CN113094636A - Interference user harmonic level estimation method based on massive monitoring data - Google Patents
Interference user harmonic level estimation method based on massive monitoring data Download PDFInfo
- Publication number
- CN113094636A CN113094636A CN202110428975.4A CN202110428975A CN113094636A CN 113094636 A CN113094636 A CN 113094636A CN 202110428975 A CN202110428975 A CN 202110428975A CN 113094636 A CN113094636 A CN 113094636A
- Authority
- CN
- China
- Prior art keywords
- amplitude
- harmonic
- interference
- cloud
- user
- Prior art date
- Legal status (The legal status is an assumption and is not a legal conclusion. Google has not performed a legal analysis and makes no representation as to the accuracy of the status listed.)
- Pending
Links
- 238000000034 method Methods 0.000 title claims abstract description 53
- 238000012544 monitoring process Methods 0.000 title claims abstract description 22
- 238000013528 artificial neural network Methods 0.000 claims abstract description 26
- 238000011156 evaluation Methods 0.000 claims abstract description 18
- 230000008569 process Effects 0.000 claims abstract description 14
- 230000002452 interceptive effect Effects 0.000 claims description 20
- 238000012549 training Methods 0.000 claims description 18
- 108010062616 filensin Proteins 0.000 claims description 14
- 238000004590 computer program Methods 0.000 claims description 13
- 238000004422 calculation algorithm Methods 0.000 claims description 9
- 238000003860 storage Methods 0.000 claims description 6
- 238000005070 sampling Methods 0.000 claims description 5
- 238000004364 calculation method Methods 0.000 abstract description 4
- 238000013507 mapping Methods 0.000 abstract description 3
- 238000003062 neural network model Methods 0.000 abstract description 3
- 238000010586 diagram Methods 0.000 description 8
- 238000004519 manufacturing process Methods 0.000 description 5
- 238000009826 distribution Methods 0.000 description 4
- 230000006870 function Effects 0.000 description 4
- 238000012545 processing Methods 0.000 description 4
- FGUUSXIOTUKUDN-IBGZPJMESA-N C1(=CC=CC=C1)N1C2=C(NC([C@H](C1)NC=1OC(=NN=1)C1=CC=CC=C1)=O)C=CC=C2 Chemical compound C1(=CC=CC=C1)N1C2=C(NC([C@H](C1)NC=1OC(=NN=1)C1=CC=CC=C1)=O)C=CC=C2 FGUUSXIOTUKUDN-IBGZPJMESA-N 0.000 description 2
- 238000004458 analytical method Methods 0.000 description 2
- 230000008859 change Effects 0.000 description 2
- 238000005516 engineering process Methods 0.000 description 2
- 239000000203 mixture Substances 0.000 description 2
- 238000012986 modification Methods 0.000 description 2
- 230000004048 modification Effects 0.000 description 2
- 238000004088 simulation Methods 0.000 description 2
- 238000012360 testing method Methods 0.000 description 2
- 101100499229 Mus musculus Dhrsx gene Proteins 0.000 description 1
- 230000009286 beneficial effect Effects 0.000 description 1
- 238000005094 computer simulation Methods 0.000 description 1
- 238000010276 construction Methods 0.000 description 1
- 238000001514 detection method Methods 0.000 description 1
- 239000006185 dispersion Substances 0.000 description 1
- 230000000694 effects Effects 0.000 description 1
- 238000005259 measurement Methods 0.000 description 1
- 238000012806 monitoring device Methods 0.000 description 1
- 230000003287 optical effect Effects 0.000 description 1
- 238000011160 research Methods 0.000 description 1
- 238000001228 spectrum Methods 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
- G06F17/11—Complex mathematical operations for solving equations, e.g. nonlinear equations, general mathematical optimization problems
-
- 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
- H02J3/01—Arrangements for reducing harmonics or ripples
-
- 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
- Y02E40/40—Arrangements for reducing harmonics
Landscapes
- Engineering & Computer Science (AREA)
- Physics & Mathematics (AREA)
- Mathematical Physics (AREA)
- General Physics & Mathematics (AREA)
- Pure & Applied Mathematics (AREA)
- Mathematical Optimization (AREA)
- Mathematical Analysis (AREA)
- Computational Mathematics (AREA)
- Data Mining & Analysis (AREA)
- Theoretical Computer Science (AREA)
- Operations Research (AREA)
- Algebra (AREA)
- Databases & Information Systems (AREA)
- Software Systems (AREA)
- General Engineering & Computer Science (AREA)
- Power Engineering (AREA)
- Management, Administration, Business Operations System, And Electronic Commerce (AREA)
Abstract
The invention relates to an interference user harmonic level estimation method based on mass monitoring data. The method uses a cloud model to represent harmonic characteristics of an interference user, reflects the average level and fluctuation range of harmonic emission of the user, and implies the influence of the operation conditions of a power system and equipment on the harmonic characteristics of the user. Then, the influence of the same type of interference user equipment on the harmonic characteristics of the same type of interference user equipment is analyzed by utilizing the strong nonlinear mapping capability of the neural network, and the trained model can predict the harmonic level of the type of interference user equipment and provides a basis for harmonic access prediction evaluation. The method has the advantages that the obtained cloud model can reflect the harmonic characteristics of the interference users in the actual running state, and in addition, the trained neural network model is used for evaluating the same kind of interference users, so that the complex calculation process is avoided.
Description
Technical Field
The invention belongs to the field of harmonic detection, and particularly relates to an interference user harmonic level estimation method based on mass monitoring data.
Background
Harmonics, one of the most serious power quality problems, must be considered when evaluating the effects of interfering users. At present, when a power grid company carries out access prediction evaluation on interference users, an empirical formula and a typical harmonic spectrum of interference equipment are generally used for carrying out estimation or simulation modeling analysis, the former is not accurate enough, a model of a single device is difficult to reflect the comprehensive harmonic characteristics of the interference users containing a plurality of electric devices in different industries, and the latter is complex in modeling and large in workload. In addition, the two methods are difficult to reflect the change of the working condition of the equipment.
At present, harmonic access prediction evaluation of interference users mainly comprises two methods: one is to analyze the harmonic equipment composition of the interference user, regard the harmonic equipment as the constant current source of the harmonic current, utilize the experience formula of the apparatus or test data that the manufacturer provides to estimate each harmonic current of the single apparatus, then utilize the superposition formula in the national standard GB/T14549-93 to get the total harmonic current level; and the other method is to use simulation software such as PSCAD/EMTDC, Simulink or Etap and the like to build a model of an interference user to obtain the total harmonic current level.
The first method has the disadvantages that: firstly, the prediction error of the empirical formula is large, and the empirical formula may deviate from the actual result greatly in application; secondly, the test data of the manufacturer is the result obtained when the equipment operates under the typical working condition, and in the actual production process of a user, the equipment is difficult to be ensured to be maintained under the typical working condition and kept constant[1](ii) a Finally, harmonic superposition coefficients in the national standard are obtained under the assumption of certain distribution, and different harmonic devices may have different harmonic distribution characteristics, so that the calculated harmonic superposition current has certain deviation from the actual situation[2-3]。
The second method has the disadvantages that: the model base of the existing simulation software is not complete, a model of the equipment to be evaluated may need to be manually built by using basic elements, the building of the model needs to research the internal structure of the equipment and the operating characteristics of the equipment, and the process is very complex and tedious[4]. In addition, the randomness and the volatility of the operation of a power system and harmonic equipment are neglected in the simulation result, and the simulation value is deviated from the real result in an actual scene.
Due to the wide application of power quality monitoring devices in power systems, harmonic monitoring systems have accumulated harmonic data for a large number of interference sources. For a certain type of monitored interference users, it is conditional and necessary to establish a harmonic feature model by using a large amount of accumulated harmonic data, so as to provide reference for access prediction evaluation of similar interference users. According to the method, the harmonic characteristics of the interference users are represented by the cloud model based on the accumulated mass harmonic monitoring data and the composition characteristics of the interference devices of the users, and the harmonic characteristics of the similar users are predicted by combining the neural network, so that reference is provided for the harmonic access prediction evaluation of the interference users.
Reference documents:
[1] shore vibrating countries, Linkunje, Chen jin plant, etc. analysis of typical working conditions of harmonic users based on interval arithmetic [ J ] electric power science and technology report, 2018,033(004): 153-.
[2] Study on Zhang Jing, multiple harmonic source system harmonic superposition method [ J ] electric network technique, 1995(03):23-27.
[3] Huahui spring, Zhenglu, Wanli, and the like, a multiple harmonic source same harmonic superposition calculation method [ J ] power system automation, 2016,40(019): 107-.
[4] The method comprises the following steps of Euron, Liwain, Suzhou Jian, and the like, a large photovoltaic power station modeling and power quality pre-evaluation method based on electrical and external characteristics [ J ]. a new electrical and power technology for electricians, 2018, v.37; no.179(05) 54-60.
Disclosure of Invention
The invention aims to provide an interference user harmonic level estimation method based on mass monitoring data, a cloud model obtained by the method can reflect harmonic characteristics of an interference user in an actual running state, and in addition, a trained neural network model is utilized to evaluate the same kind of interference users, so that a complex calculation process is avoided.
In order to achieve the purpose, the technical scheme of the invention is as follows: a method for estimating the harmonic level of an interference user based on mass monitoring data comprises the steps of firstly, constructing a harmonic cloud model of the interference user for representing the harmonic characteristics of the interference user; then, constructing a training sample of the neural network based on a harmonic cloud model of the interference user to train the neural network, and obtaining a harmonic level prediction model of the interference user; and finally, according to the equipment capacity constitution of the same type of interference users, performing access prediction evaluation on the interference users through a harmonic level prediction model of the interference users.
In an embodiment of the present invention, the specific implementation process of constructing the harmonic cloud model of the interfering user for characterizing the harmonic features of the interfering user is as follows:
n interference users of the same type are provided, the N users have M identical harmonic devices, and the device capacity of the mth device of the nth user is S _ M _ N according to the standing book information of the N users; the method comprises the following steps of constructing a 2-25-order harmonic current cloud model of the N interference users:
(1.1) acquiring historical monitoring data of 2-25 harmonic currents interfering with users
h is 2,3, …,25 is the harmonic order, n is the data length;
(1.2) constructing a cloud model of the h-th harmonic current amplitude by using a reverse Gaussian cloud algorithm:
a) calculating expectations of harmonic current amplitude cloud model
b) Entropy of cloud model for calculating harmonic current amplitude
c) Calculating the variance of the sample data
d) If Sh 2-Enh_amplitude2If not less than 0, turning to the step f), otherwise, turning to the step e);
e) remove expected Ex from current samplehIf the number of samples is less than 100, deleting one data point nearest to the expectation each time, and turning to step c);
f) super entropy of harmonic current amplitude cloud model
g) Obtaining a cloud model (Ex) of the h-th harmonic current amplitudeh_amplitude，Enh_amplitude，Heh_amplitude)；
(1.3) repeating the step (1.2) until 2-25 harmonic current amplitude cloud models of N interference users are constructed, wherein the digital characteristic of the ith harmonic current amplitude cloud model of the nth user is (Ex)i_amplitude_n，Eni_amplitude_n，Hei_amplitude_n)。
In an embodiment of the present invention, the specific implementation process of constructing the training sample of the neural network based on the harmonic cloud model of the interfering user to train the neural network to obtain the harmonic level prediction model of the interfering user is as follows:
(2.1) using the vector Xn ═ { S _1_ n, S _2_ n, S _3_ n, …, S _ M _ n } composed of the device capacities of the nth user as the input of the neural network, and using the harmonic current amplitude cloud model digital feature Yn ═ { Ex ═ of the nth userh_amplitude_n，Enh_amplitude_n，HehUsing _ amplitude _ N } as the output of the neural network, and forming N training samples { Xn, Yn } as the training samples of the neural network, wherein Exh_amplitude_n，Enh_amplitude_n，HehAmpitude _ n is a 24-dimensional column vector and corresponds to the digital characteristics of a 2-25 harmonic current amplitude cloud model, namely h is 2,3, … and 25;
and (2.2) training the neural network by using the training samples { Xn, Yn } to obtain a harmonic level prediction model of the interference user.
In an embodiment of the present invention, the specific implementation process of performing access prediction evaluation on the interference users through the harmonic level prediction model of the interference users according to the equipment capacity of the same type of interference users is as follows:
(3.1) analyzing the device capacity constitution of the same type of interference users to be evaluated, forming an input vector X _ evaluated { (S _1_ ed, S _2_ ed, S _3_ ed, …, S _ M _ ed }), inputting a constructed harmonic level prediction model of the interference users,obtaining the digital characteristic Y _ evaluated ═ { Ex) of the 2-25 th harmonic current amplitude cloud modelh_amplitude_ed，Enh_amplitude_ed，Heh-amplitude _ ed, wherein h is 2,3, …, 25;
(3.2) generating M sample cloud drops, namely analog values, by utilizing a forward Gaussian cloud algorithm and the obtained Y _ evaluated, and simulating the operation process of an interference user to be evaluated to obtain a CP95 value for evaluation;
and (3.3) performing access prediction evaluation on the interference users according to the CP95 value of the 2-25 th harmonic current.
In an embodiment of the present invention, the step (3.2) is implemented as follows:
(3.2.1) for the ith harmonic current amplitude cloud model, its numerical characteristic is (Ex)i_amplitude_ed，Eni_amplitude_ed，HeiAmplitude ed), generating M sample cloud droplets:
i) with EniDesirably, _ amplitude _ ed, Hei_amplitude_ed2Generating a normal random entropy En for variancei_angle_ed′＝NORM(Eni_amplitude_ed，Hei_amplitude_ed2)；
ii) in ExiAm amplitude ed is desired, Eni_angle_ed′2A sample cloud droplet amplitude _ i that is an ith harmonic current of the variance;
iii) repeating steps I) and ii) until M harmonic current cloud droplets are generated, keeping the set of M ith harmonic current cloud droplets as I _ I ═ amplitude _ I _1, amplitude _ I _2, …, amplitude _ I _ M };
(3.2.2) finding a CP95 value from the ith harmonic current amplitude cloud droplet set I _ I, namely, selecting [0.05 × M ] th elements from the elements according to the small-to-large arrangement, and recording the value as Icp95_ I;
(3.2.3) repeating the steps (3.2.1) and (3.2.2) until a CP95 value of a 2-25-order harmonic current amplitude analog value is obtained.
In an embodiment of the present invention, M is calculated according to a product of a sampling sample time interval and a sampling sample time period.
The invention also provides a computer readable storage medium having stored thereon computer program instructions executable by a processor, the computer program instructions when executed by the processor being capable of performing the method steps as described above.
Compared with the prior art, the invention has the following beneficial effects: the invention provides a novel interference user harmonic level estimation method, which uses a cloud model to represent harmonic characteristics of an interference user, reflects the average level and fluctuation range of harmonic emission of the user, and implies the influence of the operating conditions of a power system and equipment on the harmonic characteristics of the user. Then, the influence of the same type of interference user equipment on the harmonic characteristics of the same type of interference user equipment is analyzed by utilizing the strong nonlinear mapping capability of the neural network, and the trained model can predict the harmonic level of the type of interference user equipment and provides a basis for harmonic access prediction evaluation. The method has the advantages that the obtained cloud model can reflect the harmonic characteristics of the interference users in the actual running state, and in addition, the trained neural network model is used for evaluating the same kind of interference users, so that the complex calculation process is avoided.
Drawings
Fig. 1 is a general flow chart of the method for estimating the harmonic level of an interfering user according to the present invention.
Fig. 2 is a flow chart of constructing an interfering user harmonic cloud model.
Fig. 3 is a flow chart of a forward gaussian cloud algorithm.
Fig. 4 is a flowchart of the inverse gaussian cloud algorithm.
Detailed Description
The technical scheme of the invention is specifically explained below with reference to the accompanying drawings.
It should be noted that the following detailed description is exemplary and is intended to provide further explanation of the disclosure. Unless defined otherwise, all technical and scientific terms used herein have the same meaning as commonly understood by one of ordinary skill in the art to which this application belongs.
It is noted that the terminology used herein is for the purpose of describing particular embodiments only and is not intended to be limiting of example embodiments according to the present application. As used herein, the singular forms "a", "an" and "the" are intended to include the plural forms as well, and it should be understood that when the terms "comprises" and/or "comprising" are used in this specification, they specify the presence of stated features, steps, operations, devices, components, and/or combinations thereof, unless the context clearly indicates otherwise.
The invention relates to an interference user harmonic level estimation method based on mass monitoring data, which comprises the steps of firstly, constructing a harmonic cloud model of an interference user for representing the harmonic characteristics of the interference user; then, constructing a training sample of the neural network based on a harmonic cloud model of the interference user to train the neural network, and obtaining a harmonic level prediction model of the interference user; and finally, according to the equipment capacity constitution of the same type of interference users, performing access prediction evaluation on the interference users through a harmonic level prediction model of the interference users.
As shown in fig. 1 to 4, the implementation of the method for estimating the interference user harmonic level based on massive monitoring data of the present invention includes two parts, specifically as follows:
1. harmonic cloud model of interference users
Definition of the cloud model: given a quantitative discourse domain U, C is a qualitative concept on U, and if a quantitative value x ∈ U is a random realization of the qualitative concept C, the certainty factor mu (x) of x to C is ∈ [0, 1]]Are random numbers with a tendency to stabilize, i.e.
The distribution of x over U in the domain of discourse is called the cloud, denoted c (x), and each x becomes a cloud droplet. The numerical characteristics of the cloud are represented by the 3 quantities of expected Ex, entropy En, and super-entropy He. The expected Ex is the mathematical expectation of the cloud droplet group in the discourse domain space distribution and is the basic certainty measurement of the qualitative concept; the entropy En is an uncertainty measure of a qualitative concept, reflecting the degree of dispersion of cloud droplets of this qualitative concept; the hyper-entropy He is an uncertainty measure of entropy, which is shared by ambiguity and randomness of entropyThe decision, reflecting the uncertainty of the concept granularity.
For harmonic monitoring data of an interfering user, the quantitative universe of the amplitude of a certain harmonic current is [0, + ∞ ], each monitored value can be regarded as a cloud droplet without certainty information in the universe, and all the monitored values (cloud droplets) in a period of time can form a cloud with the numerical characteristics of (Ex, En, He). Ex is expected to be the average emission level of the subharmonic current emitted by the interfering user during the period of time, entropy En is used to measure the fluctuation range of the subharmonic current amplitude during the period of time, and hyper-entropy He is used to characterize the random variation of the subharmonic current amplitude.
Typically, the monitoring data of the harmonic monitoring system is a feature statistic, and the stored maximum value, the minimum value and the CP95 value of the amplitude of the harmonic current of a certain order within 3 minutes (or integral multiple of 1 minute and not more than 10 minutes) are stored. In this context, a harmonic cloud model of an interfering user is constructed by using an inverse gaussian cloud algorithm, and the specific steps are as follows (as shown in fig. 2):
(1) obtaining historical monitoring data of 2-25 th harmonic current of interference user
h is 2,3, …,25 is the order of harmonics, n is the length of data (the data period is at least one week, the maximum value or CP95 value, the conservative of the maximum value is higher);
(2) as shown in fig. 3, a cloud model of 2-25 times of harmonic current amplitude is respectively constructed by using a reverse gaussian cloud algorithm, taking an h-th harmonic current as an example:
a) calculating expectations of harmonic current amplitude cloud model
b) Entropy of cloud model for calculating harmonic current amplitude
c) Calculating the variance of the sample data
d) If S ish 2-Enh_amplitude2If not less than 0, turning to the step f), otherwise, turning to the step e);
e) remove expected Ex from current sample h1% of the data of the most recent amplitude (if the number of samples is less than 100, deleting one data point closest to the expectation each time), and then returning to step c);
f) super entropy of harmonic current amplitude cloud model
(3) Cloud model (Ex) for obtaining h-th harmonic current amplitude of feeder lineh_amplitude，Enh_amplitude，Heh_amplitude)；
(4) And (4) repeating the steps (2) to (3) until a cloud model of 2-25 times of feeder line harmonic current amplitude is constructed.
2. Interference user harmonic level estimation method
In actual production, a type of interfering users having the same production flow and equipment can be regarded as the same type of users, and have similarity in their harmonic interference characteristics. The harmonic equipment constitution and the mutual influence among the equipment of the same type of interference users can be considered to be the same, and the harmonic emission level depends on the production scale of the users, namely the capacity difference of each equipment among the users. Therefore, a harmonic level prediction model of a certain type of interference users can be constructed by utilizing the strong nonlinear mapping capability of the neural network and combining the existing harmonic monitoring data and equipment standing book data of a large number of interference users.
Assuming that N users with the same type of interference are provided, the N users have M types of same harmonic devices, and the device capacity of the mth device of the nth user is S _ M _ N according to the standing book information of the N users. The specific steps of the prediction model construction are as follows:
(1) constructing a 2-25 harmonic current cloud model of the N interference users by using the method in the 1 st point, wherein the ith harmonic current cloud model of the nth userThe numerical characteristic of the harmonic current cloud model is (Ex)i_amplitude_n，Eni_amplitude_n，Hei_amplitude_n)；
(2) The vector Xn formed by the equipment capacity of the nth user is used as the input of the neural network, and the harmonic cloud model digital characteristic Yn of the user is used as { S _1_ n, S _2_ n, S _3_ n, …, S _ M _ n }, and the harmonic cloud model digital characteristic Yn of the user is used as { Ex {h_amplitude_n，Enh_amplitude_n，HehAmpitude n as the output of the neural network (where Exh_amplitude_n，Enh_amplitude_n，HehEach amplitude _ N is a 24-dimensional column vector and corresponds to the digital features of a 2-25 th harmonic cloud model, namely h is 2,3, … and 25), and N training samples { Xn and Yn } are formed to serve as training samples of the neural network;
(3) training the neural network by using a training sample { Xn, Yn } to obtain a harmonic level prediction model of the interference user;
(4) analyzing the device capacity constitution of the same-class interference user to be evaluated, forming an input vector X _ evaluated { (S _1_ ed, S _2_ ed, S _3_ ed, …, S _ M _ ed }, inputting a constructed harmonic level prediction model of the interference user, and obtaining a digital characteristic Y _ evaluated { (Ex) } of a 2-25-order harmonic current cloud modelh_amplitude_ed，Enh_amplitude_ed，Heh-amplitude _ ed, wherein h is 2,3, …, 25;
(5) as shown in fig. 4, M sample cloud droplets (i.e., analog values) are generated by using a forward gaussian cloud algorithm and the obtained Y _ evaluated, and are used for simulating the operation process of the interfering user to be evaluated, so as to obtain a CP95 value for evaluation. The number of cloud drops M generated can be selected according to the requirement, and in general, the number of samples is 3min, the sampling time is one week, and M can be 3360. The method comprises the following specific steps:
a) taking the ith harmonic current cloud model as an example (i.e. the element in row i-1 of Y _ evaluated), the numerical feature is (Ex)i_amplitude_ed，Eni_amplitude_ed，HeiAmplitude ed), generating M sample cloud droplets:
i) with EniDesirably, _ amplitude _ ed, Hei_amplitude_ed2Generate one for varianceNormal random entropy Eni_angle_ed′＝NORM(Eni_amplitude_ed，Hei_amplitude_ed2)；
ii) in ExiAm amplitude ed is desired, Eni_angle_ed′2A sample cloud droplet amplitude _ i that is an ith harmonic current of the variance;
iii) repeating steps I) and ii) until M harmonic current cloud droplets are generated, keeping the set of M ith harmonic current cloud droplets as I _ I ═ amplitude _ I _1, amplitude _ I _2, …, amplitude _ I _ M };
b) and finding a CP95 value (namely, selecting [ 0.05M ] th elements from the ith harmonic current cloud droplet set I _ I in a small-to-large arrangement in the elements) from the ith harmonic current cloud droplet set I _ I, and recording the value as Icp95_ I.
c) Repeating the steps a) and b) until a CP95 value of the 2-25 th harmonic current analog value is obtained;
(6) and performing access prediction evaluation on the interference users according to the obtained CP95 value of the 2-25 th harmonic current.
The invention also provides a computer readable storage medium having stored thereon computer program instructions executable by a processor, the computer program instructions when executed by the processor being capable of performing the method steps as described above.
As will be appreciated by one skilled in the art, embodiments of the present application may be provided as a method, system, or computer program product. Accordingly, the present application may take the form of an entirely hardware embodiment, an entirely software embodiment or an embodiment combining software and hardware aspects. Furthermore, the present application may take the form of a computer program product embodied on one or more computer-usable storage media (including, but not limited to, disk storage, CD-ROM, optical storage, and the like) having computer-usable program code embodied therein.
The present application is described with reference to flowchart illustrations and/or block diagrams of methods, apparatus (systems), and computer program products according to embodiments of the application. It will be understood that each flow and/or block of the flow diagrams and/or block diagrams, and combinations of flows and/or blocks in the flow diagrams and/or block diagrams, can be implemented by computer program instructions. These computer program instructions may be provided to a processor of a general purpose computer, special purpose computer, embedded processor, or other programmable data processing apparatus to produce a machine, such that the instructions, which execute via the processor of the computer or other programmable data processing apparatus, create means for implementing the functions specified in the flowchart flow or flows and/or block diagram block or blocks.
These computer program instructions may also be stored in a computer-readable memory that can direct a computer or other programmable data processing apparatus to function in a particular manner, such that the instructions stored in the computer-readable memory produce an article of manufacture including instruction means which implement the function specified in the flowchart flow or flows and/or block diagram block or blocks.
These computer program instructions may also be loaded onto a computer or other programmable data processing apparatus to cause a series of operational steps to be performed on the computer or other programmable apparatus to produce a computer implemented process such that the instructions which execute on the computer or other programmable apparatus provide steps for implementing the functions specified in the flowchart flow or flows and/or block diagram block or blocks.
The foregoing is directed to preferred embodiments of the present invention, other and further embodiments of the invention may be devised without departing from the basic scope thereof, and the scope thereof is determined by the claims that follow. However, any simple modification, equivalent change and modification of the above embodiments according to the technical essence of the present invention are within the protection scope of the technical solution of the present invention.
Claims (7)
1. A method for estimating the harmonic level of an interference user based on massive monitoring data is characterized by comprising the following steps of firstly, constructing a harmonic cloud model of the interference user for representing the harmonic characteristics of the interference user; then, constructing a training sample of the neural network based on a harmonic cloud model of the interference user to train the neural network, and obtaining a harmonic level prediction model of the interference user; and finally, according to the equipment capacity constitution of the same type of interference users, performing access prediction evaluation on the interference users through a harmonic level prediction model of the interference users.
2. The method for estimating the harmonic level of the interfering user based on the mass monitoring data according to claim 1, wherein the specific implementation process for constructing the harmonic cloud model of the interfering user for representing the harmonic characteristics of the interfering user is as follows:
n interference users of the same type are provided, the N users have M identical harmonic devices, and the device capacity of the mth device of the nth user is S _ M _ N according to the standing book information of the N users; the method comprises the following steps of constructing a 2-25-order harmonic current cloud model of the N interference users:
(1.1) acquiring historical monitoring data of 2-25 harmonic currents interfering with users
h is 2,3, …,25 is the harmonic order, n is the data length;
(1.2) constructing a cloud model of the h-th harmonic current amplitude by using a reverse Gaussian cloud algorithm:
a) calculating expectations of harmonic current amplitude cloud model
b) Entropy of cloud model for calculating harmonic current amplitude
c) Calculating the variance of the sample data
d) If Sh 2-Enh_amplitude2If the number of steps is more than or equal to 0, turning to stepStep f), otherwise, turning to step e);
e) remove expected Ex from current samplehIf the number of samples is less than 100, deleting one data point nearest to the expectation each time, and turning to step c);
f) super entropy of harmonic current amplitude cloud model
g) Obtaining a cloud model (Ex) of the h-th harmonic current amplitudeh_amplitude，Enh_amplitude，Heh_amplitude)；
(1.3) repeating the step (1.2) until 2-25 harmonic current amplitude cloud models of N interference users are constructed, wherein the digital characteristic of the ith harmonic current amplitude cloud model of the nth user is (Ex)i_amplitude_n，Eni_amplitude_n，Hei_amplitude_n)。
3. The method for estimating the harmonic level of the interfering user based on the mass monitoring data according to claim 2, wherein the training sample for constructing the neural network based on the harmonic cloud model of the interfering user is used for training the neural network, and the specific implementation process for obtaining the harmonic level prediction model of the interfering user is as follows:
(2.1) using the vector Xn ═ { S _1_ n, S _2_ n, S _3_ n, …, S _ M _ n } composed of the device capacities of the nth user as the input of the neural network, and using the harmonic current amplitude cloud model digital feature Yn ═ { Ex ═ of the nth userh_amplitude_n，Enh_amplitude_n，HehUsing _ amplitude _ N } as the output of the neural network, and forming N training samples { Xn, Yn } as the training samples of the neural network, wherein Exh_amplitude_n，Enh_amplitude_n，HehAmpitude _ n is a 24-dimensional column vector and corresponds to the digital characteristics of a 2-25 harmonic current amplitude cloud model, namely h is 2,3, … and 25;
and (2.2) training the neural network by using the training samples { Xn, Yn } to obtain a harmonic level prediction model of the interference user.
4. The method for estimating the harmonic level of the interference users based on the massive monitoring data according to claim 3, wherein the specific implementation process for performing the access prediction evaluation of the interference users through the harmonic level prediction model of the interference users according to the equipment capacity of the same interference user is as follows:
(3.1) analyzing the equipment capacity constitution of the same type of interference users to be evaluated, forming an input vector X _ evaluated { (S _1_ ed, S _2_ ed, S _3_ ed, …, S _ M _ ed }, inputting a constructed harmonic level prediction model of the interference users, and obtaining the digital characteristic Y _ evaluated { (Ex) } of a 2-25-order harmonic current amplitude cloud modelh_amplitude_ed，Enh_amplitude_ed，Heh-amplitude _ ed, wherein h is 2,3, …, 25;
(3.2) generating M sample cloud drops, namely analog values, by utilizing a forward Gaussian cloud algorithm and the obtained Y _ evaluated, and simulating the operation process of an interference user to be evaluated to obtain a CP95 value for evaluation;
and (3.3) performing access prediction evaluation on the interference users according to the CP95 value of the 2-25 th harmonic current.
5. The method for estimating the interference user harmonic level based on the mass monitoring data according to claim 4, wherein the step (3.2) is implemented by the following steps:
(3.2.1) for the ith harmonic current amplitude cloud model, its numerical characteristic is (Ex)i_amplitude_ed，Eni_amplitude_ed，HeiAmplitude ed), generating M sample cloud droplets:
i) with EniDesirably, _ amplitude _ ed, Hei_amplitude_ed2Generating a normal random entropy En for variancei_angle_ed′＝NORM(Eni_amplitude_ed，Hei_amplitude_ed2)；
ii) in ExiAm amplitude ed is desired, Eni_angle_ed′2Is the varianceA sample cloud of the ith harmonic current of (a);
iii) repeating steps I) and ii) until M harmonic current cloud droplets are generated, keeping the set of M ith harmonic current cloud droplets as I _ I ═ amplitude _ I _1, amplitude _ I _ 2.
(3.2.2) finding a CP95 value from the ith harmonic current amplitude cloud droplet set I _ I, namely, selecting [0.05 × M ] th elements from the elements according to the small-to-large arrangement, and recording the value as Icp95_ I;
(3.2.3) repeating the steps (3.2.1) and (3.2.2) until a CP95 value of a 2-25-order harmonic current amplitude analog value is obtained.
6. The method according to claim 4, wherein M is calculated from a product of a sampling sample time interval and a sampling sample time period.
7. A computer-readable storage medium, having stored thereon computer program instructions executable by a processor, the computer program instructions, when executed by the processor, being capable of carrying out the method steps of claims 1-6.
Priority Applications (1)
| Application Number | Priority Date | Filing Date | Title |
|---|---|---|---|
| CN202110428975.4A CN113094636A (en) | 2021-04-21 | 2021-04-21 | Interference user harmonic level estimation method based on massive monitoring data |
Applications Claiming Priority (1)
| Application Number | Priority Date | Filing Date | Title |
|---|---|---|---|
| CN202110428975.4A CN113094636A (en) | 2021-04-21 | 2021-04-21 | Interference user harmonic level estimation method based on massive monitoring data |
Publications (1)
| Publication Number | Publication Date |
|---|---|
| CN113094636A true CN113094636A (en) | 2021-07-09 |
Family
ID=76679029
Family Applications (1)
| Application Number | Title | Priority Date | Filing Date |
|---|---|---|---|
| CN202110428975.4A Pending CN113094636A (en) | 2021-04-21 | 2021-04-21 | Interference user harmonic level estimation method based on massive monitoring data |
Country Status (1)
| Country | Link |
|---|---|
| CN (1) | CN113094636A (en) |
Cited By (1)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN116595368A (en) * | 2023-05-16 | 2023-08-15 | 北京航空航天大学 | Nonlinear modeling-based power amplifier harmonic prediction method |
Citations (4)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| US20170070258A1 (en) * | 2015-09-04 | 2017-03-09 | Futurewei Technologies, Inc. | Interference phase estimate system and method |
| CN110619364A (en) * | 2019-09-18 | 2019-12-27 | 哈尔滨理工大学 | Wavelet neural network three-dimensional model classification method based on cloud model |
| CN110633870A (en) * | 2019-09-24 | 2019-12-31 | 国家电网有限公司 | Harmonic early warning method, harmonic early warning device and terminal equipment |
| CN112531710A (en) * | 2020-11-18 | 2021-03-19 | 福州大学 | Method for predicting and evaluating harmonic source access |
-
2021
- 2021-04-21 CN CN202110428975.4A patent/CN113094636A/en active Pending
Patent Citations (4)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| US20170070258A1 (en) * | 2015-09-04 | 2017-03-09 | Futurewei Technologies, Inc. | Interference phase estimate system and method |
| CN110619364A (en) * | 2019-09-18 | 2019-12-27 | 哈尔滨理工大学 | Wavelet neural network three-dimensional model classification method based on cloud model |
| CN110633870A (en) * | 2019-09-24 | 2019-12-31 | 国家电网有限公司 | Harmonic early warning method, harmonic early warning device and terminal equipment |
| CN112531710A (en) * | 2020-11-18 | 2021-03-19 | 福州大学 | Method for predicting and evaluating harmonic source access |
Non-Patent Citations (1)
| Title |
|---|
| 严静;邵振国;: "电能质量谐波监测与评估综述", 电气技术, no. 07 * |
Cited By (2)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN116595368A (en) * | 2023-05-16 | 2023-08-15 | 北京航空航天大学 | Nonlinear modeling-based power amplifier harmonic prediction method |
| CN116595368B (en) * | 2023-05-16 | 2024-01-26 | 北京航空航天大学 | Nonlinear modeling-based power amplifier harmonic prediction method |
Similar Documents
| Publication | Publication Date | Title |
|---|---|---|
| Madhukumar et al. | Regression model-based short-term load forecasting for university campus load | |
| Loukatou et al. | Stochastic wind speed modelling for estimation of expected wind power output | |
| Berkes et al. | Detecting changes in the mean of functional observations | |
| CN110417011B (en) | Online dynamic security assessment method based on mutual information and iterative random forest | |
| CN109214708B (en) | Electric power system risk assessment method based on cross entropy theory optimization support vector machine | |
| CN109523155B (en) | Power grid risk assessment method of Monte Carlo and least square support vector machine | |
| CN109726865A (en) | Customer charge probability density prediction technique, device and storage medium based on EMD-QRF | |
| CN110222897A (en) | A kind of distribution network reliability analysis method | |
| Stroud et al. | Nonlinear state-space models with state-dependent variances | |
| CN115882456B (en) | Power control method and system based on large-scale power grid tide | |
| CN109981749A (en) | A kind of cloud workflow task running time prediction method promoted based on limit gradient | |
| Pinceti et al. | Data-driven generation of synthetic load datasets preserving spatio-temporal features | |
| CN118213997B (en) | Urban power grid load prediction method based on AHP-gray fuzzy algorithm | |
| CN106952077B (en) | Work order processing strategy generation method and device | |
| Gocheva-Ilieva et al. | Assaying SARIMA and generalised regularised regression for particulate matter PM10 modelling and forecasting | |
| Shariff et al. | Nonlinear system identification: Comparison between PRBS and Random Gaussian perturbation on steam distillation pilot plant | |
| CN115130764A (en) | Power distribution network situation prediction method and system based on state evaluation | |
| CN113094636A (en) | Interference user harmonic level estimation method based on massive monitoring data | |
| CN111127242A (en) | Power system reliability dynamic real-time assessment method based on small sample data | |
| Wong et al. | Estimation of Hourly Utility Usage Using Machine Learning | |
| CN112800674A (en) | Power system element reliability parameter calculation method based on extreme learning machine | |
| CN115207921B (en) | Position optimization method and system for photovoltaic access power distribution network | |
| CN111274542A (en) | Confidence capacity assessment method and device based on rattan copula and mixed offset normal distribution | |
| Li et al. | Identification and nonlinear model predictive control of MIMO Hammerstein system with constraints | |
| Alajlan et al. | Optimization of COCOMO-II Model for Effort and Development Time Estimation using Genetic Algorithms |
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 | ||
| RJ01 | Rejection of invention patent application after publication | ||
| RJ01 | Rejection of invention patent application after publication |
Application publication date: 20210709 |