CN113553755A - Power system state estimation method, device and equipment - Google Patents
Power system state estimation method, device and equipment Download PDFInfo
- Publication number
- CN113553755A CN113553755A CN202110633909.0A CN202110633909A CN113553755A CN 113553755 A CN113553755 A CN 113553755A CN 202110633909 A CN202110633909 A CN 202110633909A CN 113553755 A CN113553755 A CN 113553755A
- Authority
- CN
- China
- Prior art keywords
- matrix
- state estimation
- power
- power system
- initial data
- 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.)
- Granted
Links
- 238000000034 method Methods 0.000 title claims abstract description 89
- 239000011159 matrix material Substances 0.000 claims abstract description 118
- 239000002245 particle Substances 0.000 claims abstract description 108
- 238000012706 support-vector machine Methods 0.000 claims abstract description 59
- 238000004422 calculation algorithm Methods 0.000 claims abstract description 40
- 238000012545 processing Methods 0.000 claims abstract description 39
- 238000005457 optimization Methods 0.000 claims abstract description 28
- 238000005070 sampling Methods 0.000 claims abstract description 21
- 238000000513 principal component analysis Methods 0.000 claims abstract description 19
- 230000009467 reduction Effects 0.000 claims abstract description 19
- 238000012549 training Methods 0.000 claims abstract description 19
- 230000009466 transformation Effects 0.000 claims abstract description 16
- 238000004590 computer program Methods 0.000 claims description 31
- 230000006870 function Effects 0.000 claims description 25
- 238000007781 pre-processing Methods 0.000 claims description 22
- 238000010606 normalization Methods 0.000 claims description 13
- 238000005259 measurement Methods 0.000 claims description 8
- 238000000354 decomposition reaction Methods 0.000 claims description 5
- 238000002790 cross-validation Methods 0.000 claims description 3
- 238000003672 processing method Methods 0.000 claims 1
- 239000013598 vector Substances 0.000 claims 1
- 238000010586 diagram Methods 0.000 description 8
- 230000008569 process Effects 0.000 description 8
- 238000004088 simulation Methods 0.000 description 7
- 238000004364 calculation method Methods 0.000 description 5
- 238000012795 verification Methods 0.000 description 5
- 230000008878 coupling Effects 0.000 description 3
- 238000010168 coupling process Methods 0.000 description 3
- 238000005859 coupling reaction Methods 0.000 description 3
- 230000007547 defect Effects 0.000 description 3
- 230000000694 effects Effects 0.000 description 3
- 210000002569 neuron Anatomy 0.000 description 3
- 230000003068 static effect Effects 0.000 description 3
- 238000004891 communication Methods 0.000 description 2
- 238000013480 data collection Methods 0.000 description 2
- 230000003993 interaction Effects 0.000 description 2
- 230000003287 optical effect Effects 0.000 description 2
- 238000012163 sequencing technique Methods 0.000 description 2
- 238000013473 artificial intelligence Methods 0.000 description 1
- 238000013528 artificial neural network Methods 0.000 description 1
- 230000009286 beneficial effect Effects 0.000 description 1
- 238000012512 characterization method Methods 0.000 description 1
- 238000013461 design Methods 0.000 description 1
- 238000005516 engineering process Methods 0.000 description 1
- 238000012843 least square support vector machine Methods 0.000 description 1
- 238000012986 modification Methods 0.000 description 1
- 230000004048 modification Effects 0.000 description 1
- 238000006467 substitution reaction Methods 0.000 description 1
Images
Classifications
-
- G—PHYSICS
- G06—COMPUTING; CALCULATING OR COUNTING
- G06F—ELECTRIC DIGITAL DATA PROCESSING
- G06F30/00—Computer-aided design [CAD]
- G06F30/20—Design optimisation, verification or simulation
- G06F30/27—Design optimisation, verification or simulation using machine learning, e.g. artificial intelligence, neural networks, support vector machines [SVM] or training a model
-
- G—PHYSICS
- G06—COMPUTING; CALCULATING OR COUNTING
- G06F—ELECTRIC DIGITAL DATA PROCESSING
- G06F18/00—Pattern recognition
- G06F18/20—Analysing
- G06F18/21—Design or setup of recognition systems or techniques; Extraction of features in feature space; Blind source separation
- G06F18/213—Feature extraction, e.g. by transforming the feature space; Summarisation; Mappings, e.g. subspace methods
- G06F18/2135—Feature extraction, e.g. by transforming the feature space; Summarisation; Mappings, e.g. subspace methods based on approximation criteria, e.g. principal component analysis
-
- G—PHYSICS
- G06—COMPUTING; CALCULATING OR COUNTING
- G06F—ELECTRIC DIGITAL DATA PROCESSING
- G06F18/00—Pattern recognition
- G06F18/20—Analysing
- G06F18/24—Classification techniques
- G06F18/241—Classification techniques relating to the classification model, e.g. parametric or non-parametric approaches
- G06F18/2411—Classification techniques relating to the classification model, e.g. parametric or non-parametric approaches based on the proximity to a decision surface, e.g. support vector machines
-
- G—PHYSICS
- G06—COMPUTING; CALCULATING OR COUNTING
- G06N—COMPUTING ARRANGEMENTS BASED ON SPECIFIC COMPUTATIONAL MODELS
- G06N3/00—Computing arrangements based on biological models
- G06N3/004—Artificial life, i.e. computing arrangements simulating life
- G06N3/006—Artificial life, i.e. computing arrangements simulating life based on simulated virtual individual or collective life forms, e.g. social simulations or particle swarm optimisation [PSO]
-
- G—PHYSICS
- G06—COMPUTING; CALCULATING OR COUNTING
- G06N—COMPUTING ARRANGEMENTS BASED ON SPECIFIC COMPUTATIONAL MODELS
- G06N3/00—Computing arrangements based on biological models
- G06N3/02—Neural networks
- G06N3/04—Architecture, e.g. interconnection topology
- G06N3/045—Combinations of networks
-
- G—PHYSICS
- G06—COMPUTING; CALCULATING OR COUNTING
- G06N—COMPUTING ARRANGEMENTS BASED ON SPECIFIC COMPUTATIONAL MODELS
- G06N3/00—Computing arrangements based on biological models
- G06N3/02—Neural networks
- G06N3/08—Learning methods
-
- 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
-
- 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
- H02J2203/00—Indexing scheme relating to details of circuit arrangements for AC mains or AC distribution networks
- H02J2203/20—Simulating, e g planning, reliability check, modelling or computer assisted design [CAD]
Landscapes
- Engineering & Computer Science (AREA)
- Theoretical Computer Science (AREA)
- Physics & Mathematics (AREA)
- Data Mining & Analysis (AREA)
- Evolutionary Computation (AREA)
- General Physics & Mathematics (AREA)
- Artificial Intelligence (AREA)
- General Engineering & Computer Science (AREA)
- Life Sciences & Earth Sciences (AREA)
- Computer Vision & Pattern Recognition (AREA)
- Software Systems (AREA)
- Molecular Biology (AREA)
- Computing Systems (AREA)
- Health & Medical Sciences (AREA)
- Biomedical Technology (AREA)
- Biophysics (AREA)
- Computational Linguistics (AREA)
- General Health & Medical Sciences (AREA)
- Mathematical Physics (AREA)
- Bioinformatics & Computational Biology (AREA)
- Evolutionary Biology (AREA)
- Bioinformatics & Cheminformatics (AREA)
- Medical Informatics (AREA)
- Computer Hardware Design (AREA)
- Geometry (AREA)
- Power Engineering (AREA)
- Supply And Distribution Of Alternating Current (AREA)
Abstract
The invention discloses a method, a device and equipment for estimating the state of a power system, wherein the method comprises the following steps: acquiring power data of each node of a plurality of historical time power systems, and forming an initial data matrix according to the power data; performing dimensionality reduction processing on the initial data matrix according to a principal component analysis algorithm to obtain a projection matrix; establishing a least square depth support vector machine model, and optimizing the designated parameters of the model according to an improved particle swarm algorithm; training the optimized model according to the projection matrix to obtain a state estimation model; and acquiring power data of each node at the sampling moment, and performing state estimation on the power system according to the power data and the state estimation model at the sampling moment to obtain a state estimation value at the target moment. The particle swarm optimization is improved through a nonlinear transformation formula with control factors, and then the improved algorithm is adopted to optimize the parameters of the depth support vector machine, so that more accurate parameters can be provided, and the state estimation error of the power system is reduced.
Description
Technical Field
The present application belongs to the field of power technologies, and in particular, to a method, an apparatus, and a device for estimating a state of a power system.
Background
With the continuous access of distributed power sources, wind energy, solar energy and the like to the power grid, the structure of the power grid becomes increasingly complex. In order to ensure safe, reliable and stable operation of the power grid and to deal with various problems occurring in the power grid, the power system dispatching center is required to be capable of rapidly and unmistakably mastering the operation state of the power system.
In the prior art, the operating state of the power system is usually estimated by using a static estimation method of mixed measurement, such as a weighted least square method, a fast decomposition method, a weighted minimum absolute value method and the like, but all methods have the defect of large state estimation error.
Disclosure of Invention
In view of this, the present invention provides a method, an apparatus and a device for estimating a state of an electrical power system, and aims to solve the problem of large error in estimating the state of the electrical power system.
A first aspect of an embodiment of the present invention provides a method for estimating a state of an electric power system, including:
acquiring power data of each node in a power system at a plurality of historical moments, and forming an initial data matrix by the acquired power data;
performing dimensionality reduction processing on the initial data matrix according to a principal component analysis algorithm to obtain a projection matrix;
establishing a least square depth support vector machine model, and optimizing the specified parameters of the least square depth support vector machine model according to an improved particle swarm algorithm; wherein, the weight coefficient of the updated formula in the improved particle swarm optimization is determined according to a nonlinear transformation formula with a control factor;
training the optimized least square depth support vector machine model according to the projection matrix to obtain a state estimation model;
and acquiring power data of each node of the power system at a sampling moment, and performing state estimation on the power system according to the power data at the current moment and the state estimation model to obtain a state estimation value of the power system at a target moment.
A second aspect of an embodiment of the present invention provides a power system state estimation device, including:
the acquisition module is used for acquiring power data of each node in the power system at a plurality of historical moments and forming an initial data matrix by the acquired power data;
the dimensionality reduction module is used for carrying out dimensionality reduction on the initial data matrix according to a principal component analysis algorithm to obtain a projection matrix;
the optimization module is used for establishing a least square depth support vector machine model and optimizing the designated parameters of the least square depth support vector machine model according to the improved particle swarm algorithm; wherein, the weight coefficient of the updated formula in the improved particle swarm optimization is determined according to a nonlinear transformation formula with a control factor;
the training module is used for training the optimized least square depth support vector machine model according to the projection matrix to obtain a state estimation model;
and the estimation module is used for acquiring the power data of each node of the power system at the sampling moment, and performing state estimation on the power system according to the power data at the current moment and the state estimation model to obtain a state estimation value of the power system at the target moment.
A third aspect of the embodiments of the present invention provides an electronic device, including a memory, a processor, and a computer program stored in the memory and executable on the processor, where the processor implements the steps of the power system state estimation method according to the first aspect when executing the computer program.
A fourth aspect of embodiments of the present invention provides a computer-readable storage medium storing a computer program that, when executed by a processor, implements the steps of the power system state estimation method according to the first aspect described above.
Compared with the prior art, the invention has the following beneficial effects:
the method for estimating the state of the power system provided by the embodiment of the invention comprises the following steps: acquiring power data of each node in a power system at a plurality of historical moments, and forming an initial data matrix by the acquired power data; performing dimensionality reduction processing on the initial data matrix according to a principal component analysis algorithm to obtain a projection matrix; establishing a least square depth support vector machine model, and optimizing the specified parameters of the least square depth support vector machine model according to an improved particle swarm algorithm; wherein, the weight coefficient of the updated formula in the improved particle swarm optimization is determined according to a nonlinear transformation formula with a control factor; training the optimized least square depth support vector machine model according to the projection matrix to obtain a state estimation model; and acquiring power data of each node of the power system at the sampling moment, and performing state estimation on the power system according to the power data and the state estimation model at the sampling moment to obtain a state estimation value of the power system at the target moment. The particle algorithm is improved by updating the weight coefficient of the formula according to the nonlinear transformation formula with the control factor, and then the improved particle swarm algorithm is adopted to optimize the parameters of the depth support vector machine, so that more accurate parameters can be provided, and the state estimation error of the power system is reduced.
Drawings
In order to more clearly illustrate the technical solutions in the embodiments of the present invention, the drawings needed to be used in the embodiments or the prior art descriptions will be briefly described below, and it is obvious that the drawings in the following description are only some embodiments of the present invention, and it is obvious for those skilled in the art to obtain other drawings based on these drawings without inventive exercise.
Fig. 1 is an application environment diagram of a power system state estimation method according to an embodiment of the present invention;
FIG. 2 is a flow chart of an implementation of a method for estimating a state of a power system according to an embodiment of the present invention;
FIG. 3 is a schematic structural diagram of a least squares depth support vector machine model provided by one embodiment of the present invention;
FIG. 4 is a simulation of the optimization of the particle swarm optimization for the specified parameters of the least squares depth support vector machine model;
FIG. 5 is a plot of the mean absolute error versus the estimated value of the voltage phase angle using the PCA-LS-DSVM method, the WLS method, the LS-SVM method;
FIG. 6 is a plot of mean absolute error versus voltage amplitude estimates using the PCA-LS-DSVM method, the WLS method, the LS-SVM method;
fig. 7 is a schematic structural diagram of a power system state estimation device according to an embodiment of the present invention;
fig. 8 is a schematic diagram of an electronic device provided by an embodiment of the invention.
Detailed Description
In the following description, for purposes of explanation and not limitation, specific details are set forth, such as particular system structures, techniques, etc. in order to provide a thorough understanding of the embodiments of the invention. It will be apparent, however, to one skilled in the art that the present invention may be practiced in other embodiments that depart from these specific details. In other instances, detailed descriptions of well-known systems, devices, circuits, and methods are omitted so as not to obscure the description of the present invention with unnecessary detail.
In order to make the objects, technical solutions and advantages of the present invention more apparent, the following description is made by way of specific embodiments with reference to the accompanying drawings.
With the continuous access of distributed power sources, wind energy, solar energy and the like to the power grid, the structure of the power grid becomes increasingly complex. In order to ensure safe, reliable and stable operation of the power grid and to deal with various problems occurring in the power grid, the power system dispatching center is required to be capable of rapidly and unmistakably mastering the operation state of the power system. In view of this, we must quickly and accurately perform state estimation of the power system.
In the prior art, the operating state of the power system is usually estimated by using static estimation methods of mixed measurement, such as a weighted least square method, a fast decomposition method, a weighted minimum absolute value method and the like, but the static estimation methods have the defects of large state estimation error and slow estimation speed. In recent years, with the rapid rise of artificial intelligence, artificial neural network models have been widely used. In the prior art, a regression prediction method (SVM) of a Support Vector Machine is gradually used for state estimation, and compared with a traditional method, the estimation accuracy is greatly improved, but the SVM has some defects, the SVM excessively depends on a prior kernel function, the hidden layer has limited characterization capability, and the state estimation is unstable.
The invention provides a power system state estimation method, which is characterized in that a particle algorithm is improved according to a nonlinear transformation formula with a control factor by updating a weight coefficient of the formula, and then the parameters of a depth support vector machine are optimized by adopting an improved particle swarm optimization, so that more accurate parameters can be provided, and the power system state estimation error is reduced.
Fig. 1 is an application environment diagram of a power system state estimation method according to an embodiment of the present invention. The power system state estimation method provided by the embodiment of the invention can be applied to the application environment but is not limited to the application environment. As shown in fig. 1, the application environment includes: the power dispatching system comprises a power data acquisition device 11, an electronic device 12 and a power dispatching center 13.
The power dispatching center 13 is configured to send a state estimation instruction to the electronic device 12. The electronic device 12 is configured to send a collection instruction to the power data collection device 11 in the target area after receiving the state estimation. The power data acquisition device 11 is configured to, after receiving the acquisition instruction, acquire power data of each node in the power system at a plurality of historical times, and send the power data to the electronic device 12. The electronic device 12 is further configured to perform state estimation on the power system after receiving the power data, and send the obtained state estimation result to the power dispatching center 13. The electronic device 12 may also obtain power data of each node in the power system at a plurality of historical times from a database of the power dispatching center 13, which is not limited herein.
The power data collection device 11 may be an electromechanical integrated electric meter, an all-electronic electric meter, etc., and is not limited herein. The electronic device 12 may be a server, a terminal, etc., and is not limited thereto. The server may be implemented as a stand-alone server or as a server cluster comprised of multiple servers. The terminal may include, but is not limited to, a desktop computer, a laptop computer, a tablet computer, and the like. The power data acquisition device 11, the electronic device 12, and the power dispatching center 13 may perform data interaction through a line, or may perform data interaction through a network or a bluetooth, which is not limited herein. The electronic device 12 may be a device installed independently, or may be a device installed in the power dispatching center 13, and is not limited herein.
Fig. 2 is a flowchart of an implementation of a method for estimating a state of a power system according to an embodiment of the present invention. In this embodiment, the method is applied to the electronic device in fig. 1 as an example. As shown in fig. 2, the method includes:
s201, acquiring power data of each node in the power system at a plurality of historical times, and forming an initial data matrix by the acquired power data.
In this embodiment, the plurality of historical moments may be selected according to actual needs, for example, the power data may be selected in units of 15 minutes from an hour of a certain day, or the power data may be selected at a fixed time of each day of a certain month, which is not limited herein. Optionally, the power data of each node at a plurality of historical time instants includes, but is not limited to, one or more of the following: active power, reactive power, voltage amplitude and voltage phase angle.
S202, performing dimensionality reduction processing on the initial data matrix according to a principal component analysis algorithm to obtain a projection matrix.
S203, establishing a least square depth support vector machine model, and optimizing the designated parameters of the least square depth support vector machine model according to an improved particle swarm algorithm; wherein, the weight coefficient of the updated formula in the improved particle swarm optimization is determined according to the nonlinear transformation formula with the control factor.
In this embodiment, in the least square depth support vector machine model, the hidden layer of the depth support vector machine model has n layers in total, where n is greater than or equal to 2 and less than or equal to 4, and may be specifically selected according to the requirements of the calculation time and the calculation accuracy, and is not limited herein. Alternatively, the kernel function of the least squares depth support vector machine model may be a radial basis kernel function.
In this embodiment, the stability of state estimation can be improved by using a depth support vector machine model with multiple hidden layers.
And S204, training the optimized least square depth support vector machine model according to the projection matrix to obtain a state estimation model.
S205, acquiring power data of each node of the power system at the sampling time, and performing state estimation on the power system according to the power data at the sampling time and the state estimation model to obtain a state estimation value of the power system at the target time.
In this embodiment, the sampling time may be a certain time, for example, the current time, or may be multiple times, for example, the current time, the hour before the current time, and the two hours before the current time, which is not limited herein. Optionally, the state estimation value includes a voltage amplitude estimation value and a voltage phase angle estimation value of each node.
In this embodiment, the power system state estimation method includes: acquiring power data of each node in a power system at a plurality of historical moments, and forming an initial data matrix by the acquired power data; performing dimensionality reduction processing on the initial data matrix according to a principal component analysis algorithm to obtain a projection matrix; establishing a least square depth support vector machine model, and optimizing the specified parameters of the least square depth support vector machine model according to an improved particle swarm algorithm; wherein, the weight coefficient of the updated formula in the improved particle swarm optimization is determined according to a nonlinear transformation formula with a control factor; training the optimized least square depth support vector machine model according to the projection matrix to obtain a state estimation model; and acquiring power data of each node of the power system at the sampling moment, and performing state estimation on the power system according to the power data and the state estimation model at the sampling moment to obtain a state estimation value of the power system at the target moment. The particle algorithm is improved by updating the weight coefficient of the formula according to the nonlinear transformation formula with the control factor, and then the improved particle swarm algorithm is adopted to optimize the parameters of the depth support vector machine, so that more accurate parameters can be provided, and the state estimation error of the power system is reduced.
In some embodiments, the specified parameters include a standard deviation and a penalty factor based on the embodiment described in fig. 2. The nonlinear transformation equation with control factors is as follows:
where ω is a weight coefficient, ωmaxIs the maximum weight coefficient, ωminIs the minimum weight coefficient, T is the iteration number, T is the maximum iteration number, and k is the control factor.
In the embodiment, the particle algorithm is improved according to the nonlinear transformation formula with the control factor by updating the weight coefficient of the formula, so that the optimization effect of the particle swarm optimization can be effectively improved. The standard deviation and the penalty coefficient of the depth support vector machine are optimized by adopting an improved particle swarm algorithm, so that more accurate standard deviation and penalty coefficient can be provided, and the state estimation error of the power system is reduced.
Optionally, optimizing the specified parameters of the least square depth support vector machine model according to an improved particle swarm optimization, includes:
initializing parameters and particle positions of the improved particle swarm algorithm;
acquiring a current particle position;
determining a current particle fitness value according to the current particle position and the fitness function;
updating the current particle position according to the particle fitness value and an updating formula;
if the updated particle position does not meet the preset precision requirement and the iteration times are less than the preset times, skipping to the step of obtaining the current particle position;
if the updated particle position meets the preset precision requirement or the iteration times are equal to the preset times, outputting the current particle position as a parameter optimization result;
the fitness function is as follows:
wherein MSE is fitness, m is the number of particles, xiIs the current position of the particle and is,
is the target particle position;
the update formula is as follows:
wherein v isi(t) is the velocity of the ith particle before the tth iteration, vi(t +1) is the velocity of the ith particle before the t +1 th iteration, n is the search space dimension, c1And c2Is a learning factor, r1And r2Is uniformly distributed in [0,1]]Random number in between, ai(t) is the position of the ith particle before the tth iteration, ai(t +1) is the position of the ith particle before the t +1 th iteration, pi(t) is the optimal position of the ith particle at the tth iteration, pg(t) is the optimal position in the whole particle swarm at the t-th iteration.
In this embodiment, the smaller the fitness value, the better the position of the particle. The particle position satisfying the preset precision requirement may be that a fitness value corresponding to the particle position is smaller than a certain threshold.
In some embodiments, on the basis of any of the above embodiments, the method further comprises:
preprocessing the initial data matrix to obtain a preprocessing matrix;
performing dimensionality reduction processing on the initial data matrix according to a principal component analysis algorithm to obtain a projection matrix, wherein the method comprises the following steps:
determining the dimensionality of principal component analysis according to a cross validation algorithm;
performing centralized processing on all elements of the preprocessing matrix;
calculating a covariance matrix of the preprocessed matrix after the centralization processing;
performing eigenvalue decomposition on the covariance matrix to obtain a plurality of eigenvalues and a plurality of eigenvectors; the eigenvalues and the eigenvectors are in one-to-one correspondence;
and constructing a projection matrix according to the plurality of eigenvalues, the plurality of eigenvectors and the dimension number.
In this embodiment, the initial data matrix is preprocessed and then subjected to dimensionality reduction, so that the dimensionality of the data can be reduced and the state estimation time can be effectively reduced while maintaining the characteristics of the measured data.
Optionally, constructing a projection matrix according to the plurality of groups of eigenvalues, eigenvectors and dimension numbers, including:
and sequencing the plurality of eigenvalues from large to small, and selecting eigenvectors corresponding to the eigenvalues with the appointed number in the front of the sequenced number sequence to form a projection matrix, wherein the appointed number is the dimension number of the principal component analysis.
Optionally, preprocessing the initial data matrix to obtain a preprocessing matrix, including:
carrying out bad data processing, filling processing and normalization processing on the initial data matrix to obtain a preprocessing matrix;
carrying out bad data processing on the initial data matrix, comprising the following steps:
deleting the active power and the reactive power of each node which does not meet the power balance equation in the initial data matrix;
and filling the initial data matrix, including:
aiming at each node with missing active power and/or reactive power, obtaining pseudo measurement data of the node according to a bus load prediction algorithm, and filling the missing active power and/or reactive power of the node in an initial data matrix;
and normalizing the initial data matrix, which comprises the following steps:
according to a normalization formula, performing normalization processing on the initial data matrix;
the normalized formula is:
where x' is the element of the pre-processing matrix, x is the element of the initial data matrix, xminIs the minimum value, x, in the initial data matrix elementsmaxIs the maximum value in the initial data matrix elements.
In this embodiment, the power balance equation is as follows:
wherein, PGiBeing active power of the generator, QGiIs the reactive power of the generator, PLDiActive power of the load, QLDiBeing reactive power of the load, PLFor active power lost from the line, QLIs reactive power.
In this embodiment, after normalization, the value range of the element x' in the obtained preprocessing matrix is [0,1 ].
In this embodiment, the accuracy of state estimation of the power system can be improved by performing bad data processing and padding processing on the initial data matrix. By the normalization processing, the amount of calculation of state estimation can be reduced, and the state estimation time can be reduced.
In some embodiments, on the basis of any of the above embodiments, training the optimized least squares depth support vector machine model according to the projection matrix includes:
selecting data from the projection matrix according to a preset time window and a preset step length;
and training the optimized least square depth support vector machine model according to the data selected from the projection matrix to obtain the trained parameters to be learned and the deviation.
The above-described power system state estimation method is described below with reference to an embodiment, but is not limited thereto. The specific steps of the implementation example are as follows:
the method comprises the steps of firstly, obtaining measured values of each node in the power system at a plurality of historical moments, wherein the measured values comprise active power, reactive power, voltage amplitude and voltage phase angle.
And step two, carrying out bad data processing, filling processing and normalization processing on the measurement value to obtain the preprocessed measurement value.
And step three, performing dimensionality reduction on the preprocessed measurement values according to a principal component analysis algorithm to obtain a projection matrix.
And step four, establishing a least square depth support vector machine model.
Fig. 3 is a schematic structural diagram of a least-squares depth support vector machine model according to an embodiment of the present invention. As shown in fig. 3, the hidden layer of the least squares depth support vector machine model may have multiple layers. The hidden layer of the optional depth support vector machine model has n layers in total, wherein n is more than or equal to 2 and less than or equal to 4. The number of hidden layers may be specifically selected from table one according to the calculation time and the calculation accuracy.
TABLE 1 comparison of prediction errors for different number of hidden layers of least squares depth support vector machine model
| Number of |
2 | 3 | 4 |
| Phase angle average estimation error | 0.000751 | 0.000562 | 0.000559 |
| Amplitude average estimation error | 0.000298 | 0.000235 | 0.000234 |
In the present embodiment, the state estimation time is reduced as much as possible when the state estimation accuracy is satisfied. Therefore, n is 3, and the number of the neurons in the three hidden layers is 50, 10 and 50 in sequence. The kernel function of the least square depth support vector machine model is a radial basis function, and the expression is as follows:
wherein, κ (h)(s)H) is a kernel function, h is a hidden feature sequence of model input data in each hidden layer, s is the number of neurons in the hidden layer, h(s)The standard deviation is sigma of the hidden feature sequence of each neuron in each hidden layer.
And fifthly, optimizing the standard deviation and the penalty coefficient of the least square depth support vector machine model according to the improved particle swarm optimization. The method comprises the following specific steps:
setting the dimension of a search population to be 2, the size a (T) of the population to be 20, the preset number of iterations T to be 200, and the maximum weight coefficient omegamax0.9, minimum weight coefficient ωmin0.4. Learning factor c1＝1.5，c21.7, random number r1And r2All are 0.5.
The particle population is initialized and each particle is given a random initial position and velocity.
And acquiring the current particle position, and determining the current particle fitness value according to the current particle position and the fitness function.
And updating the current particle position according to the particle fitness value and the updating formula.
If the updated particle position does not meet the preset precision requirement and the iteration times are less than the preset times, skipping to the step of obtaining the current particle position;
and if the updated particle position meets the preset precision requirement or the iteration times are equal to the preset times, outputting the current particle position as a parameter optimization result.
And step six, training the optimized least square depth support vector machine model according to the projection matrix to obtain a state estimation model. The method comprises the following specific steps:
and 2, training the optimized least square depth support vector machine model according to the data selected from the projection matrix to obtain the trained parameters to be learned and the deviation.
The resulting state estimation model expression is as follows:
wherein,
is the model output value, β(s) is the parameter to be learned, and c is the deviation.
Step 4, if the end time is reached, ending; and if the termination time is not reached, moving the time window according to a preset step length, and returning to the step 1, wherein the preset step length is 1.
And seventhly, acquiring power data of each node of the power system at the sampling moment, and carrying out state estimation on the power system according to the power data at the sampling moment and the state estimation model to obtain a state estimation value of the power system at the target moment.
FIG. 4 is a simulation of the optimization of the particle swarm optimization algorithm for the specified parameters of the least squares depth support vector machine model. As shown in fig. 4, in the present embodiment, simulation verification is performed in the IEEE-14 system in a process of optimizing the specified parameters of the least square depth support vector machine by using the improved particle swarm optimization, and the finally obtained simulation verification result is that the standard deviation σ is 15.7647 and the penalty coefficient g is 3.7827. In fig. 4, the horizontal axis represents the number of iterations, the vertical axis represents the Mean Square Error (MSE), and the two curves represent the optimum Mean Square Error and the Mean Square Error, respectively.
The method for estimating the state of the power system in this embodiment may be referred to as a principal Component Analysis-Least square-depth Support Vector Machine method (PCA-LS-DSVM).
FIG. 5 is a plot of the mean absolute error of voltage phase angle estimates using the PCA-LS-DSVM method, the WLS method, the LS-SVM method. FIG. 6 is a plot of mean absolute error versus voltage amplitude estimates using the PCA-LS-DSVM method, the WLS method, the LS-SVM method. As shown in fig. 5 and fig. 6, the PCA-LS-DSVM method, the weighted Least square method (WLS), and the Least square-Support Vector Machine method (LS-SVM) described in this embodiment are respectively subjected to simulation verification in the IEEE-14 system, so as to obtain a simulation verification result. In fig. 5, the horizontal axis represents the sampling time, and the vertical axis represents the average absolute error ξ of the voltage phase angle estimation valueθ. In fig. 6, the horizontal axis represents the sampling time, and the vertical axis represents the average absolute error ξ of the voltage amplitude estimation valuev. It can be found that the Mean Absolute Error (MAE) of the voltage phase angle estimation value and the voltage amplitude estimation value of the PCA-LS-DSVM method provided by the invention is smaller and is closer to the true value.
In order to further embody the effect of the PCA-LS-DSVM method proposed by the present invention, the simulation verification result is drawn as a table, which is specifically as follows:
TABLE 2 error comparison of three methods in IEEE-14 System
Table 2 shows a comparison of the performance of the three estimation methods in terms of both mean error and maximum error. The PCA-LS-DSVM method provided by the invention has the advantages that the overall estimation precision is greatly improved, the stability is good, and large errors do not occur at a certain time.
In the embodiment, the original data is identified and processed for data loss and abnormity, then the data is normalized and input to the principal component analysis for data dimension reduction, so that the dimension of the data is reduced under the condition of keeping the characteristics of the measured data, and the state estimation time can be effectively reduced. And then, the improved particle swarm optimization is adopted to optimize the parameters of the depth support vector machine, so that more accurate parameters are provided, and the accuracy of state estimation is effectively improved.
It should be understood that, the sequence numbers of the steps in the foregoing embodiments do not imply an execution sequence, and the execution sequence of each process should be determined by its function and inherent logic, and should not constitute any limitation to the implementation process of the embodiments of the present invention.
Fig. 7 is a schematic structural diagram of a power system state estimation device according to an embodiment of the present invention. As shown in fig. 7, the power system state estimation device 7 includes:
the obtaining module 710 is configured to obtain power data of each node in the power system at a plurality of historical times, and configure the obtained power data into an initial data matrix.
And the dimension reduction module 720 is configured to perform dimension reduction processing on the initial data matrix according to a principal component analysis algorithm to obtain a projection matrix.
The optimization module 730 is used for establishing a least square depth support vector machine model and optimizing the designated parameters of the least square depth support vector machine model according to the improved particle swarm algorithm; wherein, the weight coefficient of the updated formula in the improved particle swarm optimization is determined according to a nonlinear transformation formula with a control factor;
and the training module 740 is configured to train the optimized least square depth support vector machine model according to the projection matrix to obtain a state estimation model.
And the estimating module 750 is configured to acquire power data of each node of the power system at the sampling time, and perform state estimation on the power system according to the power data at the sampling time and the state estimation model to obtain a state estimation value of the power system at the target time.
Optionally, the specified parameters include standard deviation and penalty coefficient;
the nonlinear transformation equation with control factors is as follows:
where ω is a weight coefficient, ωmaxIs the maximum weight coefficient, ωminIs the minimum weight coefficient, T is the iteration number, T is the maximum iteration number, and k is the control factor.
Optionally, the optimizing module 730 is configured to:
initializing parameters and particle positions of the improved particle swarm algorithm;
acquiring a current particle position;
determining a current particle fitness value according to the current particle position and the fitness function;
updating the current particle position according to the particle fitness value and an updating formula;
if the updated particle position does not meet the preset precision requirement and the iteration times are less than the preset times, skipping to the step of obtaining the current particle position;
if the updated particle position meets the preset precision requirement or the iteration times are equal to the preset times, outputting the current particle position as a parameter optimization result;
the fitness function is as follows:
wherein MSE is fitness, m is the number of particles, xiIs the current position of the particle and is,
is the target particle position;
the update formula is as follows:
wherein v isi(t) is the velocity of the ith particle before the tth iteration, vi(t +1) is the velocity of the ith particle before the t +1 th iteration, n is the search space dimension, c1And c2Is a learning factor, r1And r2Is uniformly distributed in [0,1]]Random number in between, ai(t) is the position of the ith particle before the tth iteration, ai(t +1) is the position of the ith particle before the t +1 th iteration, pi(t) is the optimal position of the ith particle at the tth iteration, pg(t) is the optimal position in the whole particle swarm at the t-th iteration.
Optionally, the power system state estimation device 7 further includes: a pre-processing module 760;
the preprocessing module 760 is configured to preprocess the initial data matrix to obtain a preprocessing matrix.
A dimension reduction module 720 to:
determining the dimensionality of principal component analysis according to a cross validation algorithm;
performing centralized processing on all elements of the preprocessing matrix;
calculating a covariance matrix of the preprocessed matrix after the centralization processing;
performing eigenvalue decomposition on the covariance matrix to obtain a plurality of eigenvalues and a plurality of eigenvectors; the eigenvalues and the eigenvectors are in one-to-one correspondence;
and constructing a projection matrix according to the plurality of eigenvalues, the plurality of eigenvectors and the dimension number.
Optionally, the dimension reduction module 720 is configured to:
and sequencing the plurality of eigenvalues from large to small, and selecting eigenvectors corresponding to the eigenvalues with the appointed number in the front of the sequenced number sequence to form a projection matrix, wherein the appointed number is the dimension number of the principal component analysis.
Optionally, the preprocessing module 760 is configured to perform bad data processing, padding processing, and normalization processing on the initial data matrix to obtain a preprocessing matrix.
Optionally, the preprocessing module 760 is configured to delete active power and reactive power of each node that does not satisfy the power balance equation in the initial data matrix;
aiming at each node with missing active power and/or reactive power, obtaining pseudo measurement data of the node according to a bus load prediction algorithm, and filling the missing active power and/or reactive power of the node in an initial data matrix;
according to a normalization formula, performing normalization processing on the initial data matrix;
the normalized formula is:
where x' is the element of the pre-processing matrix, x is the element of the initial data matrix, xminIs the minimum value, x, in the initial data matrix elementsmaxIs the maximum value in the initial data matrix elements.
Optionally, the power data of each node at a plurality of historical time instants includes active power, reactive power, voltage amplitude and voltage phase angle.
Optionally, the state estimation value includes a voltage amplitude estimation value and a voltage phase angle estimation value of each node.
Optionally, the kernel function of the least squares depth support vector machine model is a radial basis kernel function.
Optionally, the training module 740 is configured to:
selecting data from the projection matrix according to a preset time window and a preset step length;
and training the optimized least square depth support vector machine model according to the data selected from the projection matrix to obtain the trained parameters to be learned and the deviation.
The power load prediction apparatus provided in this embodiment may be used to implement the above method embodiments, and the implementation principle and technical effect are similar, which are not described herein again
Fig. 8 is a schematic diagram of an electronic device provided by an embodiment of the invention. As shown in fig. 8, an embodiment of the present invention provides an electronic device 8, where the electronic device 8 of the embodiment includes: a processor 80, a memory 81, and a computer program 82 stored in the memory 81 and operable on the processor 80. The processor 80, when executing the computer program 82, implements the steps in the various power load prediction method embodiments described above, such as the steps 201 to 204 shown in fig. 2. Alternatively, the processor 80, when executing the computer program 82, implements the functions of the various modules/units in the various device embodiments described above, such as the functions of the modules 710-750 shown in fig. 7.
Illustratively, the computer program 82 may be divided into one or more modules/units, which are stored in the memory 81 and executed by the processor 80 to carry out the invention. One or more of the modules/units may be a series of computer program instruction segments capable of performing specific functions that describe the execution of the computer program 82 in the electronic device 8.
The electronic device 8 may be a desktop computer, a notebook, a palm computer, a cloud server, or other computing device. The terminal may include, but is not limited to, a processor 80, a memory 81. Those skilled in the art will appreciate that fig. 8 is merely an example of an electronic device 8 and does not constitute a limitation of the electronic device 8 and may include more or less components than those shown, or combine certain components, or different components, e.g., the terminal may also include input-output devices, network access devices, buses, etc.
The Processor 80 may be a Central Processing Unit (CPU), other general purpose Processor, a Digital Signal Processor (DSP), an Application Specific Integrated Circuit (ASIC), a Field Programmable Gate Array (FPGA) or other Programmable logic device, discrete Gate or transistor logic, discrete hardware components, etc. A general purpose processor may be a microprocessor or the processor may be any conventional processor or the like.
The storage 81 may be an internal storage unit of the electronic device 8, such as a hard disk or a memory of the electronic device 8. The memory 81 may also be an external storage device of the electronic device 8, such as a plug-in hard disk provided on the electronic device 8, a Smart Media Card (SMC), a Secure Digital (SD) Card, a Flash memory Card (Flash Card), and the like. Further, the memory 81 may also include both an internal storage unit of the electronic device 8 and an external storage device. The memory 81 is used to store computer programs and other programs and data required by the terminal. The memory 81 may also be used to temporarily store data that has been output or is to be output.
Embodiments of the present invention provide a computer-readable storage medium, which stores a computer program, and when the computer program is executed by a processor, the steps in the above power load prediction method embodiments are implemented.
The computer-readable storage medium stores a computer program 82, the computer program 82 includes program instructions, and when the program instructions are executed by the processor 80, all or part of the processes in the method according to the above embodiments may be implemented by the computer program 82 instructing related hardware, and the computer program 82 may be stored in a computer-readable storage medium, and when the computer program 82 is executed by the processor 80, the steps of the above embodiments of the method may be implemented. The computer program 82 comprises, among other things, computer program code, which may be in the form of source code, object code, an executable file or some intermediate form. The computer readable medium may include: any entity or device capable of carrying computer program code, recording medium, U.S. disk, removable hard disk, magnetic disk, optical disk, computer Memory, Read-Only Memory (ROM), Random Access Memory (RAM), electrical carrier wave signals, telecommunications signals, software distribution media, and the like. It should be noted that the computer readable medium may include any suitable increase or decrease as required by legislation and patent practice in the jurisdiction, for example, in some jurisdictions, computer readable media may not include electrical carrier signals and telecommunications signals in accordance with legislation and patent practice.
The computer readable storage medium may be an internal storage unit of the terminal of any of the foregoing embodiments, for example, a hard disk or a memory of the terminal. The computer readable storage medium may also be an external storage device of the terminal, such as a plug-in hard disk provided on the terminal, a Smart Media Card (SMC), a Secure Digital (SD) Card, a Flash memory Card (Flash Card), and the like. Further, the computer-readable storage medium may also include both an internal storage unit and an external storage device of the terminal. The computer-readable storage medium is used for storing a computer program and other programs and data required by the terminal. The computer-readable storage medium may also be used to temporarily store data that has been output or is to be output.
It should be understood that, the sequence numbers of the steps in the foregoing embodiments do not imply an execution sequence, and the execution sequence of each process should be determined by its function and inherent logic, and should not constitute any limitation to the implementation process of the embodiments of the present invention.
It will be apparent to those skilled in the art that, for convenience and brevity of description, only the above-mentioned division of the functional units and modules is illustrated, and in practical applications, the above-mentioned function distribution may be performed by different functional units and modules according to needs, that is, the internal structure of the apparatus is divided into different functional units or modules, so as to perform all or part of the functions described above. Each functional unit and module in the embodiments may be integrated in one processing unit, or each unit may exist alone physically, or two or more units are integrated in one unit, and the integrated unit may be implemented in a form of hardware, or in a form of software functional unit. In addition, specific names of the functional units and modules are only for convenience of distinguishing from each other, and are not used for limiting the protection scope of the present application. The specific working processes of the units and modules in the system may refer to the corresponding processes in the foregoing method embodiments, and are not described herein again.
In the above embodiments, the descriptions of the respective embodiments have respective emphasis, and reference may be made to the related descriptions of other embodiments for parts that are not described or illustrated in a certain embodiment.
Those of ordinary skill in the art will appreciate that the various illustrative elements and algorithm steps described in connection with the embodiments disclosed herein may be implemented as electronic hardware or combinations of computer software and electronic hardware. Whether such functionality is implemented as hardware or software depends upon the particular application and design constraints imposed on the implementation. Skilled artisans may implement the described functionality in varying ways for each particular application, but such implementation decisions should not be interpreted as causing a departure from the scope of the present invention.
In the embodiments provided in the present invention, it should be understood that the disclosed apparatus/terminal and method may be implemented in other ways. For example, the above-described apparatus/terminal embodiments are merely illustrative, and for example, a module or a unit may be divided into only one logical function, and may be implemented in other ways, for example, a plurality of units or components may be combined or integrated into another system, or some features may be omitted or not executed. In addition, the shown or discussed mutual coupling or direct coupling or communication connection may be an indirect coupling or communication connection through some interfaces, devices or units, and may be in an electrical, mechanical or other form.
Units described as separate parts may or may not be physically separate, and parts displayed as units may or may not be physical units, may be located in one place, or may be distributed on a plurality of network units. Some or all of the units can be selected according to actual needs to achieve the purpose of the solution of the embodiment.
In addition, functional units in the embodiments of the present invention may be integrated into one processing unit, or each unit may exist alone physically, or two or more units are integrated into one unit. The integrated unit can be realized in a form of hardware, and can also be realized in a form of a software functional unit.
The integrated modules/units, if implemented in the form of software functional units and sold or used as separate products, may be stored in a computer readable storage medium. Based on such understanding, all or part of the flow in the method according to the embodiments of the present invention may also be implemented by a computer program to instruct related hardware, where the computer program may be stored in a computer readable storage medium, and when the computer program is executed by a processor, the computer program may implement the steps of the embodiments of the method. Wherein the computer program comprises computer program code, which may be in the form of source code, object code, an executable file or some intermediate form, etc. The computer readable medium may include: any entity or device capable of carrying computer program code, recording medium, U.S. disk, removable hard disk, magnetic disk, optical disk, computer Memory, Read-Only Memory (ROM), Random Access Memory (RAM), electrical carrier wave signals, telecommunications signals, software distribution media, and the like. It should be noted that the computer readable medium may include any suitable increase or decrease as required by legislation and patent practice in the jurisdiction, for example, in some jurisdictions, computer readable media may not include electrical carrier signals and telecommunications signals in accordance with legislation and patent practice.
The above examples are only intended to illustrate the technical solution of the present invention, but not to limit it; although the present 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 solutions described in the foregoing embodiments may still be modified, or some technical features may be equivalently replaced; such modifications and substitutions do not substantially depart from the spirit and scope of the embodiments of the present invention, and are intended to be included within the scope of the present invention.
Claims (10)
1. A method of estimating a state of a power system, comprising: acquiring power data of each node in a power system at a plurality of historical moments, and forming an initial data matrix by the acquired power data;
performing dimensionality reduction processing on the initial data matrix according to a principal component analysis algorithm to obtain a projection matrix;
establishing a least square depth support vector machine model, and optimizing the specified parameters of the least square depth support vector machine model according to an improved particle swarm algorithm; wherein, the weight coefficient of the updated formula in the improved particle swarm optimization is determined according to a nonlinear transformation formula with a control factor; training the optimized least square depth support vector machine model according to the projection matrix to obtain a state estimation model;
and acquiring power data of each node of the power system at a sampling moment, and performing state estimation on the power system according to the power data at the sampling moment and the state estimation model to obtain a state estimation value of the power system at a target moment.
2. The power system state estimation method according to claim 1, wherein the specified parameters include a standard deviation and a penalty coefficient;
the nonlinear transformation formula with the control factor is as follows:
where ω is a weight coefficient, ωmaxIs the maximum weight coefficient, ωminIs the minimum weight coefficient, T is the iteration number, T is the maximum iteration number, and k is the control factor.
3. The power system state estimation method according to claim 2, wherein the optimizing specified parameters of the least squares depth support vector machine model according to the improved particle swarm optimization comprises:
initializing parameters and particle positions of the improved particle swarm algorithm;
acquiring a current particle position;
determining a current particle fitness value according to the current particle position and the fitness function;
updating the current particle position according to the particle fitness value and an updating formula;
if the updated particle position does not meet the preset precision requirement and the iteration times are less than the preset times, skipping to the step of obtaining the current particle position;
if the updated particle position meets the preset precision requirement or the iteration times are equal to the preset times, outputting the current particle position as a parameter optimization result;
the fitness function is as follows:
wherein MSE is fitness, m is the number of particles, xiIs the current position of the particle and is,
is the target particle position;
the update formula is as follows:
wherein v isi(t) is the velocity of the ith particle before the tth iteration, vi(t +1) is the velocity of the ith particle before the t +1 th iteration, n is the search space dimension, c1And c2Is a learning factor, r1And r2Is uniformly distributed in [0,1]]Random number in between, ai(t) is the position of the ith particle before the tth iteration, ai(t +1) is the position of the ith particle before the t +1 th iteration, pi(t) is the optimal position of the ith particle at the tth iteration, pg(t) is the optimal position in the whole particle swarm at the t-th iteration.
4. The power system state estimation method according to claim 1, characterized in that the method further comprises:
preprocessing the initial data matrix to obtain a preprocessing matrix;
performing dimensionality reduction processing on the initial data matrix according to a principal component analysis algorithm to obtain a projection matrix, wherein the processing method comprises the following steps:
determining the dimensionality of principal component analysis according to a cross validation algorithm;
performing centralization processing on all elements of the preprocessing matrix;
calculating a covariance matrix of the preprocessed matrix after the centralization processing;
performing eigenvalue decomposition on the covariance matrix to obtain a plurality of eigenvalues and a plurality of eigenvectors; the characteristic values and the characteristic vectors are in one-to-one correspondence;
and constructing a projection matrix according to the plurality of eigenvalues, the plurality of eigenvectors and the dimensionality.
5. The power system state estimation method according to claim 4, wherein the constructing a projection matrix from the plurality of sets of eigenvalues and the eigenvectors and the dimensionality comprises:
and sorting the plurality of eigenvalues from large to small, and selecting eigenvectors corresponding to the eigenvalues with the appointed number in the front of the sorted array to form a projection matrix, wherein the appointed number is the dimension number of the principal component analysis.
6. The method according to claim 4, wherein the preprocessing the initial data matrix to obtain a preprocessed matrix comprises:
carrying out bad data processing, filling processing and normalization processing on the initial data matrix to obtain the preprocessing matrix;
the bad data processing of the initial data matrix comprises:
deleting the active power and the reactive power of each node which does not meet the power balance equation in the initial data matrix;
the filling processing of the initial data matrix includes:
aiming at each node with missing active power and/or reactive power, obtaining pseudo measurement data of the node according to a bus load prediction algorithm, and filling the missing active power and/or reactive power of the node in the initial data matrix;
the normalizing the initial data matrix includes:
according to a normalization formula, performing normalization processing on the initial data matrix;
the normalization formula is:
wherein x' is an element of the pre-processing matrix, x is an element of the initial data matrix, xminIs the minimum value, x, in the initial data matrix elementsmaxIs the maximum value in the initial data matrix elements.
7. The power system state estimation method according to any one of claims 1 to 6,
the electric power data of each node at a plurality of historical moments comprise active power, reactive power, voltage amplitude and voltage phase angle;
the state estimation value comprises a voltage amplitude estimation value and a voltage phase angle estimation value of each node;
the kernel function of the least square depth support vector machine model is a radial basis kernel function;
the training of the optimized least square depth support vector machine model according to the projection matrix comprises the following steps:
selecting data from the projection matrix according to a preset time window and a preset step length;
and training the optimized least square depth support vector machine model according to the data selected from the projection matrix to obtain the trained parameters to be learned and the deviation.
8. An electric power system state estimation device characterized by comprising:
the acquisition module is used for acquiring power data of each node in the power system at a plurality of historical moments and forming an initial data matrix by the acquired power data;
the dimensionality reduction module is used for carrying out dimensionality reduction on the initial data matrix according to a principal component analysis algorithm to obtain a projection matrix;
the optimization module is used for establishing a least square depth support vector machine model and optimizing the designated parameters of the least square depth support vector machine model according to the improved particle swarm algorithm; wherein, the weight coefficient of the updated formula in the improved particle swarm optimization is determined according to a nonlinear transformation formula with a control factor;
the training module is used for training the optimized least square depth support vector machine model according to the projection matrix to obtain a state estimation model;
and the estimation module is used for acquiring the power data of each node of the power system at the sampling moment, and performing state estimation on the power system according to the power data at the sampling moment and the state estimation model to obtain a state estimation value of the power system at the target moment.
9. An electronic device comprising a memory, a processor and a computer program stored in the memory and executable on the processor, characterized in that the processor implements the steps of the power system state estimation method according to any of the above claims 1 to 7 when executing the computer program.
10. A computer-readable storage medium, in which a computer program is stored which, when being executed by a processor, carries out the steps of the power system state estimation method according to any one of claims 1 to 7 above.
Priority Applications (1)
| Application Number | Priority Date | Filing Date | Title |
|---|---|---|---|
| CN202110633909.0A CN113553755B (en) | 2021-06-07 | 2021-06-07 | Power system state estimation method, device and equipment |
Applications Claiming Priority (1)
| Application Number | Priority Date | Filing Date | Title |
|---|---|---|---|
| CN202110633909.0A CN113553755B (en) | 2021-06-07 | 2021-06-07 | Power system state estimation method, device and equipment |
Publications (2)
| Publication Number | Publication Date |
|---|---|
| CN113553755A true CN113553755A (en) | 2021-10-26 |
| CN113553755B CN113553755B (en) | 2022-12-13 |
Family
ID=78102027
Family Applications (1)
| Application Number | Title | Priority Date | Filing Date |
|---|---|---|---|
| CN202110633909.0A Active CN113553755B (en) | 2021-06-07 | 2021-06-07 | Power system state estimation method, device and equipment |
Country Status (1)
| Country | Link |
|---|---|
| CN (1) | CN113553755B (en) |
Cited By (5)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN114238271A (en) * | 2021-12-14 | 2022-03-25 | 广东电网有限责任公司广州供电局 | State data cleaning method and device for substation equipment and computer equipment |
| CN116207864A (en) * | 2023-04-28 | 2023-06-02 | 佰聆数据股份有限公司 | Method and system for controlling power equipment in low-voltage area based on Internet of things |
| CN116307284A (en) * | 2023-05-19 | 2023-06-23 | 工业富联(佛山)创新中心有限公司 | Energy consumption prediction method, electronic device and storage medium |
| CN116760195A (en) * | 2023-08-18 | 2023-09-15 | 国网浙江省电力有限公司宁波供电公司 | Method, system, equipment and storage medium for monitoring all-element resources of power system |
| EP4254705A1 (en) * | 2022-03-30 | 2023-10-04 | Fundación Tecnalia Research & Innovation | Computer-implemented method or assessment of a power distribution grid |
Citations (4)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN106952183A (en) * | 2017-04-24 | 2017-07-14 | 武汉大学 | A kind of short-term load forecasting method based on particle group optimizing least square method supporting vector machine |
| CN109256773A (en) * | 2018-10-19 | 2019-01-22 | 东北大学 | Power system state estimation method of the noise reduction from coding and depth support vector machines |
| CN109740859A (en) * | 2018-12-11 | 2019-05-10 | 国网山东省电力公司淄博供电公司 | Transformer condition evaluation and system based on Principal Component Analysis and support vector machines |
| CN111563348A (en) * | 2020-04-10 | 2020-08-21 | 西安工程大学 | Transformer fault diagnosis method based on deep support vector machine |
-
2021
- 2021-06-07 CN CN202110633909.0A patent/CN113553755B/en active Active
Patent Citations (4)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN106952183A (en) * | 2017-04-24 | 2017-07-14 | 武汉大学 | A kind of short-term load forecasting method based on particle group optimizing least square method supporting vector machine |
| CN109256773A (en) * | 2018-10-19 | 2019-01-22 | 东北大学 | Power system state estimation method of the noise reduction from coding and depth support vector machines |
| CN109740859A (en) * | 2018-12-11 | 2019-05-10 | 国网山东省电力公司淄博供电公司 | Transformer condition evaluation and system based on Principal Component Analysis and support vector machines |
| CN111563348A (en) * | 2020-04-10 | 2020-08-21 | 西安工程大学 | Transformer fault diagnosis method based on deep support vector machine |
Non-Patent Citations (4)
| Title |
|---|
| 姜妍等: ""基于最小二乘支持向量机的短期负荷预测"", 《黑龙江电力》 * |
| 张瑞: ""基于深度支持向量机的旋转机械故障诊断方法研究"", 《CNKI硕士电子期刊》 * |
| 王秀云等: ""改进粒子群算法在无功优化中的应用"", 《电测与仪表》 * |
| 贾嵘等: ""基于主成分分析和最小二乘支持向量机的电力系统状态估计"", 《电网技术》 * |
Cited By (7)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN114238271A (en) * | 2021-12-14 | 2022-03-25 | 广东电网有限责任公司广州供电局 | State data cleaning method and device for substation equipment and computer equipment |
| EP4254705A1 (en) * | 2022-03-30 | 2023-10-04 | Fundación Tecnalia Research & Innovation | Computer-implemented method or assessment of a power distribution grid |
| CN116207864A (en) * | 2023-04-28 | 2023-06-02 | 佰聆数据股份有限公司 | Method and system for controlling power equipment in low-voltage area based on Internet of things |
| CN116307284A (en) * | 2023-05-19 | 2023-06-23 | 工业富联(佛山)创新中心有限公司 | Energy consumption prediction method, electronic device and storage medium |
| CN116307284B (en) * | 2023-05-19 | 2023-08-08 | 工业富联(佛山)创新中心有限公司 | Energy consumption prediction method, electronic device and storage medium |
| CN116760195A (en) * | 2023-08-18 | 2023-09-15 | 国网浙江省电力有限公司宁波供电公司 | Method, system, equipment and storage medium for monitoring all-element resources of power system |
| CN116760195B (en) * | 2023-08-18 | 2024-01-02 | 国网浙江省电力有限公司宁波供电公司 | Method, system, equipment and storage medium for monitoring all-element resources of power system |
Also Published As
| Publication number | Publication date |
|---|---|
| CN113553755B (en) | 2022-12-13 |
Similar Documents
| Publication | Publication Date | Title |
|---|---|---|
| CN113553755B (en) | Power system state estimation method, device and equipment | |
| CN106600059B (en) | Intelligent power grid short-term load prediction method based on improved RBF neural network | |
| CN109117951B (en) | BP neural network-based probability load flow online calculation method | |
| CN111967679B (en) | Ionosphere total electron content forecasting method based on TCN model | |
| CN111860982A (en) | Wind power plant short-term wind power prediction method based on VMD-FCM-GRU | |
| CN111027732B (en) | Method and system for generating multi-wind power plant output scene | |
| CN111079351B (en) | Power distribution network probability power flow acquisition method and device considering wind power uncertainty | |
| CN113836823A (en) | Load combination prediction method based on load decomposition and optimized bidirectional long-short term memory network | |
| CN112884236B (en) | Short-term load prediction method and system based on VDM decomposition and LSTM improvement | |
| CN107832789B (en) | Feature weighting K nearest neighbor fault diagnosis method based on average influence value data transformation | |
| CN111310722A (en) | Power equipment image fault identification method based on improved neural network | |
| CN113887801A (en) | Building cold load prediction method, system, equipment and readable storage medium | |
| CN112834927A (en) | Lithium battery residual life prediction method, system, device and medium | |
| CN114490065A (en) | Load prediction method, device and equipment | |
| CN111506868B (en) | Ultra-short-term wind speed prediction method based on HHT weight optimization | |
| CN112560966A (en) | Polarimetric SAR image classification method, medium and equipment based on scattergram convolution network | |
| CN110738363B (en) | Photovoltaic power generation power prediction method | |
| CN114781692A (en) | Short-term power load prediction method and device and electronic equipment | |
| CN116707331A (en) | Inverter output voltage high-precision adjusting method and system based on model prediction | |
| CN114597970A (en) | Active power distribution network partitioning method based on graph convolution network | |
| CN116706907B (en) | Photovoltaic power generation prediction method based on fuzzy reasoning and related equipment | |
| CN112232565A (en) | Two-stage time sequence prediction method, prediction system, terminal and medium | |
| CN115545164A (en) | Photovoltaic power generation power prediction method, system, equipment and medium | |
| CN116224070A (en) | OCV (open circuit voltage) -SOC (system on a chip) model-based full-temperature lithium ion battery OCV (open circuit voltage) evaluation method and system | |
| CN110829434B (en) | Method for improving expansibility of deep neural network tidal current model |
Legal Events
| Date | Code | Title | Description |
|---|---|---|---|
| PB01 | Publication | ||
| PB01 | Publication | ||
| SE01 | Entry into force of request for substantive examination | ||
| SE01 | Entry into force of request for substantive examination | ||
| GR01 | Patent grant | ||
| GR01 | Patent grant |