CN111708987B - Method for predicting load of multiple parallel transformers of transformer substation - Google Patents
Method for predicting load of multiple parallel transformers of transformer substation Download PDFInfo
- Publication number
- CN111708987B CN111708987B CN202010549550.4A CN202010549550A CN111708987B CN 111708987 B CN111708987 B CN 111708987B CN 202010549550 A CN202010549550 A CN 202010549550A CN 111708987 B CN111708987 B CN 111708987B
- Authority
- CN
- China
- Prior art keywords
- load
- transformer
- substation
- data
- transformers
- 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
- 238000000034 method Methods 0.000 title claims abstract description 50
- 238000013507 mapping Methods 0.000 claims abstract description 15
- 238000012417 linear regression Methods 0.000 claims abstract description 9
- 238000005259 measurement Methods 0.000 claims description 5
- 230000006872 improvement Effects 0.000 abstract description 4
- 230000008859 change Effects 0.000 description 6
- 230000008901 benefit Effects 0.000 description 5
- 238000004364 calculation method Methods 0.000 description 2
- 230000009977 dual effect Effects 0.000 description 2
- 238000005516 engineering process Methods 0.000 description 2
- LFQSCWFLJHTTHZ-UHFFFAOYSA-N Ethanol Chemical compound CCO LFQSCWFLJHTTHZ-UHFFFAOYSA-N 0.000 description 1
- 238000013528 artificial neural network Methods 0.000 description 1
- 230000001419 dependent effect Effects 0.000 description 1
- 238000011156 evaluation Methods 0.000 description 1
- 230000036541 health Effects 0.000 description 1
- 238000009413 insulation Methods 0.000 description 1
- 238000005065 mining Methods 0.000 description 1
- 230000004048 modification Effects 0.000 description 1
- 238000012986 modification Methods 0.000 description 1
- 238000012544 monitoring process Methods 0.000 description 1
- 210000002569 neuron Anatomy 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
-
- 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
- G06Q10/04—Forecasting or optimisation specially adapted for administrative or management purposes, e.g. linear programming or "cutting stock problem"
-
- 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
-
- Y—GENERAL TAGGING OF NEW TECHNOLOGICAL DEVELOPMENTS; GENERAL TAGGING OF CROSS-SECTIONAL TECHNOLOGIES SPANNING OVER SEVERAL SECTIONS OF THE IPC; TECHNICAL SUBJECTS COVERED BY FORMER USPC CROSS-REFERENCE ART COLLECTIONS [XRACs] AND DIGESTS
- Y04—INFORMATION OR COMMUNICATION TECHNOLOGIES HAVING AN IMPACT ON OTHER TECHNOLOGY AREAS
- Y04S—SYSTEMS INTEGRATING TECHNOLOGIES RELATED TO POWER NETWORK OPERATION, COMMUNICATION OR INFORMATION TECHNOLOGIES FOR IMPROVING THE ELECTRICAL POWER GENERATION, TRANSMISSION, DISTRIBUTION, MANAGEMENT OR USAGE, i.e. SMART GRIDS
- Y04S10/00—Systems supporting electrical power generation, transmission or distribution
- Y04S10/50—Systems or methods supporting the power network operation or management, involving a certain degree of interaction with the load-side end user applications
Landscapes
- Engineering & Computer Science (AREA)
- Physics & Mathematics (AREA)
- Business, Economics & Management (AREA)
- General Physics & Mathematics (AREA)
- Economics (AREA)
- Theoretical Computer Science (AREA)
- Data Mining & Analysis (AREA)
- Human Resources & Organizations (AREA)
- Strategic Management (AREA)
- Mathematical Physics (AREA)
- Computational Mathematics (AREA)
- Tourism & Hospitality (AREA)
- Operations Research (AREA)
- General Business, Economics & Management (AREA)
- Marketing (AREA)
- Health & Medical Sciences (AREA)
- Pure & Applied Mathematics (AREA)
- Mathematical Optimization (AREA)
- Mathematical Analysis (AREA)
- Bioinformatics & Cheminformatics (AREA)
- Databases & Information Systems (AREA)
- Evolutionary Biology (AREA)
- Bioinformatics & Computational Biology (AREA)
- Quality & Reliability (AREA)
- Probability & Statistics with Applications (AREA)
- Life Sciences & Earth Sciences (AREA)
- Algebra (AREA)
- Development Economics (AREA)
- Game Theory and Decision Science (AREA)
- Software Systems (AREA)
- General Engineering & Computer Science (AREA)
- Entrepreneurship & Innovation (AREA)
- Public Health (AREA)
- Water Supply & Treatment (AREA)
- General Health & Medical Sciences (AREA)
- Primary Health Care (AREA)
- Supply And Distribution Of Alternating Current (AREA)
- Management, Administration, Business Operations System, And Electronic Commerce (AREA)
Abstract
A method for predicting the load of a plurality of parallel transformers of a transformer substation comprises the following steps: step 1, acquiring historical data of the transformer substation in a set time period, wherein the historical data comprises transformer substation load data, load data of each transformer and transformer operation mode data in the set time period; step 2, calculating the operation mode C of the transformer substation by using historical data of the transformer substation j Transformer T during operation i Load distribution factor F at time t t (T i ，C j ) (ii) a Step 3, the load distribution coefficient F obtained in step 2 t (T i ，C j ) Combined with the load L of the substation s (t) use of a non-linear regression function G (L) s (t)，T i ，C j ) Quantized load distribution factor F t (T i ，C j ) Load L with substation s (t) a non-linear mapping relationship; step 4, the nonlinear regression function G (L) obtained in the step 3 s (t)，T i ，C j ) Combined with the load L of the substation s (t) load L of ith transformer at time t i (t) performing a prediction. On the premise of improving the accuracy of the load prediction result of the transformer, the workload of load prediction modeling is greatly reduced, and the precision is realizedAnd the double improvement of the efficiency.
Description
Technical Field
The invention relates to the field of load prediction of power equipment, in particular to a method for predicting loads of multiple parallel transformers of a transformer substation.
Background
The transformer load is an important factor influencing the health state and the insulation life of equipment, and the realization of accurate transformer load prediction has important significance for optimizing load distribution, equipment state evaluation and fault prediction. In practice, besides conventional factors such as day type, season and weather, the transformer load is influenced by changes of the operation mode of the transformer substation to present a more complex change rule than that of the transformer substation level load, so that the load of the transformer cannot be accurately predicted by the existing power system load prediction technology. On the other hand, the number of transformers in the power grid is large, and heavy workload can be generated when a load prediction model is established for each device independently.
Prior art document 1 (dunnaging et al, a load prediction method [ P ]. CN110009136A, 2019-07-12.) of a distribution transformer and a distribution line discloses a load prediction method of a distribution transformer and a distribution line, which initializes each weight of historical load, meteorological data, a workday type and the like, and performs neuron calculation and prediction based on an Elman neural network algorithm.
The method disclosed in prior art document 1 follows the conventional load prediction method for the power system level to the load of the transformer level. However, in practice, besides conventional factors such as historical load, meteorological data and working day type, the transformer load may also be changed under the influence of special factors such as adjustment of the operation mode of the transformer substation, and a more complex change rule is presented than that of the system-level load, and if only the conventional factors are considered and the influence of the operation mode of the transformer substation on the transformer load is ignored, a large prediction error may be caused. On the other hand, the number of transformers in the power grid is large, and heavy workload can be generated when a load prediction model is established for each transformer independently.
Disclosure of Invention
The invention aims to provide a method for predicting loads of a plurality of parallel transformers of a transformer substation, which realizes the prediction of the loads of the plurality of parallel transformers by defining a load distribution coefficient and quantizing the nonlinear mapping relation between the loads of the parallel transformers and the loads of the transformer substation under different operation modes of the transformer substation by using a nonlinear regression function.
The invention adopts the following technical scheme. Method for predicting load of multiple parallel transformers in transformer substation by T i The method comprises the following steps of representing the ith transformer in N transformers which are in parallel operation in a transformer substation, wherein N and i are positive integers, N is more than or equal to 2, i is more than or equal to 1 and less than or equal to N; c j The j-th operation mode in K operation modes of the transformer substation is represented, K and j are positive integers, K is more than or equal to 2, j is more than or equal to 1 and less than or equal to K; t represents the measurement time, and t is a positive integer; l is i (t) represents the load of the ith transformer at time t; l is s (t) represents the load of the substation at time t; the method is characterized by comprising the following steps:
step 1, acquiring historical data of the transformer substation in a set time period, wherein the historical data comprises transformer substation load data, load data of each transformer and transformer substation operation mode data in the set time period;
step 2, calculating the operation mode C of the transformer substation by using historical data of the transformer substation and adopting the following formula (1) j Transformer T during operation i Load distribution factor F at time t t (T i ，C j )
In the formula:
F t (T i ，C j ) Representing a load sharing factor;
T i representing the ith transformer in N transformers which are operated in parallel in the transformer substation;
C j representing the jth operation mode in the K operation modes of the transformer substation;
t represents a measurement time;
L i (t) represents the load of the ith transformer at time t;
L s (t) represents the load of the substation at time t;
step 3, the load distribution coefficient F obtained in step 2 t (T i ，C j ) Combined with the load L of the substation s (t) using a nonlinear regression function G (L) s (t)，T i ，C j ) Quantized load distribution factor F t (T i ，C j ) Load L with substation s (t) a non-linear mapping relationship,
F t (T i ，C j )＝G(L s (t)，T i ，C j )(2)
in the formula:
G(L s (t)，T i ，C j ) Representing the inclusion of independent variables as substation load L s (t) a non-linear regression function;
step 4, the nonlinear regression function G (L) obtained in the step 3 s (t)，T i ，C j ) Combined with the load L of the substation s (t) applying the following formula (3) to the load L of the ith transformer at time t i (t) performing a prediction of the current,
L i (t)＝G(L s (t)，T i ，C j )·L s (t) (3)。
preferably, as the nonlinear regression function G (L), a power function containing a constant term is used as follows s (t)，T i ，C j )
G(L s (t)，T i ，C j )＝aL s (t) b +c (4)
L s (t) represents the load of the substation at time t;
a, b, c represent G (L) s (t)，T i ，C j ) The parameter value of (2).
Preferably, the nonlinear regression function G (L) is estimated using a least squares method s (t)，T i ，C j ) The parameter values a, b, c.
Preferably, the set period of time in step 1 is in the range of 1 year to 3 years.
Preferably, the step 1 of acquiring the operation mode data of the substation refers to the shutdown and operation states of the transformer occurring in the historical operation.
Preferably, at least 4 historical data of historical moments are obtained, namely t is more than or equal to 4, the historical data comprise substation load data, load data of each transformer and substation operation mode data, and the historical data are used for fitting a nonlinear function and predicting.
Compared with the prior art, the method has the advantages that the load distribution coefficients are defined to describe the distribution relation between the parallel transformers and the transformer substation level loads, the nonlinear regression function is used for quantizing the nonlinear mapping relation between the load distribution coefficients and the transformer substation level loads in different operation modes of the transformer substation, and finally the prediction of the loads of the plurality of parallel transformers is realized according to the load distribution coefficients of the transformers by taking the prediction result of the transformer substation load as input.
The load score of each transformer is quantified by using a nonlinear regression function compared with the method of simplifying the load score into a constantCoefficient of distribution F t (T i ，C j ) And the load L of the transformer substation s And (t) the nonlinear mapping relation can accurately and reasonably reflect the real dynamic change characteristics of the load distribution coefficients. According to the method, on the premise of improving the accuracy of the load prediction result of the transformer, the workload of load prediction modeling is greatly reduced, and the dual improvement of the precision and the efficiency is realized.
According to the invention, the nonlinear mapping relation between the transformer substation level load and the loads of the multiple parallel transformers is excavated under different operation modes of the transformer substation, the load prediction results of the multiple parallel transformers are taken as input, the load prediction of the multiple parallel transformers is realized, and the workload of the load prediction is greatly reduced on the premise of improving the load prediction accuracy.
As long as the substation is in a certain state C j The amount of historical data collected at run-time is not less than 4, including 4, i.e. not less than 4 points, and then the nonlinear function can be fitted and predicted. Therefore, the method for predicting the load of the plurality of transformers connected in parallel in the transformer substation has an obvious advantage that the method can be used in the scene of scarce historical load data.
Drawings
FIG. 1 shows the operation mode of the substation as C 1 Time, transformer T 1 Load distribution coefficient of (F) t (T i ，C j ) And the load L of the transformer substation s (t) a map scatter plot;
FIG. 2 shows the operation of the substation as C 4 Time, transformer T 1 Load distribution coefficient of (F) t (T i ，C j ) And the load L of the transformer substation s (t) a map scatter plot;
FIG. 3 shows a transformer T 1 A load prediction result map of (1);
fig. 4 is a flow chart of a method for predicting the load of a plurality of parallel transformers in a transformer substation.
Detailed Description
The present application is further described below with reference to the accompanying drawings. The following examples are only for illustrating the technical solutions of the present invention more clearly, and the protection scope of the present application is not limited thereby.
The invention provides a method for predicting load of a plurality of parallel transformers of a transformer substation, wherein the transformer substation S comprises N transformers which are operated in parallel and are connected in parallel by T i The method comprises the steps of representing the ith transformer in N transformers which run in parallel in a transformer substation, namely the number of the transformers, wherein N and i are positive integers, N is more than or equal to 2, and i is more than or equal to 1 and less than or equal to N; with C j The j-th operation mode in K operation modes of the transformer substation is represented, K and j are positive integers, K is more than or equal to 2, j is more than or equal to 1 and less than or equal to K; t represents the measurement time, t is a positive integer, and if the time span for acquiring the historical data is n days, t is more than or equal to 1 and less than or equal to 24n; l is a radical of an alcohol i (t) represents the load of the ith transformer at time t; l is s And (t) represents the load of the substation at the time t.
As shown in fig. 4, the method for predicting the load of a plurality of parallel transformers in a transformer substation comprises the following steps:
step 1, acquiring historical data of the transformer substation in a set time period, wherein the historical data comprises transformer substation load data, load data of each transformer and transformer operation mode data in the set time period. Preferably, but not limitatively, the set period of time ranges from 1 year to 3 years. The acquisition of the operation mode data of the transformer substation refers to the shutdown and normal operation states of the transformer in historical operation.
Step 2, defining a load distribution coefficient F t (T i ，C j ) At a certain time t, the operation mode of the transformer substation is C j Then, the ith transformer load L i (t) and substation load L s (t) ratio. Calculating the operation mode C of the transformer substation by using the historical data of the transformer substation and adopting the following formula (1) j Transformer T during operation i Load distribution factor F at time t t (T i ，C j )，
In the formula:
F t (T i ，C j ) Representing a load distribution coefficient;
T i representing the ith transformer in N transformers which are operated in parallel in the transformer substation;
C j representing the jth operation mode in the K operation modes of the transformer substation;
t represents a measurement time;
L i (t) represents the load of the ith transformer at time t;
L s and (t) represents the load of the substation at time t.
Step 3, the load distribution coefficient F obtained in the step 2 t (T i ，C j ) Combined with the load L of the substation s (t) use of a non-linear regression function G (L) s (t)，T i ，C j ) Quantifying the load distribution coefficient F by the following equation (2) t (T i ，C j ) Load L with substation s (t) a non-linear mapping relationship,
F t (T i ，C j )＝G(L s (t)，T i ，C j )(2)
in the formula:
G(L s (t)，T i ，C j ) Representing the load L of a substation containing independent variables s (t) a non-linear regression function;
T i representing the ith transformer in N transformers which are operated in parallel in the transformer substation;
C j and the j operation mode in the K operation modes of the transformer substation is shown.
Under ideal conditions, the transformer load sharing factor is considered constant. However, in a real scene, various operation parameters of different parallel transformers are affected by the load level of the transformer substation to generate changes with different degrees, and the load distribution coefficient of each parallel transformer is indirectly affected. Thus, the load distribution coefficient F of each transformer is quantized using a non-linear regression function, as opposed to being reduced to a constant t (T i ，C j ) And the load L of the transformer substation s And (t) the nonlinear mapping relation can accurately and reasonably reflect the real dynamic change characteristics of the load distribution coefficients.
Preferably, in order to changeLoad L of power station s (t) as an argument with a load distribution factor F t (T i ，C j ) For dependent variables, a power function G (L) is used which contains constant terms s (t)，T i ，C j ) Load L of quantitative transformer substation s (t) and the load distribution factor F t (T i ，C j ) The non-linear mapping relationship between the two is expressed by formula (3)
G(L s (t)，T i ，C j )＝aL s (t) b +c(3)
L s (t) represents the load of the substation at time t;
a, b, c represent G (L) s (t)，T i ，C j ) The parameter value of (2).
Estimation of the nonlinear regression function G (L) using the least squares method s (t)，T i ，C j ) The parameter values a, b, c. It can be seen that the parameter values a, b, c are subject to the load L of the substation s (T), transformer number T i And operation mode C of transformer substation j The influence of (c) changes.
Step 4, the nonlinear regression function G (L) obtained in the step 3 s (t)，T i ，C j ) Combined with the load L of the substation s (t) applying the following formula (4) to the load L of the ith transformer at time t i (t) prediction, L s (t) can be realized by a short-term or ultra-short-term load forecasting technology at a substation level, and is easily obtained in a power system because the load at the substation level is required to be forecasted by a power grid.
L i (t)＝G(L s (t)，T i ，C j )·L s (t) (4)
In the formula:
L i (t) represents the load of the ith transformer at time t;
G(L s (t)，T i ，C j ) Representing loads L comprising independent variable substations s (t) a non-linear regression function;
L s and (t) represents the load of the substation at the time t.
When transformer substation operatesFormula C i Or number T of transformer i When the change occurs, only the corresponding nonlinear function G (L) needs to be replaced s (t)，T i ，C j ) And the load prediction of different running states and different parallel transformers of the transformer substation can be realized.
It is worth noting that as long as the substation is in a certain state C j The amount of historical data collected at run-time is not less than 4, including 4, i.e. not less than 4 points, and then the nonlinear function can be fitted and predicted. Therefore, the method for predicting the load of the multiple parallel transformers of the transformer substation has an obvious advantage that the method can be used in the scene of scarce load data in the calendar.
Compared with the load of the transformer level, represented by the prior art document 1, which is obtained by applying the traditional load prediction method aiming at the power system level to the load of the transformer level, the load prediction of a plurality of parallel transformers is realized by mining the nonlinear mapping relation between the load of the transformer station and the load of a plurality of parallel transformers under different operation modes of the transformer station and taking the load prediction result of the transformer station as input, and the workload of the load prediction is greatly reduced on the premise of improving the load prediction precision.
The following implementation examples of the prediction by the load prediction method for the plurality of parallel transformers in the transformer substation are given:
some transformer substation S comprises 4 transformers T running in parallel 1 ，T 2 ，T 3 ，T 4 In an Energy Management System (EMS for short), 4 transformers T running in parallel are stored 1 ，T 2 ，T 3 ，T 4 In 2015-2016 historical online monitoring data of active power, the substation S has a total of 4 operating modes in these two years, as shown in table 1:
in a real situation, as shown in table 2 below, generally, a substation operates at the time C1 for most of the time (that is, all transformers in the substation operate normally), but C2 to C4 are not common (a certain transformer in the substation stops operating, and the rest transformers operate normally), so that C1 often has a large amount of historical data, and the historical data of C2 to C4 is scarce. Since the power function structure including the constant term is very simple, even if the amount of data used for fitting is very large, no significant influence is caused on the calculation efficiency.
TABLE 1 operation mode of transformer substation
By T 1 For example, when the substation is at C 1 And C 4 When operating in a mode, T 1 Load distribution coefficient F t (T 1 ，C 1 ) And F t (T 1 ，C 4 ) And the load L of the transformer substation s (t) scattergrams of the mapping are shown in FIGS. 1 and 2, respectively.
According to the load distribution coefficient and the substation load L in the historical load data as shown in the attached figure 1 s (t) scatterplot, quantifying F using a nonlinear regression function as shown in equation (2) t (T 1 ，C 1 ) And F t (T 1 ，C 4 ) And L s (t) and fitting results are shown as black curves in fig. 1 and 2, respectively. According to the graph, the power function with the constant terms can accurately quantify and fit the nonlinear mapping relation between the transformer load distribution coefficient and the transformer substation load. The results of the parameter fitting of the nonlinear regression functions of the shunt transformers in the operating state of the remaining substations are shown in table 2.
TABLE 2 results of parameter fitting of nonlinear regression functions
242 historical load values of substation S over a certain period of time are collected, wherein [63, 133 [ ]]And [160, 234 ]]In two periods of time, the operation mode of the transformer substation is C 4 (T 3 Brief exit of operation) and the rest of the time period is C 1 . By T 1 For example, load prediction is performed using equation (4), and the corresponding G (L) is replaced according to the substation operation mode s (t)，T 1 ，C 1 ) And G (L) s (t)，T 1 ，C 4 ) As a non-linear regression function. The prediction results are shown in fig. 3, and the root mean square error of the predicted values is shown in table 3. Compared with the load distribution coefficient which is taken as a constant value, the accuracy of the transformer load prediction can be remarkably improved by using the nonlinear regression function to predict the load.
TABLE 3 prediction result error of different load prediction methods
As can be seen from the prediction results shown in FIG. 3, the transformer load method of the invention has high prediction accuracy. When the operation mode of the transformer substation changes or the loads of other parallel transformers need to be predicted, the loads of any transformer in any operation mode can be accurately predicted only by replacing the corresponding nonlinear regression function. In addition, compared with the method of establishing a separate load prediction model for each transformer, the method of replacing the nonlinear regression function can greatly reduce the workload of load prediction.
The method has the advantages that compared with the prior art, the method firstly defines the load distribution coefficient to describe the distribution relation between the parallel transformers and the transformer substation level load, uses the nonlinear regression function to quantize the nonlinear mapping relation between the load distribution coefficient and the transformer substation level load under different operation modes of the transformer substation, and finally takes the prediction result of the transformer substation load as input to realize the prediction of the loads of the plurality of parallel transformers according to the load distribution coefficient of the transformers.
The load distribution coefficient F of each transformer is quantified by using a nonlinear regression function compared with the method of simplifying the load distribution coefficient F into a constant t (T i ,C j ) And the load L of the transformer substation s The non-linear mapping relation between (t) can be accurateAnd reasonably reflects the real dynamic change characteristics of the load distribution coefficients. According to the method, on the premise of improving the accuracy of the load prediction result of the transformer, the workload of load prediction modeling is greatly reduced, and the dual improvement of the precision and the efficiency is realized.
As long as the substation is in a certain state C j The amount of historical data collected at run-time is not less than 4, including 4, i.e. not less than 4 points, and then the nonlinear function can be fitted and predicted. Therefore, the method for predicting the load of the plurality of transformers connected in parallel in the transformer substation has an obvious advantage that the method can be used in the scene of scarce historical load data.
The present applicant has described and illustrated embodiments of the present invention in detail with reference to the accompanying drawings, but it should be understood by those skilled in the art that the above embodiments are merely preferred embodiments of the present invention, and the detailed description is only for the purpose of helping the reader to better understand the spirit of the present invention, and not for limiting the scope of the present invention, and on the contrary, any improvement or modification made based on the spirit of the present invention should fall within the scope of the present invention.
Claims (5)
1. A method for predicting the load of multiple parallel transformers in transformer substation
Representing in a substation>
Fifth in a transformer with parallel operation>
Stand transformer, and/or>
Is a positive integer, <' > based on>
；
Representing a substation +>
In seed operating mode>
Seed operation mode>
Is a positive integer, <' > based on>
；
Indicates the measurement time and>
is a positive integer;
represents->
At a moment in time +>
The load of the transformer;
Represents->
The load of the substation at any moment; the method is characterized by comprising the following steps:
step 1, acquiring historical data of the transformer substation in a set time period, wherein the historical data comprises transformer substation load data, load data of each transformer and transformer operation mode data in the set time period;
the obtained transformer substation operation mode data refer to transformer outage and operation states of a transformer in historical operation;
step 2, using historical data of the transformer substation to adopt the following formula
Method for operating a computer substation>
Transformer on operation>
In or on>
The load distribution factor at a time instant->
step 3, the load distribution coefficient obtained in step 2
Combined with the load of the substation>
Based on a non-linear regression function>
Quantized load distribution factor>
And the load of the substation>
The non-linear mapping relationship of (a), device for selecting or keeping>
In the formula:
step 4, the nonlinear regression function obtained in step 3
Combined with the load of the substation>
Using the following formula>
To (X)>
At a moment in time +>
Load of table transformer>
The prediction is carried out in such a way that,
2. the method for predicting the load of the plurality of transformers connected in parallel in the substation according to claim 1, wherein the method comprises the following steps:
using a power function containing a constant term as a nonlinear regression function
3. The method for predicting the load of the plurality of parallel transformers in the substation according to claim 2, wherein the method comprises the following steps:
estimating a nonlinear regression function using a least squares method
Is greater than or equal to>
。
4. The method for predicting the load of the plurality of parallel transformers in the substation according to any one of claims 1 to 3, wherein the method comprises the following steps:
the set time period in step 1 ranges from 1 year to 3 years.
5. The method for predicting the load of the plurality of parallel transformers in the substation according to any one of claims 1 to 3, wherein the method comprises the following steps:
obtaining historical data for at least 4 historical moments, i.e.
The method comprises the steps of fitting a nonlinear function and predicting, wherein the data comprises transformer substation load data, load data of each transformer and transformer operation mode data. />
Priority Applications (1)
| Application Number | Priority Date | Filing Date | Title |
|---|---|---|---|
| CN202010549550.4A CN111708987B (en) | 2020-06-16 | 2020-06-16 | Method for predicting load of multiple parallel transformers of transformer substation |
Applications Claiming Priority (1)
| Application Number | Priority Date | Filing Date | Title |
|---|---|---|---|
| CN202010549550.4A CN111708987B (en) | 2020-06-16 | 2020-06-16 | Method for predicting load of multiple parallel transformers of transformer substation |
Publications (2)
| Publication Number | Publication Date |
|---|---|
| CN111708987A CN111708987A (en) | 2020-09-25 |
| CN111708987B true CN111708987B (en) | 2023-04-07 |
Family
ID=72540693
Family Applications (1)
| Application Number | Title | Priority Date | Filing Date |
|---|---|---|---|
| CN202010549550.4A Active CN111708987B (en) | 2020-06-16 | 2020-06-16 | Method for predicting load of multiple parallel transformers of transformer substation |
Country Status (1)
| Country | Link |
|---|---|
| CN (1) | CN111708987B (en) |
Families Citing this family (2)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN112529250B (en) * | 2020-11-16 | 2023-06-30 | 贵州电网有限责任公司 | Comprehensive monitoring method for load condition of transformer |
| CN112583032A (en) * | 2020-11-18 | 2021-03-30 | 浙江华云信息科技有限公司 | Energy storage strategy configuration method based on load demand as guidance |
Citations (13)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN101159381A (en) * | 2007-11-16 | 2008-04-09 | 国电南瑞科技股份有限公司 | Transforming plant voltage reactive integrated control system acting equipment selection technology |
| CN102244384A (en) * | 2010-05-13 | 2011-11-16 | 河南省电力公司济源供电公司 | Optimal operation method of main transformers based on economic equivalent analysis |
| CN103678931A (en) * | 2013-12-23 | 2014-03-26 | 国家电网公司 | Transformer substation coverage area energy efficiency assessing method based on precise measurement load data |
| CN105184388A (en) * | 2015-08-05 | 2015-12-23 | 三峡大学 | Non-linear regression method for urban power load short-period prediction |
| CN105826921A (en) * | 2016-05-26 | 2016-08-03 | 广东电网有限责任公司佛山供电局 | Distribution network load prediction method and distribution network load prediction system based on transformer operation data |
| JP2017221040A (en) * | 2016-06-08 | 2017-12-14 | 株式会社東芝 | Power distribution system monitoring device |
| CN108805310A (en) * | 2017-04-26 | 2018-11-13 | 苏文电能科技有限公司 | A kind of intelligent online analysis system of transformer station high-voltage side bus |
| CN109460917A (en) * | 2018-11-08 | 2019-03-12 | 中国南方电网有限责任公司 | A kind of bus load prediction technique based on distribution factor and support vector machines |
| CN110009136A (en) * | 2019-03-12 | 2019-07-12 | 国网江西省电力有限公司电力科学研究院 | A kind of load forecasting method of distribution transformer and distribution line |
| CN110114766A (en) * | 2016-12-23 | 2019-08-09 | 必凯达能源股份公司 | The method that the existing power grid of distribution electric energy is constructed |
| CN110163429A (en) * | 2019-05-10 | 2019-08-23 | 湖南大学 | A kind of short-term load forecasting method based on similar day optimal screening |
| CN209448470U (en) * | 2019-03-14 | 2019-09-27 | 国网福建省电力有限公司电力科学研究院 | The double battery group intelligent management systems of substation's list charger based on electronic switch |
| CN111262243A (en) * | 2020-03-04 | 2020-06-09 | 国网浙江省电力有限公司 | Intelligent identification and optimization method for operation mode of park power distribution system |
Family Cites Families (3)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| US9020874B2 (en) * | 2011-10-31 | 2015-04-28 | Siemens Aktiengesellschaft | Short-term load forecast using support vector regression and feature learning |
| US11804717B2 (en) * | 2017-05-05 | 2023-10-31 | The Board Of Trustees Of The Leland Stanford Junior University | Systems and methods for coordinating distributed energy storage |
| US10700523B2 (en) * | 2017-08-28 | 2020-06-30 | General Electric Company | System and method for distribution load forecasting in a power grid |
-
2020
- 2020-06-16 CN CN202010549550.4A patent/CN111708987B/en active Active
Patent Citations (13)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN101159381A (en) * | 2007-11-16 | 2008-04-09 | 国电南瑞科技股份有限公司 | Transforming plant voltage reactive integrated control system acting equipment selection technology |
| CN102244384A (en) * | 2010-05-13 | 2011-11-16 | 河南省电力公司济源供电公司 | Optimal operation method of main transformers based on economic equivalent analysis |
| CN103678931A (en) * | 2013-12-23 | 2014-03-26 | 国家电网公司 | Transformer substation coverage area energy efficiency assessing method based on precise measurement load data |
| CN105184388A (en) * | 2015-08-05 | 2015-12-23 | 三峡大学 | Non-linear regression method for urban power load short-period prediction |
| CN105826921A (en) * | 2016-05-26 | 2016-08-03 | 广东电网有限责任公司佛山供电局 | Distribution network load prediction method and distribution network load prediction system based on transformer operation data |
| JP2017221040A (en) * | 2016-06-08 | 2017-12-14 | 株式会社東芝 | Power distribution system monitoring device |
| CN110114766A (en) * | 2016-12-23 | 2019-08-09 | 必凯达能源股份公司 | The method that the existing power grid of distribution electric energy is constructed |
| CN108805310A (en) * | 2017-04-26 | 2018-11-13 | 苏文电能科技有限公司 | A kind of intelligent online analysis system of transformer station high-voltage side bus |
| CN109460917A (en) * | 2018-11-08 | 2019-03-12 | 中国南方电网有限责任公司 | A kind of bus load prediction technique based on distribution factor and support vector machines |
| CN110009136A (en) * | 2019-03-12 | 2019-07-12 | 国网江西省电力有限公司电力科学研究院 | A kind of load forecasting method of distribution transformer and distribution line |
| CN209448470U (en) * | 2019-03-14 | 2019-09-27 | 国网福建省电力有限公司电力科学研究院 | The double battery group intelligent management systems of substation's list charger based on electronic switch |
| CN110163429A (en) * | 2019-05-10 | 2019-08-23 | 湖南大学 | A kind of short-term load forecasting method based on similar day optimal screening |
| CN111262243A (en) * | 2020-03-04 | 2020-06-09 | 国网浙江省电力有限公司 | Intelligent identification and optimization method for operation mode of park power distribution system |
Non-Patent Citations (3)
| Title |
|---|
| Dong HAN.The Forecasting of Electrical Consumption Proportion of Different Industries in Substation Based on SCADA and the Daily Load Curve of Load Control System.《2012 International Conference on Computer Distributed Control and Intelligent Environmental Monitoring》.2012,第738-741页. * |
| 袁明军.配电系统可靠性评估方法与应用研究.《中国博士学位论文全文数据库-工程科技II辑》.2012,全文. * |
| 赵凯.配电系统多目标综合优化运行的研究.《中国优秀硕士学位论文全文数据库-工程科技II辑》.2002,全文. * |
Also Published As
| Publication number | Publication date |
|---|---|
| CN111708987A (en) | 2020-09-25 |
Similar Documents
| Publication | Publication Date | Title |
|---|---|---|
| WO2021213192A1 (en) | Load prediction method and load prediction system employing general distribution | |
| CN110474339B (en) | Power grid reactive power control method based on deep power generation load prediction | |
| CN108388962B (en) | Wind power prediction system and method | |
| CN110334952A (en) | A kind of distribution network planning Post-assessment Method based on the improved grey model degree of association | |
| CN111708987B (en) | Method for predicting load of multiple parallel transformers of transformer substation | |
| CN110222897A (en) | A kind of distribution network reliability analysis method | |
| CN110490409B (en) | DNN-based low-voltage transformer area line loss rate benchmarking value setting method | |
| CN102426674A (en) | Power system load prediction method based on Markov chain | |
| CN114372360A (en) | Method, terminal and storage medium for power load prediction | |
| CN114140176B (en) | Adjustable capacity prediction method and device for load aggregation platform | |
| CN109787295B (en) | Wind power ultra-short term prediction calculation method considering wind power plant state | |
| CN110969478A (en) | Method for multidimensional improvement of energy storage value under new energy high-permeability background | |
| CN107977898B (en) | Generated energy insurance pricing evaluation method of photovoltaic power station | |
| Monteiro et al. | Long-term sizing of lead–acid batteries in order to reduce technical losses on distribution networks: A distributed generation approach | |
| CN117332215A (en) | High-low voltage power distribution cabinet abnormal fault information remote monitoring system | |
| CN115545333A (en) | Method for predicting load curve of multi-load daily-type power distribution network | |
| CN111724049A (en) | Research and judgment method for potential power energy efficiency service customer | |
| CN117236638B (en) | Canal micro-grid distributed energy management system based on multi-mode network | |
| CN108108871B (en) | Type selection method for wind power plant group power transmission equipment | |
| CN108345996B (en) | System and method for reducing wind power assessment electric quantity | |
| Duan et al. | Heavy Overload Prediction Method of Distribution Transformer Based on GBDT | |
| Ye et al. | Short term output prediction method of runoff type medium and small hydropower stations | |
| CN113705103A (en) | Distributed photovoltaic power separation method based on improved BP neural network | |
| CN112446551A (en) | Power grid investment measuring and calculating method and device, electronic equipment and storage medium | |
| Zhong et al. | An evaluation method of voltage characteristics for medium-voltage distribution network considering probability distribution and fluctuation |
Legal Events
| Date | Code | Title | Description |
|---|---|---|---|
| PB01 | Publication | ||
| PB01 | Publication | ||
| SE01 | Entry into force of request for substantive examination | ||
| SE01 | Entry into force of request for substantive examination | ||
| GR01 | Patent grant | ||
| GR01 | Patent grant |