CN115618229A - Line loss allocation algorithm based on big data - Google Patents
Line loss allocation algorithm based on big data Download PDFInfo
- Publication number
- CN115618229A CN115618229A CN202211302552.9A CN202211302552A CN115618229A CN 115618229 A CN115618229 A CN 115618229A CN 202211302552 A CN202211302552 A CN 202211302552A CN 115618229 A CN115618229 A CN 115618229A
- Authority
- CN
- China
- Prior art keywords
- data
- line loss
- clustering
- average
- big
- 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
- 238000010606 normalization Methods 0.000 claims abstract description 9
- 230000002159 abnormal effect Effects 0.000 claims abstract description 3
- 238000001914 filtration Methods 0.000 claims abstract description 3
- 238000004364 calculation method Methods 0.000 claims description 18
- 230000001419 dependent effect Effects 0.000 claims description 6
- 238000000034 method Methods 0.000 description 6
- 238000003064 k means clustering Methods 0.000 description 5
- 230000007480 spreading Effects 0.000 description 2
- 230000004075 alteration Effects 0.000 description 1
- 238000004458 analytical method Methods 0.000 description 1
- 230000001174 ascending effect Effects 0.000 description 1
- 230000009286 beneficial effect Effects 0.000 description 1
- 238000007405 data analysis Methods 0.000 description 1
- 230000007547 defect Effects 0.000 description 1
- 238000010586 diagram Methods 0.000 description 1
- 230000000694 effects Effects 0.000 description 1
- 238000005516 engineering process Methods 0.000 description 1
- 238000012986 modification Methods 0.000 description 1
- 230000004048 modification Effects 0.000 description 1
- 230000001737 promoting effect Effects 0.000 description 1
- 230000009467 reduction Effects 0.000 description 1
- 238000013468 resource allocation Methods 0.000 description 1
- 238000012163 sequencing technique Methods 0.000 description 1
- 238000006467 substitution reaction Methods 0.000 description 1
- 230000002123 temporal effect Effects 0.000 description 1
- 230000000007 visual effect Effects 0.000 description 1
Images
Classifications
-
- 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
Landscapes
- Engineering & Computer Science (AREA)
- Physics & Mathematics (AREA)
- Data Mining & Analysis (AREA)
- General Physics & Mathematics (AREA)
- Mathematical Optimization (AREA)
- Pure & Applied Mathematics (AREA)
- Theoretical Computer Science (AREA)
- Mathematical Physics (AREA)
- Computational Mathematics (AREA)
- Mathematical Analysis (AREA)
- Life Sciences & Earth Sciences (AREA)
- Operations Research (AREA)
- Probability & Statistics with Applications (AREA)
- Bioinformatics & Cheminformatics (AREA)
- Algebra (AREA)
- Evolutionary Biology (AREA)
- Databases & Information Systems (AREA)
- Software Systems (AREA)
- General Engineering & Computer Science (AREA)
- Bioinformatics & Computational Biology (AREA)
- Management, Administration, Business Operations System, And Electronic Commerce (AREA)
Abstract
The invention discloses a line loss allocation algorithm based on big data, which comprises the following steps: data normalization: extracting the electrical characteristics of the data, integrating the data through a normalization method, and filtering abnormal points; data clustering: setting a clustering number k, and calculating a profile coefficient St; determining a sample center; clustering the time intervals based on historical data; line loss sharing: in different categories, the clustering center is used as a standard to respectively calculate the correlation coefficient of each allocation main body about line loss, and determine the allocation proportion.
Description
Technical Field
The invention relates to the technical field of line loss allocation calculation methods, in particular to a line loss allocation algorithm based on big data.
Background
In the current electric power system, the network structure of the power grid is complex, line loss sharing calculation is performed through early simple calculation methods such as electric quantity sharing and load flow calculation methods, the calculation result precision is poor, and a large space is provided in the aspect of improving the line loss calculation result precision.
Disclosure of Invention
The invention aims to overcome the defects in the prior art, provides a line loss allocation algorithm based on big data, can realize fair, reasonable and visual line loss allocation calculation, and plays an important promoting role in economic operation of a regional power grid, reduction of the network loss of the regional power grid, effective exertion of resource allocation advantages and the like.
In order to achieve the purpose, the invention provides the following technical scheme: a line loss allocation algorithm based on big data comprises the following steps:
data normalization: extracting the electrical characteristics of the data, integrating the data through a normalization method, and filtering abnormal points;
data clustering:
setting a clustering number k, and calculating a profile coefficient St;
determining a sample center;
clustering the time intervals based on historical data;
line loss sharing: in different categories, the clustering center is used as a standard to respectively calculate the correlation coefficient of each apportionment main body about the line loss, and the apportionment proportion is determined.
In the data clustering, k is increased from 3 to 8, and the contour coefficients St are respectively calculated; and selecting the clustering number k corresponding to the maximum value of the profile coefficient St for clustering.
In a preferred embodiment of the present invention, each sample in the data normalization contains 5 independent variables and 1 dependent variable; the independent variables comprise a power output average value X1, a power output variance X2, a load average value X3, a load variance X4 and a line average load rate X5, and the dependent variable is a line loss rate.
In a preferred embodiment of the present invention, in the data cluster,
contour coefficients S (i) = (b (i) -a (i))/(maxa (i), b (i));
wherein
a (i) average distance of other samples in the cluster to which i belongs, and if only i samples are in the cluster, let s (i) =0
i∈A,a(i)=average j∈A,j≠i (dist(i,j))
Minimum of average distances of i from samples of other clusters
i∈A,C≠A,dist(i,C)=averagej∈C(dist(i,j))
b(i)=minc≠Adist(i,C)
Contour coefficient of cluster population: average of all sample contour coefficients
As a preferred technical scheme of the invention, a correlation coefficient calculation formula in the line loss sharing is as follows
Wherein Cov (Xi, Y) is covariance of X and Y, var [ Xi ] is variance of Xi, var [ Y ] is variance of Y, and Y is the clustering center.
Compared with the prior art, the invention has the beneficial effects that: the traditional line loss allocation method has the prominent problem of calculation accuracy and poor adaptability to different transaction modes. The line loss sharing algorithm based on the big data can adapt to all power grid structures, the calculation precision is effectively improved, although the calculation amount of the method is greatly increased due to the huge data amount, the calculation precision of the calculation method can be greatly improved, and the calculation time is not much different from that of the original method.
Drawings
FIG. 1 is a logic diagram of the present invention.
Detailed Description
The technical solutions in the embodiments of the present invention will be clearly and completely described below with reference to the drawings in the embodiments of the present invention, and it is obvious that the described embodiments are only a part of the embodiments of the present invention, and not all of the embodiments. All other embodiments, which can be derived by a person skilled in the art from the embodiments given herein without making any creative effort, shall fall within the protection scope of the present invention.
When the running state of the power system is known, the apportionment scale factor can be calculated according to the load flow tracking, but a plurality of sections with load flow data lost exist, and the load flow tracking method cannot effectively calculate;
referring to fig. 1, the present invention provides a technical solution: a line loss allocation algorithm based on big data introduces big data analysis technology to determine allocation scale factors.
600 samples are selected, and each sample data comprises 5 independent variables and 1 dependent variable. X1 (MW) is the power output average value, X2 is the power output variance, X3 (MW) is the load average value, X4 is the load variance, X5 (%) is the line average load rate, and the line loss rate is the dependent variable. The application steps are as follows:
(1) And extracting the electrical characteristic indexes and carrying out standardization processing.
(2) And classifying the samples by adopting an improved K-Means clustering method.
1) Determining the number of clusters in a time section
And clustering 600 groups of standardized time sections by using the improved K-Means clustering algorithm. And calculating the performance index PE of each sample according to the normalized data, and further sequencing the samples in an ascending order according to the PE values. The results of the ranking are shown in table 1.
TABLE 1 PE values for the zones
As can be seen from Table 1, the value of PE is in the range of 0.6 to 11.5.
In order to determine the optimal number of clustering centers, the initial clustering number k is increased from 3 to 8, the total profile coefficient St of the clustering result under the corresponding k value is respectively calculated, and the calculation result is shown in Table 2.
TABLE 2 Total Profile coefficients of clustering results at different k values
St comparison shows that when the clustering number k is 6, the total contour coefficient of the clustering result is the largest, and the clustering effect is the best. Therefore an initial cluster number of 6 is chosen here.
2) Determining sample centers for clustering
The samples sorted according to PE were equally divided into 6 classes, and the center sample of each class was selected as the initial clustering center, as shown in table 3.
TABLE 3 initial clustering center
3) Clustering temporal discontinuities based on historical data
The samples were subjected to K-Means clustering analysis, and the clustering results are shown in Table 4.
TABLE 4 number of samples contained in each class
The first class has 155 samples, the second class has 305 samples, the third class has 9 samples, the fourth class has 39 samples, the fifth class has 84 samples, and the sixth class has 8 samples, for a total of 601 samples.
(3) And respectively calculating the correlation coefficient of each apportionment main body about the line loss by taking the clustering center as a standard in different categories, and determining the apportionment proportion.
After the sample data is clustered by using an improved K-means clustering method, the apportionment proportion under each category is based on the calculation result of a clustering center. Since the selected sample apportionment main body includes three power sources and nine load centers, it is necessary to calculate the correlation coefficient between each apportionment main body and the line loss under the clustering center. The calculation results are shown in table 5:
TABLE 5 correlation coefficient table of each apportioned body and line loss
After normalization, the spreading ratios of the respective spreading bodies can be obtained as shown in table 6, for example:
table 6 apportionment ratio table of each apportioned body
Table 6 shows the apportionment scale factors of the six-cluster centers, and for the time section to be given, the category of the time section can be determined by adopting K-means clustering, and then the line loss can be apportioned according to the apportionment scale factors of the corresponding categories in table 6.
Although embodiments of the present invention have been shown and described, it will be appreciated by those skilled in the art that changes, modifications, substitutions and alterations can be made in these embodiments without departing from the principles and spirit of the invention, the scope of which is defined in the appended claims and their equivalents.
Claims (5)
1. A line loss allocation algorithm based on big data is characterized by comprising the following steps:
data normalization: extracting the electrical characteristics of the data, integrating the data through a normalization method, and filtering abnormal points;
data clustering:
setting a clustering number k, and calculating a profile coefficient St;
determining a sample center;
clustering the time slots based on historical data;
line loss sharing: in different categories, the clustering center is used as a standard to respectively calculate the correlation coefficient of each apportionment main body about the line loss, and the apportionment proportion is determined.
2. The big-data based line loss sharing algorithm according to claim 1, wherein: in the data clustering, k is increased from 3 to 8, and contour coefficients St are respectively calculated; and selecting the clustering number k corresponding to the maximum value of the profile coefficient St for clustering.
3. The big-data based line loss sharing algorithm of claim 1, wherein: in the data normalization, each sample contains 5 independent variables and 1 dependent variable; the independent variables comprise a power output average value X1, a power output variance X2, a load average value X3, a load variance X4 and a line average load rate X5, and the dependent variable is a line loss rate.
4. The big-data based line loss sharing algorithm of claim 1, wherein: in the cluster of data, the data is classified into a plurality of classes,
contour coefficients S (i) = (b (i) -a (i))/(maxa (i), b (i)) of a single sample i;
wherein
a (i) average distance of other samples in the cluster to which i belongs, and if only i is one sample in the cluster, let s (i) =0
i∈A,a(i)=average j∈A,j≠i (dist(i,j))
b (i) minimum of average distances of i from samples of other clusters
i∈A,C≠A,dist(i,C)=average j∈C (dist(i,j))
b(i)=min C≠A dist(i,C)
Contour coefficient of cluster population: average of all sample contour coefficients
5. The big-data based line loss sharing algorithm according to claim 1, wherein: the calculation formula of the correlation coefficient in the line loss sharing is as follows
Wherein Cov (Xi, Y) is covariance of X and Y, var [ Xi ] is variance of Xi, var [ Y ] is variance of Y, and Y is the clustering center.
Priority Applications (1)
Application Number | Priority Date | Filing Date | Title |
---|---|---|---|
CN202211302552.9A CN115618229A (en) | 2022-10-24 | 2022-10-24 | Line loss allocation algorithm based on big data |
Applications Claiming Priority (1)
Application Number | Priority Date | Filing Date | Title |
---|---|---|---|
CN202211302552.9A CN115618229A (en) | 2022-10-24 | 2022-10-24 | Line loss allocation algorithm based on big data |
Publications (1)
Publication Number | Publication Date |
---|---|
CN115618229A true CN115618229A (en) | 2023-01-17 |
Family
ID=84863872
Family Applications (1)
Application Number | Title | Priority Date | Filing Date |
---|---|---|---|
CN202211302552.9A Pending CN115618229A (en) | 2022-10-24 | 2022-10-24 | Line loss allocation algorithm based on big data |
Country Status (1)
Country | Link |
---|---|
CN (1) | CN115618229A (en) |
Cited By (1)
Publication number | Priority date | Publication date | Assignee | Title |
---|---|---|---|---|
CN116910602A (en) * | 2023-09-14 | 2023-10-20 | 广东电网有限责任公司 | Line loss analysis method and system based on relevance analysis |
-
2022
- 2022-10-24 CN CN202211302552.9A patent/CN115618229A/en active Pending
Cited By (2)
Publication number | Priority date | Publication date | Assignee | Title |
---|---|---|---|---|
CN116910602A (en) * | 2023-09-14 | 2023-10-20 | 广东电网有限责任公司 | Line loss analysis method and system based on relevance analysis |
CN116910602B (en) * | 2023-09-14 | 2024-01-19 | 广东电网有限责任公司 | Line loss analysis method and system based on relevance analysis |
Similar Documents
Publication | Publication Date | Title |
---|---|---|
CN108020752B (en) | Distribution line loss diagnosis method and system based on multi-source through correlation | |
CN113267692B (en) | Low-voltage transformer area line loss intelligent diagnosis and analysis method and system | |
CN110781332A (en) | Electric power resident user daily load curve clustering method based on composite clustering algorithm | |
CN106372747B (en) | Random forest-based reasonable line loss rate estimation method for transformer area | |
CN111126429A (en) | Low-voltage distribution area user access point identification method based on PCA (principal component analysis) degradation and K-Means clustering | |
CN111817291A (en) | Low-voltage transformer area household relation identification method based on voltage correlation characteristics | |
CN111612053A (en) | Calculation method for reasonable interval of line loss rate | |
CN115618229A (en) | Line loss allocation algorithm based on big data | |
CN112001441A (en) | Power distribution network line loss anomaly detection method based on Kmeans-AHC hybrid clustering algorithm | |
CN112510817A (en) | Intelligent identification method for low-voltage topological relation of transformer area | |
CN113159106A (en) | Load curve clustering method, medium and equipment based on morphological trend characteristics | |
CN107730399B (en) | Theoretical line loss evaluation method based on wind power generation characteristic curve | |
CN116049705A (en) | Clustering analysis-based power system user load characteristic clustering method and system | |
CN114611738A (en) | Load prediction method based on user electricity consumption behavior analysis | |
CN111259965A (en) | Method and system for carrying out mean value clustering on electrical characteristic data based on dimension reduction | |
Li et al. | Time series prediction of wireless network traffic flow based on wavelet analysis and BP neural network | |
CN111340645B (en) | Improved association analysis method for power load | |
CN114897097A (en) | Power consumer portrait method, device, equipment and medium | |
CN114266457A (en) | Method for detecting different loss inducement of distribution line | |
CN113112177A (en) | Transformer area line loss processing method and system based on mixed indexes | |
CN112415304B (en) | Line identification method based on low-voltage transformer area voltage data curve grouping | |
CN113706034A (en) | Method for determining matching relationship between water resource and social economy based on rank difference | |
CN116304537B (en) | Electricity larceny user checking method based on intelligent measuring terminal | |
CN112464059A (en) | Power distribution network user classification method and device, computer equipment and storage medium | |
CN112508254A (en) | Method for determining investment prediction data of transformer substation engineering project |
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 |