CN110676855B - Intelligent optimization adjustment method for reactive voltage control parameters of power distribution network - Google Patents
Intelligent optimization adjustment method for reactive voltage control parameters of power distribution network Download PDFInfo
- Publication number
- CN110676855B CN110676855B CN201910942342.8A CN201910942342A CN110676855B CN 110676855 B CN110676855 B CN 110676855B CN 201910942342 A CN201910942342 A CN 201910942342A CN 110676855 B CN110676855 B CN 110676855B
- Authority
- CN
- China
- Prior art keywords
- parameters
- power distribution
- distribution network
- reactive voltage
- voltage control
- 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 28
- 238000005457 optimization Methods 0.000 title claims abstract description 28
- 230000002159 abnormal effect Effects 0.000 claims description 23
- 238000013528 artificial neural network Methods 0.000 claims description 21
- 239000013598 vector Substances 0.000 claims description 15
- 238000004364 calculation method Methods 0.000 claims description 12
- 238000012549 training Methods 0.000 claims description 12
- 238000012937 correction Methods 0.000 claims description 6
- 238000012417 linear regression Methods 0.000 claims description 6
- 238000007781 pre-processing Methods 0.000 claims description 4
- 238000011156 evaluation Methods 0.000 claims description 3
- 238000010606 normalization Methods 0.000 claims description 3
- 238000012545 processing Methods 0.000 claims description 3
- 238000011160 research Methods 0.000 abstract description 2
- 238000012986 modification Methods 0.000 description 2
- 230000004048 modification Effects 0.000 description 2
- 230000005856 abnormality Effects 0.000 description 1
- 230000032683 aging Effects 0.000 description 1
- 230000009286 beneficial effect Effects 0.000 description 1
- 230000007547 defect Effects 0.000 description 1
- 238000012217 deletion Methods 0.000 description 1
- 230000037430 deletion Effects 0.000 description 1
- 210000001061 forehead Anatomy 0.000 description 1
- 238000012423 maintenance Methods 0.000 description 1
- 238000005259 measurement Methods 0.000 description 1
Classifications
-
- H—ELECTRICITY
- H02—GENERATION; CONVERSION OR DISTRIBUTION OF ELECTRIC POWER
- H02J—CIRCUIT ARRANGEMENTS OR SYSTEMS FOR SUPPLYING OR DISTRIBUTING ELECTRIC POWER; SYSTEMS FOR STORING ELECTRIC ENERGY
- H02J3/00—Circuit arrangements for ac mains or ac distribution networks
- H02J3/12—Circuit arrangements for ac mains or ac distribution networks for adjusting voltage in ac networks by changing a characteristic of the network load
- H02J3/16—Circuit arrangements for ac mains or ac distribution networks for adjusting voltage in ac networks by changing a characteristic of the network load by adjustment of reactive power
-
- H—ELECTRICITY
- H02—GENERATION; CONVERSION OR DISTRIBUTION OF ELECTRIC POWER
- H02J—CIRCUIT ARRANGEMENTS OR SYSTEMS FOR SUPPLYING OR DISTRIBUTING ELECTRIC POWER; SYSTEMS FOR STORING ELECTRIC ENERGY
- H02J3/00—Circuit arrangements for ac mains or ac distribution networks
- H02J3/18—Arrangements for adjusting, eliminating or compensating reactive power in networks
-
- 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
- Y02—TECHNOLOGIES OR APPLICATIONS FOR MITIGATION OR ADAPTATION AGAINST CLIMATE CHANGE
- Y02E—REDUCTION OF GREENHOUSE GAS [GHG] EMISSIONS, RELATED TO ENERGY GENERATION, TRANSMISSION OR DISTRIBUTION
- Y02E40/00—Technologies for an efficient electrical power generation, transmission or distribution
- Y02E40/30—Reactive power compensation
Landscapes
- Engineering & Computer Science (AREA)
- Power Engineering (AREA)
- Supply And Distribution Of Alternating Current (AREA)
Abstract
The invention relates to the technical field of optimization adjustment of reactive voltage control parameters of a power distribution network, in particular to an intelligent optimization adjustment method of reactive voltage control parameters of the power distribution network. According to the intelligent power distribution network reactive voltage three-level coordination control method, research and analysis can be conducted on the reactive voltage three-level coordination control parameters of the power distribution network, and intelligent optimization adjustment is conducted on target parameters of the three-level coordination control of the power distribution network, so that the reactive voltage level of the whole power distribution network is improved.
Description
Technical Field
The invention relates to the technical field of optimization adjustment of reactive voltage control parameters of a power distribution network, in particular to an intelligent optimization adjustment method of reactive voltage control parameters of a power distribution network.
Background
Aiming at inaccurate data measurement of the power distribution network, a learner proposes to identify and correct the data by adopting a time sequence method and an RBF neural network, but the method does not optimally learn the measured data of the power distribution network and gives more meaningful guidance; the scholars also adopt a gray GM (1, 1) model algorithm to correct the bad data of the power distribution network load system, but do not study the parameter optimization targets of the load data and reactive voltage of the corrected forehead distribution network station; in addition, when a learner aims at bad data in a large amount of data, an improved data rejection algorithm is proposed to solve the problem, and application analysis is not performed on an actual power distribution network.
Disclosure of Invention
The invention aims to overcome the defect that the existing method cannot intelligently optimize the reactive voltage control parameters of a power distribution network, and provides an intelligent optimization adjustment method for the reactive voltage control parameters of the power distribution network, wherein the control target is reactive voltage control of a transformer substation, a 10kV line and a transformer area, and the intelligent optimization adjustment method can be used for researching and analyzing the reactive voltage three-level coordination control parameters of the power distribution network and intelligently optimizing and adjusting the target parameters of the three-level coordination control of the power distribution network so as to improve the reactive voltage level of the whole power distribution network.
In order to solve the technical problems, the invention adopts the following technical scheme:
the intelligent optimization adjustment method for the reactive voltage control parameters of the power distribution network comprises the following steps:
s1, collecting reactive voltage control parameters of a power distribution network, and preprocessing bad parameters in the reactive voltage control parameters;
s2, taking a power factor of three-level coordination control of the power grid as a target parameter, and optimizing and adjusting the target parameter based on the RBF neural network;
s3, transmitting the parameters subjected to optimization adjustment to a three-level voltage coordination controller of the power distribution network in real time.
The invention discloses an intelligent optimization adjustment method for reactive voltage control parameters of a power distribution network, which can conduct research and analysis on the reactive voltage three-level coordination control parameters of the power distribution network, and conduct intelligent optimization adjustment on target parameters of the three-level coordination control of the power distribution network so as to improve the reactive voltage level of the whole power distribution network.
Further, the specific steps of the step S1 are as follows:
s11, eliminating the obviously abnormal parameters, and then carrying out subset regression on the residual parameters within the abnormal parameter range;
s12, repairing the missing parameters by using a Lagrange difference algorithm.
Further, in step S11, the following linear regression model is utilized:
where m+n=k, M n=Φ, myn= {1,2,..k };
recording device
Y=(Y 1 ,Y 2 ,...,Y K ) T ,X=(X 1 ,X 2 ,...,X K ) T ,
H=(h ii ) K×K =X(X T X) -1 X R ,
δ=(W 1 ,W 2 ,…,W K ) T =(I-H)Y,
In the formula, { e i i.e.M. is independently subject to N (0, e) 2 ) Random variable set, { Z j j.epsilon.N } is independently subject to N (0, be) 2 ) The random variable set M, N represents two unknown index sets, M represents the number of indexes in the unknown index set M, and N represents the number of indexes in the unknown index set N.
Further, in step S11, the following stopping rule is used for preventing the normal parameters from being culled:
E||W|| 2 =(K-L)c 2 ,
Y i e -2 ~i 2 (1),
when the probability is 0.995, there are
For the linear regression model, takeWhen->Consider Y j Is an abnormal parameter;
taking outWhen Y is i <T||W|| 2 Consider Y i Is a normal parameter.
Further, in step S11, the number of remaining parameters is K 2 =K-t 1 -m 1 The number of the residual abnormal parameters is n 1 =K·10%-t 1 The method comprises the steps of carrying out a first treatment on the surface of the Wherein t is 1 And m 1 Respectively representing the number of abnormal parameters and normal parameters, K represents the total number of parameters, K 2 Representing the remaining ginsengSeveral numbers, n 1 Representing the number of residual abnormal parameters, and K is the number of residual parameters 2 By passing throughSum of squares of residuals->Finding an abnormal data set J, wherein:
further, the specific steps of the step S12 are as follows:
S 121. let x= { X 0 ,x 1 ,x 2 ,...,x n And Y= { Y } is the interpolation sample set 0 ,y 1 ,y 2 ,...,y n The value of the corresponding X function is shown, n represents the number of the nodes, and X represents the interpolated nodes;
s122, inputting n+1 interpolation sample points x 0 ,x 1 ,x 2 ,...,x n And the corresponding function value y 0 ,y 1 ,y 2 ,...,y n ;
S123, calculating an n-order Lagrange basis function:
wherein i=0, 1,2,..n;
s124, calculating an n-order Lagrange interpolation function:
wherein, I i (x) Representing an n-th order Lagrangian basis function;
s125, inputting an interpolation point x and bringing the interpolation point x into the interpolation function in the step S124 to obtain a calculation result.
Further, the specific steps of the step S2 are as follows:
s21, adaptively adjusting parameters subjected to correction based on an RBF neural network algorithm;
s22, aiming at the three-level coordination control target parameters of the power distribution network, which mainly are the voltage and the power factor of each level, the three-level coordination control target parameters are optimally adjusted and coordinated.
Further, the specific steps of the step S21 are as follows:
s211, selecting a Gaussian functionAs a function of the basis function,
wherein c represents the center of the basis function, and σ represents the width of the radial basis function;
s212, acquiring a basis function center c, wherein the constraint conditions are as follows:
d i1 =min||x p -c i ||,(p=1,2,...,P,i=1,2,...,k),
wherein x is p (p=1, 2,., P) represents training data, c i Representing the starting center;
s213, acquiring the width sigma of the radial basis function, wherein the calculation formula of the width sigma is as follows:
σ i =bd i ,i=1,2,...,k,
d i2 =min||c i -c g ||,
wherein, c i ,c j All represent the center of a certain class, b represents the overlap coefficient, d i1 、d i2 All represent constraint conditions;
s214, acquiring a weight W, wherein the calculation formula of the weight W is as follows:
W j =(H T H) -1 H T T j ,j=1,2,...,m,
wherein H= [ H ] 1 ,h 2 ,...,h k ]Represents the intermediate layer output vector, h represents the radial basis function, k represents the number of intermediate layers, and m represents the output layerThe number T represents the network output target amount T j Representing the j-th emissive layer element.
Further, the specific steps of the step S22 are as follows:
s221, setting a target voltage and a target power factor;
s222, establishing an RBF neural network with a plurality of input vectors, a plurality of voltage and power factor output vectors of a three-level network of the power distribution network;
s223, constructing a training sample, carrying out normalization processing on the training sample, and then training an RBF neural network through the processed data;
s224, inputting an input vector into the RBF neural network which is trained in the step S222 to obtain a group of corresponding output values, and comparing the output values with the target voltage and the target power factor of the step S221;
s225, evaluating the accuracy of the corrected output result by using the relative error, and evaluating the correction capability of the RBF neural network; the evaluation calculation formula is as follows:
wherein Z represents an actual value, Z f Indicating the corrected value.
Further, in step S222, the several input vectors include distribution network voltages, currents, phase angles, active power, reactive power of different voltage classes.
Compared with the prior art, the invention has the beneficial effects that:
the invention relates to an intelligent optimization adjustment method for reactive voltage control parameters of a power distribution network, which can reduce the action times of reactive voltage control equipment by preprocessing bad parameters, then performing intelligent optimization adjustment on power factors of three-level coordination control of the power distribution network based on an RBF neural network, and transmitting an optimized target value to a three-level voltage coordination controller of the power distribution network in real time so as to improve the reactive voltage level of the whole power distribution network.
Drawings
Fig. 1 is a flowchart of an intelligent optimization adjustment method for reactive voltage control parameters of a power distribution network.
Detailed Description
The invention is further described below in connection with the following detailed description. Wherein the drawings are for illustrative purposes only and are shown in schematic, non-physical, and not intended to be limiting of the present patent; for the purpose of better illustrating embodiments of the invention, certain elements of the drawings may be omitted, enlarged or reduced and do not represent the size of the actual product; it will be appreciated by those skilled in the art that certain well-known structures in the drawings and descriptions thereof may be omitted.
The same or similar reference numbers in the drawings of embodiments of the invention correspond to the same or similar components; in the description of the present invention, it should be understood that, if there is an azimuth or positional relationship indicated by terms such as "upper", "lower", "left", "right", etc., based on the azimuth or positional relationship shown in the drawings, it is only for convenience of describing the present invention and simplifying the description, but it is not indicated or implied that the apparatus or element referred to must have a specific azimuth, be constructed and operated in a specific azimuth, and thus terms describing the positional relationship in the drawings are merely illustrative and should not be construed as limitations of the present patent, and specific meanings of the terms described above may be understood by those skilled in the art according to specific circumstances.
Example 1
Fig. 1 shows a first embodiment of an intelligent optimization adjustment method for reactive voltage control parameters of a power distribution network, which comprises the following steps:
s1, collecting reactive voltage control parameters of a power distribution network, and preprocessing bad parameters in the reactive voltage control parameters;
s2, taking the power factor of the three-level coordination control power supply box of the power grid as a target parameter, and optimizing and adjusting the target parameter based on the RBF neural network;
s3, transmitting the parameters subjected to optimization adjustment to a three-level voltage coordination controller of the power distribution network in real time.
The pretreatment of the bad parameters aims at correcting or eliminating the problem of abnormity and errors of the acquisition parameters in the power distribution system. Reactive voltage analysis of power distribution historical data is usually a parameter within one year, and the parameter quantity is huge, so that a point-by-point removal method is adopted to find out obviously abnormal parameter points, then normal parameters are determined, and finally all possible subset regression is carried out on the remaining parameters within an abnormal parameter range. In addition, because the power distribution network can cause data deletion or abnormality due to equipment power failure maintenance, equipment acquisition channel failure or aging, the missing parameters are also required to be repaired. The specific steps of step S1 are as follows:
s11, eliminating the obviously abnormal parameters, and then carrying out subset regression on the residual parameters within the abnormal parameter range;
s12, repairing the missing parameters by using a Lagrange difference algorithm.
Specifically, in step S11, the following linear regression model is utilized:
where m+n=k, M n=Φ, myn= {1,2,..k };
recording device
Y=(Y 1 ,Y 2 ,...,Y K ) T ,X=(X 1 ,X 2 ,...,X K ) T ,
H=(h ii ) K×K =X(X T X) -1 X T ,
δ=(W 1 ,W 2 ,…,W K ) T =(I-H)Y,
In the formula, { e i i.e.M. is independently subject to N (0, e) 2 ) Random variable set, { Z j j.epsilon.N } is independently subject to N (0, be) 2 ) Random variable set M, N represents two unknown index sets, m represents unknown fingersThe number of indexes in the index set M, and N represents the number of indexes in the unknown index set N.
To prevent the normal parameters from being culled, the following stopping rules are used:
E||W|| 2 =(K-L)e 2 ,
Y i e -2 ~i 2 (1),
when the probability is 0.995, there are
For the linear regression model, takeWhen->Consider Y j Is an abnormal parameter;
taking outWhen Y is i <T||W|| 2 Consider Y i Is a normal parameter.
The number of the residual parameters obtained through the steps is K 2 =K-t 1 -m 1 The number of the residual abnormal parameters is n 1 =K·10%-t 1 The method comprises the steps of carrying out a first treatment on the surface of the Wherein t is 1 And m 1 Respectively representing the number of abnormal parameters and normal parameters, K represents the total number of parameters, K 2 Indicating the number of remaining parameters, n 1 Representing the number of residual abnormal parameters, and K is the number of residual parameters 2 By passing throughSum of squares of residuals->Finding an abnormal data set J, wherein:
specifically, the specific steps of step S12 are:
s121. let x= { X 0 ,x 1 ,x 2 ,...,x n And Y= { Y } is the interpolation sample set 0 ,y 1 ,y 2 ,...,y n The value of the corresponding X function is shown, n represents the number of the nodes, and X represents the interpolated nodes;
s122, inputting n+1 interpolation sample points x 0 ,x 1 ,x 2 ,...,x n And the corresponding function value y 0 ,y 1 ,y 2 ,...,y n ;
S123, calculating an n-order Lagrange basis function:
wherein i=0, 1,2,..n;
s124, calculating an n-order Lagrange interpolation function:
wherein, I i (x) Representing an n-th order Lagrangian basis function;
s125, inputting an interpolation point x and bringing the interpolation point x into the interpolation function in the step S124 to obtain a calculation result.
Example 2
The embodiment is similar to embodiment 1, except that the specific steps of step S2 in the embodiment are as follows:
s21, adaptively adjusting parameters subjected to correction based on an RBF neural network algorithm;
s22, aiming at the three-level coordination control target parameters of the power distribution network, mainly including the voltage and the power factor of each level, optimizing and adjusting the three-level coordination control target parameters; wherein, the control target parameters of the reactive voltage are the voltage U and the voltage of the transformer substation, the feeder line and the transformer areaPower factor
Specifically, the specific steps of step S21 are:
s211, selecting a Gaussian functionAs a function of the basis function,
wherein c represents the center of the basis function, and σ represents the width of the radial basis function;
s212, acquiring a basis function center c, wherein the constraint conditions are as follows:
d i1 =min||x p -c i ||,(p=1,2,...,P,i=1,2,...,k),
wherein x is p (p=1, 2,., P) represents training data, c i Representing the starting center;
s213, acquiring the width sigma of the radial basis function, wherein the calculation formula of the width sigma is as follows:
σ i =bd i ,i=1,2,...,k,
d i2 =min||c i -c g ||,
wherein, c i ,c j All represent the center of a certain class, b represents the overlap coefficient, d i1 、d i2 All represent constraint conditions;
s214, acquiring a weight W, wherein the calculation formula of the weight W is as follows:
W j =(H T H) -1 H R T j ,j=1,2,...,m,
wherein H= [ H ] 1 ,h 2 ,...,h k ]Represents an intermediate layer output vector, h represents a radial basis function, k represents the number of intermediate layers, m represents the number of output layers, T represents a network output target amount, T j Representing the j-th emissive layer element.
Specifically, the specific steps of step S22 are:
s221, setting a target voltage and a target power factor;
s222, establishing an RBF neural network with a plurality of input vectors, a plurality of voltage and power factor output vectors of a three-level network of the power distribution network; the input vectors comprise power distribution network voltages, currents, phase angles, active power and reactive power of different voltage classes;
s223, constructing a training sample, carrying out normalization processing on the training sample, and then training an RBF neural network through the processed data;
s224, inputting an input vector into the RBF neural network which is trained in the step S222 to obtain a group of corresponding output values, and comparing the output values with the target voltage and the target power factor of the step S221;
s225, evaluating the accuracy of the corrected output result by using the relative error, and evaluating the correction capability of the RBF neural network; the evaluation calculation formula is as follows:
wherein Z represents an actual value, Z f Indicating the corrected value.
And the reactive power and voltage target values of the distribution network are optimally learned based on the RBF neural network and are transmitted to a three-level voltage coordination controller of the distribution network in real time, so that the action times of reactive voltage control equipment are reduced, and the reactive voltage level of the whole distribution network is improved.
It is to be understood that the above examples of the present invention are provided by way of illustration only and not by way of limitation of the embodiments of the present invention. Other variations or modifications of the above teachings will be apparent to those of ordinary skill in the art. It is not necessary here nor is it exhaustive of all embodiments. Any modification, equivalent replacement, improvement, etc. which come within the spirit and principles of the invention are desired to be protected by the following claims.
Claims (8)
1. The intelligent optimization adjustment method for the reactive voltage control parameters of the power distribution network is characterized by comprising the following steps of:
s1, collecting reactive voltage control parameters of a power distribution network, and preprocessing bad parameters in the reactive voltage control parameters; the specific steps of the step S1 are as follows:
s11, eliminating the obviously abnormal parameters, and then carrying out subset regression on the residual parameters within the abnormal parameter range; wherein the following linear regression model is utilized:
wherein m+n=k, M n=Φ, M n= {1,2, & gt, K };
recording device
Y=(Y 1 ,Y 2 ,...,Y K ) T ,X=(X 1 ,X 2 ,...,X K ) T ,
H=(h ii ) K×K =X(X T X) -1 X T ,
δ=(W 1 ,W 2 ,...,W K ) T =(I-H)Y,
In the formula, { e i i.e.M. is independently subject to N (0, e) 2 ) Random variable set, { Z j j.epsilon.N } is independently subject to N (0, be) 2 ) A random variable set M, N represents two unknown index sets, M represents the number of indexes in the unknown index set M, and N represents the number of indexes in the unknown index set N;
s12, repairing the missing parameters by using a Lagrangian difference method;
s2, taking a power factor of three-level coordination control of the power grid as a target parameter, and optimizing and adjusting the target parameter based on the RBF neural network;
s3, transmitting the parameters subjected to optimization adjustment to a three-level voltage coordination controller of the power distribution network in real time.
2. The intelligent optimization adjustment method for reactive voltage control parameters of power distribution network according to claim 1, wherein in step S11, the following stopping rules are used to prevent the normal parameters from being removed:
E||W|| 2 =(K-L)e 2 ,
Y i e -2 ~i 2 (1),
when the probability is 0.995, there are
For the linear regression model, takeWhen->Consider Y j Is an abnormal parameter;
taking outWhen Y is i <T||W|| 2 Consider Y i Is a normal parameter.
3. The intelligent optimization adjustment method for reactive voltage control parameters of power distribution network according to claim 2, wherein in step S11, the number of remaining parameters is K 2 =K-t 1 -m 1 The number of the residual abnormal parameters is n 1 =K·10%-t 1 The method comprises the steps of carrying out a first treatment on the surface of the Wherein t is 1 And m 1 Respectively representing the number of abnormal parameters and normal parameters, K represents the total number of parameters, K 2 Indicating the number of remaining parameters, n 1 Representing the number of residual abnormal parameters, and K is the number of residual parameters 2 By passing throughSum of squares of residuals->Finding an abnormal data set J, wherein:
4. the intelligent optimization adjustment method for the reactive voltage control parameters of the power distribution network according to claim 1, wherein the specific steps of the step S12 are as follows:
s121. assume x= (X) 0 ,x 1 ,x 2 ,...,x n And y= (Y) is the interpolated sample set 0 ,y 1 ,y 2 ,...,y n The value of the corresponding X function is shown, n represents the number of the nodes, and X represents the interpolated nodes;
s122, inputting n+1 interpolation sample points x 0 ,x 1 ,x 2 ,...,x n And the corresponding function value y 0 ,y 1 ,y 2 ,...,y n ;
S123, calculating an n-order Lagrange basis function:
wherein i=0, 1,2,..n;
s124, calculating an n-order Lagrange interpolation function:
wherein, I i (x) Representing an n-th order Lagrangian basis function;
s125, inputting an interpolation point x and bringing the interpolation point x into the interpolation function in the step S124 to obtain a calculation result.
5. The intelligent optimization adjustment method for the reactive voltage control parameters of the power distribution network according to claim 1, wherein the specific steps of the step S2 are as follows:
s21, adaptively adjusting parameters subjected to correction based on an RBF neural network algorithm;
s22, aiming at the three-level coordination control target parameters of the power distribution network, which mainly are the voltage and the power factor of each level, the three-level coordination control target parameters are optimally adjusted and coordinated.
6. The intelligent optimization adjustment method for the reactive voltage control parameters of the power distribution network according to claim 5, wherein the specific steps of the step S21 are as follows:
s211, selecting a Gaussian functionAs a function of the basis function,
wherein c represents the center of the basis function, and σ represents the width of the radial basis function;
s212, acquiring a basis function center c, wherein the constraint conditions are as follows:
d i1 =min||x p -c i ||,(p=1,2,...,P,i=1,2,...,k),
wherein x is p (p=1, 2,., P) represents training data, c i Representing the starting center;
s213, acquiring the width sigma of the radial basis function, wherein the calculation formula of the width sigma is as follows:
σ i =bd i ,i=1,2,...,k,
d i2 =min||c i -c g ||,
wherein, c i ,c j All represent the center of a certain class, b represents the overlap coefficient, d i1 、d i2 All represent constraint conditions;
s214, acquiring a weight W, wherein the calculation formula of the weight W is as follows:
W j =(H T H) -1 H T T j ,j=1,2,...,m,
wherein H= [ H ] 1 ,h 2 ,...,h k ]Represents the intermediate layer output vector, h represents the radial basis functionNumber k represents the number of intermediate layers, m represents the number of output layers, T represents the network output target amount, T j Representing the j-th emissive layer element.
7. The intelligent optimization adjustment method for the reactive voltage control parameters of the power distribution network according to claim 5, wherein the specific steps of the step S22 are as follows:
s221, setting a target voltage and a target power factor;
s222, establishing an RBF neural network with a plurality of input vectors, a plurality of voltage and power factor output vectors of a three-level network of the power distribution network;
s223, constructing a training sample, carrying out normalization processing on the training sample, and then training an RBF neural network through the processed data;
s224, inputting an input vector into the RBF neural network which is trained in the step S222 to obtain a group of corresponding output values, and comparing the output values with the target voltage and the target power factor of the step S221;
s225, evaluating the accuracy of the corrected output result by using the relative error, and evaluating the correction capability of the RBF neural network; the evaluation calculation formula is as follows:
wherein Z represents an actual value, Z f Indicating the corrected value.
8. The intelligent optimization method for the reactive voltage control parameters of the power distribution network according to claim 7, wherein in step S222, the plurality of input vectors include the power distribution network voltages, currents, phase angles, active power and reactive power of different voltage classes.
Priority Applications (1)
Application Number | Priority Date | Filing Date | Title |
---|---|---|---|
CN201910942342.8A CN110676855B (en) | 2019-09-30 | 2019-09-30 | Intelligent optimization adjustment method for reactive voltage control parameters of power distribution network |
Applications Claiming Priority (1)
Application Number | Priority Date | Filing Date | Title |
---|---|---|---|
CN201910942342.8A CN110676855B (en) | 2019-09-30 | 2019-09-30 | Intelligent optimization adjustment method for reactive voltage control parameters of power distribution network |
Publications (2)
Publication Number | Publication Date |
---|---|
CN110676855A CN110676855A (en) | 2020-01-10 |
CN110676855B true CN110676855B (en) | 2023-10-31 |
Family
ID=69078866
Family Applications (1)
Application Number | Title | Priority Date | Filing Date |
---|---|---|---|
CN201910942342.8A Active CN110676855B (en) | 2019-09-30 | 2019-09-30 | Intelligent optimization adjustment method for reactive voltage control parameters of power distribution network |
Country Status (1)
Country | Link |
---|---|
CN (1) | CN110676855B (en) |
Families Citing this family (1)
Publication number | Priority date | Publication date | Assignee | Title |
---|---|---|---|---|
CN111193269B (en) * | 2020-02-19 | 2023-05-30 | 云南电网有限责任公司昆明供电局 | Automatic voltage control parameter configuration method based on automatic generation of statistical report |
Citations (11)
Publication number | Priority date | Publication date | Assignee | Title |
---|---|---|---|---|
CN102231144A (en) * | 2011-06-03 | 2011-11-02 | 中国电力科学研究院 | Method for predicting theoretical line loss of power distribution network based on Boosting algorithm |
CN104485692A (en) * | 2014-12-02 | 2015-04-01 | 常州大学 | Distributed photovoltaic power generation energy dispatching system and method |
CN105610162A (en) * | 2016-01-04 | 2016-05-25 | 河海大学常州校区 | Adaptive fuzzy sliding mode RBF neural network control method for active power filter |
CN106354995A (en) * | 2016-08-24 | 2017-01-25 | 华北电力大学(保定) | Predicting method based on Lagrange interpolation and time sequence |
CN106549392A (en) * | 2016-10-12 | 2017-03-29 | 中国南方电网有限责任公司电网技术研究中心 | A kind of power distribution network control method for coordinating |
CN107257133A (en) * | 2017-06-12 | 2017-10-17 | 浙江群力电气有限公司 | A kind of idle work optimization method, device and AVC systems |
CN108336739A (en) * | 2018-01-15 | 2018-07-27 | 重庆大学 | A kind of Probabilistic Load Flow on-line calculation method based on RBF neural |
CN108734391A (en) * | 2018-05-08 | 2018-11-02 | 重庆大学 | Electric-gas integrated energy system probability energy flow computational methods based on storehouse noise reduction autocoder |
CN109687479A (en) * | 2017-10-19 | 2019-04-26 | 中国南方电网有限责任公司 | Power swing stabilizes method, system, storage medium and computer equipment |
CN109726503A (en) * | 2019-01-12 | 2019-05-07 | 国电联合动力技术有限公司 | Missing data complementing method and device |
CN109816017A (en) * | 2019-01-24 | 2019-05-28 | 电子科技大学 | Power grid missing data complementing method based on fuzzy clustering and Lagrange's interpolation |
-
2019
- 2019-09-30 CN CN201910942342.8A patent/CN110676855B/en active Active
Patent Citations (11)
Publication number | Priority date | Publication date | Assignee | Title |
---|---|---|---|---|
CN102231144A (en) * | 2011-06-03 | 2011-11-02 | 中国电力科学研究院 | Method for predicting theoretical line loss of power distribution network based on Boosting algorithm |
CN104485692A (en) * | 2014-12-02 | 2015-04-01 | 常州大学 | Distributed photovoltaic power generation energy dispatching system and method |
CN105610162A (en) * | 2016-01-04 | 2016-05-25 | 河海大学常州校区 | Adaptive fuzzy sliding mode RBF neural network control method for active power filter |
CN106354995A (en) * | 2016-08-24 | 2017-01-25 | 华北电力大学(保定) | Predicting method based on Lagrange interpolation and time sequence |
CN106549392A (en) * | 2016-10-12 | 2017-03-29 | 中国南方电网有限责任公司电网技术研究中心 | A kind of power distribution network control method for coordinating |
CN107257133A (en) * | 2017-06-12 | 2017-10-17 | 浙江群力电气有限公司 | A kind of idle work optimization method, device and AVC systems |
CN109687479A (en) * | 2017-10-19 | 2019-04-26 | 中国南方电网有限责任公司 | Power swing stabilizes method, system, storage medium and computer equipment |
CN108336739A (en) * | 2018-01-15 | 2018-07-27 | 重庆大学 | A kind of Probabilistic Load Flow on-line calculation method based on RBF neural |
CN108734391A (en) * | 2018-05-08 | 2018-11-02 | 重庆大学 | Electric-gas integrated energy system probability energy flow computational methods based on storehouse noise reduction autocoder |
CN109726503A (en) * | 2019-01-12 | 2019-05-07 | 国电联合动力技术有限公司 | Missing data complementing method and device |
CN109816017A (en) * | 2019-01-24 | 2019-05-28 | 电子科技大学 | Power grid missing data complementing method based on fuzzy clustering and Lagrange's interpolation |
Non-Patent Citations (2)
Title |
---|
Immune RBF neural network algorithm for DSTATCOM;G.Arthy等;《2016 International Conference on Computer Communication and Informatics (ICCCI)》;20160530;1-6页 * |
基于负荷预测的500kV变电站无功优化研究;黄厚明;《中国优秀硕士学位论文全文数据库》;20170215(第02期);29-43页 * |
Also Published As
Publication number | Publication date |
---|---|
CN110676855A (en) | 2020-01-10 |
Similar Documents
Publication | Publication Date | Title |
---|---|---|
CN110263866B (en) | Power consumer load interval prediction method based on deep learning | |
CN106548230B (en) | Diagnosis Method of Transformer Faults based on Modified particle swarm optimization neural network | |
CN116757534B (en) | Intelligent refrigerator reliability analysis method based on neural training network | |
CN110443447B (en) | Method and system for adjusting power system load flow based on deep reinforcement learning | |
CN110688809B (en) | Box transformer fault diagnosis method based on VPRS-RBF neural network | |
CN110766212A (en) | Ultra-short-term photovoltaic power prediction method for historical data missing electric field | |
CN110119588B (en) | On-line optimization design method based on extended Kalman filtering state estimation value | |
CN114386312A (en) | Equipment fault diagnosis method | |
CN110738349A (en) | Power grid fault first-aid repair duration prediction method based on multi-model fusion | |
CN110045317B (en) | Mutual inductor metering error online detection method and system | |
CN115293326A (en) | Training method and device of power load prediction model and power load prediction method | |
CN110676855B (en) | Intelligent optimization adjustment method for reactive voltage control parameters of power distribution network | |
CN110766190A (en) | Power distribution network load prediction method | |
CN115062864A (en) | Method and system for decomposing-integrating prediction of medium-term load of power distribution network | |
CN113984969A (en) | Air quality prediction method and system based on multi-source space-time data fusion | |
CN110096723B (en) | High-voltage switch cabinet insulation state analysis method based on operation and maintenance detection big data | |
Wang et al. | A DRL-aided multi-layer stability model calibration platform considering multiple events | |
CN112651519A (en) | Secondary equipment fault positioning method and system based on deep learning theory | |
CN103952724B (en) | For the optimization weight Relative Principal Component Analysis Algorithm of aluminium cell condition trouble diagnosis | |
CN113866552B (en) | Medium voltage distribution network user electricity consumption abnormality diagnosis method based on machine learning | |
CN111882114A (en) | Short-term traffic flow prediction model construction method and prediction method | |
CN113189513B (en) | Ripple-based redundant power supply current sharing state identification method | |
CN117313522A (en) | Oil immersed transformer service life prediction method based on digital-analog interaction and federal learning | |
CN108345996B (en) | System and method for reducing wind power assessment electric quantity | |
CN115146827B (en) | Power distribution network online optimization method considering measurement deficiency |
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 | ||
TA01 | Transfer of patent application right |
Effective date of registration: 20230918 Address after: No.17 Binhe Road, Nanming District, Guiyang City, Guizhou Province Applicant after: Guizhou Power Grid Co.,Ltd. Address before: 556000 No.3, Ningbo West Road, Kaili City, Qiandongnan Miao and Dong Autonomous Prefecture, Guizhou Province Applicant before: KAILI POWER SUPPLY BUREAU, GUIZHOU POWER GRID CO.,LTD. |
|
TA01 | Transfer of patent application right | ||
GR01 | Patent grant | ||
GR01 | Patent grant |