CN113224748A - Method for calculating line loss of low-voltage distribution station area - Google Patents
Method for calculating line loss of low-voltage distribution station area Download PDFInfo
- Publication number
- CN113224748A CN113224748A CN202110452787.5A CN202110452787A CN113224748A CN 113224748 A CN113224748 A CN 113224748A CN 202110452787 A CN202110452787 A CN 202110452787A CN 113224748 A CN113224748 A CN 113224748A
- Authority
- CN
- China
- Prior art keywords
- line loss
- line
- data
- low
- 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.)
- Pending
Links
- 238000000034 method Methods 0.000 title claims abstract description 43
- 230000005611 electricity Effects 0.000 claims abstract description 21
- 230000002159 abnormal effect Effects 0.000 claims abstract description 15
- 238000004364 calculation method Methods 0.000 claims abstract description 11
- 238000004422 calculation algorithm Methods 0.000 claims abstract description 10
- 238000000611 regression analysis Methods 0.000 claims abstract description 10
- 238000013450 outlier detection Methods 0.000 claims abstract description 9
- 238000010801 machine learning Methods 0.000 claims abstract description 8
- 238000012360 testing method Methods 0.000 claims description 6
- 238000012549 training Methods 0.000 claims description 6
- 230000005856 abnormality Effects 0.000 claims description 4
- 230000011218 segmentation Effects 0.000 claims description 4
- 238000001514 detection method Methods 0.000 claims description 2
- 238000005070 sampling Methods 0.000 claims description 2
- 230000031068 symbiosis, encompassing mutualism through parasitism Effects 0.000 claims description 2
- 238000013528 artificial neural network Methods 0.000 description 2
- 238000004458 analytical method Methods 0.000 description 1
- 238000013473 artificial intelligence Methods 0.000 description 1
- 238000010276 construction Methods 0.000 description 1
- 238000011161 development Methods 0.000 description 1
- 230000018109 developmental process Effects 0.000 description 1
- 238000011156 evaluation Methods 0.000 description 1
- 238000011160 research Methods 0.000 description 1
- 238000007619 statistical method Methods 0.000 description 1
- 238000006467 substitution reaction Methods 0.000 description 1
- 230000001360 synchronised effect Effects 0.000 description 1
Images
Classifications
-
- H—ELECTRICITY
- H02—GENERATION; CONVERSION OR DISTRIBUTION OF ELECTRIC POWER
- H02J—CIRCUIT ARRANGEMENTS OR SYSTEMS FOR SUPPLYING OR DISTRIBUTING ELECTRIC POWER; SYSTEMS FOR STORING ELECTRIC ENERGY
- H02J3/00—Circuit arrangements for ac mains or ac distribution networks
-
- G—PHYSICS
- G06—COMPUTING; CALCULATING OR COUNTING
- G06F—ELECTRIC DIGITAL DATA PROCESSING
- G06F17/00—Digital computing or data processing equipment or methods, specially adapted for specific functions
- G06F17/10—Complex mathematical operations
- G06F17/11—Complex mathematical operations for solving equations, e.g. nonlinear equations, general mathematical optimization problems
- G06F17/12—Simultaneous equations, e.g. systems of linear equations
-
- G—PHYSICS
- G06—COMPUTING; CALCULATING OR COUNTING
- G06F—ELECTRIC DIGITAL DATA PROCESSING
- G06F17/00—Digital computing or data processing equipment or methods, specially adapted for specific functions
- G06F17/10—Complex mathematical operations
- G06F17/18—Complex mathematical operations for evaluating statistical data, e.g. average values, frequency distributions, probability functions, regression analysis
-
- H—ELECTRICITY
- H02—GENERATION; CONVERSION OR DISTRIBUTION OF ELECTRIC POWER
- H02J—CIRCUIT ARRANGEMENTS OR SYSTEMS FOR SUPPLYING OR DISTRIBUTING ELECTRIC POWER; SYSTEMS FOR STORING ELECTRIC ENERGY
- H02J2203/00—Indexing scheme relating to details of circuit arrangements for AC mains or AC distribution networks
- H02J2203/20—Simulating, e g planning, reliability check, modelling or computer assisted design [CAD]
Landscapes
- Engineering & Computer Science (AREA)
- Physics & Mathematics (AREA)
- General Physics & Mathematics (AREA)
- Mathematical Physics (AREA)
- Mathematical Analysis (AREA)
- Pure & Applied Mathematics (AREA)
- Computational Mathematics (AREA)
- Data Mining & Analysis (AREA)
- Mathematical Optimization (AREA)
- Theoretical Computer Science (AREA)
- Algebra (AREA)
- Operations Research (AREA)
- Databases & Information Systems (AREA)
- Software Systems (AREA)
- General Engineering & Computer Science (AREA)
- Evolutionary Biology (AREA)
- Probability & Statistics with Applications (AREA)
- Bioinformatics & Computational Biology (AREA)
- Bioinformatics & Cheminformatics (AREA)
- Life Sciences & Earth Sciences (AREA)
- Power Engineering (AREA)
- Supply And Distribution Of Alternating Current (AREA)
Abstract
The invention belongs to the technical field of power distribution network management of a power system, and particularly relates to a method for calculating line loss of a low-voltage distribution area. According to the method, firstly, under the condition that the topological structure of the power distribution network and the data of a single user electric meter are unknown, the characteristic of 'virtual line resistance' is obtained by calculation by considering the use of measured data. And adding the measured power supply and sales electricity quantity, current, line loss statistics and other characteristics, and performing data outlier detection by adopting an iForest isolated forest algorithm. After the abnormal values of the data are eliminated, a theoretical line loss estimation model is established for a large amount of actually measured data by adopting a regression analysis method in machine learning, and an estimated line loss value is obtained through calculation. The method provided by the invention gives consideration to interpretability and accuracy and provides reference for line loss management work of the low-voltage distribution network. The method has small calculation amount, thereby reducing the workload and saving the cost, and the line loss estimation value is calculated by a regression analysis method in machine learning only according to the measured data and the power supply and sale quantity of the low-voltage side of the transformer.
Description
Technical Field
The invention belongs to the technical field of power distribution network management of a power system, and particularly relates to a method for calculating line loss of a low-voltage distribution area.
Background
The electric energy loss of the low-voltage distribution network is mainly expressed as the loss of a line, and the line loss is an important comprehensive index reflecting the management level of the distribution network and is also the main content of performance level evaluation of a power grid enterprise. However, the theoretical line loss of the low-voltage distribution network is difficult to calculate due to the influence factors such as large electricity consumption of the low-voltage distribution area, complex distribution lines, weak distribution area archive management and the like. The traditional equivalent resistance method, the root mean square current method, the average current method and the like have high dependence on the original data of the line. There are many documents focusing on the research goal on the load side, and it is hoped that the theoretical line loss is calculated by forward-backward substitution method by starting from the load side. There are also documents focusing on the mean and variance of the load, correcting the theoretical line loss rate, and improving the accuracy of the theoretical line loss calculation. However, these methods need to have correct network topology and a large amount of power consumption data of users on the load side, and when the low-voltage distribution network is complicated or the construction age is early, the actual topology structure may not be obtained, and it is not practical to obtain the data of each user.
With the development of the artificial intelligence subject, researchers also try to calculate the theoretical line loss by using methods such as neural networks, clustering and the like. The general idea of these methods is: selecting some characteristics of the station area information, firstly clustering various low-voltage station areas, and establishing respective neural network regression models based on each type to obtain a theoretical line loss value. However, the methods are all based on fitting of statistical methods, physical models of the power grid are abandoned, and the interpretability aspect needs to be further enhanced.
Disclosure of Invention
The invention aims to provide a method for calculating line loss of a low-voltage distribution area, which aims to solve the problems of line loss analysis in the prior art, and is based on a physical model, the method obtains the characteristic of virtual line resistance through calculation of measured data, adopts an iForest isolated forest algorithm to detect data outliers, adopts a regression analysis method in machine learning to a large amount of measured data, establishes a line loss estimation model and further estimates the line loss.
The invention provides a method for calculating the line loss of a low-voltage distribution area, which comprises the following steps:
(1) calculating to obtain virtual line resistance according to actually measured voltage, current and electric quantity data of the low-voltage side of the transformer of the low-voltage distribution transformer area;
(2) according to the virtual line resistance obtained through calculation, combining with actually measured electric quantity and current data, carrying out data outlier detection by adopting an iForest isolated forest algorithm to obtain the platform area data of normal points;
(3) after the abnormal values of the data are eliminated, a regression analysis method in machine learning is adopted for a large amount of actually measured data, a line loss estimation model is built, and the line loss of the low-voltage distribution transformer area is obtained.
The invention provides a method for calculating the line loss of a low-voltage distribution station area, which has the characteristics and advantages that:
the method for calculating the line loss of the low-voltage distribution area comprises the steps of firstly, under the condition that the topological structure of a power distribution network and the data of a single user electric meter are unknown, considering the use of measured data, and calculating to obtain the characteristic of virtual line resistance. And adding the measured power supply and sales electricity quantity, current, line loss statistics and other characteristics, and performing data outlier detection by adopting an iForest isolated forest algorithm. After the abnormal values of the data are eliminated, a theoretical line loss estimation model is established for a large amount of actually measured data by adopting a regression analysis method in machine learning, and an estimated line loss value is obtained through calculation. The method provided by the invention gives consideration to interpretability and accuracy and provides reference for line loss management work of the low-voltage distribution network. The method has small calculation amount, thereby reducing the workload, saving the cost, not needing to obtain the network topology of the low-voltage distribution network and a large amount of power consumption data of users at the load side, and only needing to calculate the line loss estimated value by a regression analysis method in machine learning according to the measured data and the power supply and sale quantity of the low-voltage side of the transformer.
Drawings
Fig. 1 is a flow chart of a method for calculating line loss of a low-voltage distribution station area according to the present invention.
Detailed Description
The invention provides a method for calculating the line loss of a low-voltage distribution area, which comprises the following steps:
(1) calculating to obtain virtual line resistance according to actually measured voltage, current and electric quantity data of the low-voltage side of the transformer of the low-voltage distribution transformer area;
(2) according to the virtual line resistance obtained through calculation, combining with actually measured electric quantity and current data, carrying out data outlier detection by adopting an iForest isolated forest algorithm to obtain the platform area data of normal points;
(3) after the abnormal values of the data are eliminated, a regression analysis method in machine learning is adopted for a large amount of actually measured data, a line loss estimation model is built, and the line loss of the low-voltage distribution transformer area is obtained.
The specific flow of the method for calculating the line loss of the low-voltage distribution station area is shown in fig. 1, and the method comprises the following steps:
(1) establishing measured data characteristics:
in different days, a variable virtual line resistance is used for 'equivalence' of different line losses caused by different conditions of user access loads in different days, and meanwhile, daily loads are equivalent to 'total load equivalent resistance';
in units of "day", with low pressureModeling by taking the phase A of the transformer area as an example, wherein the equivalent resistance of the total load changes once per hour and is respectively recorded as R0_A、R1_A…R23_AThe virtual resistance of the line is not changed and is marked as Rline_A(ii) a The active loss of the A phase total load equivalent resistance at the day is the A phase electricity selling quantity at the day:
wherein the subscript t is the sampling time, Wcon_ASelling electricity for distribution area A, It_APhase A current at time t, Rt_AThe proportional relation between the A-phase electricity selling quantity and the three-phase total electricity selling quantity meets the proportional relation between the A-phase active power and the three-phase total active power:
wherein, Wsup_AFor supply of phase A, Wcon_allU, I is the total three-phase electricity sales,
Voltage, current, power factor of the corresponding phase;
according to ohm's law, the voltage, current and power factor of the A phase of the low-voltage distribution area per hour are set up as follows:
the formula (1) and the formula (4) are combined and arranged, and an equation system of the A-phase resistance R of the low-voltage distribution area is obtained as follows:
the R equation set is full rank and has unique solution, the equation set of the resistance R is solved, and the virtual line resistance R of the phase A of the day is obtainedline_AAnd an hourly "overall load equivalent resistance" R0_A、R1_A…R23_A；
Because the unbalanced condition of three phases of loads in a low-voltage distribution area is obvious, the ABC three phases need to be respectively modeled and solved. The modeling solving process of the phase B and the phase C is the same as that of the phase A.
(2) The method adopts an isolated forest algorithm to perform outlier detection on data, and comprises the following steps:
(2-1) constructing a data set: the electricity selling quantity W of the power distribution area obtained from the electricity information acquisition system of the power distribution areacon_ADaily current I at low voltage side of transformert_AThe load equivalent daily resistance R calculated in the step (1)t_AAnd a line dummy resistor Rline_ARespectively taking the line loss rate of the transformer area obtained on the synchronous line loss management platform as an original sample set X;
(2-2) training the original sample set of step (2-1), comprising the steps of:
(2-2-1) randomly extracting psi sample points X from an original sample set X, constructing an isolated tree iTree by using the psi sample points X, and setting T as one node in the isolated tree iTree, T as an external node in the isolated tree iTree without sub-nodes, or T with two sub-nodeslAnd TrThe inner nodes in the orphan tree iTree;
(2-2-2) discriminating the sample of the node T based on a randomly assigned attribute q and a randomly assigned segmentation point p, if q is q, determining the sample of the node T<p, then the sample point x is divided into the left branch T of the current node TlIf q is more than or equal to p, the sample point x is divided into the right branch T of the current node TrNamely, a hyperplane is generated at the segmentation point p, and the data space of the current node T is segmented into two subspaces;
(2-2-3) setting a depth threshold of the isolated tree iTree, and repeating the steps (2-2-1) to (2-2-2) until the depth of the isolated tree iTree reaches the depth threshold, or only one sample point exists under each node and no sub-node exists;
(2-2-4) the path length h (x) of the sample point x in the isolated tree is the number of edges of the sample point x from the root node of the iTree to the leaf node, i isolated trees are formed by symbiosis, and an isolated forest is formed;
(2-3) evaluating the isolated forest generated in the step (2-2), comprising the following steps:
(2-3-1) traversing each isolated tree iTree in the solitary forest for each sample point x to be evaluated in the step (2-2), respectively calculating the height h (x) of the sample point x in each isolated tree iTree, calculating the average height E (h (x)) of the sample point x in the solitary forest, and calculating the abnormal value fraction of the sample point x according to the average height E (h (x)):
score_sample＝-s(x,ψ)＝-2^(E(h(x))/c(ψ))(6)
wherein ^ is a power exponent operator, E (h (x)) is an expectation of the isolated book height h (x), and c (ψ) is an average of the training sample path lengths when the number ψ of samples is selected in step (2-2-1); because of the small number of outliers and the interspersion with most samples, outliers are isolated earlier, i.e., outliers are closer to the root node of the iTree, while normal values are farther from the root node. When the abnormal value score is closer to-1, the possibility of being an abnormal sample is higher; the closer the outlier score is to 0, the greater the likelihood of being a normal sample.
(2-3-2) selling electric quantity W by the power distribution station area in the step (2-1) respectivelycon_ALow-voltage side daily current I of transformer of low-voltage distribution transformer areat_AThe load equivalent daily resistance R calculated in the step (1)t_AAnd a line dummy resistor Rline_AAs an index, performing outlier detection by using an isolated forest algorithm, namely setting a quantile of 10% as a percentage value for distinguishing normality from abnormality to perform data detection when performing final normal abnormality judgment on the sample point to be evaluated in the step (2-2), namely selecting the first 10% of abnormal value which is closest to-1 as an abnormal value, and removing the abnormal value to obtain the station area data of the normal value;
(3) establishing a line loss estimation model:
after outliers are removed from the power distribution area data in the step (1), a regression analysis method is adopted, and a line loss estimation model is established as follows:
Y＝ω1×Wcon_all+ω2×It+ω3×Rline+b
in the formula, Y is the line loss rate of the distribution station area, omega1、ω2、ω3And b is the model coefficient, Wcon_allFor total electricity sales in the distribution area, ItFor the mean value of the daily current at the low-voltage side of the transformer in the distribution transformer area, RlineAnd the three-phase mean value of the virtual resistance of the line of the power distribution station area is obtained.
Randomly selecting 80% of data from the station area normal value data obtained in the step (2-3-2) as a training set of the line loss estimation model, and fitting the station area line loss estimation model to obtain a line loss estimation model coefficient omega1、ω2、ω3And b, taking 20% of data as a test set of the line loss estimation model, testing the line loss estimation model, and adjusting the model coefficient omega according to the test result1、ω2、ω3B, obtaining a final model coefficient result, and further obtaining a line loss estimation model;
(4) based on the real-time acquisition's low pressure distribution station area measured data, calculate the line loss in low pressure distribution station area:
the total electricity selling quantity W of the power distribution area acquired by the power utilization information acquisition system of the power distribution areacon_allAverage daily current value I of low-voltage side of transformertThe three-phase mean value R of the virtual resistance of the line calculated in the step (1)lineAnd (3) after the outlier is detected and removed in the step (2), inputting the data into the power distribution area line loss estimation model established in the step (3), and outputting the line loss rate Y of the low-voltage power distribution area by the line loss estimation model. The method of the invention obtains the line loss rate of the distribution room which is more accurate than the line loss statistics, and the calculation process is faster and more convenient.
Claims (2)
1. A method for calculating line loss of a low-voltage distribution area is characterized by comprising the following steps:
(1) calculating to obtain virtual line resistance according to actually measured voltage, current and electric quantity data of the low-voltage side of the transformer of the low-voltage distribution transformer area;
(2) according to the virtual line resistance obtained through calculation, combining with actually measured electric quantity and current data, carrying out data outlier detection by adopting an iForest isolated forest algorithm to obtain the platform area data of normal points;
(3) after the abnormal values of the data are eliminated, a regression analysis method in machine learning is adopted for a large amount of actually measured data, a line loss estimation model is built, and the line loss of the low-voltage distribution transformer area is obtained.
2. A method for calculating line loss of a low-voltage distribution area is characterized by comprising the following steps:
(1) establishing measured data characteristics:
in different days, a variable virtual line resistance is used for 'equivalence' of different line losses caused by different conditions of user access loads in different days, and meanwhile, daily loads are equivalent to 'total load equivalent resistance';
taking the day as a unit and taking the A phase of the low-voltage distribution area as an example for modeling, the equivalent resistance of the total load changes once every hour and is respectively recorded as R0_A、R1_A…R23_AThe virtual resistance of the line is not changed and is marked as Rline_A(ii) a The active loss of the A phase total load equivalent resistance at the day is the A phase electricity selling quantity at the day:
wherein the subscript t is the sampling time, Wcon_ASelling electricity for distribution area A, It_APhase A current at time t, Rt_AThe proportional relation between the A-phase electricity selling quantity and the three-phase total electricity selling quantity meets the proportional relation between the A-phase active power and the three-phase total active power:
wherein, Wsup_AFor supply of phase A, Wcon_allU, I is the total three-phase electricity sales,
Voltage, current, power factor of the corresponding phase;
according to ohm's law, the voltage, current and power factor of the A phase of the low-voltage distribution area per hour are set up as follows:
the formula (1) and the formula (4) are combined and arranged, and an equation system of the A-phase resistance R of the low-voltage distribution area is obtained as follows:
the R equation set is full rank and has unique solution, the equation set of the resistance R is solved, and the virtual line resistance R of the phase A of the day is obtainedline_AAnd an hourly "overall load equivalent resistance" R0_A、R1_A…R23_A；
(2) The method adopts an isolated forest algorithm to perform outlier detection on data, and comprises the following steps:
(2-1) constructing a data set: the electricity selling quantity W of the power distribution area obtained from the electricity information acquisition system of the power distribution areacon_ADaily current I at low voltage side of transformert_AThe load equivalent daily resistance R calculated in the step (1)t_AAnd a line dummy resistor Rline_ARespectively obtained on the same period line loss management platformTaking the line loss rate of the transformer area as an original sample set X;
(2-2) training the original sample set of step (2-1), comprising the steps of:
(2-2-1) randomly extracting psi sample points X from an original sample set X, constructing an isolated tree iTree by using the psi sample points X, and setting T as one node in the isolated tree iTree, T as an external node in the isolated tree iTree without sub-nodes, or T with two sub-nodeslAnd TrThe inner nodes in the orphan tree iTree;
(2-2-2) discriminating the sample of the node T based on a randomly assigned attribute q and a randomly assigned segmentation point p, if q is q, determining the sample of the node T<p, then the sample point x is divided into the left branch T of the current node TlIf q is more than or equal to p, the sample point x is divided into the right branch T of the current node TrNamely, a hyperplane is generated at the segmentation point p, and the data space of the current node T is segmented into two subspaces;
(2-2-3) setting a depth threshold of the isolated tree iTree, and repeating the steps (2-2-1) to (2-2-2) until the depth of the isolated tree iTree reaches the depth threshold, or only one sample point exists under each node and no sub-node exists;
(2-2-4) the path length h (x) of the sample point x in the isolated tree is the number of edges of the sample point x from the root node of the iTree to the leaf node, i isolated trees are formed by symbiosis, and an isolated forest is formed;
(2-3) evaluating the isolated forest generated in the step (2-2), comprising the following steps:
(2-3-1) traversing each isolated tree iTree in the solitary forest for each sample point x to be evaluated in the step (2-2), respectively calculating the height h (x) of the sample point x in each isolated tree iTree, calculating the average height E (h (x)) of the sample point x in the solitary forest, and calculating the abnormal value fraction of the sample point x according to the average height E (h (x)):
score_sample＝-s(x,ψ)＝-2^(E(h(x))/c(ψ)) (6)
wherein ^ is a power exponent operator, E (h (x)) is an expectation of the isolated book height h (x), and c (ψ) is an average of the training sample path lengths when the number ψ of samples is selected in step (2-2-1);
(2-3-2) selling electric quantity W by the power distribution station area in the step (2-1) respectivelycon_ALow-voltage side daily current I of transformer of low-voltage distribution transformer areat_AThe load equivalent daily resistance R calculated in the step (1)t_AAnd a line dummy resistor Rline_AAs an index, performing outlier detection by using an isolated forest algorithm, namely setting a quantile of 10% as a percentage value for distinguishing normality from abnormality to perform data detection when performing final normal abnormality judgment on the sample point to be evaluated in the step (2-2), namely selecting the first 10% of abnormal value which is closest to-1 as an abnormal value, and removing the abnormal value to obtain the station area data of the normal value;
(3) establishing a line loss estimation model:
after outliers are removed from the power distribution area data in the step (1), a regression analysis method is adopted, and a line loss estimation model is established as follows:
Y＝ω1×Wcon_all+ω2×It+ω3×Rline+b
in the formula, Y is the line loss rate of the distribution station area, omega1、ω2、ω3And b is the model coefficient, Wcon_allFor total electricity sales in the distribution area, ItFor the mean value of the daily current at the low-voltage side of the transformer in the distribution transformer area, RlineAnd the three-phase mean value of the virtual resistance of the line of the power distribution station area is obtained.
Randomly selecting 80% of data from the station area normal value data obtained in the step (2-3-2) as a training set of the line loss estimation model, and fitting the station area line loss estimation model to obtain a line loss estimation model coefficient omega1、ω2、ω3And b, taking 20% of data as a test set of the line loss estimation model, testing the line loss estimation model, and adjusting the model coefficient omega according to the test result1、ω2、ω3B, obtaining a final model coefficient result, and further obtaining a line loss estimation model;
(4) based on the real-time acquisition's low pressure distribution station area measured data, calculate the line loss in low pressure distribution station area:
the total electricity selling quantity W of the power distribution area acquired by the power utilization information acquisition system of the power distribution areacon_allAverage daily current value I of low-voltage side of transformertThe three-phase mean value R of the virtual resistance of the line calculated in the step (1)lineAnd (3) after the outlier is detected and removed in the step (2), inputting the data into the power distribution area line loss estimation model established in the step (3), and outputting the line loss rate Y of the low-voltage power distribution area by the line loss estimation model.
Priority Applications (1)
| Application Number | Priority Date | Filing Date | Title |
|---|---|---|---|
| CN202110452787.5A CN113224748A (en) | 2021-04-26 | 2021-04-26 | Method for calculating line loss of low-voltage distribution station area |
Applications Claiming Priority (1)
| Application Number | Priority Date | Filing Date | Title |
|---|---|---|---|
| CN202110452787.5A CN113224748A (en) | 2021-04-26 | 2021-04-26 | Method for calculating line loss of low-voltage distribution station area |
Publications (1)
| Publication Number | Publication Date |
|---|---|
| CN113224748A true CN113224748A (en) | 2021-08-06 |
Family
ID=77089060
Family Applications (1)
| Application Number | Title | Priority Date | Filing Date |
|---|---|---|---|
| CN202110452787.5A Pending CN113224748A (en) | 2021-04-26 | 2021-04-26 | Method for calculating line loss of low-voltage distribution station area |
Country Status (1)
| Country | Link |
|---|---|
| CN (1) | CN113224748A (en) |
Cited By (1)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN114609480A (en) * | 2022-05-16 | 2022-06-10 | 国网四川省电力公司电力科学研究院 | Power grid loss abnormal data detection method, system, terminal and medium |
-
2021
- 2021-04-26 CN CN202110452787.5A patent/CN113224748A/en active Pending
Cited By (2)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN114609480A (en) * | 2022-05-16 | 2022-06-10 | 国网四川省电力公司电力科学研究院 | Power grid loss abnormal data detection method, system, terminal and medium |
| CN114609480B (en) * | 2022-05-16 | 2022-08-16 | 国网四川省电力公司电力科学研究院 | Power grid loss abnormal data detection method, system, terminal and medium |
Similar Documents
| Publication | Publication Date | Title |
|---|---|---|
| CN103476051B (en) | A kind of communication net node importance evaluation method | |
| CN107169628B (en) | Power distribution network reliability assessment method based on big data mutual information attribute reduction | |
| CN112149873B (en) | Low-voltage station line loss reasonable interval prediction method based on deep learning | |
| CN106372747B (en) | Random forest-based reasonable line loss rate estimation method for transformer area | |
| CN102999791A (en) | Power load forecasting method based on customer segmentation in power industry | |
| CN114519514B (en) | Low-voltage transformer area reasonable line loss value measuring and calculating method, system and computer equipment | |
| CN103514368B (en) | Real-time and stage theory line loss fast estimation method with clustering technique adopted | |
| CN113723844B (en) | Low-voltage station theoretical line loss calculation method based on ensemble learning | |
| CN106570779A (en) | DC power distribution network reliability analysis method and system | |
| CN113189418B (en) | Topological relation identification method based on voltage data | |
| CN109242174A (en) | A kind of adaptive division methods of seaonal load based on decision tree | |
| CN114021433A (en) | Construction method and application of dominant instability mode recognition model of power system | |
| CN111654392A (en) | Low-voltage distribution network topology identification method and system based on mutual information | |
| CN111709668A (en) | Power grid equipment parameter risk identification method and device based on data mining technology | |
| CN116148753A (en) | Intelligent electric energy meter operation error monitoring system | |
| CN113224748A (en) | Method for calculating line loss of low-voltage distribution station area | |
| CN107742883A (en) | A kind of power system topology island system for rapidly identifying and method based on Spark | |
| CN107122919A (en) | A kind of distribution efficiency estimation method and system based on intelligence operation | |
| Perez et al. | Suitability of voltage stability study methods for real-time assessment | |
| CN109684749B (en) | Photovoltaic power station equivalent modeling method considering operating characteristics | |
| CN112508254A (en) | Method for determining investment prediction data of transformer substation engineering project | |
| CN113949079B (en) | Power distribution station user three-phase unbalance prediction optimization method based on deep learning | |
| CN112103950A (en) | Power grid partitioning method based on improved GN splitting algorithm | |
| Zhang et al. | Analysis of influencing factors of transmission line loss based on GBDT algorithm | |
| CN115600494A (en) | Low-voltage distribution area topology automatic identification method and device |
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 |