general table in each phasetPower Wt(ii) a Finally, 3 x k data sets T are constructed according to the collected dataij(Wux Vux,Wtij,Vtij) (ii) a Wherein k is the total number of the cell, i is the number of the cell, and j is one of A, B, C phases;
s32: data set TijEach piece of data in S21 is normalized according to the mean and variance in S21;
s33: estimating the voltage value of each phase of each station area at corresponding moment according to the voltage loss model; the specific formula of the voltage loss model is as follows:
wherein, V'tijRepresenting the voltage estimate, V, of the i-th cell summary in the j-phaseux、WuxRespectively representing the voltage and power, W, of the electric energy meter of the user to be identifiedtijRepresenting the power of the ith cell summary table in the j phase.
5. The method for automatically identifying the electric energy meter distribution area according to claim 4, wherein the method comprises the following steps: the S4 specifically includes:
s41: each data set TijRespectively sequencing the obtained estimated voltage value and actual value of the jth phase of the ith station zone from small to large, and calculating corresponding rank RiAnd Qi；
S42: according to the calculated rank, a Spearman rank correlation coefficient is calculated, and the specific formula is as follows:
6. the automatic identification method of the electric energy meter distribution area according to claim 1, characterized in that: the S5 specifically includes:
s51: taking three correlation coefficients r calculated by the ith station areaiA、riB、riCThe square of the maximum value in (b) is taken as the correlation degree r of the regioni 2；
S52: if zone correlation ri 2Less than gamma1If yes, removing the ith station zone from the alternative station zone; wherein r is more than or equal to 02≤1，ri 2The closer to 1, the stronger the correlation between the user electric energy meter and the ith station area; gamma ray1Is a threshold value, obtained empirically;
s53: in the rest of the alternative stations, r with the maximum correlation degree is searchedi 2Then, the user electric energy meter to be identified belongs to the ith station area;
s54: if the appropriate distribution area can not be matched finally, more data are obtained and then analyzed; and repeating the steps S3 to S5 to identify more user electric energy meters without constructing a voltage loss model.
Priority Applications (1)
| Application Number | Priority Date | Filing Date | Title |
|---|---|---|---|
| CN201811643294.4A CN109725219B (en) | 2018-12-29 | 2018-12-29 | Automatic identification method for electric energy meter distribution area |
Applications Claiming Priority (1)
| Application Number | Priority Date | Filing Date | Title |
|---|---|---|---|
| CN201811643294.4A CN109725219B (en) | 2018-12-29 | 2018-12-29 | Automatic identification method for electric energy meter distribution area |
Publications (2)
| Publication Number | Publication Date |
|---|---|
| CN109725219A CN109725219A (en) | 2019-05-07 |
| CN109725219B true CN109725219B (en) | 2021-02-09 |
Family
ID=66299409
Family Applications (1)
| Application Number | Title | Priority Date | Filing Date |
|---|---|---|---|
| CN201811643294.4A Active CN109725219B (en) | 2018-12-29 | 2018-12-29 | Automatic identification method for electric energy meter distribution area |
Country Status (1)
| Country | Link |
|---|---|
| CN (1) | CN109725219B (en) |
Families Citing this family (6)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN109857975B (en) * | 2018-12-29 | 2023-04-07 | 重庆邮电大学 | Electric energy meter area and three-phase automatic identification method |
| CN110389267B (en) * | 2019-07-17 | 2021-05-04 | 国网陕西省电力公司电力科学研究院 | Low-voltage transformer area subscriber relationship identification method |
| CN110749852B (en) * | 2019-10-15 | 2022-02-01 | 南京林洋电力科技有限公司 | Phase identification method based on instantaneous three-phase power unbalance |
| CN111505446B (en) * | 2020-05-25 | 2022-07-26 | 广州市奔流电力科技有限公司 | Method, device and equipment for identifying subscriber relationship of platform area vacant house subscriber |
| CN112067922B (en) * | 2020-08-24 | 2022-06-14 | 广东电网有限责任公司 | Low-voltage transformer area household transformation relation identification method |
| CN115508662B (en) * | 2022-11-23 | 2023-03-07 | 青岛鼎信通讯股份有限公司 | Method for judging affiliation relationship between district ammeter and meter box |
Family Cites Families (7)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CH704480A2 (en) * | 2011-02-01 | 2012-08-15 | Goldprincess Guenter Holzner | Canceling or reducing negative effects of oxidation of cell membranes, preferably mitochondria and other organelles of human organs comprises providing molecules of biochemical energy during or shortly after occurrence of triggering event |
| CN103577695A (en) * | 2013-11-07 | 2014-02-12 | 广东电网公司佛山供电局 | Method and device for detecting suspect data in power quality data |
| US9479788B2 (en) * | 2014-03-17 | 2016-10-25 | Qualcomm Incorporated | Systems and methods for low complexity encoding and background detection |
| CN104218570B (en) * | 2014-08-21 | 2017-04-05 | 国家电网公司 | A kind of online evaluation method and system of electric power meter entirety error in dipping |
| CN204241598U (en) * | 2014-12-09 | 2015-04-01 | 国网安徽省电力公司淮南供电公司 | Intelligent platform zone identifier |
| CN107220906B (en) * | 2017-05-31 | 2019-10-11 | 国网上海市电力公司 | Multiple Time Scales multiplexing electric abnormality analysis method based on electricity consumption acquisition system |
| CN108335229A (en) * | 2018-01-25 | 2018-07-27 | 国网浙江海宁市供电有限公司 | A kind of theoretical line loss caluclation method based on power grid operation data |
-
2018
- 2018-12-29 CN CN201811643294.4A patent/CN109725219B/en active Active
Non-Patent Citations (2)
| Title |
|---|
| Measuring the Quality of Quality Measures;Hila Nachlieli等;《IEEE TRANSACTIONS ON IMAGE PROCESSING》;20111231;全文 * |
| 基于CRITIC 和理想点法的计量设备运行质量评估;杨光盛等;《电力系统保护与控制》;20181216;第46卷(第24期);全文 * |
Also Published As
| Publication number | Publication date |
|---|---|
| CN109725219A (en) | 2019-05-07 |
Similar Documents
| Publication | Publication Date | Title |
|---|---|---|
| CN109725219B (en) | Automatic identification method for electric energy meter distribution area | |
| CN109738723B (en) | Three-phase automatic identification method for electric energy meter | |
| US10009064B2 (en) | Method for differentiating power distribution areas and phases by using voltage characteristics | |
| CN109857975B (en) | Electric energy meter area and three-phase automatic identification method | |
| CN104794206B (en) | A kind of substation data QA system and method | |
| CN103020459B (en) | A kind of cognitive method of various dimensions electricity consumption behavior and system | |
| CN109840691B (en) | Non-invasive polynomial electric quantity estimation method based on deep neural network | |
| CN111080105A (en) | Transformer area user-to-user relationship identification method and system based on voltage time sequence data | |
| CN108445435A (en) | A kind of electric energy meter calibrating apparatus error online evaluation method | |
| CN113406558B (en) | Ammeter misalignment detection method and device based on linear regression and electronic equipment | |
| CN109767054A (en) | Efficiency cloud appraisal procedure and edge efficiency gateway based on deep neural network algorithm | |
| CN110489783B (en) | QNNN-based low-voltage transformer area line loss rate reasonable range estimation method | |
| CN102856896B (en) | On-line analytical method for direct-current transmission loss | |
| CN108490285B (en) | Low-voltage transformer area line loss rate calculation method based on voltage drop method | |
| CN111091223B (en) | Matching short-term load prediction method based on intelligent sensing technology of Internet of things | |
| CN103617560A (en) | Electricity energy efficiency monitoring and evaluating system applied to enterprise and evaluating method thereof | |
| CN114266457A (en) | Method for detecting different loss inducement of distribution line | |
| CN112182499A (en) | Low-voltage distribution network topological structure identification method based on time sequence electric quantity data | |
| CN108226664A (en) | A kind of user side electric energy quality synthesis evaluation system and method | |
| CN113806899B (en) | Power distribution network topological relation identification method and device and mobile terminal | |
| CN115908051A (en) | Method for determining energy storage capacity of power system | |
| CN115564180A (en) | Power network reliability assessment method based on big data analysis | |
| CN110865328B (en) | Intelligent electric meter phase identification, topology identification and impedance estimation method based on AMI | |
| CN116136580A (en) | Line loss grading detection method and device based on sensing equipment | |
| CN104573313B (en) | The acquisition methods and system of customer response model under Peak-valley TOU power price |
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 |