CN117314678A - Electric energy quality prediction analysis method and system - Google Patents
Electric energy quality prediction analysis method and system Download PDFInfo
- Publication number
- CN117314678A CN117314678A CN202311073666.5A CN202311073666A CN117314678A CN 117314678 A CN117314678 A CN 117314678A CN 202311073666 A CN202311073666 A CN 202311073666A CN 117314678 A CN117314678 A CN 117314678A
- Authority
- CN
- China
- Prior art keywords
- index
- power quality
- sample
- matrix
- factor
- 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
- 238000004458 analytical method Methods 0.000 title claims abstract description 35
- 239000011159 matrix material Substances 0.000 claims abstract description 47
- 238000000034 method Methods 0.000 claims abstract description 17
- 238000012545 processing Methods 0.000 claims abstract description 16
- 238000012706 support-vector machine Methods 0.000 claims abstract description 12
- 238000012549 training Methods 0.000 claims abstract description 10
- 238000007621 cluster analysis Methods 0.000 claims description 7
- 238000012163 sequencing technique Methods 0.000 claims description 4
- 238000004590 computer program Methods 0.000 claims description 3
- 230000000875 corresponding effect Effects 0.000 description 5
- 238000010586 diagram Methods 0.000 description 4
- 238000011156 evaluation Methods 0.000 description 3
- 238000012216 screening Methods 0.000 description 3
- XEEYBQQBJWHFJM-UHFFFAOYSA-N Iron Chemical compound [Fe] XEEYBQQBJWHFJM-UHFFFAOYSA-N 0.000 description 2
- 238000010219 correlation analysis Methods 0.000 description 2
- 230000006870 function Effects 0.000 description 2
- 238000003723 Smelting Methods 0.000 description 1
- 230000009286 beneficial effect Effects 0.000 description 1
- 230000005494 condensation Effects 0.000 description 1
- 238000009833 condensation Methods 0.000 description 1
- 238000010276 construction Methods 0.000 description 1
- 230000002596 correlated effect Effects 0.000 description 1
- 230000000694 effects Effects 0.000 description 1
- 238000004146 energy storage Methods 0.000 description 1
- 238000005286 illumination Methods 0.000 description 1
- 229910052742 iron Inorganic materials 0.000 description 1
- 238000010295 mobile communication Methods 0.000 description 1
- 238000012986 modification Methods 0.000 description 1
- 230000004048 modification Effects 0.000 description 1
- 230000003287 optical effect Effects 0.000 description 1
- 238000010248 power generation Methods 0.000 description 1
- 238000013139 quantization Methods 0.000 description 1
- 238000006467 substitution reaction Methods 0.000 description 1
Classifications
-
- G—PHYSICS
- G06—COMPUTING; CALCULATING OR COUNTING
- G06Q—INFORMATION AND COMMUNICATION TECHNOLOGY [ICT] SPECIALLY ADAPTED FOR ADMINISTRATIVE, COMMERCIAL, FINANCIAL, MANAGERIAL OR SUPERVISORY PURPOSES; SYSTEMS OR METHODS SPECIALLY ADAPTED FOR ADMINISTRATIVE, COMMERCIAL, FINANCIAL, MANAGERIAL OR SUPERVISORY PURPOSES, NOT OTHERWISE PROVIDED FOR
- G06Q50/00—Information and communication technology [ICT] specially adapted for implementation of business processes of specific business sectors, e.g. utilities or tourism
- G06Q50/06—Energy or water supply
-
- G—PHYSICS
- G06—COMPUTING; CALCULATING OR COUNTING
- G06F—ELECTRIC DIGITAL DATA PROCESSING
- G06F18/00—Pattern recognition
- G06F18/20—Analysing
- G06F18/23—Clustering techniques
-
- G—PHYSICS
- G06—COMPUTING; CALCULATING OR COUNTING
- G06F—ELECTRIC DIGITAL DATA PROCESSING
- G06F18/00—Pattern recognition
- G06F18/20—Analysing
- G06F18/27—Regression, e.g. linear or logistic regression
-
- 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
- G06Q10/00—Administration; Management
- G06Q10/06—Resources, workflows, human or project management; Enterprise or organisation planning; Enterprise or organisation modelling
- G06Q10/063—Operations research, analysis or management
- G06Q10/0639—Performance analysis of employees; Performance analysis of enterprise or organisation operations
- G06Q10/06393—Score-carding, benchmarking or key performance indicator [KPI] 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
- G06Q10/06—Resources, workflows, human or project management; Enterprise or organisation planning; Enterprise or organisation modelling
- G06Q10/063—Operations research, analysis or management
- G06Q10/0639—Performance analysis of employees; Performance analysis of enterprise or organisation operations
- G06Q10/06395—Quality analysis or management
Landscapes
- Engineering & Computer Science (AREA)
- Business, Economics & Management (AREA)
- Human Resources & Organizations (AREA)
- Economics (AREA)
- Theoretical Computer Science (AREA)
- Strategic Management (AREA)
- Physics & Mathematics (AREA)
- General Physics & Mathematics (AREA)
- Data Mining & Analysis (AREA)
- Entrepreneurship & Innovation (AREA)
- Development Economics (AREA)
- Marketing (AREA)
- General Business, Economics & Management (AREA)
- Tourism & Hospitality (AREA)
- Educational Administration (AREA)
- Game Theory and Decision Science (AREA)
- Quality & Reliability (AREA)
- Operations Research (AREA)
- Health & Medical Sciences (AREA)
- Evolutionary Biology (AREA)
- General Engineering & Computer Science (AREA)
- Evolutionary Computation (AREA)
- Computer Vision & Pattern Recognition (AREA)
- Life Sciences & Earth Sciences (AREA)
- Artificial Intelligence (AREA)
- Bioinformatics & Cheminformatics (AREA)
- Bioinformatics & Computational Biology (AREA)
- Primary Health Care (AREA)
- Public Health (AREA)
- General Health & Medical Sciences (AREA)
- Water Supply & Treatment (AREA)
- Supply And Distribution Of Alternating Current (AREA)
Abstract
The invention discloses a method and a system for predicting and analyzing electric energy quality, wherein the method comprises the following steps: constructing a first matrix according to at least one influencing factor and the power quality index, and carrying out mean value specification processing on the first matrix to obtain a second matrix; calculating the association degree index between each influence factor and the power quality index in the second matrix, and sorting each association degree index based on the values to obtain an association degree index sequence, and selecting at least one target association degree index in the association degree index sequence; classifying at least one influencing factor of the harmonic source to be predicted, which corresponds to at least one target association index, into a certain power quality parameter sample; and training influencing factors of a certain power quality parameter sample through a support vector machine regression algorithm, and predicting the power quality index of the harmonic source to be predicted. The method can provide reference analysis for the power quality condition of equipment before and after the harmonic source is connected into the power grid.
Description
Technical Field
The invention belongs to the technical field of power grid power quality analysis, and particularly relates to a power quality prediction analysis method and system.
Background
The power quality problems of the existing power system generally comprise steady-state power quality problems such as harmonic waves and the like and transient-state power quality problems such as voltage sag and the like, wherein the steady-state power quality problems can damage system equipment, threaten the safe operation of the system, or can directly influence or even interrupt the normal power supply of a user, so that serious economic loss is caused.
With the construction of the power grid, nonlinear loads such as distributed new energy, electric iron, smelting and the like are accessed in a large quantity, and a large quantity of harmonic waves are introduced into the power grid. In order to ensure safe and stable operation of the power grid, the electric energy quality analysis before and after the harmonic source is accessed is particularly important.
Disclosure of Invention
The invention provides a power quality prediction analysis method and a power quality prediction analysis system, which are used for solving the technical problem that the power quality before and after the harmonic source is accessed cannot be analyzed.
In a first aspect, the present invention provides a method for predicting and analyzing power quality, including:
acquiring power quality parameter samples of each historical harmonic source, and performing cluster analysis on the power quality parameter samples to obtain at least one type of power quality parameter samples, wherein the power quality parameter samples comprise at least one influencing factor and a power quality index;
constructing a first matrix according to the at least one influencing factor and the electric energy quality index, and carrying out mean value specification processing on the first matrix to obtain a second matrix;
calculating the association degree index between each influence factor and the power quality index in the second matrix, and sequencing each association degree index based on the numerical value to obtain an association degree index sequence;
selecting at least one target relevance index from the relevance index sequence, wherein the at least one target relevance index is the relevance index with the largest numerical value in the relevance index sequence;
acquiring at least one influence factor of the harmonic source to be predicted, which corresponds to the at least one target association index, and calculating a standardized Euclidean distance between the at least one influence factor and the influence factors in the at least one type of power quality parameter samples, so that the at least one influence factor of the harmonic source to be predicted, which corresponds to the at least one target association index, is classified into a certain power quality parameter sample;
training the influencing factors of the certain power quality parameter sample through a support vector machine regression algorithm, and predicting the power quality index of the harmonic source to be predicted.
In a second aspect, the present invention provides a power quality predictive analysis system comprising:
the clustering module is configured to acquire power quality parameter samples of all the historical harmonic sources, and perform clustering analysis on the power quality parameter samples to obtain at least one type of power quality parameter samples, wherein the power quality parameter samples comprise at least one influencing factor and a power quality index;
the processing module is configured to construct a first matrix according to the at least one influencing factor and the electric energy quality index, and perform mean value specification processing on the first matrix to obtain a second matrix;
the calculating module is configured to calculate the association degree index between each influence factor and the power quality index in the second matrix, and sort each association degree index based on the numerical value to obtain an association degree index sequence;
the selecting module is configured to select at least one target relevance index from the relevance index sequence, wherein the at least one target relevance index is the relevance index with the largest numerical value in the relevance index sequence;
the classifying module is configured to acquire at least one influence factor of the harmonic source to be predicted, which corresponds to the at least one target association index, calculate a standardized Euclidean distance between the at least one influence factor and the influence factors in the at least one type of power quality parameter samples, and classify the at least one influence factor of the harmonic source to be predicted, which corresponds to the at least one target association index, into a certain power quality parameter sample;
and the prediction module is used for training the influencing factors of the certain electric energy quality parameter sample through a support vector machine regression algorithm and predicting the electric energy quality index of the harmonic source to be predicted.
In a third aspect, there is provided an electronic device, comprising: the system comprises at least one processor and a memory communicatively connected with the at least one processor, wherein the memory stores instructions executable by the at least one processor to enable the at least one processor to perform the steps of the power quality prediction analysis method of any one of the embodiments of the present invention.
In a fourth aspect, the present invention also provides a computer readable storage medium having stored thereon a computer program, which when executed by a processor, causes the processor to perform the steps of the power quality prediction analysis method of any of the embodiments of the present invention.
According to the power quality prediction analysis method and system, aiming at the access characteristics of the harmonic interference source, the gray correlation analysis algorithm is used for screening factors with larger influence, and then the mass operation data are used for forming training samples from power quality indexes of various types and corresponding influence factor data, prediction evaluation is carried out through the support vector machine model, and reference analysis is provided for power quality conditions of equipment before and after the harmonic source is accessed into a power grid.
Drawings
In order to more clearly illustrate the technical solutions of the embodiments of the present invention, the drawings required for the description of the embodiments will be briefly described below, and it is obvious that the drawings in the following description are some embodiments of the present invention, and other drawings may be obtained according to these drawings without inventive effort for a person skilled in the art.
FIG. 1 is a flowchart of a power quality prediction analysis method according to an embodiment of the present invention;
FIG. 2 is a block diagram of a power quality prediction analysis system according to an embodiment of the present invention;
fig. 3 is a schematic structural diagram of an electronic device according to an embodiment of the present invention.
Detailed Description
For the purpose of making the objects, technical solutions and advantages of the embodiments of the present invention more apparent, the technical solutions of the embodiments of the present invention will be clearly and completely described below with reference to the accompanying drawings in the embodiments of the present invention, and it is apparent that the described embodiments are some embodiments of the present invention, but not all embodiments of the present invention. All other embodiments, which can be made by those skilled in the art based on the embodiments of the invention without making any inventive effort, are intended to be within the scope of the invention.
Referring to fig. 1, a flowchart of a power quality prediction analysis method of the present application is shown.
As shown in fig. 1, the power quality prediction analysis method specifically includes the following steps:
step S101, obtaining power quality parameter samples of all historical harmonic sources, and carrying out cluster analysis on the power quality parameter samples to obtain at least one type of power quality parameter samples, wherein the power quality parameter samples comprise at least one influencing factor and a power quality index.
In this step, for each type of harmonic source, the main influencing factors related to the harmonic source are first combed, the 95% probability value of the harmonic voltage or the 95% probability value of the harmonic current is used as the final evaluation index of the electric energy quality, each type of factors possibly influencing the harmonic index are listed, m historical data samples are collected, and n influencing factors are related to each sample, as shown in the following table:
when the harmonic source is connected into a distributed photovoltaic, possible influencing factors include the annual average power generation hour number of the photovoltaic, the capacity of a photovoltaic power station, the energy storage capacity, the position of a grid connection point, the illumination intensity, the access voltage level, the system short-circuit capacity and the like; when the harmonic source is rail transit, factors that may be affected include traction load, traction transformer model and capacity, access voltage class, system short circuit capacity, and the like. In general, the larger the number of samples m that are present, the closer the final predicted result is to the real case.
Step S102, a first matrix is constructed according to the at least one influencing factor and the electric energy quality index, and mean value specification processing is carried out on the first matrix to obtain a second matrix.
In this step, a first matrix is constructed according to at least one influencing factor and the power quality index, and the expression of the first matrix is:
wherein Z is a first matrix, X ij The j-th influencing factor of the i-th sample, Y i For the power quality index of the ith sample, i.e. [1, m]，j∈[1，n]。
It should be noted that, the average value specification process is performed on the first matrix to obtain the second matrix.
The expression for carrying out mean value specification processing on the first matrix is as follows:
wherein X is ij The j-th influencing factor of the i-th sample, Y i For the power quality index of the ith sample, i.e. [1, m]，j∈[1，n]，x ij Mean value of jth influencing factors of ith sample, y i Is the average value of the power quality index of the ith sample.
Step S103, calculating the association index between each influence factor and the power quality index in the second matrix, and sorting each association index based on the values to obtain an association index sequence.
In this step, the expression for calculating the association index between each influencing factor and the power quality index in the second matrix is:
wherein, gamma i Is the index of the degree of association, eta, of the ith influencing factor and the index of the electric energy quality ij As the correlation parameter of the j-th influencing factor of the i-th sample and the power quality index,n is the total number of influencing factors;
wherein x is ij Mean value of jth influencing factors of ith sample, y i The mean value of the power quality index of the ith sample is obtained, ω is a resolution coefficient, and the value is 0.5.
It should be noted that the general case relevance index is in [0,1]In the interval, the closer the value is to 1, the greater the correlation degree between the two is, and it is generally considered that |gamma i I > 0.6, considered highly correlated; 0.6 Not less than |gamma i The I is more than or equal to 0.2, and is regarded as medium correlation; y i The correlation is considered extremely weak when the I is less than 0.2.
Step S104, selecting at least one target relevance index from the relevance index sequence, wherein the at least one target relevance index is the relevance index with the largest numerical value in the relevance index sequence.
Step S105, obtaining at least one influence factor of the harmonic source to be predicted, which corresponds to the at least one target association index, and calculating a standardized euclidean distance between the at least one influence factor and the influence factor in the at least one type of power quality parameter sample, so as to classify the at least one influence factor of the harmonic source to be predicted, which corresponds to the at least one target association index, into a certain power quality parameter sample.
In the step, after the conditions of association of each influence factor and the power quality index are combed, the first n' influence factors with higher relativity are optimized, then cluster analysis is carried out on the collected m samples, and a condensation hierarchical clustering algorithm is utilized, so that the standardized Euclidean distance is defined as a quantization index of the similarity degree of each index.
It should be noted that, the expression for calculating the normalized euclidean distance between the at least one influencing factor and the influencing factor in the at least one type of power quality parameter sample is:
wherein d il The spatial distance, x, between the i-th sample and the i-th sample ik 、x lk The k-th influencing factor of the i-th sample and the k-th influencing factor of the i-th sample, x max k For the maximum value of the kth influencing factor in all samples, gamma k And n' is the total number of influence factors corresponding to the target association degree index, wherein the association degree index is the association degree index of the kth influence factor and the power quality index.
And S106, training the influencing factors of the certain power quality parameter sample through a support vector machine regression algorithm, and predicting the power quality index of the harmonic source to be predicted.
In this step, n' related parameter values of the harmonic source to be connected to the system are obtained, and the spatial distance d between the sample and the previous m samples is calculated il And screening out the class group with the smallest sum of the distances between the sample to be predicted and the historical sample, and marking the class group as the q-th class. And learning the q-th type of historical samples by means of a support vector machine regression algorithm, and inputting sample parameter values to be predicted to obtain a final power quality index.
In summary, according to the method, aiming at the access characteristics of the harmonic interference source, the gray correlation analysis algorithm is used for screening larger influencing factors, then various electric energy quality indexes and corresponding influencing factor data are formed into training samples by means of massive operation data, prediction and evaluation are carried out through the support vector machine model, and reference analysis is provided for the electric energy quality condition of equipment before and after the harmonic source is accessed into the power grid.
Referring to fig. 2, a block diagram of a power quality prediction analysis system of the present application is shown.
As shown in fig. 2, the power quality prediction analysis system 200 includes a clustering module 210, a processing module 220, a computing module 230, a selection module 240, a categorizing module 250, and a prediction module 260.
The clustering module 210 is configured to obtain power quality parameter samples of each historical harmonic source, and perform cluster analysis on the power quality parameter samples to obtain at least one type of power quality parameter samples, wherein the power quality parameter samples comprise at least one influencing factor and a power quality index; the processing module 220 is configured to construct a first matrix according to the at least one influencing factor and the power quality index, and perform mean value specification processing on the first matrix to obtain a second matrix; the calculating module 230 is configured to calculate a relevance index between each influencing factor and the power quality index in the second matrix, and sort each relevance index based on the values, so as to obtain a relevance index sequence; a selecting module 240, configured to select at least one target relevance index from the relevance index sequence, where the at least one target relevance index is a relevance index with a maximum value in the relevance index sequence; a classifying module 250 configured to obtain at least one influence factor of the harmonic source to be predicted, which corresponds to the at least one target association index, and calculate a standardized euclidean distance between the at least one influence factor and an influence factor in the at least one type of power quality parameter samples, so as to classify the at least one influence factor of the harmonic source to be predicted, which corresponds to the at least one target association index, into a certain power quality parameter sample; the prediction module 260 trains the influencing factors of the certain power quality parameter sample through a support vector machine regression algorithm and predicts the power quality index of the harmonic source to be predicted.
It should be understood that the modules depicted in fig. 2 correspond to the various steps in the method described with reference to fig. 1. Thus, the operations and features described above for the method and the corresponding technical effects are equally applicable to the modules in fig. 2, and are not described here again.
In other embodiments, embodiments of the present invention further provide a computer readable storage medium having stored thereon a computer program, the program instructions, when executed by a processor, cause the processor to perform the power quality prediction analysis method of any of the method embodiments described above;
as one embodiment, the computer-readable storage medium of the present invention stores computer-executable instructions configured to:
acquiring power quality parameter samples of each historical harmonic source, and performing cluster analysis on the power quality parameter samples to obtain at least one type of power quality parameter samples, wherein the power quality parameter samples comprise at least one influencing factor and a power quality index;
constructing a first matrix according to the at least one influencing factor and the electric energy quality index, and carrying out mean value specification processing on the first matrix to obtain a second matrix;
calculating the association degree index between each influence factor and the power quality index in the second matrix, and sequencing each association degree index based on the numerical value to obtain an association degree index sequence;
selecting at least one target relevance index from the relevance index sequence, wherein the at least one target relevance index is the relevance index with the largest numerical value in the relevance index sequence;
acquiring at least one influence factor of the harmonic source to be predicted, which corresponds to the at least one target association index, and calculating a standardized Euclidean distance between the at least one influence factor and the influence factors in the at least one type of power quality parameter samples, so that the at least one influence factor of the harmonic source to be predicted, which corresponds to the at least one target association index, is classified into a certain power quality parameter sample;
training the influencing factors of the certain power quality parameter sample through a support vector machine regression algorithm, and predicting the power quality index of the harmonic source to be predicted.
The computer readable storage medium may include a storage program area and a storage data area, wherein the storage program area may store an operating system, at least one application program required for a function; the storage data area may store data created from the use of the power quality predictive analysis system, and the like. In addition, the computer-readable storage medium may include high-speed random access memory, and may also include memory, such as at least one magnetic disk storage device, flash memory device, or other non-volatile solid-state storage device. In some embodiments, the computer readable storage medium optionally includes memory remotely located with respect to the processor, the remote memory being connectable to the power quality prediction analysis system through a network. Examples of such networks include, but are not limited to, the internet, intranets, local area networks, mobile communication networks, and combinations thereof.
Fig. 3 is a schematic structural diagram of an electronic device according to an embodiment of the present invention, as shown in fig. 3, where the device includes: a processor 310 and a memory 320. The electronic device may further include: an input device 330 and an output device 340. The processor 310, memory 320, input device 330, and output device 340 may be connected by a bus or other means, for example in fig. 3. Memory 320 is the computer-readable storage medium described above. The processor 310 executes various functional applications of the server and data processing, i.e., implements the power quality prediction analysis method of the above-described method embodiment, by running non-volatile software programs, instructions, and modules stored in the memory 320. The input device 330 may receive input numeric or character information and generate key signal inputs related to user settings and function control of the power quality prediction analysis system. The output device 340 may include a display device such as a display screen.
The electronic equipment can execute the method provided by the embodiment of the invention, and has the corresponding functional modules and beneficial effects of the execution method. Technical details not described in detail in this embodiment may be found in the methods provided in the embodiments of the present invention.
As an embodiment, the electronic device is applied to a power quality prediction analysis system, and is used for a client, and includes: at least one processor; and a memory communicatively coupled to the at least one processor; wherein the memory stores instructions executable by the at least one processor, the instructions being executable by the at least one processor to enable the at least one processor to:
acquiring power quality parameter samples of each historical harmonic source, and performing cluster analysis on the power quality parameter samples to obtain at least one type of power quality parameter samples, wherein the power quality parameter samples comprise at least one influencing factor and a power quality index;
constructing a first matrix according to the at least one influencing factor and the electric energy quality index, and carrying out mean value specification processing on the first matrix to obtain a second matrix;
calculating the association degree index between each influence factor and the power quality index in the second matrix, and sequencing each association degree index based on the numerical value to obtain an association degree index sequence;
selecting at least one target relevance index from the relevance index sequence, wherein the at least one target relevance index is the relevance index with the largest numerical value in the relevance index sequence;
acquiring at least one influence factor of the harmonic source to be predicted, which corresponds to the at least one target association index, and calculating a standardized Euclidean distance between the at least one influence factor and the influence factors in the at least one type of power quality parameter samples, so that the at least one influence factor of the harmonic source to be predicted, which corresponds to the at least one target association index, is classified into a certain power quality parameter sample;
training the influencing factors of the certain power quality parameter sample through a support vector machine regression algorithm, and predicting the power quality index of the harmonic source to be predicted.
From the above description of the embodiments, it will be apparent to those skilled in the art that the embodiments may be implemented by means of software plus necessary general hardware platforms, or of course may be implemented by means of hardware. Based on such understanding, the foregoing technical solutions may be embodied essentially or in part in the form of a software product, which may be stored in a computer-readable storage medium, such as a ROM/RAM, a magnetic disk, an optical disk, etc., including several instructions to cause a computer device (which may be a personal computer, a server, or a network device, etc.) to perform the various embodiments or methods of some parts of the embodiments.
Finally, it should be noted that: the above embodiments are only for illustrating the technical solution of the present invention, and are not limiting; although the invention has been described in detail with reference to the foregoing embodiments, it will be understood by those of ordinary skill in the art that: the technical scheme described in the foregoing embodiments can be modified or some technical features thereof can be replaced by equivalents; such modifications and substitutions do not depart from the spirit and scope of the technical solutions of the embodiments of the present invention.
Claims (9)
1. A power quality predictive analysis method, comprising:
acquiring power quality parameter samples of each historical harmonic source, and performing cluster analysis on the power quality parameter samples to obtain at least one type of power quality parameter samples, wherein the power quality parameter samples comprise at least one influencing factor and a power quality index;
constructing a first matrix according to the at least one influencing factor and the electric energy quality index, and carrying out mean value specification processing on the first matrix to obtain a second matrix;
calculating the association degree index between each influence factor and the power quality index in the second matrix, and sequencing each association degree index based on the numerical value to obtain an association degree index sequence;
selecting at least one target relevance index from the relevance index sequence, wherein the at least one target relevance index is the relevance index with the largest numerical value in the relevance index sequence;
acquiring at least one influence factor of the harmonic source to be predicted, which corresponds to the at least one target association index, and calculating a standardized Euclidean distance between the at least one influence factor and the influence factors in the at least one type of power quality parameter samples, so that the at least one influence factor of the harmonic source to be predicted, which corresponds to the at least one target association index, is classified into a certain power quality parameter sample;
training the influencing factors of the certain power quality parameter sample through a support vector machine regression algorithm, and predicting the power quality index of the harmonic source to be predicted.
2. The power quality predictive analysis method of claim 1, wherein the power quality indicator comprises a harmonic voltage 95% probability value or a harmonic current 95% probability value.
3. The power quality predictive analysis method of claim 1, wherein the first matrix is expressed as:
wherein z is a first matrix, X ij The j-th influencing factor of the i-th sample, Y i For the power quality index of the ith sample, i.e. [1, m]，j∈[1，n]。
4. A method of power quality prediction analysis according to claim 3, wherein the expression for performing the mean value specification processing on the first matrix is:
wherein X is ij The j-th influencing factor of the i-th sample, Y i For the power quality index of the ith sample, i.e. [1, m]，j∈[1，n]，x ij Mean value of jth influencing factors of ith sample, y i Is the average value of the power quality index of the ith sample.
5. The power quality prediction analysis method according to claim 1, wherein the expression for calculating the association degree index between each influencing factor and the power quality index in the second matrix is:
wherein, gamma i Is the index of the degree of association, eta, of the ith influencing factor and the index of the electric energy quality ij The correlation parameter of the j-th influencing factor of the i-th sample and the electric energy quality index is obtained, and n is the total number of influencing factors;
wherein x is ij Mean value of jth influencing factors of ith sample, y i The mean value of the power quality index of the ith sample is obtained, ω is a resolution coefficient, and the value is 0.5.
6. The power quality predictive analysis method of claim 1, wherein the expression for calculating a normalized euclidean distance between the at least one influencing factor and the influencing factor in the at least one type of power quality parameter sample is:
wherein d il The spatial distance, x, between the i-th sample and the i-th sample ik 、x lk The k-th influencing factor of the i-th sample and the k-th influencing factor of the i-th sample, x maxk For the maximum value of the kth influencing factor in all samples, gamma k And n' is the total number of influence factors corresponding to the target association degree index, wherein the association degree index is the association degree index of the kth influence factor and the power quality index.
7. A power quality predictive analysis system, comprising:
the clustering module is configured to acquire power quality parameter samples of all the historical harmonic sources, and perform clustering analysis on the power quality parameter samples to obtain at least one type of power quality parameter samples, wherein the power quality parameter samples comprise at least one influencing factor and a power quality index;
the processing module is configured to construct a first matrix according to the at least one influencing factor and the electric energy quality index, and perform mean value specification processing on the first matrix to obtain a second matrix;
the calculating module is configured to calculate the association degree index between each influence factor and the power quality index in the second matrix, and sort each association degree index based on the numerical value to obtain an association degree index sequence;
the selecting module is configured to select at least one target relevance index from the relevance index sequence, wherein the at least one target relevance index is the relevance index with the largest numerical value in the relevance index sequence;
the classifying module is configured to acquire at least one influence factor of the harmonic source to be predicted, which corresponds to the at least one target association index, calculate a standardized Euclidean distance between the at least one influence factor and the influence factors in the at least one type of power quality parameter samples, and classify the at least one influence factor of the harmonic source to be predicted, which corresponds to the at least one target association index, into a certain power quality parameter sample;
and the prediction module is used for training the influencing factors of the certain electric energy quality parameter sample through a support vector machine regression algorithm and predicting the electric energy quality index of the harmonic source to be predicted.
8. An electronic device, comprising: at least one processor, and a memory communicatively coupled to the at least one processor, wherein the memory stores instructions executable by the at least one processor to enable the at least one processor to perform the method of any one of claims 1 to 6.
9. A computer readable storage medium, on which a computer program is stored, characterized in that the program, when being executed by a processor, implements the method of any one of claims 1 to 6.
Priority Applications (1)
| Application Number | Priority Date | Filing Date | Title |
|---|---|---|---|
| CN202311073666.5A CN117314678A (en) | 2023-08-24 | 2023-08-24 | Electric energy quality prediction analysis method and system |
Applications Claiming Priority (1)
| Application Number | Priority Date | Filing Date | Title |
|---|---|---|---|
| CN202311073666.5A CN117314678A (en) | 2023-08-24 | 2023-08-24 | Electric energy quality prediction analysis method and system |
Publications (1)
| Publication Number | Publication Date |
|---|---|
| CN117314678A true CN117314678A (en) | 2023-12-29 |
Family
ID=89259247
Family Applications (1)
| Application Number | Title | Priority Date | Filing Date |
|---|---|---|---|
| CN202311073666.5A Pending CN117314678A (en) | 2023-08-24 | 2023-08-24 | Electric energy quality prediction analysis method and system |
Country Status (1)
| Country | Link |
|---|---|
| CN (1) | CN117314678A (en) |
-
2023
- 2023-08-24 CN CN202311073666.5A patent/CN117314678A/en active Pending
Similar Documents
| Publication | Publication Date | Title |
|---|---|---|
| CN108694470B (en) | Data prediction method and device based on artificial intelligence | |
| CN111915092B (en) | Ultra-short-term wind power prediction method based on long-short-term memory neural network | |
| CN110837939A (en) | Power grid multi-target project screening method and system | |
| CN116245033B (en) | Artificial intelligent driven power system analysis method and intelligent software platform | |
| WO2021004318A1 (en) | Resource data processing method and apparatus, computer device and storage medium | |
| CN115358481A (en) | Early warning and identification method, system and device for enterprise ex-situ migration | |
| CN113762591B (en) | Short-term electric quantity prediction method and system based on GRU and multi-core SVM countermeasure learning | |
| CN110781206A (en) | Method for predicting whether electric energy meter in operation fails or not by learning meter-dismantling and returning failure characteristic rule | |
| CN114037209A (en) | Comprehensive benefit analysis method and device for distributed photovoltaic access direct-current power distribution system | |
| CN113033898A (en) | Electrical load prediction method and system based on K-means clustering and BI-LSTM neural network | |
| Han et al. | Deep belief rule based photovoltaic power forecasting method with interpretability | |
| CN112633528A (en) | Power grid primary equipment operation and maintenance cost determination method based on support vector machine | |
| Wang et al. | Cloud computing and extreme learning machine for a distributed energy consumption forecasting in equipment-manufacturing enterprises | |
| Guo et al. | Wind speed forecasting of genetic neural model based on rough set theory | |
| CN116956702A (en) | Electricity safety early warning method, medium and system | |
| Tang et al. | Predicting typhoon-induced transmission line outages with coordination of static and dynamic data | |
| CN111060755A (en) | Electromagnetic interference diagnosis method and device | |
| CN116561569A (en) | Industrial power load identification method based on EO feature selection and AdaBoost algorithm | |
| CN117314678A (en) | Electric energy quality prediction analysis method and system | |
| CN115310355A (en) | Multi-energy coupling-considered multi-load prediction method and system for comprehensive energy system | |
| Li et al. | Long-term electricity consumption forecasting for future power systems combining system dynamics and impact equation | |
| CN113808071A (en) | Non-invasive load monitoring method and system based on deep learning | |
| Zhuang et al. | DyS-IENN: a novel multiclass imbalanced learning method for early warning of tardiness in rocket final assembly process | |
| Zheng et al. | [Retracted] Application Based on Artificial Intelligence in Substation Operation and Maintenance Management | |
| Khairuddin et al. | Hybrid neighbourhood component analysis with gradient tree boosting for feature selection in forecasting crime rate |
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 |