CN115392648A - Transformer area line loss fusion diagnosis system and diagnosis method thereof - Google Patents
Transformer area line loss fusion diagnosis system and diagnosis method thereof Download PDFInfo
- Publication number
- CN115392648A CN115392648A CN202210928385.2A CN202210928385A CN115392648A CN 115392648 A CN115392648 A CN 115392648A CN 202210928385 A CN202210928385 A CN 202210928385A CN 115392648 A CN115392648 A CN 115392648A
- Authority
- CN
- China
- Prior art keywords
- transformer area
- line loss
- abnormal
- loss
- diagnosis
- 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
- 238000003745 diagnosis Methods 0.000 title claims abstract description 62
- 230000004927 fusion Effects 0.000 title claims abstract description 29
- 238000000034 method Methods 0.000 title claims description 34
- 230000002159 abnormal effect Effects 0.000 claims abstract description 83
- 238000004364 calculation method Methods 0.000 claims abstract description 49
- 238000004458 analytical method Methods 0.000 claims abstract description 24
- 230000005611 electricity Effects 0.000 claims description 15
- 230000005856 abnormality Effects 0.000 claims description 13
- 238000010801 machine learning Methods 0.000 claims description 9
- 238000003491 array Methods 0.000 claims description 7
- 230000003068 static effect Effects 0.000 claims description 7
- 230000008569 process Effects 0.000 claims description 6
- 238000003066 decision tree Methods 0.000 claims description 4
- 230000007812 deficiency Effects 0.000 claims description 4
- 230000002265 prevention Effects 0.000 abstract 1
- 239000007787 solid Substances 0.000 abstract 1
- 230000009467 reduction Effects 0.000 description 10
- 238000007726 management method Methods 0.000 description 4
- 238000005516 engineering process Methods 0.000 description 3
- 238000013024 troubleshooting Methods 0.000 description 3
- 238000005259 measurement Methods 0.000 description 2
- 238000013139 quantization Methods 0.000 description 2
- 238000012360 testing method Methods 0.000 description 2
- 230000009286 beneficial effect Effects 0.000 description 1
- 230000008859 change Effects 0.000 description 1
- 230000003111 delayed effect Effects 0.000 description 1
- 238000011161 development Methods 0.000 description 1
- 238000010586 diagram Methods 0.000 description 1
- 230000000694 effects Effects 0.000 description 1
- 230000006872 improvement Effects 0.000 description 1
- 238000004519 manufacturing process Methods 0.000 description 1
- 238000012986 modification Methods 0.000 description 1
- 230000004048 modification Effects 0.000 description 1
- 230000002035 prolonged effect Effects 0.000 description 1
- 238000011160 research Methods 0.000 description 1
- 230000001502 supplementing effect Effects 0.000 description 1
Images
Classifications
-
- G—PHYSICS
- G06—COMPUTING; CALCULATING OR COUNTING
- G06Q—INFORMATION AND COMMUNICATION TECHNOLOGY [ICT] SPECIALLY ADAPTED FOR ADMINISTRATIVE, COMMERCIAL, FINANCIAL, MANAGERIAL OR SUPERVISORY PURPOSES; SYSTEMS OR METHODS SPECIALLY ADAPTED FOR ADMINISTRATIVE, COMMERCIAL, FINANCIAL, MANAGERIAL OR SUPERVISORY PURPOSES, NOT OTHERWISE PROVIDED FOR
- G06Q10/00—Administration; Management
- G06Q10/06—Resources, workflows, human or project management; Enterprise or organisation planning; Enterprise or organisation modelling
- G06Q10/063—Operations research, analysis or management
- G06Q10/0639—Performance analysis of employees; Performance analysis of enterprise or organisation operations
- G06Q10/06395—Quality analysis or management
-
- G—PHYSICS
- G06—COMPUTING; CALCULATING OR COUNTING
- G06N—COMPUTING ARRANGEMENTS BASED ON SPECIFIC COMPUTATIONAL MODELS
- G06N20/00—Machine learning
Landscapes
- Business, Economics & Management (AREA)
- Engineering & Computer Science (AREA)
- Human Resources & Organizations (AREA)
- Theoretical Computer Science (AREA)
- Development Economics (AREA)
- Educational Administration (AREA)
- Economics (AREA)
- Entrepreneurship & Innovation (AREA)
- Software Systems (AREA)
- Strategic Management (AREA)
- General Physics & Mathematics (AREA)
- Physics & Mathematics (AREA)
- Tourism & Hospitality (AREA)
- Data Mining & Analysis (AREA)
- General Business, Economics & Management (AREA)
- Operations Research (AREA)
- Marketing (AREA)
- Artificial Intelligence (AREA)
- Computer Vision & Pattern Recognition (AREA)
- Quality & Reliability (AREA)
- Evolutionary Computation (AREA)
- Medical Informatics (AREA)
- Game Theory and Decision Science (AREA)
- Computing Systems (AREA)
- General Engineering & Computer Science (AREA)
- Mathematical Physics (AREA)
- Supply And Distribution Of Alternating Current (AREA)
Abstract
The invention discloses a transformer area line loss fusion diagnosis system, which comprises a transformer area state analysis module: the system is used for searching for the normal state of the transformer area, judging the abnormal source, classifying and judging the main cause of the transformer area and outputting the loss-reducing electric quantity; the under-platform data abnormal user diagnosis module: diagnosing user data under the transformer area according to the analysis result of the transformer area state analysis module; a calculation module: and performing reducible power calculation, reducible power trial calculation and line loss rate trial calculation according to the diagnosis result of the under-station data abnormal user diagnosis module. The transformer area line loss fusion diagnosis system can eliminate partial abnormity which does not influence transformer area line loss, more accurately positions the reasons of transformer area line loss abnormity, provides line loss treatment reference and scheme for basic level service personnel, enhances transformer area line loss prevention and control capacity, powerfully leaks and increases income, provides a solid foundation for effective transformer area line loss treatment of each power supply company by means of efficient system data support, and has good prospects.
Description
Technical Field
The invention relates to the field of transformer area management, in particular to a transformer area line loss fusion diagnosis system and a diagnosis method thereof.
Background
In an electric power system, a transformer area refers to a power supply range or area of a transformer;
with the development of society and the continuous improvement of the living standard of people, the demand on electric energy is more and more increased. Due to the simultaneity of electric energy production and consumption, the transformer area needs to be reasonably managed, and the transformer area state needs to be managed for better management of the transformer area;
the line loss rate of the transformer area is managed in the transformer area state management process;
the line loss rate of the cell is described as the loss condition of the power of one cell, that is, the line loss rate of the cell = (total power supply amount-total power sale amount)/power supply amount × 100%, and a smaller line loss rate indicates a smaller power loss of the cell, otherwise, the loss is larger.
In order to reduce the line loss rate of the transformer area, some auxiliary systems are invented, wherein a transformer area line loss fusion diagnosis system is provided;
through research, the existing transformer area line loss fusion diagnosis system has certain disadvantages when in use;
in the use process of the conventional transformer area line loss fusion diagnosis system, part of abnormal reasons which do not influence the transformer area line loss are output as main transformer reasons of the transformer area, so that error judgment is generated when basic level personnel conduct troubleshooting, real abnormal reasons of the transformer area are ignored, abnormal management of the transformer area is delayed, the troubleshooting period of the real abnormal reasons of the transformer area is prolonged, and troubleshooting efficiency is influenced.
Disclosure of Invention
The invention mainly aims to provide a transformer area line loss fusion diagnosis system and a diagnosis method thereof, which can effectively solve the problems in the background technology.
In order to realize the purpose, the invention adopts the technical scheme that:
a block line loss fusion diagnostic system, comprising:
a transformer area state analysis module: the system is used for searching for the normal state of the transformer area, judging the abnormal source, classifying and judging the main cause of the transformer area and outputting the loss-reducing electric quantity;
the under-platform data abnormal user diagnosis module: diagnosing user data under the transformer area according to the analysis result of the transformer area state analysis module;
a calculation module: performing reducible power calculation, reducible power trial calculation and line loss rate trial calculation according to the diagnosis result of the under-platform data abnormal user diagnosis module;
an exception list output module: and outputting the calculation result of the calculation module in a list mode.
Preferably, the method for diagnosing the line loss fusion of the transformer area comprises the following steps:
(1) analyzing and judging a main reason of the platform area state and outputting the electricity quantity which can be reduced;
(2) user diagnosis of abnormal data under the platform area;
(3) calculating the loss-reducing electric quantity;
(4) trial calculation of the loss-reducing electric quantity and trial calculation of the line loss rate;
(5) and outputting an exception list.
Preferably, the step of analyzing the station status in step (1) to determine the main cause and outputting the loss-capable power amount includes:
i, searching a station area normal state;
II, judging an abnormal source;
III, weak classification judgment of main causes of the transformer area.
Preferably, when the district normality is searched in the step I, a DBscan clustering algorithm is adopted to cluster the power supply quantity and the power consumption quantity of the district, linear fitting is carried out on the maximum class, and the predicted power consumption quantity a and the residual error of a diagnosis day are calculated according to the power supply quantity, wherein the residual error = the actual power consumption quantity-the predicted power consumption quantity, and the residual error is the electricity loss quantity; when the absolute value of error > K, it is judged that the power supply amount or the power consumption amount on the day is abnormal.
Preferably, when the source of the abnormality is judged in the step ii, an array is respectively constructed according to the power consumption and the power supply amount 7 days before the diagnosis day:
A＝{a1,a2,……a7}，B＝{b1,b2……b7}
respectively calculating the standard deviations x and y of the 2 arrays;
when x > K1 y, the anomaly originates from a user under the platform region;
when y > K2 x, the anomalies are derived from the table summary.
Preferably, the weak classification step in step iii is as follows:
a. constructing sample data, and selecting 80% of the sample as an expert sample and 20% of the sample as an experimental sample;
b. constructing characteristics and machine learning;
c. and judging the main cause of the abnormality of the transformer area through a decision tree model.
Preferably, the sample sources of the sample data in step a are in the history case: the method comprises the following steps of measuring abnormal data by a terminal, acquiring abnormal data by the terminal, measuring abnormal data by a user, acquiring abnormal data by the file and default electricity utilization data;
b, dividing the constructed features and the machine learning features into static attributes and dynamic features, wherein the static attributes are the station area file information, and the dynamic features are line loss related features; and constructing statistical class characteristics for the dynamic characteristics, and constructing derived characteristics of the dynamic characteristics by combining window division.
Preferably, in the step (2), when the user with abnormal data in the platform area diagnoses and uses the data, such as files, electricity consumption, loads and the like, the abnormal data is diagnosed through consistency, paradox, deficiency, extreme value and repeatability, the abnormal user and the abnormal time period are diagnosed, and the accuracy of abnormal diagnosis and analysis is improved. And performing correlation trial calculation according to the abnormal data and the station area main factor residual error, wherein the correlation trial calculation is mainly used for calculating a vector cos value by constructing a vector.
Preferably, in the step (3), the daily power consumption and the power supply capacity of the power distribution room of the user are complemented according to the power abnormality data during power consumption reduction calculation, and the single abnormality power consumption reduction = predicted power consumption-power recorded by the system.
Preferably, trial calculation of the loss-reducing electric quantity = the sum of all abnormal loss-reducing electric quantities when trial calculation of the loss-reducing electric quantity is performed in step (4), and when a residual error between the trial calculation of the loss-reducing electric quantity and linear fitting does not exceed K, the assumption is valid;
when the abnormality belongs to the terminal in the line loss rate trial calculation process, then
Line loss rate = (predicted power supply amount-power consumption amount + abnormal loss-allowable power amount)/predicted power supply amount = 100%.
Compared with the prior art, the transformer area line loss fusion diagnosis system and the diagnosis method thereof have the following beneficial effects:
the invention discloses a transformer area line loss fusion diagnosis system and a diagnosis method thereof, which are based on a marketing system and a power utilization information acquisition system, fuse multi-source data, aim at 'full analysis, accurate positioning and hierarchical recommendation', utilize big data and a machine learning algorithm, surround dimensions such as files, acquisition, measurement, technology and electricity stealing and the like, form a transformer area line loss treatment hierarchical recommendation strategy by line loss abnormity quantization and influence degree analysis and combining transformer area line loss characteristics, solve the problems of complex positioning of line loss reasons, difficult data volume huge analysis and large pressure of basic capability, realize hierarchical treatment recommendation of abnormal transformer areas, improve line loss rectification efficiency, reduce basic layer burden, have good practical value and can be popularized and applied in a large scale.
Drawings
FIG. 1 is a flow chart of a line loss fusion diagnosis method for a distribution room according to the present invention;
fig. 2 is a structural block diagram of user diagnosis of abnormal data under the transformer area in the transformer area line loss fusion diagnosis method of the present invention.
Detailed Description
In order to make the technical means, the creation characteristics, the achievement purposes and the effects of the invention easy to understand, the invention is further explained by combining the specific embodiments.
Example 1
A block line loss fusion diagnostic system, comprising:
a transformer area state analysis module: the system is used for searching for the normal state of the transformer area, judging the abnormal source, classifying and judging the main cause of the transformer area and outputting the loss-reducing electric quantity;
the user diagnosis module for abnormal data under the transformer area comprises: diagnosing user data under the transformer area according to the analysis result of the transformer area state analysis module;
a calculation module: performing reducible power calculation, reducible power trial calculation and line loss rate trial calculation according to the diagnosis result of the under-platform data abnormal user diagnosis module;
an exception list output module: and outputting the calculation result of the calculation module in a list mode.
Example 2
A transformer area line loss fusion diagnosis method comprises the following steps:
(1) analyzing and judging the main cause of the transformer area state and outputting the loss-reducing electric quantity;
the method for analyzing and judging the main cause of the transformer area state and outputting the loss-reducing electric quantity comprises the following steps:
i, searching a station area normal state;
clustering the power supply quantity and the power consumption quantity of the distribution area by adopting a DBscan clustering algorithm when the distribution area is in a normal state, performing linear fitting on the maximum class, and calculating predicted power consumption quantity a and residual error according to the power supply quantity, wherein the residual error = actual power consumption quantity-predicted power consumption quantity, and the residual error is the electricity loss quantity capable of being reduced; when the absolute value of error is larger than K, judging that the power supply quantity or the power consumption quantity on the day is abnormal;
II, judging the source of the abnormality;
when an abnormal source is judged, respectively constructing arrays according to the power consumption and the power supply amount 7 days before the diagnosis day:
A＝{a1,a2,……a7}，B＝{b1,b2……b7}
respectively calculating the standard deviations x and y of the 2 arrays;
when x > K1 x y, the exception is from a user under the platform area;
when y > K2 x, the anomaly is derived from the table summary.
III, judging the main cause of the transformer area in a weak classification manner;
the weak classification step for judging the main cause of the transformer area comprises the following steps:
a. constructing sample data, and selecting 80% of the samples as expert samples and 20% of the samples as test samples;
the sample source of the sample data is in the history case: the method comprises the following steps of measuring abnormal data by a terminal, acquiring abnormal data by the terminal, measuring abnormal data by a user, acquiring abnormal data by the file and default electricity utilization data;
b. constructing features and machine learning;
the constructed features and the features during machine learning are divided into static attributes and dynamic features, the static attributes are the station area file information, and the dynamic features are line loss related features; and constructing statistical class characteristics for the dynamic characteristics, and constructing derived characteristics of the dynamic characteristics by combining window division.
c. And judging the main cause of the abnormality of the transformer area through a decision tree model.
(2) Diagnosing abnormal data users in the transformer area;
when the abnormal data users in the transformer area are diagnosed and used, the abnormal data diagnosis is carried out through consistency, paradox, deficiency, extreme value and repeatability on the basis of data such as files, electricity and loads, the abnormal users and abnormal time periods are diagnosed, and the accuracy of abnormal diagnosis analysis is improved. And performing correlation trial calculation according to the abnormal data and the station area main factor residual error, wherein the correlation trial calculation mainly calculates a vector cos value by constructing a vector.
(3) Calculating the loss-reducing electric quantity;
and completing the daily electric quantity and the station area power supply quantity of the user according to the electric quantity abnormal data during calculation of the loss-reducing electric quantity, wherein the single abnormal loss-reducing electric quantity = predicted electric quantity-electric quantity recorded by a system.
(4) Trial calculation of the loss-reducing electric quantity and trial calculation of the line loss rate;
trial-calculating loss reduction electric quantity = the sum of all abnormal loss reduction electric quantities when the loss reduction electric quantity is trial-calculated, and assuming to be effective when the residual error between the trial-calculated loss reduction electric quantity and the linear fitting does not exceed K;
when the abnormality belongs to the terminal in the process of trial calculation of the line loss rate, then
Line loss rate = (predicted power supply amount-power consumption amount + abnormal loss-allowable power amount)/predicted power supply amount = 100%.
(5) And outputting an exception list.
Example 3
A transformer area line loss fusion diagnosis method comprises the following steps:
(1) analyzing and judging main reason of the transformer area state and outputting loss-reducing electric quantity
I, finding station normality
Clustering the power supply quantity and the power consumption quantity of the distribution room by using a DBsacan clustering algorithm, performing linear fitting on the maximum class, and calculating the predicted power consumption quantity a and the residual error of the diagnosis day according to the power supply quantity, wherein the residual = the actual power consumption quantity-the predicted power consumption quantity, and the residual error is the electricity loss-reducing quantity. When the absolute value of error is larger than K, judging that the power supply quantity or the power consumption quantity on the day is abnormal;
II, judging the source of the abnormality
Respectively constructing arrays according to the power consumption and the power supply quantity 7 days before the diagnosis day
A＝{a1,a2,……a7}，B＝{b1,b2……b7}
And the standard deviations x and y of the 2 arrays are calculated, respectively.
When x > K1 x y, the exception is from a user under the platform area;
when y > K2 x, the anomaly is derived from the total table of lands;
III, weak classification judgment platform zone main cause
a. Constructing sample data, and selecting 80% of the sample as an expert sample and 20% of the sample as a test sample.
Sample source: selecting the following in history cases: abnormal terminal metering, abnormal terminal acquisition, abnormal user metering, abnormal user acquisition, abnormal archives (mainly selecting user change cases), and default power utilization; since the technical factors are already embodied in the stage area normal state searching, the abnormity judgment is not added, and other abnormity has little or no influence on the line loss, so the abnormity judgment is not added.
b. Building features and machine learning
The characteristics are divided into static attributes (mainly including the station area file information), and the dynamic characteristics are mainly line loss related characteristics; and constructing statistical class characteristics such as average values and standard deviations for the dynamic characteristics, and constructing derivative characteristics of the dynamic characteristics by combining windowing.
c. And judging the main cause of the abnormality of the transformer area through a decision tree model.
(2) Diagnosing abnormal data users in the transformer area;
based on data such as archives, electricity consumption, load and the like, data abnormity diagnosis is carried out through consistency, paradox, deficiency, extreme value and repeatability, abnormal users and abnormal time periods are diagnosed, and the accuracy of abnormity diagnosis analysis is improved. And performing correlation trial calculation according to the abnormal data and the station area main factor residual error, wherein the correlation trial calculation is mainly used for calculating a vector cos value by constructing a vector.
Data items for the main diagnosis are as follows
Within the day of analysis, the amount of power supply was lost:
in an analysis day, 2 accumulated time points of the B-phase current are lost, 10 accumulated time points of the C-phase current are opposite to the real current, 8 accumulated time points of the active power are O, and 3 accumulated time points of the forward active total electric energy are extreme values;
(3) calculating the loss-reducing electric quantity;
supplementing daily electric quantity and station power supply quantity of a user according to the electric quantity abnormal data, and enabling the single abnormal loss-reducing electric quantity to be = predicted electric quantity-electric quantity recorded by a system;
(4) the electric quantity loss can be reduced and the line loss rate can be reduced;
trial-calculating loss reduction electric quantity = the sum of all abnormal loss reduction electric quantities when the loss reduction electric quantity is trial-calculated, and assuming to be effective when the residual error between the trial-calculated loss reduction electric quantity and the linear fitting does not exceed K;
when the abnormality belongs to the terminal in the process of trial calculation of the line loss rate, then
Line loss rate = (predicted power supply amount-power consumption amount + abnormal reducible power loss)/predicted power supply amount = 100%.
(5) Output of exception list
For example, the following table:
the line loss fusion diagnosis system and the diagnosis method thereof are based on a marketing system and a power consumption information acquisition system, fuse multi-source data, aim at 'full analysis, accurate positioning and hierarchical recommendation', utilize big data and a machine learning algorithm, surround dimensions such as archives, acquisition, measurement, technology and electricity stealing, and form a hierarchical recommendation strategy for line loss treatment by virtue of line loss abnormity quantization and influence degree analysis and combining with line loss characteristics of the distribution area, so that the problems of complex positioning of line loss reasons, difficult analysis of huge data quantity and weak pressure of basic capability are solved, the hierarchical treatment recommendation of abnormal distribution areas is realized, the line loss rectification efficiency is improved, the burden of a basic layer is reduced, and the system and the method have good practical value and can be popularized and applied in a large scale.
The foregoing shows and describes the general principles and features of the present invention, together with the advantages thereof. It will be understood by those skilled in the art that the present invention is not limited to the embodiments described above, which are described in the specification and illustrated only to illustrate the principle of the present invention, but that various changes and modifications may be made therein without departing from the spirit and scope of the present invention, which fall within the scope of the invention as claimed. The scope of the invention is defined by the appended claims and equivalents thereof.
Claims (10)
1. A block line loss fusion diagnostic system, comprising:
a transformer area state analysis module: the system is used for searching for the normal state of the transformer area, judging the abnormal source, classifying and judging the main cause of the transformer area and outputting the loss-reducing electric quantity;
the under-platform data abnormal user diagnosis module: diagnosing user data under the transformer area according to the analysis result of the transformer area state analysis module;
a calculation module: performing reducible power calculation, reducible power trial calculation and line loss rate trial calculation according to the diagnosis result of the under-platform data abnormal user diagnosis module;
an exception list output module: and outputting the calculation result of the calculation module in a list mode.
2. The transformer area line loss fusion diagnosis method according to claim 1, comprising the steps of:
(1) analyzing and judging a main reason of the platform area state and outputting the electricity quantity which can be reduced;
(2) user diagnosis of abnormal data under the platform area;
(3) calculating the loss-reducing electric quantity;
(4) trial calculation of the loss-reducing electric quantity and trial calculation of the line loss rate;
(5) and outputting an exception list.
3. The transformer area line loss fusion diagnosis method according to claim 2, wherein: the step of analyzing and judging the main cause of the station area state and outputting the loss-reducing electric quantity in the step (1) is as follows:
i, searching a station area normal state;
II, judging an abnormal source;
III, weak classification judgment of main causes of the transformer area.
4. The transformer area line loss fusion diagnosis method according to claim 3, wherein: the method comprises the following steps that firstly, when the station area normality is searched in the step I, the DBscan clustering algorithm is adopted to cluster the power supply quantity and the power consumption quantity of the station area, linear fitting is carried out on the maximum class, and the predicted power consumption quantity and the residual error of a diagnosis day are calculated according to the power supply quantity, wherein the residual error = the actual power consumption quantity-the predicted power consumption quantity, and the residual error is the electricity consumption quantity capable of being reduced; and when the absolute value of the residual error is larger than a set value K, judging that the power supply quantity or the power consumption quantity on the day is abnormal.
5. The transformer area line loss fusion diagnosis method according to claim 4, characterized in that: and (II) respectively constructing arrays according to the power consumption and the power supply quantity 7 days before the diagnosis day when the abnormal source is judged:
respectively calculating the standard deviations x and y of the 2 arrays;
when x > K1 x y, the exception is from a user under the platform area;
when y > K2 x, the anomaly is derived from the table summary.
6. The transformer area line loss fusion diagnosis method according to claim 5, wherein: and III, judging the main causes of the transformer area in a weak classification manner, wherein the weak classification determination method comprises the following steps:
a. constructing sample data, and selecting 80% of the sample as an expert sample and 20% of the sample as an experimental sample;
b. constructing features and machine learning;
c. and judging the main cause of the abnormality of the transformer area through a decision tree model.
7. The transformer area line loss fusion diagnosis method according to claim 6, wherein: the sample source of the sample data in the step a is in the history case: the method comprises the following steps of measuring abnormal data by a terminal, acquiring abnormal data by the terminal, measuring abnormal data by a user, acquiring abnormal data by the file and default electricity utilization data;
b, dividing the constructed features and the machine learning features into static attributes and dynamic features, wherein the static attributes are the station area file information, and the dynamic features are line loss related features; and constructing statistical class characteristics for the dynamic characteristics, and constructing derived characteristics of the dynamic characteristics by combining window division.
8. The transformer area line loss fusion diagnosis method according to claim 7, characterized in that: in the step (2), when the abnormal data users in the cell are diagnosed and used, the abnormal data users and the abnormal time periods are diagnosed by performing abnormal data diagnosis through consistency, paradox, deficiency, extreme value and repeatability on the basis of data such as archives, electricity consumption and loads, and the accuracy of abnormal diagnosis analysis is improved. And performing correlation trial calculation according to the abnormal data and the main factor residual error of the transformer area, wherein the correlation trial calculation mainly calculates a vector cos value by constructing a vector.
9. The transformer area line loss fusion diagnosis method according to claim 8, wherein: and (3) completing the daily electric quantity and the station power supply quantity of the user according to the electric quantity abnormal data during calculation of the loss-reducing electric quantity, wherein the single abnormal loss-reducing electric quantity = predicted electric quantity-electric quantity recorded by the system.
10. The transformer area line loss fusion diagnosis method according to claim 9, wherein: trial calculation of the loss-reducing electric quantity during trial calculation of the loss-reducing electric quantity in the step (4), wherein the sum of all abnormal loss-reducing electric quantities is = and when the residual error between the trial calculation of the loss-reducing electric quantity and linear fitting does not exceed K, the assumption is valid;
when the abnormality belongs to the terminal in the line loss rate trial calculation process, then
Line loss rate = (predicted power supply amount-power consumption amount + abnormal loss-allowable power amount)/predicted power supply amount = 100%.
Priority Applications (1)
| Application Number | Priority Date | Filing Date | Title |
|---|---|---|---|
| CN202210928385.2A CN115392648A (en) | 2022-08-03 | 2022-08-03 | Transformer area line loss fusion diagnosis system and diagnosis method thereof |
Applications Claiming Priority (1)
| Application Number | Priority Date | Filing Date | Title |
|---|---|---|---|
| CN202210928385.2A CN115392648A (en) | 2022-08-03 | 2022-08-03 | Transformer area line loss fusion diagnosis system and diagnosis method thereof |
Publications (1)
| Publication Number | Publication Date |
|---|---|
| CN115392648A true CN115392648A (en) | 2022-11-25 |
Family
ID=84118091
Family Applications (1)
| Application Number | Title | Priority Date | Filing Date |
|---|---|---|---|
| CN202210928385.2A Pending CN115392648A (en) | 2022-08-03 | 2022-08-03 | Transformer area line loss fusion diagnosis system and diagnosis method thereof |
Country Status (1)
| Country | Link |
|---|---|
| CN (1) | CN115392648A (en) |
Citations (6)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN102280874A (en) * | 2010-06-10 | 2011-12-14 | 上海市电力公司 | Platform-area line loss rate detecting system |
| CN109472714A (en) * | 2018-06-11 | 2019-03-15 | 国网浙江海宁市供电有限公司 | A kind of route platform area's exception analysis system and method based on big data |
| CN111781463A (en) * | 2020-06-25 | 2020-10-16 | 国网福建省电力有限公司 | Auxiliary diagnosis method for abnormal line loss of transformer area |
| CN112598234A (en) * | 2020-12-14 | 2021-04-02 | 广东电网有限责任公司广州供电局 | Low-voltage transformer area line loss abnormity analysis method, device and equipment |
| CN113267692A (en) * | 2021-05-17 | 2021-08-17 | 国网吉林省电力有限公司营销服务中心 | Low-voltage transformer area line loss intelligent diagnosis and analysis method and system |
| CN113902062A (en) * | 2021-12-13 | 2022-01-07 | 国网江西省电力有限公司电力科学研究院 | Transformer area line loss abnormal reason analysis method and device based on big data |
-
2022
- 2022-08-03 CN CN202210928385.2A patent/CN115392648A/en active Pending
Patent Citations (6)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN102280874A (en) * | 2010-06-10 | 2011-12-14 | 上海市电力公司 | Platform-area line loss rate detecting system |
| CN109472714A (en) * | 2018-06-11 | 2019-03-15 | 国网浙江海宁市供电有限公司 | A kind of route platform area's exception analysis system and method based on big data |
| CN111781463A (en) * | 2020-06-25 | 2020-10-16 | 国网福建省电力有限公司 | Auxiliary diagnosis method for abnormal line loss of transformer area |
| CN112598234A (en) * | 2020-12-14 | 2021-04-02 | 广东电网有限责任公司广州供电局 | Low-voltage transformer area line loss abnormity analysis method, device and equipment |
| CN113267692A (en) * | 2021-05-17 | 2021-08-17 | 国网吉林省电力有限公司营销服务中心 | Low-voltage transformer area line loss intelligent diagnosis and analysis method and system |
| CN113902062A (en) * | 2021-12-13 | 2022-01-07 | 国网江西省电力有限公司电力科学研究院 | Transformer area line loss abnormal reason analysis method and device based on big data |
Similar Documents
| Publication | Publication Date | Title |
|---|---|---|
| CN113267692B (en) | Low-voltage transformer area line loss intelligent diagnosis and analysis method and system | |
| CN110264107B (en) | Large data technology-based abnormal diagnosis method for line loss rate of transformer area | |
| CN110675275B (en) | Electric load regulation and control method and system for demand side response application of virtual power plant | |
| CN105426980A (en) | Power distribution network health index assessment engineering application system | |
| CN112286063A (en) | Non-intrusive measurement-based regional energy consumption monitoring system and method | |
| CN111310854A (en) | Low false alarm rate electricity stealing detection secondary screening method based on electricity load fingerprint | |
| CN111476397B (en) | Bus load prediction method and system applied to medium and long term electric quantity safety check | |
| CN103617447A (en) | Evaluation system and method for intelligent substation | |
| CN114611842B (en) | Whole-county roof distributed photovoltaic power prediction method | |
| CN112001441A (en) | Power distribution network line loss anomaly detection method based on Kmeans-AHC hybrid clustering algorithm | |
| WO2024056050A1 (en) | Massive flexible load rapid aggregation control method and apparatus | |
| CN115392648A (en) | Transformer area line loss fusion diagnosis system and diagnosis method thereof | |
| CN116522746A (en) | Power distribution hosting method for high-energy-consumption enterprises | |
| CN115603318A (en) | Method and system for studying and judging cross-region large-area power failure fault based on marketing and distribution data | |
| CN115864531A (en) | Monitoring system and method for carbon emission of regional distributed photovoltaic power generation | |
| CN116468302A (en) | Building park energy structure evaluation method, system, electronic equipment and storage medium | |
| CN112113316B (en) | Method for extracting air conditioner load | |
| CN116027687A (en) | Intelligent energy consumption building energy consumption monitoring system and energy saving effect monitoring method | |
| Ya’An | Application of artificial intelligence in computer network technology in the era of big data | |
| Li et al. | Research on Key Technology of State Evaluation and Replacement Acquisition System of Intelligent Electric Energy Meter Based on Smart Grid | |
| CN111178768A (en) | Smart energy management system based on cloud platform | |
| Quan et al. | Analysis of line loss based on matlab and oracle database | |
| CN117892212B (en) | Distributed heterogeneous energy station situation awareness monitoring method | |
| CN113269435B (en) | New energy station running state coupling monitoring and evaluating system | |
| CN113283702B (en) | Power flow state evaluation method and device integrating safety and stability characteristics of power system |
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 |