CN104318489B - Transformer grouping method based on load characteristic analysis - Google Patents
Transformer grouping method based on load characteristic analysis Download PDFInfo
- Publication number
- CN104318489B CN104318489B CN201410564530.9A CN201410564530A CN104318489B CN 104318489 B CN104318489 B CN 104318489B CN 201410564530 A CN201410564530 A CN 201410564530A CN 104318489 B CN104318489 B CN 104318489B
- Authority
- CN
- China
- Prior art keywords
- load
- load factor
- transformator
- num
- central point
- Prior art date
- Legal status (The legal status is an assumption and is not a legal conclusion. Google has not performed a legal analysis and makes no representation as to the accuracy of the status listed.)
- Active
Links
- 238000004458 analytical method Methods 0.000 title claims abstract description 31
- 238000000034 method Methods 0.000 title claims abstract description 20
- 230000009467 reduction Effects 0.000 claims abstract description 10
- 238000012545 processing Methods 0.000 claims abstract description 5
- 239000000284 extract Substances 0.000 claims description 8
- 238000000605 extraction Methods 0.000 claims description 2
- 238000012163 sequencing technique Methods 0.000 claims 1
- 238000004364 calculation method Methods 0.000 abstract 1
- 101100517651 Caenorhabditis elegans num-1 gene Proteins 0.000 description 2
- 230000009466 transformation Effects 0.000 description 2
- PEDCQBHIVMGVHV-UHFFFAOYSA-N Glycerine Chemical compound OCC(O)CO PEDCQBHIVMGVHV-UHFFFAOYSA-N 0.000 description 1
- 230000008901 benefit Effects 0.000 description 1
- 230000015572 biosynthetic process Effects 0.000 description 1
- 150000001875 compounds Chemical class 0.000 description 1
- 238000011161 development Methods 0.000 description 1
- 239000006185 dispersion Substances 0.000 description 1
- 230000006872 improvement Effects 0.000 description 1
- 238000012544 monitoring process Methods 0.000 description 1
- 230000008569 process Effects 0.000 description 1
- 238000012360 testing method Methods 0.000 description 1
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
- G06Q50/00—Information and communication technology [ICT] specially adapted for implementation of business processes of specific business sectors, e.g. utilities or tourism
- G06Q50/06—Energy or water supply
-
- G—PHYSICS
- G16—INFORMATION AND COMMUNICATION TECHNOLOGY [ICT] SPECIALLY ADAPTED FOR SPECIFIC APPLICATION FIELDS
- G16Z—INFORMATION AND COMMUNICATION TECHNOLOGY [ICT] SPECIALLY ADAPTED FOR SPECIFIC APPLICATION FIELDS, NOT OTHERWISE PROVIDED FOR
- G16Z99/00—Subject matter not provided for in other main groups of this subclass
Landscapes
- Business, Economics & Management (AREA)
- Health & Medical Sciences (AREA)
- Engineering & Computer Science (AREA)
- Economics (AREA)
- Public Health (AREA)
- Water Supply & Treatment (AREA)
- General Health & Medical Sciences (AREA)
- Human Resources & Organizations (AREA)
- Marketing (AREA)
- Primary Health Care (AREA)
- Strategic Management (AREA)
- Tourism & Hospitality (AREA)
- Physics & Mathematics (AREA)
- General Business, Economics & Management (AREA)
- General Physics & Mathematics (AREA)
- Theoretical Computer Science (AREA)
- Supply And Distribution Of Alternating Current (AREA)
Abstract
Disclosed is a transformer grouping method based on load characteristic analysis. The transformer grouping method based on load characteristic analysis includes the following steps that firstly, transformer load data are processed to form load rate data, and dimensionality reduction is performed to extract three transformer load characteristics such as annual average load rate, load rate fluctuation and load rate trend; then transformer load characteristic samples are formed through index calculation, and a characteristic sample set is subjected to standardization and to clustering grouping processing by a k-medoids algorithm; finally, grouping results are subjected to characteristic analysis. The transformer grouping method based on load characteristic analysis is provided in consideration of differences of different transformer load characteristics, transformer operation grouping results and suggestions are obtained, and a technological means is provided for grasping transformer economical operation conditions and trends.
Description
Technical field
The present invention relates to a kind of by setting up transformer load characteristic index and the side that transformer load divides group being realized with this
Method.
Background technology
Development with social economy and the continuous improvement of industrial economy benefit consciousness, reduce loss, saves energy are
It is increasingly becoming power supply industry focus of attention problem.Therefore, controlled using the economical operation that technological means realize transformator, to fall
Low-loss, saves energy are of great practical significance.Wherein, the load characteristic of analysis transformator is that transformator is carried out
The basis that economical operation controls.
Traditional Example of Transformer Economical Run, mainly according to transformer technology parameter, in conjunction with actual load situation, passes through
The size of load factor simply judges transformer economic operation situation.The method can reflect the current running status of transformator, but
It is difficult to definitely reflect account of the history and the future trends of load, the analysis method of its load factor also only reflects averagely negative
The relation of load rate and maximum load rate, the intensity of load, the low ebb loading condition running without reflection, the dispersion of load
Degree, therefore, it is necessary to comprehensively be analyzed to transformer load rate, seeks the feature of more scientific ground reflected load situation
Amount, carries out Rational Classification to the performance driving economy of transformator, and can with this according to the reasonable operation compound mode arranging transformator,
Effectively improve the economy of transformer station high-voltage side bus in local distribution network, reduce the overall electric energy loss of distribution network system.
Content of the invention
The technical problem to be solved is the load data according to transformator, analysis transformator running status with
And future load trend.
Solve above-mentioned technical problem, the technical solution used in the present invention is to calculate load factor according to transformer load data
Data simultaneously extracts the load characteristic of transformator, further according to load characteristic to a transformator cluster point group, analyzes the inside of each point of group
Feature, identifies each point of group's running state of transformer.
The a kind of of the present invention specifically includes following steps based on the transformator grouping method of load characteristic analysis：
Step 1：Using transformer load data computational load rate data；
Step 2：Through Data Dimensionality Reduction, load factor data processing is obtained per day load factor；
Step 3：Extract transformer load feature, obtain annual load factor, load factor fluctuation and load factor trend, formed
Feature samples collection；
Step 4：Feature samples collection is standardized, then carries out transformer load k-medoids cluster point group；
Step 5：Feature analysiss are carried out to grouping result.
Load data in described step 1 include that P_H- high-pressure side is active, Q_H- high-pressure side is idle and monitoring when
Between t；
Described load factor data is the capacity V and load factor computing formula according to transformator
It is calculated load factor the data sequence { (f of transformator1,t1),(f2,t2),…,(fs,ts), wherein t1,t2,…,tsBe according to
The ordered arrangement that time order and function order is carried out, (fi,ti) represent in tiThe load factor of moment transformator is fi.
The Data Dimensionality Reduction of described step 2 is in units of sky, calculates the daily Rate of average load of each transformator, within the next few days
Rate of average load
The extraction transformer load feature of described step 3 is specially：The annual load factor of one transformator, load factor
The computing formula of fluctuation and load factor trend is respectively：
(1) annual load factorDay_fjIt is the per day load factor in jth sky；
(2) load factor fluctuation
(3) calculating of load factor trend is divided into two steps：
The first step：Calculate the monthly average load factor in each month：Day_fj, wherein ml is l
The natural law of the moon；
Second step：Fitting a straight line is carried out with the monthly average load factor of the 1-12 month, obtains the slope of this straight line, as load factor
TrendWherein
Calculate the characteristic index value of all transformators, form feature samples collection.
Described step 4 feature samples collection is standardized for：
Each characteristic index is standardized, standardization formula is as follows：
Annual load factor after standardization Wherein
Load factor fluctuation after standardizationWherein
Load factor trend after standardizationWherein
The transformer load k-medoids Cluster Classification of described step 4 comprises following sub-step：
S4.1：Randomly choose k transformator as the initial central point of cluster point group, each central point represents one point
Group.
S4.2：After k central point is selected, the transformator of remaining n-k non-central point is grouped into from its nearest choosing
Point group representated by transformator.More specifically：If num_j is the transformator of a non-central point, num_i is in one
Heart point (selected object), and d (num_i, num_j) is that num_j is minimum with all k central point distances, then and num_j belongs to
Point group representated by num_i；
S4.3：To each central point num_i, replaced former with the transformator num_h of each non-central point in this point of group
Carry out central point num_i, calculate its total cost S=current_cost-past_cost, during wherein current_cost represents non-
After the transformator num_h of heart point replaces original central point num_i, redistribute non-central point arrive nearest central point place minute
Group, calculates non-central point to affiliated minute group center's point apart from summation；Past_cost represents the transformator num_h of non-central point
Before replacing original central point num_i, non-central point to affiliated minute group center's point apart from summation；
S4.4：If it is little to replace its total cost S of original central point num_i to have in the transformator num_h of all non-central points
In 0 presence, then find out total cost S minimum one, and replace corresponding central point originally with the transformator of this non-central point,
Form k new central point；
S4.5：Repeat step S4.3, S4.4 replaces original central point num_ until the transformator num_h of all non-central points
Total cost S of i is all higher than 0.
Described step 5 is specially：Respectively to three characteristic indexs of each point of group, draw probability density figure, divide further
Analyse the distribution situation of the transformator under the different loads characteristic index of each point of group.
According to the scheme of the embodiments of the present invention, the present invention considers the diversity of different transformer load characteristics, carries
Supply a kind of transformator grouping method based on load characteristic analysis, obtain transformer station high-voltage side bus grouping result and suggestion, empirical tests,
To running state of transformer classifying quality substantially, a kind of technological means are provided for grasping transformer economic operation situation and trend.
Brief description
Fig. 1 is the transformator grouping method schematic flow sheet based on load characteristic analysis of the present invention；
Fig. 2 is point each index probability density figure of group 1 of the embodiment of the present invention；
Fig. 3 is point each index probability density figure of group 2 of the embodiment of the present invention；
Fig. 4 is point each index probability density figure of group 3 of the embodiment of the present invention；
Fig. 5 is point each index probability density figure of group 4 of the embodiment of the present invention.
Specific embodiment
With reference to the accompanying drawings and examples technical scheme is described in detail.
As shown in figure 1, the transformator grouping method based on load characteristic analysis of the present invention, adopt first and utilize transformation
Device load data is processed into load factor data, then through dimensionality reduction, extracts three transformer load features：Annual load factor,
Load factor fluctuation and load factor trend, are then passed through index and calculate formation transformer load feature samples, feature samples collection is entered
Row standardization simultaneously carries out cluster point group's process using k-medoids algorithm to it, finally carries out feature analysiss to the result of point group.
The present invention is comprised the steps based on the transformator grouping method of load characteristic analysis：
Step 1：Using transformer load data computational load rate data；
Step 2：Through Data Dimensionality Reduction, load factor data processing is obtained per day load factor；
Step 3：Extract transformer load feature, obtain annual load factor, load factor fluctuation and load factor trend, formed
Feature samples collection；
Step 4：Feature samples collection is standardized, then carries out transformer load k-medoids cluster point group；
Step 5：Feature analysiss are carried out to grouping result.
Described step 1 is described as follows：
Load data includes the time t that P_H- high-pressure side is active, Q_H- high-pressure side is idle and monitors, according to transformator
Capacity V and load factor computing formulaObtain the load factor data sequence of transformator
{(f1,t1),(f2,t2),…,(fs,ts), wherein t1,t2,…,tsBe according to time order and function order carry out orderly
Arrangement, (fi,ti) represent in tiThe load factor of moment transformator is fi；
Described step 2 is described as follows：
Load data is every 3-5 minute record once, and load factor data is also just to have a note every 3-5 minute in the same manner
Record, is not suitable for direct analysis because data volume is excessive, needs to carry out dimensionality reduction to data；
Dimensionality reduction, in units of sky, calculates the daily Rate of average load of each transformator, this day Rate of average load
Described step 3 is described as follows：
Sort out reaction transformer load feature further according to the per day load factor of the calculated transformator of step 2 to refer to
Mark：Annual load factor, load factor fluctuation and load factor trend.The annual load factor of one transformator, load factor fluctuation and
The computing formula of load factor trend is respectively
(1) annual load factorDay_fjIt is the per day load factor in jth sky
(2) load factor fluctuation
(3) calculating of load factor trend is divided into two steps, the first step：Calculate the monthly average load factor in each monthDay_fj, wherein ml is the natural law of the l month；
Second step：Fitting a straight line is carried out with the monthly average load factor of the 1-12 month, obtains the slope of this straight line, as load factor
TrendWherein
Calculate the characteristic index value of all transformators, form feature samples collection, be shown in Table 1,
Table 1. feature samples collection example
| Transformator is numbered | Annual load factor | Load factor fluctuates | Load factor trend |
| num_1 | Year_f1 | Var_f1 | Trend_f1 |
| num_2 | Year_f2 | Var_f2 | Trend_f2 |
| num_3 | Year_f3 | Var_f3 | Trend_f3 |
| … | … | … | … |
| num_n-1 | Year_fn-1 | Var_fn-1 | Trend_fn-1 |
| num_n | Year_fn | Var_fn | Trend_fn |
Described step 4 is described as follows：
The feature samples collection being formed according to step 3, is standardized to each characteristic index, standardization formula is as follows：
Annual load factor after standardization Wherein
Load factor fluctuation after standardizationWherein
Load factor trend after standardizationWherein
Feature samples collection after standardization is shown in Table 2
Feature samples collection example after table 2. standardization
| Transformator is numbered | Annual load factor | Load factor fluctuates | Load factor trend |
| num_1 | NormYear_f1 | NormVar_f1 | NormTrend_f1 |
| num_2 | NormYear_f2 | NormVar_f2 | NormTrend_f2 |
| num_3 | NormYear_f3 | NormVar_f3 | NormTrend_f3 |
| … | … | … | … |
| num_n-1 | NormYear_fn-1 | NormVar_fn-1 | NormTrend_fn-1 |
| num_n | NormYear_fn | NormVar_fn | NormTrend_fn |
Recycle k-medoids clustering algorithm, distance function selects Euclidean distance
, select suitable cluster numbers k, divide group to the feature samples clustering after standardization, comprise the following steps that：
S4.1：Randomly choose k transformator as the initial central point of cluster point group, each central point represents one point
Group.
S4.2：After k central point is selected, the transformator of remaining n-k non-central point is grouped into from its nearest choosing
Point group representated by transformator.More specifically：If num_j is the transformator of a non-central point, num_i is in one
Heart point (selected object), and d (num_i, num_j) is that num_j is minimum with all k central point distances, then and num_j belongs to
Point group representated by num_i；
S4.3：To each central point num_i, replaced former with the transformator num_h of each non-central point in this point of group
Carry out central point num_i, calculate its total cost S=current_cost-past_cost, during wherein current_cost represents non-
After the transformator num_h of heart point replaces original central point num_i, redistribute non-central point arrive nearest central point place minute
Group, calculates non-central point to affiliated minute group center's point apart from summation；Past_cost represents the transformator num_h of non-central point
Before replacing original central point num_i, non-central point to affiliated minute group center's point apart from summation；
S4.4：If it is little to replace its total cost S of original central point num_i to have in the transformator num_h of all non-central points
In 0 presence, then find out total cost S minimum one, and replace corresponding central point originally with the transformator of this non-central point,
Form k new central point；
S4.5：Repeat step S4.3, S4.4 replaces original central point num_ until the transformator num_h of all non-central points
Total cost S of i is all higher than 0.
Described step 5 is described as follows：
Respectively to three characteristic indexs of each point of group, draw probability density figure, the difference analyzing each point of group further is born
Carry the distribution situation of the transformator under characteristic index.
Algorithm example
Below by embodiment, and combine accompanying drawing 1, the inventive method is described in further detail.
Step 1：Using transformer load data computational load rate data；
Extract Guangdong Power Grid all 500kV transformator depressor load data to be analyzed, extract the time period for 1 year, wherein
The fractional load data of certain transformator is shown in Table 3, and the capacity V=250*3MVA=750MVA of this transformator, according to load factor
Formula can obtain corresponding load factor data, is shown in Table 4.
The fractional load data of certain transformator of table 3.
| Time | P_H | Q_H | Time | P_H | Q_H |
| 2013-09-23 15:37 | 540.97 | 102.346 | 2013-09-23 18:36 | 448.371 | 121.84 |
| 2013-09-23 16:19 | 545.843 | 107.219 | 2013-09-23 18:43 | 472.739 | 126.714 |
| 2013-09-23 17:05 | 531.222 | 92.5984 | 2013-09-23 18:46 | 477.613 | 131.587 |
| 2013-09-23 17:12 | 526.349 | 87.7248 | 2013-09-23 19:39 | 492.234 | 131.587 |
| 2013-09-23 17:15 | 521.475 | 92.5984 | 2013-09-23 21:05 | 467.866 | 121.84 |
| 2013-09-23 17:21 | 511.728 | 87.7248 | 2013-09-23 21:11 | 462.992 | 116.966 |
| 2013-09-23 17:28 | 506.854 | 82.8512 | 2013-09-23 21:14 | 458.118 | 112.093 |
| 2013-09-23 17:34 | 492.234 | 77.9776 | 2013-09-23 21:17 | 453.245 | 121.84 |
| 2013-09-23 17:37 | 477.613 | 121.84 | 2013-09-23 21:42 | 433.75 | 112.093 |
| 2013-09-23 17:40 | 462.992 | 126.714 | 2013-09-23 21:49 | 428.877 | 116.966 |
| 2013-09-23 17:43 | 438.624 | 116.966 | 2013-09-23 22:05 | 419.13 | 116.966 |
| 2013-09-23 18:18 | 424.003 | 121.84 | 2013-09-23 22:08 | 414.256 | 112.093 |
| 2013-09-23 18:33 | 438.624 | 126.714 | 2013-09-23 22:14 | 404.509 | 107.219 |
The fractional load rate data of certain transformator of table 4.
| Time | Load factor | Time | Load factor |
| 2013-09-23 15:37 | 73.40884 | 2013-09-23 18:36 | 61.95074 |
| 2013-09-23 16:19 | 74.16984 | 2013-09-23 18:43 | 65.25691 |
| 2013-09-23 17:05 | 71.89761 | 2013-09-23 18:46 | 66.05443 |
| 2013-09-23 17:12 | 71.14791 | 2013-09-23 19:39 | 67.93585 |
| 2013-09-23 17:15 | 70.61767 | 2013-09-23 21:05 | 64.46271 |
| 2013-09-23 17:21 | 69.22571 | 2013-09-23 21:11 | 63.67175 |
| 2013-09-23 17:28 | 68.47745 | 2013-09-23 21:14 | 62.8843 |
| 2013-09-23 17:34 | 66.44962 | 2013-09-23 21:17 | 62.57809 |
| 2013-09-23 17:37 | 65.72118 | 2013-09-23 21:42 | 59.73332 |
| 2013-09-23 17:40 | 64.0025 | 2013-09-23 21:49 | 59.27211 |
| 2013-09-23 17:43 | 60.52688 | 2013-09-23 22:05 | 58.01931 |
| 2013-09-23 18:18 | 58.82154 | 2013-09-23 22:08 | 57.22049 |
| 2013-09-23 18:33 | 60.87473 | 2013-09-23 22:14 | 55.797 |
Step 2：Through Data Dimensionality Reduction, load factor data processing is obtained per day load factor；
The load factor data being obtained according to step 1, in units of sky, calculates the daily Rate of average load of each transformator,
This day Rate of average load
Step 3：Extract transformer load feature, obtain annual load factor, load factor fluctuation and load factor trend, formed
Feature samples collection；
By the computing formula of the annual load factor of transformator, load factor fluctuation and load factor trend, obtain feature samples
Collection, is shown in Table 5.
Table 5. feature samples collection
Step 4：Feature samples collection is standardized, then carries out transformer load k-medoids cluster point group；
After feature samples collection is standardized, selecting cluster number k is 4, carries out transformer load k-medoids cluster
Divide group, the cluster result of output is shown in Table 6 and table 7.
Table 6. cluster result (one)
Table 7. cluster result (two)
Step 5：Feature analysiss are carried out to grouping result
The grouping result being obtained according to step 4, to each point of group, be respectively directed to annual load factor, load factor fluctuation and
Load factor trend feature index, draws probability density figure, analyzes the transformation of the different loads characteristic index of each point of group further
The distribution situation of device, evaluates the out-of-limit running status of different points of groups.
1) divide group 1 feature analysiss (see Fig. 2)
Figure it is seen that for a point group 1, the annual load factor of transformator is in medium level, substantially arrives 20%
Between 60%；Load factor fluctuation is larger, substantially between 0.1 to 0.4；Load factor trend is substantially between -0.4 to 0.2.Explanation
But the transformer station high-voltage side bus of point group 1 are both economical unstable.
2) divide group 2 feature analysiss (see Fig. 3)
From figure 3, it can be seen that for a point group 2, the annual load factor of transformator is in reduced levels, substantially arrives 10%
Between 40%；Load factor fluctuation is less, substantially between 0 to 0.15；Load factor trend is substantially between -0.1 to 0.4.Explanation
Although the transformator running and comparing of point group 2 steadily, runs less economy, loading trends are in ascent stage simultaneously, need to stay
Meaning user power utilization situation, in the growth of load to a certain extent it is considered to dilatation.
3) divide group 3 feature analysiss (see Fig. 4)
From fig. 4, it can be seen that for a point group 3, the annual load factor of transformator is in medium level, substantially arrives 10%
Between 60%；Load factor fluctuation is larger, substantially between 0 to 0.4；Load factor trend is substantially between 0 to 1.2.Point group 3 is described
Transformer station high-voltage side bus more economical, but run unstable and loading trends are in ascent stage, user power utilization situation need to be noticed,
In the growth of load to a certain extent it is considered to dilatation.
4) divide group 4 feature analysiss (see Fig. 5)
From fig. 5, it can be seen that for a point group 4, the annual load factor of transformator is in medium level, substantially arrives 30%
Between 60%；Load factor fluctuates for medium level, substantially between 0 to 0.2；Load factor trend substantially -0.2 to 0.4 it
Between.Illustrate that the transformer station high-voltage side bus of point group 4 more economical steadily relatively simultaneously.
Claims (6)
1. a kind of transformator grouping method based on load characteristic analysis, is characterized in that comprising the following steps：
Step 1：Using transformer load data computational load rate data；
Step 2：Through Data Dimensionality Reduction, load factor data processing is obtained per day load factor；
Step 3：Extract transformer load feature, obtain annual load factor, load factor fluctuation and load factor trend, form feature
Sample set；
Step 4：Feature samples collection is standardized, then carries out transformer load k-medoids cluster point group；
Step 5：Feature analysiss are carried out to grouping result；
Load data in described step 1 includes the time t that P_H- high-pressure side is active, Q_H- high-pressure side is idle and monitors；
Described load factor data is the capacity V and load factor computing formula according to transformatorCalculate
Obtain load factor the data sequence { (f of transformator1,t1),(f2,t2),…,(fs,ts), wherein t1,t2,…,tsIt is according to the time
The ordered arrangement that sequencing is carried out, (fi,ti) represent in tiThe load factor of moment transformator is fi.
2. the transformator grouping method based on load characteristic analysis according to claim 1, is characterized in that：Described step
2 Data Dimensionality Reduction is in units of sky, calculates the daily Rate of average load of each transformator, this day Rate of average load
3. the transformator grouping method based on load characteristic analysis according to claim 2, is characterized in that：Described step
3 extraction transformer load feature is specially：The annual load factor of one transformator, load factor fluctuation and load factor trend
Computing formula is respectively：
(1) annual load factorDay_fjIt is the per day load factor in jth sky；
(2) load factor fluctuation
(3) calculating of load factor trend is divided into two steps：
The first step：Calculate the monthly average load factor in each month：Wherein mlFor the l month
Natural law；
Second step：Fitting a straight line is carried out with the monthly average load factor of the 1-12 month, obtains the slope of this straight line, as load factor trend
Wherein
Calculate the characteristic index value of all transformators, form feature samples collection.
4. the transformator grouping method based on load characteristic analysis according to claim 3, is characterized in that：Described step
4 feature samples collection is standardized for：
Each characteristic index is standardized, standardization formula is as follows：
Annual load factor after standardizationWherein
Load factor fluctuation after standardizationWherein
Load factor trend after standardizationWherein
5. the transformator grouping method based on load characteristic analysis according to claim 1, is characterized in that：Described step
4 transformer load k-medoids cluster point group comprises following sub-step：
S4.1：Randomly choose k transformator as the initial central point of cluster point group, each central point represents a point of group；
S4.2：After k central point is selected, the transformator of remaining n-k non-central point be grouped into from this point nearest choose change
Point group representated by depressor；
I.e.：If num_j is the transformator of a non-central point, num_i is a central point, and d (num_i, num_j) is
Num_j and all k central point distance minimums, then num_j belongs to point group representated by num_i；
S4.3：To each central point num_i, in being replaced originally with the transformator num_h of each non-central point in this point of group
Heart point num_i, calculates its total cost S=current_cost-past_cost, and wherein current_cost represents non-central point
Transformator num_h replace original central point num_i after, redistribute minute group that non-central point arrives nearest central point place,
Calculate non-central point to affiliated minute group center's point apart from summation；Past_cost represents that the transformator num_h of non-central point replaces
Originally before central point num_i, non-central point to affiliated minute group center's point apart from summation；
S4.4：If replacing its total cost S of original central point num_i to have less than 0 in the transformator num_h of all non-central points
Exist, then find out total cost S minimum one, and replace corresponding central point originally with the transformator of this non-central point, formed
K new central point；
S4.5：Repeat step S4.3, S4.4 replaces original central point num_i's until the transformator num_h of all non-central points
Total cost S is all higher than 0.
6. the transformator grouping method based on load characteristic analysis according to claim 5, is characterized in that：Described step
5 are specially：Respectively the annual load factor of each point of group, load factor are fluctuated and three characteristic indexs of load factor trend, draw
Probability density figure, analyzes annual load factor, load factor fluctuation and these three features of load factor trend of each point of group further
The distribution situation of the transformator under index.
Priority Applications (1)
| Application Number | Priority Date | Filing Date | Title |
|---|---|---|---|
| CN201410564530.9A CN104318489B (en) | 2014-10-21 | 2014-10-21 | Transformer grouping method based on load characteristic analysis |
Applications Claiming Priority (1)
| Application Number | Priority Date | Filing Date | Title |
|---|---|---|---|
| CN201410564530.9A CN104318489B (en) | 2014-10-21 | 2014-10-21 | Transformer grouping method based on load characteristic analysis |
Publications (2)
| Publication Number | Publication Date |
|---|---|
| CN104318489A CN104318489A (en) | 2015-01-28 |
| CN104318489B true CN104318489B (en) | 2017-02-08 |
Family
ID=52373715
Family Applications (1)
| Application Number | Title | Priority Date | Filing Date |
|---|---|---|---|
| CN201410564530.9A Active CN104318489B (en) | 2014-10-21 | 2014-10-21 | Transformer grouping method based on load characteristic analysis |
Country Status (1)
| Country | Link |
|---|---|
| CN (1) | CN104318489B (en) |
Families Citing this family (4)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN106682705B (en) * | 2017-02-04 | 2019-12-24 | 武汉阿帕科技有限公司 | Load characteristic identification method and device |
| CN108306303B (en) * | 2018-01-17 | 2021-06-15 | 南方电网科学研究院有限责任公司 | Voltage stability evaluation method considering load increase and new energy output randomness |
| CN108828342B (en) * | 2018-03-30 | 2019-12-10 | 广州供电局有限公司 | Power equipment state detection method and device, computer equipment and storage medium |
| CN110263873A (en) * | 2019-06-27 | 2019-09-20 | 华北电力大学 | A kind of power distribution network platform area classification method merging sparse noise reduction autoencoder network dimensionality reduction and cluster |
Family Cites Families (3)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| KR100956162B1 (en) * | 2009-06-19 | 2010-05-06 | 주식회사 헤코 | Combo type a circuit breaker and method thereof |
| CN103646354A (en) * | 2013-11-28 | 2014-03-19 | 国家电网公司 | Effective index FCM and RBF neural network-based substation load characteristic categorization method |
| CN103793756A (en) * | 2014-01-17 | 2014-05-14 | 广西电网公司电力科学研究院 | Transformer economic operation characteristic analyzing method |
-
2014
- 2014-10-21 CN CN201410564530.9A patent/CN104318489B/en active Active
Also Published As
| Publication number | Publication date |
|---|---|
| CN104318489A (en) | 2015-01-28 |
Similar Documents
| Publication | Publication Date | Title |
|---|---|---|
| CN104318489B (en) | Transformer grouping method based on load characteristic analysis | |
| CN106909933B (en) | A kind of stealing classification Forecasting Methodology of three stages various visual angles Fusion Features | |
| CN103617568B (en) | Setting method for abnormal data determination threshold in steady-state power quality early-warning mechanism | |
| CN110110887A (en) | To the prediction technique of low-voltage platform area line loss per unit | |
| CN103903189A (en) | Method for clustering low-voltage distribution network transformer districts based on fuzzy clustering | |
| CN108681744A (en) | A kind of electric load curve hierarchy clustering method divided based on data | |
| CN104063480A (en) | Load curve parallel clustering method based on big data of electric power | |
| CN110263873A (en) | A kind of power distribution network platform area classification method merging sparse noise reduction autoencoder network dimensionality reduction and cluster | |
| CN105654196A (en) | Adaptive load prediction selection method based on electric power big data | |
| CN110544177A (en) | Load identification method based on power fingerprint and computer readable storage medium | |
| CN104535905A (en) | Partial discharge diagnosis method based on naive bayesian classification | |
| CN103793756A (en) | Transformer economic operation characteristic analyzing method | |
| LinLin et al. | Diversity based on entropy: A novel evaluation criterion in multi-objective optimization algorithm | |
| CN110690701A (en) | Analysis method for influence factors of abnormal line loss | |
| CN110991527B (en) | Similarity threshold determining method considering average fluctuation rate of voltage curve | |
| CN104701867A (en) | Day-ahead reactive power optimization method based on branch-bound method and primal-dual interior point method | |
| CN104537432A (en) | Decision-making method for electric system multi-objective optimization dispatching and based on evidence reasoning | |
| CN111339167A (en) | Analysis method of influencing factors of line loss rate in Taiwan area based on K-means and principal component linear regression | |
| CN112101487A (en) | Compression method and device for fine-grained recognition model | |
| CN110674971A (en) | A Transformer Transformation Plan Analysis Method Based on Orthogonal Control Load Prediction | |
| CN104361259B (en) | A kind of transformer violation operation characteristic analysis method | |
| CN111080089A (en) | Method and device for determining critical factors of line loss rate based on random matrix theory | |
| CN112464059B (en) | Distribution network user classification method, device, computer equipment and storage medium | |
| CN110852370A (en) | A Segmentation Method of Large Industrial Users Based on Clustering Algorithm | |
| CN106597853A (en) | Active dynamic regulation method in hydrocracking process |
Legal Events
| Date | Code | Title | Description |
|---|---|---|---|
| C06 | Publication | ||
| PB01 | Publication | ||
| C10 | Entry into substantive examination | ||
| SE01 | Entry into force of request for substantive examination | ||
| C14 | Grant of patent or utility model | ||
| GR01 | Patent grant |