CN117349998A - Frequency prediction method, system and medium based on wind-storage combined system disturbance - Google Patents
Frequency prediction method, system and medium based on wind-storage combined system disturbance Download PDFInfo
- Publication number
- CN117349998A CN117349998A CN202311615224.9A CN202311615224A CN117349998A CN 117349998 A CN117349998 A CN 117349998A CN 202311615224 A CN202311615224 A CN 202311615224A CN 117349998 A CN117349998 A CN 117349998A
- Authority
- CN
- China
- Prior art keywords
- frequency
- wind
- disturbance
- power
- layer
- 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
- 238000003860 storage Methods 0.000 title claims abstract description 120
- 238000000034 method Methods 0.000 title claims abstract description 71
- 230000004044 response Effects 0.000 claims abstract description 51
- 230000001537 neural effect Effects 0.000 claims abstract description 31
- 230000003044 adaptive effect Effects 0.000 claims abstract description 20
- 238000004146 energy storage Methods 0.000 claims description 38
- 230000006870 function Effects 0.000 claims description 28
- 238000010606 normalization Methods 0.000 claims description 24
- 230000008569 process Effects 0.000 claims description 24
- 238000013528 artificial neural network Methods 0.000 claims description 18
- 238000004590 computer program Methods 0.000 claims description 14
- 238000012546 transfer Methods 0.000 claims description 13
- 239000011159 matrix material Substances 0.000 claims description 5
- 230000004913 activation Effects 0.000 claims description 4
- 238000010586 diagram Methods 0.000 description 13
- 230000009466 transformation Effects 0.000 description 5
- 230000008859 change Effects 0.000 description 4
- 238000012545 processing Methods 0.000 description 4
- 230000005611 electricity Effects 0.000 description 3
- 230000004927 fusion Effects 0.000 description 3
- 238000012549 training Methods 0.000 description 3
- 230000005540 biological transmission Effects 0.000 description 2
- 238000004422 calculation algorithm Methods 0.000 description 2
- 238000011217 control strategy Methods 0.000 description 2
- 238000013135 deep learning Methods 0.000 description 2
- 230000000694 effects Effects 0.000 description 2
- 238000005516 engineering process Methods 0.000 description 2
- 238000012986 modification Methods 0.000 description 2
- 230000004048 modification Effects 0.000 description 2
- 238000003062 neural network model Methods 0.000 description 2
- 230000003287 optical effect Effects 0.000 description 2
- 238000004088 simulation Methods 0.000 description 2
- 238000011276 addition treatment Methods 0.000 description 1
- 238000004458 analytical method Methods 0.000 description 1
- 230000008901 benefit Effects 0.000 description 1
- 238000013016 damping Methods 0.000 description 1
- 238000007418 data mining Methods 0.000 description 1
- 230000007547 defect Effects 0.000 description 1
- 238000009826 distribution Methods 0.000 description 1
- 230000006872 improvement Effects 0.000 description 1
- 230000010354 integration Effects 0.000 description 1
- 238000010801 machine learning Methods 0.000 description 1
- 238000004519 manufacturing process Methods 0.000 description 1
- 238000013507 mapping Methods 0.000 description 1
- 230000035699 permeability Effects 0.000 description 1
- 238000007637 random forest analysis Methods 0.000 description 1
- 238000011160 research Methods 0.000 description 1
- 230000003068 static effect Effects 0.000 description 1
- 238000006467 substitution reaction Methods 0.000 description 1
- 238000012706 support-vector machine Methods 0.000 description 1
- 238000012360 testing method Methods 0.000 description 1
- 230000001052 transient effect Effects 0.000 description 1
- 238000011282 treatment Methods 0.000 description 1
Classifications
-
- G—PHYSICS
- G06—COMPUTING; CALCULATING OR COUNTING
- G06F—ELECTRIC DIGITAL DATA PROCESSING
- G06F30/00—Computer-aided design [CAD]
- G06F30/10—Geometric CAD
- G06F30/18—Network design, e.g. design based on topological or interconnect aspects of utility systems, piping, heating ventilation air conditioning [HVAC] or cabling
-
- 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
- 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
- G06N3/044—Recurrent networks, e.g. Hopfield networks
- G06N3/0442—Recurrent networks, e.g. Hopfield networks characterised by memory or gating, e.g. long short-term memory [LSTM] or gated recurrent units [GRU]
-
- G—PHYSICS
- G06—COMPUTING; CALCULATING OR COUNTING
- G06N—COMPUTING ARRANGEMENTS BASED ON SPECIFIC COMPUTATIONAL MODELS
- G06N5/00—Computing arrangements using knowledge-based models
- G06N5/04—Inference or reasoning models
- G06N5/048—Fuzzy inferencing
-
- G—PHYSICS
- G06—COMPUTING; CALCULATING OR COUNTING
- G06F—ELECTRIC DIGITAL DATA PROCESSING
- G06F2113/00—Details relating to the application field
- G06F2113/06—Wind turbines or wind farms
-
- G—PHYSICS
- G06—COMPUTING; CALCULATING OR COUNTING
- G06F—ELECTRIC DIGITAL DATA PROCESSING
- G06F2119/00—Details relating to the type or aim of the analysis or the optimisation
- G06F2119/06—Power analysis or power optimisation
Landscapes
- Engineering & Computer Science (AREA)
- Physics & Mathematics (AREA)
- Theoretical Computer Science (AREA)
- Evolutionary Computation (AREA)
- General Physics & Mathematics (AREA)
- Software Systems (AREA)
- General Engineering & Computer Science (AREA)
- Artificial Intelligence (AREA)
- Geometry (AREA)
- Data Mining & Analysis (AREA)
- Computer Hardware Design (AREA)
- Computational Linguistics (AREA)
- Computing Systems (AREA)
- Mathematical Physics (AREA)
- Mathematical Optimization (AREA)
- Pure & Applied Mathematics (AREA)
- Computer Vision & Pattern Recognition (AREA)
- Health & Medical Sciences (AREA)
- Life Sciences & Earth Sciences (AREA)
- Biomedical Technology (AREA)
- Biophysics (AREA)
- Medical Informatics (AREA)
- Mathematical Analysis (AREA)
- General Health & Medical Sciences (AREA)
- Molecular Biology (AREA)
- Computational Mathematics (AREA)
- Computer Networks & Wireless Communication (AREA)
- Automation & Control Theory (AREA)
- Fuzzy Systems (AREA)
- Control Of Eletrric Generators (AREA)
Abstract
The embodiment of the invention provides a frequency prediction method, a system and a medium based on a wind power and storage combined system after disturbance, and belongs to the field of wind power combination. The method comprises the following steps: obtaining disturbance power of a disturbance instant wind power storage combined power system, inputting the disturbance power into a frequency response model of the wind power storage combined power system, and outputting a first dynamic frequency predicted value; acquiring node state information of the wind storage combined system before and after disturbance, inputting a dynamic frequency prediction model of the wind storage combined system after disturbance, and outputting a second dynamic frequency prediction value; and inputting the first dynamic frequency predicted value and the second dynamic frequency predicted value into the self-adaptive neural fuzzy inference system to obtain the frequency after the disturbance of the wind-storage combined system. The adaptive neural fuzzy inference system is used for fusing the first dynamic frequency predicted value and the second dynamic frequency predicted value, so that the current situation that the calculation amount in the existing physical model driving is large, the solving precision is low after simplification is improved, the physical relation in the wind storage combined system is avoided being ignored in the data driving, and the influence of the number and the quality of samples on the predicting precision is avoided.
Description
Technical Field
The invention relates to the technical field of wind power integration, in particular to a frequency prediction method, a system and a medium based on disturbance of a wind power storage integrated system.
Background
Along with the continuous increase of the wind power proportion in the power system, the frequency support resources are continuously reduced, the safe operation of the power system is threatened, and huge obstruction is caused to the frequency adjustment of the power system, so that various frequency modulation strategies of the fan are researched, an energy storage system is added, the frequency modulation service is assisted, and the frequency modulation pressure can be effectively relieved to a certain extent.
However, due to uncertainty and randomness of fans and fluctuation of loads, the stability of a modern power system is still a problem, after high-power disturbance, the frequency of the wind-storage combined system usually goes through a dynamic process and then reaches a steady state again, and the frequency fluctuation condition in the process has a great influence on the stability of the system. Therefore, predicting the dynamic frequency characteristic value of the wind-storage combined system after disturbance becomes important, and the rapid and accurate prediction can provide reference for formulating a frequency emergency control strategy, so that the stability of the system is greatly improved.
The existing research method for dynamic frequency prediction after power system disturbance can be divided into model driving and data driving, wherein the model driving comprises a time domain simulation method for describing complex control characteristics and load characteristics of various units and an equivalent model method for solving a frequency response curve after system disturbance, the time domain simulation method is applied to an air-storage combined power system, each part needs to be modeled in detail, after repeated iteration, the time is too long, the equivalent model method is applied to the air-storage combined power system to excessively simplify parameters and error conditions, and the accuracy is low. The data driving comprises a support vector machine, a random forest, an artificial neural network and other shallow machine learning algorithms, a long-short-time memory neural network, a convolution neural network, a deep learning network of a deep confidence network and other deep learning networks, wherein the operation characteristic value of the electric power system is taken as input, the frequency characteristic index is taken as output, and the data samples before and after the history disturbance are utilized for learning and training. However, these data-driven algorithms only use the correlation between the input and output of the historical data mining, completely neglect the physical relationship of the system, impair the reliability of the result, and have obvious effects on the result due to the number and quality of samples, and the prediction accuracy may be affected due to the insufficient number of samples or unbalanced samples, which still has a great disadvantage.
Disclosure of Invention
The embodiment of the invention aims to provide a frequency prediction method, a system and a medium based on wind-storage combined system disturbance, which are used for completely or at least partially solving the technical problems in the prior art.
In order to achieve the above objective, an embodiment of the present invention provides a method for predicting a frequency after disturbance based on a wind-storage combined system, including:
obtaining disturbance power of a power system power disturbance instant wind-storage combined power system, inputting the disturbance power into a pre-constructed wind-storage combined system frequency response model, and outputting a disturbed first dynamic frequency predicted value;
acquiring node state information of the wind power storage combined power system at the moment before and after power disturbance of the power system, inputting the node state information into a pre-constructed dynamic frequency prediction model of the wind power storage combined system after disturbance, and outputting a disturbed second dynamic frequency prediction value;
and inputting the first dynamic frequency predicted value and the second dynamic frequency predicted value into a self-adaptive neural fuzzy inference system to obtain the frequency after the wind-storage combined system is disturbed.
Optionally, the node state information of the wind-storage combined power system at the moment before and after disturbance includes: at least one of electromagnetic power, mechanical power, voltage of each node, phase angle, active power of each load, standby energy of each energy storage device, voltage of each node after disturbance, phase angle, electromagnetic power of the generator, mechanical power, charge and discharge power of the energy storage device, unbalanced power of each generator, standby capacity of each generator and energy storage device, and active power of each load.
Optionally, the pre-constructed frequency response model of the wind-storage combined system is as follows:
wherein G is W (s) represents a fan system frequency model transfer function,(s) represents the energy storage system frequency model transfer function.
Optionally, the pre-built post-disturbance wind-storage combined system dynamic frequency prediction model is built based on a long-short-term memory neural network, and the long-short-term memory neural network comprises a forgetting gate, an input gate and an output gate:
in the method, in the process of the invention,o t indicating the output gate, W o 、b o Respectively represento t And the weight matrix and bias of sigma is a sigmod activation function,x t 、h t-1 respectively representing the node state information input by the forgetting gate at the current moment and the hidden layer state of the last moment stored by the memory cell.
Optionally, the adaptive neural fuzzy inference system comprises a fuzzification layer, a fuzzy rule layer, a normalization layer, an input connection layer and an output layer.
Optionally, the inputting the first dynamic frequency prediction value and the second dynamic frequency prediction value into an adaptive neural fuzzy inference system to obtain the frequency after the disturbance of the wind-storage combined system includes:
and sequentially inputting the first dynamic frequency predicted value and the second dynamic frequency predicted value into a fuzzification layer, a fuzzy rule layer, a normalization layer, an input connection layer and an output layer of the self-adaptive neural fuzzy inference system to obtain the frequency after the wind power storage combined system is disturbed.
Optionally, inputting the first dynamic frequency predicted value and the second dynamic frequency predicted value into a fuzzification layer, a fuzzy rule layer, a normalization layer, an input connection layer and an output layer of the adaptive neural fuzzy inference system in sequence to obtain the frequency after disturbance of the wind-storage combined system, including:
the blurring layer is adopted to carry out blurring operation on the first dynamic frequency predicted value and the second dynamic frequency predicted value, and a first characteristic value and a second characteristic value of the first dynamic frequency predicted value and the second dynamic frequency predicted value which are subjected to blurring are respectively output;
inputting the first characteristic value and the second characteristic value into the fuzzy rule layer for combination, and outputting a plurality of fuzzy rule intensities after the first characteristic value and the second characteristic value are combined;
inputting the plurality of fuzzy rule intensities combined by the first characteristic value and the second characteristic value to a normalization layer, and outputting the plurality of normalized fuzzy rule intensities;
inputting the normalized multiple fuzzy rule intensities, the first dynamic frequency predicted value and the second dynamic frequency predicted value to the input connection layer, and outputting the proportion of each fuzzy rule intensity in the frequency after the disturbance of the wind-storage combined system;
and inputting an output result of the input connection layer to an output layer to obtain the frequency of the wind-storage combined system after disturbance.
On the other hand, the invention also provides a frequency prediction system based on the wind-storage combined system after disturbance, which comprises the following steps:
the first output unit is used for acquiring disturbance power of the disturbance moment wind-storage combined power system, inputting the disturbance power into a pre-constructed wind-storage combined system frequency response model and outputting a disturbed first dynamic frequency predicted value;
the second output unit is used for acquiring node state information of the wind-storage combined power system at the moment before and after disturbance, inputting the node state information into a pre-constructed dynamic frequency prediction model of the wind-storage combined system after disturbance, and outputting a disturbed second dynamic frequency prediction value;
the obtaining unit is used for inputting the first dynamic frequency predicted value and the second dynamic frequency predicted value into the adaptive neural fuzzy inference system to obtain the frequency after the wind-storage combined system is disturbed.
Optionally, the adaptive neural fuzzy inference system comprises a fuzzification layer, a fuzzy rule layer, a normalization layer, an input connection layer and an output layer.
Optionally, the obtaining unit is configured to:
and sequentially inputting the first dynamic frequency predicted value and the second dynamic frequency predicted value into a fuzzification layer, a fuzzy rule layer, a normalization layer, an input connection layer and an output layer of the self-adaptive neural fuzzy inference system to obtain the frequency after the wind power storage combined system is disturbed.
Optionally, the obtaining unit is configured to:
the blurring layer is adopted to carry out blurring operation on the first dynamic frequency predicted value and the second dynamic frequency predicted value, and a first characteristic value and a second characteristic value of the first dynamic frequency predicted value and the second dynamic frequency predicted value which are subjected to blurring are respectively output;
inputting the first characteristic value and the second characteristic value into the fuzzy rule layer for combination, and outputting a plurality of fuzzy rule intensities after the first characteristic value and the second characteristic value are combined;
inputting the plurality of fuzzy rule intensities combined by the first characteristic value and the second characteristic value to a normalization layer, and outputting the plurality of normalized fuzzy rule intensities;
inputting the normalized multiple fuzzy rule intensities, the first dynamic frequency predicted value and the second dynamic frequency predicted value to the input connection layer, and outputting the proportion of each fuzzy rule intensity in the frequency after the disturbance of the wind-storage combined system;
and inputting an output result of the input connection layer to an output layer to obtain the frequency of the wind-storage combined system after disturbance.
In another aspect, the present invention further provides an electronic device, including a memory, a processor, and a computer program stored in the memory and capable of running on the processor, where the processor implements the steps of the frequency prediction method described above when executing the program.
In another aspect, the present invention also provides a non-transitory computer readable storage medium having stored thereon a computer program which, when executed by a processor, implements the steps of the frequency prediction method described above.
According to the technical scheme, the predicted value obtained based on the frequency response model of the wind storage combined system and the predicted value obtained based on the frequency dynamic predicted model of the wind storage combined system after disturbance are fused together, so that the current situation that solving parameters are complex, the operation amount is large, the solving precision is low after simplification in the existing physical model driving is improved, the physical relation in the wind storage combined system is completely ignored in the data driving, and the influence of the number and quality of samples on the predicting precision is avoided.
Additional features and advantages of embodiments of the invention will be set forth in the detailed description which follows.
Drawings
The accompanying drawings are included to provide a further understanding of embodiments of the invention and are incorporated in and constitute a part of this specification, illustrate embodiments of the invention and together with the description serve to explain, without limitation, the embodiments of the invention. In the drawings:
FIG. 1 is a flowchart of an implementation of a method for predicting a frequency after disturbance based on a wind-storage combined system according to an embodiment of the present invention;
FIG. 2 is a schematic diagram of a conventional average system frequency response model provided by an embodiment of the present invention;
FIG. 3 is a schematic diagram of a frequency response model of a wind-powered electricity generation combined system according to an embodiment of the present invention;
FIG. 4 is a graph showing the frequency response of the wind-powered electricity generation combined system active frequency adjustment process divided into three phases according to the embodiment of the present invention;
FIG. 5 is an internal structure diagram of a forgetting gate, an input gate and an output gate in long-short-term memory neural network drive prediction provided by an embodiment of the present invention;
FIG. 6 is a schematic diagram of an adaptive neuro-fuzzy inference system according to an embodiment of the present invention;
FIG. 7 is a flow chart of dynamic frequency prediction after disturbance of a wind-storage combined system based on physical-information fusion, which is provided by the embodiment of the invention;
fig. 8 is a schematic structural diagram of a frequency prediction system based on disturbance of a wind-storage combined system according to an embodiment of the present invention.
Detailed Description
The following describes the detailed implementation of the embodiments of the present invention with reference to the drawings. It should be understood that the detailed description and specific examples, while indicating and illustrating the invention, are not intended to limit the invention.
Referring to fig. 1, a flowchart of an implementation of a method for predicting a frequency after disturbance based on a wind-storage combined system according to an embodiment of the present invention is shown, including the following implementation steps:
step 100: and obtaining disturbance power of the power disturbance instant wind power storage combined system of the electric power system, inputting the disturbance power into a pre-constructed wind power storage combined system frequency response model, and outputting a disturbed first dynamic frequency predicted value.
In some embodiments, the pre-built wind-storage-combined-system frequency response model is:
wherein G is W (s) represents a fan system frequency model transfer function,(s) represents the energy storage system frequency model transfer function.
In some embodiments, prior to performing step 100, adding wind power storage system frequency modulation control to a conventional average system frequency response model, and establishing a physical connection between power disturbance and frequency characteristic indexes of the power system, so as to obtain a frequency response model of the wind power storage combined power system, wherein prime movers in the conventional average system frequency response model (see fig. 2) are thermal power and hydroelectric generating sets, and the prime movers in the conventional average system frequency response model are all power generator power changes (% output by 1-N prime mover-speed regulator models) under disturbance power of the power systemP G ) Load power variation deltaP L ) For input, respond to frequency fluctuation condition) Outputting the disturbed dynamic frequency deviation (delta)f) In FIG. 2HIs the time constant of inertia, which is the time constant of inertia,Dis the damping coefficient. However, with the continuous increase of the permeability of wind power, some fan frequency modulation strategies of the system are researched, and in order to make the frequency modulation effect more obvious and effective, an energy storage device is often added into the power system to perform inertia control and primary frequency modulation controlTherefore, the fan and the energy storage device (wind storage system model) are integrated on the original frequency response model, and the wind storage combined system frequency response model (see fig. 3) related to the wind power plant and the energy storage device is formed.
In some embodiments, referring to FIG. 3, a fan control system may adjust fan speed, adjust fan blade angle, and thereby increase control over rotor inertia and pitch angle. Therefore, the fan system mainly comprises two frequency modulation means of rotor inertia and variable pitch control, the rotor inertia control technical characteristics are suitable for simulating the inertia response of a traditional generator, and the transfer function of a frequency model is as follows:
in the method, in the process of the invention,k df is the inertial response coefficient;T ω is the rotor inertia response time constant; deltaP ω Power supplied for the inertial response of the rotor; deltafRepresenting the frequency variation; s denotes a transform parameter in the laplace transform.
The wind turbine generator system variable pitch control technical characteristics are suitable for simulating primary frequency modulation of a traditional generator, and the transfer function of a frequency model is as follows:
in the method, in the process of the invention,k pf is a primary frequency modulation coefficient;T β is a pitch response time constant; deltaP β Providing power for pitch control; deltafRepresenting the frequency variation; s denotes a transform parameter in the laplace transform.
The inertia control and the variable pitch control of the doubly-fed wind turbine generator set are combined, so that the wind farm has inertia response and primary frequency modulation capacity similar to those of a traditional generator set, and the transfer function of a frequency model is as follows:
in the method, in the process of the invention,k df as a coefficient of the inertial response,T β in order to change the pitch response time constant,k pf for the primary frequency modulation factor,T ω for the rotor inertia response time constant, S represents a transformation parameter in the laplace transformation.
The battery energy storage processes the condition of frequency fluctuation by adopting virtual inertial response and virtual sagging control, and combines the analysis of an energy storage frequency modulation control strategy, and the transfer function of the energy storage system frequency model is as follows:
in the method, in the process of the invention,T E for the response time constant of the energy storage device, the inertial response coefficient of the energy storage systemk df And primary frequency modulation coefficientk pf Keeping consistent with corresponding parameters of frequency modulation of doubly-fed wind generator, deltaP E Representing the power supplied by the energy storage device, S representing the transformation parameters in the laplace transformation.
The energy storage device assists the wind turbine generator to participate in frequency adjustment, and by virtue of the technical characteristics of quick response and stable operation of the energy storage device, the defect of self frequency modulation power of a wind power plant is overcome, so that the wind storage combined system has inertial response and primary frequency modulation capacity similar to those of a traditional generator, the frequency modulation requirement of a power system on the wind power system is met, and the frequency model transfer function of the energy storage system is as follows:
in the method, in the process of the invention,representing the power, delta, provided by the energy storage equivalent in the wind-storage combined systemfRepresents the frequency variation, S represents the transformation parameters in the laplace transform,k df as a coefficient of the inertial response,T β in order to change the pitch response time constant,k pf for the primary frequency modulation factor,T ω for the rotor inertia response time constant,T E indicating the energy storage device response time constant.
Thus, the average system frequency response model of the improved wind-storage combination system is:
wherein G is W (s) represents a fan system frequency model transfer function,(s) represents the energy storage system frequency model transfer function.
Step 101: and acquiring node state information of the wind power storage combined system at the moment before and after power disturbance of the power system, inputting the node state information into a pre-constructed dynamic frequency prediction model of the wind power storage combined system after disturbance, and outputting a disturbed second dynamic frequency prediction value.
In some embodiments, the node state information of the wind power storage system immediately before and after the disturbance includes: at least one of electromagnetic power, mechanical power, voltage of each node, phase angle, active power of each load, standby energy of each energy storage device, voltage of each node after disturbance, phase angle, electromagnetic power of the generator, mechanical power, charge and discharge power of the energy storage device, unbalanced power of each generator, standby capacity of each generator and energy storage device, and active power of each load.
In some embodiments, the pre-built post-disturbance wind-storage combined system dynamic frequency prediction model is built based on a long-short-term memory neural network, which includes a forget gate, an input gate, and an output gate:
in the method, in the process of the invention,o t indicating the output gate, W o 、b o Respectively represento t And the weight matrix and bias of sigma is a sigmod activation function,x t 、h t-1 respectively representing the node state information input by the forgetting gate at the current moment and the hidden layer state of the last moment stored by the memory cell.
In some embodiments, the wind-powered electricity-storage combined power system active-frequency regulation process may be divided into three phases, the frequency response graphs of which are shown in figure 4,t 0- in order to be able to determine the moment before the disturbance occurs,t 0+ in order to be able to determine the moment after the disturbance has occurred,t nadir at the moment of the lowest point of the frequency,tthe time at which the frequency returns to steady state. The first phase, i.e. the moment of power disturbance, unbalanced power instantaneous distribution: the conventional generator and fan will distribute the unbalanced power of the system according to the respective synchronization coefficients. On the basis, electromagnetic power, mechanical power, voltage and phase angle of each node, active power of each load, standby energy of each energy storage device, voltage and phase angle of each node after disturbance and unbalanced power of each generator are selected as input characteristic values; in the second stage, before the fault occurs and the energy storage is subjected to inertial response, the disturbance power dominant frequency changes: the unbalanced power of the system is redistributed according to the inertia of the generator through a transient process, so that the electromagnetic power and the mechanical power of the generator after disturbance and the charge and discharge power of the energy storage device are selected as input characteristic values; in the third stage, the generator speed regulator starts to generate response and the energy storage device performs primary frequency modulation control, and the frequency is restored to the steady-state frequency from the extreme point: the spare capacity of each generator and energy storage device after disturbance is introduced as an input characteristic value; in which, the partial load is affected by voltage and frequency fluctuation, and its active power may change, so that load power before and after disturbance needs to be added as an input characteristic value. Selecting proper power system characteristic values according to different stages to form a certain disturbance data set, then performing normalization pretreatment to obtain an input xt, constructing a sample set for training a test long-short-time memory neural network by using historical data, wherein the selected system characteristic values comprise electromagnetic power of each generator before disturbanceThe power and the mechanical power of the generator, the voltage and the phase angle of each node, the active power of each load, the standby energy of each energy storage device, the voltage and the phase angle of each node after disturbance, the electromagnetic power and the mechanical power of the generator, the charge and discharge power of the energy storage device, the unbalanced power of each generator, the standby capacity of each generator and the energy storage device, and the active power of each load are shown in table 1 in detail.
TABLE 1
In some embodiments, the pre-built post-disturbance wind-storage combined system dynamic frequency prediction model is built based on a long-short-time memory neural network, the long-short-time memory neural network drives a forgetting gate, an input gate and an internal structure diagram of the output gate is shown in fig. 5:
firstly, the forgetting gate in the neural network is memorized for a long timef t ) Receiving the input of the current moment and the hidden layer state of the last moment stored in the memory cell respectively byx t Andh t-1 indicating that a determination is then made as to the information that needs to be discarded from the cell state, in order to make a [0,1]The output value between them represents the forgetting degree, and is expressed by the following formula:
where σ is the sigmod activation function, i.e., σ (z) = (1+e) -z ） -1 The values can be compressed to [0,1 ]]A range; w (W) f 、b f Respectively representf t Weight matrix and bias of (a).
Next, the input door structure is adoptedi t ) The process of determining information to be updated can be split into two steps to be seen, the first step:i t the layer determines the value to be updated and then creates a new candidate valuec * t The method comprises the steps of carrying out a first treatment on the surface of the And a second step of:f t from the state of old cellsc t-1 Discarding unnecessary messagesExtinguishing, adding new information, and finishingc t Is represented by the following formula:
in which W is i 、W c Respectively representing different weight matrixes; b i 、b c Representing different biases.
Finally, the door layer is outputo t ) Deciding which values to output,c t processed by tanh function and then witho t Multiplication to achieve cell statec t Is represented by the following formula:
in which W is o 、b o Respectively represento t Weight matrix and bias of (a).
Step 102: and inputting the first dynamic frequency predicted value and the second dynamic frequency predicted value into a self-adaptive neural fuzzy inference system to obtain the frequency after the wind-storage combined system is disturbed.
In some embodiments, the adaptive neural fuzzy inference system includes a fuzzification layer, a fuzzy rule layer, a normalization layer, an input connection layer, and an output layer.
In some embodiments, the inputting the first dynamic frequency prediction value and the second dynamic frequency prediction value into an adaptive neural fuzzy inference system to obtain the frequency after the disturbance of the wind-storage combined system includes:
and sequentially inputting the first dynamic frequency predicted value and the second dynamic frequency predicted value into a fuzzification layer, a fuzzy rule layer, a normalization layer, an input connection layer and an output layer of the self-adaptive neural fuzzy inference system to obtain the frequency after the wind power storage combined system is disturbed.
Specifically, when step 102 is performed, the following steps are specifically performed:
s1020: and carrying out blurring operation on the first dynamic frequency predicted value and the second dynamic frequency predicted value by adopting the blurring layer, and respectively outputting a first characteristic value and a second characteristic value of the first dynamic frequency predicted value and the second dynamic frequency predicted value after blurring.
In some embodiments, the first layer of the adaptive neural fuzzy inference system fuzzifies each input by using a plurality of membership functions, the input is the output of an improved wind storage frequency response model and a long-short-term memory neural network model, and the generalized bell-shaped membership function and the Gaussian membership function are selected for fuzzification operation, and the fuzzy operation is represented by the following formula:
in the middle of，xIs an input variable;a，b，c，σparameters representing membership functions.
The output of the blurring layer is the characteristic value of each input after blurring. The blur layer is represented by the following formula:
in the method, in the process of the invention,O 1 A,i andO 1 B,j an output representing the obscuring layer;μrepresenting a membership function;iandjrepresenting the type of membership function employed;Aand (3) withBTwo inputs representing the adaptive neural fuzzy inference system model are the output of the improved wind-storage combined system average frequency response model (namely a first dynamic frequency predicted value) and the predicted output of the long-short-term memory neural network model (namely a second dynamic frequency predicted value).
S1021: and inputting the first characteristic value and the second characteristic value into the fuzzy rule layer for combination, and outputting a plurality of fuzzy rule intensities after the first characteristic value and the second characteristic value are combined.
In some embodiments, the fuzzy rule layer combines and multiplies the two groups of outputs subjected to the first layer fuzzification in pairs, and the multiplied result obtains a fuzzy rule and outputs the strength of each rule. The fuzzy rule layer realizes the full combination of fuzzy characteristics of the two sub-models. The fuzzy rule layer is expressed by the following formula:
in the method, in the process of the invention,O 1 A,i andO 1 B,j representing the output of the obscuring layer.
S1022: and inputting the plurality of fuzzy rule intensities after the combination of the first characteristic value and the second characteristic value to a normalization layer, and outputting the plurality of fuzzy rule intensities after normalization.
In some embodiments, the normalization layer divides each fuzzy rule intensity output by the previous layer by the total rule intensity, and obtains a normalized fuzzy rule intensity value, which is expressed by the following formula:
in the method, in the process of the invention,O 2 l each fuzzy rule intensity representing the fuzzy rule layer output,indicating the overall rule strength.
S1023: and inputting the normalized multiple fuzzy rule intensities, the first dynamic frequency predicted value and the second dynamic frequency predicted value to the input connection layer, and outputting the proportion of each fuzzy rule intensity in the frequency after the wind-storage combined system is disturbed.
In some embodiments, the input connection layer connects each normalized fuzzy rule intensity value with the input value of the adaptive neural fuzzy inference system, and defuzzifies the input value, and the obtained result represents the contribution of each fuzzy rule intensity to the final result, and is represented by the following formula:
in the method, in the process of the invention,f * ASF andf * LSTM the frequency prediction values output by the wind-storage combined system average frequency response model and the long-short-term memory neural network prediction model are respectively represented;a l 、b l 、c l is a back-piece parameter of the defuzzification layer.
S1024: and inputting an output result of the input connection layer to an output layer to obtain the frequency of the wind-storage combined system after disturbance.
In some embodiments, the output layer sums the results of the defuzzification layers to yield a final frequency prediction result, which is expressed by the following formula:
in the method, in the process of the invention,f * ANFIS the predicted frequency (frequency after disturbance of the wind energy storage system) output by the adaptive neural fuzzy inference system is represented.
In some embodiments, referring to FIG. 6, the wind-powered electricity storage complex is averagedThe first dynamic frequency predictive value outputted by the frequency response modelf * ASF ) A input into the first fuzzification layer 1 And A 2 The second dynamic frequency predictive value output by the long-short-term memory neural network predictive model is calculatedf * LSTM ) B input into the first blurring layer 1 And B 2 Outputting a first characteristic value and a second characteristic value, inputting the first characteristic value and the second characteristic value into a second fuzzy rule layer for combination, outputting a plurality of fuzzy rule intensities obtained by combining the first characteristic value and the second characteristic value, then entering a third normalization layer, and obtaining a plurality of normalized fuzzy rule intensities and a first dynamic frequency predicted value #f * ASF ) And a second dynamic frequency prediction value [ ]f * LSTM ) Input to the fourth input connection layer 1, 2, 3, 4, input the output result of the connection layer to the fifth output layer, and after the addition treatment of the output layer, obtain the frequency of the wind-energy-storage combined system after disturbancef * ANFIS ）。
By using the self-adaptive neural fuzzy inference system to introduce an integrated learning idea, a frequency response physical model of the wind-storage combined system and a long-short-term memory neural network data driving model based on sample size training are properly integrated, and frequency prediction output after disturbance which accurately and rapidly contains a certain physical relationship is obtained after weighted mapping.
In some implementations, referring to fig. 7, a flowchart of dynamic frequency prediction after disturbance of a wind-storage combined system based on physical-information fusion is provided in the embodiment of the present invention, which specifically performs the steps of simultaneously performing two branches when power of an electric power system is disturbed, wherein one branch step is to obtain unbalanced power of the wind-storage combined system at the moment of disturbance and input the unbalanced power to an improved wind-storage combined system frequency response model, obtain a predicted result of the improved wind-storage combined system frequency response model after disturbance, and the other branch step is to obtain node state information of the wind-storage combined system at the moment before and after disturbance, input the node state information into a dynamic frequency predicted model after disturbance of the electric power system based on a long-short-time memory neural network, obtain a predicted result of a long-short-time memory neural network driving model after disturbance, and input the results obtained by the two branches to a self-adaptive neural fuzzy inference system, so as to obtain a comprehensive frequency predicted result after physical-data fusion.
The predicted value obtained based on the frequency response model of the wind storage combined system and the predicted value obtained based on the frequency dynamic predicted model of the wind storage combined system after disturbance are fused together, so that the current situations of complex solving parameters, large operation amount and low solving precision after simplification existing in the existing physical model driving are improved, the physical relationship in the wind storage combined system is avoided being completely ignored in the data driving, and the influence of the number and quality of samples on the predicting precision is avoided.
Referring to fig. 8, a schematic structural diagram of a frequency prediction system based on disturbance of a wind-storage combined system according to an embodiment of the present invention is shown, including:
the first output unit 800 is configured to obtain a disturbance power of the disturbance-moment wind-storage combined power system, input the disturbance power to a pre-constructed wind-storage combined system frequency response model, and output a disturbed first dynamic frequency prediction value.
And the second output unit 801 is configured to obtain node state information of the wind-storage combined power system immediately before and after the disturbance, input the node state information to a pre-constructed dynamic frequency prediction model of the wind-storage combined system after the disturbance, and output a second dynamic frequency predicted value after the disturbance.
The obtaining unit 802 is configured to input the first dynamic frequency prediction value and the second dynamic frequency prediction value into an adaptive neural fuzzy inference system, so as to obtain a frequency after disturbance of the wind-storage combined system.
In some embodiments, the adaptive neural fuzzy inference system includes a fuzzification layer, a fuzzy rule layer, a normalization layer, an input connection layer, and an output layer.
In some embodiments, the obtaining unit is configured to:
and sequentially inputting the first dynamic frequency predicted value and the second dynamic frequency predicted value into a fuzzification layer, a fuzzy rule layer, a normalization layer, an input connection layer and an output layer of the self-adaptive neural fuzzy inference system to obtain the frequency after the wind power storage combined system is disturbed.
In some embodiments, the obtaining unit is configured to:
the blurring layer is adopted to carry out blurring operation on the first dynamic frequency predicted value and the second dynamic frequency predicted value, and a first characteristic value and a second characteristic value of the first dynamic frequency predicted value and the second dynamic frequency predicted value which are subjected to blurring are respectively output;
inputting the first characteristic value and the second characteristic value into the fuzzy rule layer for combination, and outputting a plurality of fuzzy rule intensities after the first characteristic value and the second characteristic value are combined;
inputting the plurality of fuzzy rule intensities combined by the first characteristic value and the second characteristic value to a normalization layer, and outputting the plurality of normalized fuzzy rule intensities;
inputting the normalized multiple fuzzy rule intensities, the first dynamic frequency predicted value and the second dynamic frequency predicted value to the input connection layer, and outputting the proportion of each fuzzy rule intensity in the frequency after the disturbance of the wind-storage combined system;
and inputting an output result of the input connection layer to an output layer to obtain the frequency of the wind-storage combined system after disturbance.
According to the system, the predicted value of the first output unit and the predicted value of the second output unit are fused, so that the finally obtained predicted result of the frequency after the wind-storage combined system is disturbed is more accurate.
In another aspect, the present invention further provides an electronic device, including a memory, a processor, and a computer program stored in the memory and capable of running on the processor, where the steps of the frequency prediction method according to any one of the foregoing embodiments are implemented when the processor executes the program.
In another aspect, the present invention also provides a non-transitory computer readable storage medium, on which a computer program is stored, which when executed by a processor, implements the steps of the frequency prediction method according to any one of the embodiments above.
It will be appreciated by those skilled in the art that embodiments of the present application may be provided as a method, system, or computer program product. Accordingly, the present application may take the form of an entirely hardware embodiment, an entirely software embodiment, or an embodiment combining software and hardware aspects. Furthermore, the present application may take the form of a computer program product embodied on one or more computer-usable storage media (including, but not limited to, disk storage, CD-ROM, optical storage, and the like) having computer-usable program code embodied therein.
The present application is described with reference to flowchart illustrations and/or block diagrams of methods, apparatus (systems) and computer program products according to embodiments of the application. It will be understood that each flow and/or block of the flowchart illustrations and/or block diagrams, and combinations of flows and/or blocks in the flowchart illustrations and/or block diagrams, can be implemented by computer program instructions. These computer program instructions may be provided to a processor of a general purpose computer, special purpose computer, embedded processor, or other programmable data processing apparatus to produce a machine, such that the instructions, which execute via the processor of the computer or other programmable data processing apparatus, create means for implementing the functions specified in the flowchart flow or flows and/or block diagram block or blocks.
These computer program instructions may also be stored in a computer-readable memory that can direct a computer or other programmable data processing apparatus to function in a particular manner, such that the instructions stored in the computer-readable memory produce an article of manufacture including instruction means which implement the function specified in the flowchart flow or flows and/or block diagram block or blocks.
These computer program instructions may also be loaded onto a computer or other programmable data processing apparatus to cause a series of operational steps to be performed on the computer or other programmable apparatus to produce a computer implemented process such that the instructions which execute on the computer or other programmable apparatus provide steps for implementing the functions specified in the flowchart flow or flows and/or block diagram block or blocks.
In one typical configuration, a computing device includes one or more processors (CPUs), input/output interfaces, network interfaces, and memory.
The memory may include volatile memory in a computer-readable medium, random Access Memory (RAM) and/or nonvolatile memory, etc., such as Read Only Memory (ROM) or flash RAM. Memory is an example of a computer-readable medium.
Computer readable media, including both non-transitory and non-transitory, removable and non-removable media, may implement information storage by any method or technology. The information may be computer readable instructions, data structures, modules of a program, or other data. Examples of storage media for a computer include, but are not limited to, phase change memory (PRAM), static Random Access Memory (SRAM), dynamic Random Access Memory (DRAM), other types of Random Access Memory (RAM), read Only Memory (ROM), electrically Erasable Programmable Read Only Memory (EEPROM), flash memory or other memory technology, compact disc read only memory (CD-ROM), digital Versatile Discs (DVD) or other optical storage, magnetic cassettes, magnetic tape magnetic disk storage or other magnetic storage devices, or any other non-transmission medium, which can be used to store information that can be accessed by a computing device. Computer-readable media, as defined herein, does not include transitory computer-readable media (transmission media), such as modulated data signals and carrier waves.
It should also be noted that the terms "comprises," "comprising," or any other variation thereof, are intended to cover a non-exclusive inclusion, such that a process, method, article, or apparatus that comprises a list of elements does not include only those elements but may include other elements not expressly listed or inherent to such process, method, article, or apparatus. Without further limitation, an element defined by the phrase "comprising one … …" does not exclude the presence of other like elements in a process, method, article or apparatus that comprises an element.
The foregoing is merely exemplary of the present application and is not intended to limit the present application. Various modifications and changes may be made to the present application by those skilled in the art. Any modifications, equivalent substitutions, improvements, etc. which are within the spirit and principles of the present application are intended to be included within the scope of the claims of the present application.
Claims (13)
1. The frequency prediction method based on the wind-storage combined system after disturbance is characterized by comprising the following steps of:
obtaining disturbance power of a power system power disturbance instant wind-storage combined power system, inputting the disturbance power into a pre-constructed wind-storage combined system frequency response model, and outputting a disturbed first dynamic frequency predicted value;
acquiring node state information of the wind power storage combined system at the moment before and after power disturbance of the power system, inputting the node state information into a pre-constructed dynamic frequency prediction model of the wind power storage combined system after disturbance, and outputting a disturbed second dynamic frequency prediction value;
and inputting the first dynamic frequency predicted value and the second dynamic frequency predicted value into a self-adaptive neural fuzzy inference system to obtain the frequency after the wind-storage combined system is disturbed.
2. The method of claim 1, wherein the node state information of the wind-storage-combined power system at the moment before and after the disturbance includes: at least one of electromagnetic power, mechanical power, voltage of each node, phase angle, active power of each load, standby energy of each energy storage device, voltage of each node after disturbance, phase angle, electromagnetic power of the generator, mechanical power, charge and discharge power of the energy storage device, unbalanced power of each generator, standby capacity of each generator and energy storage device, and active power of each load.
3. The method of claim 1, wherein the pre-constructed wind-storage-combined-system frequency response model is:
wherein G is W (s) represents a fan system frequency model transfer function,(s) represents the energy storage system frequency model transfer function.
4. The frequency prediction method according to claim 1, wherein the pre-built post-disturbance wind-storage combined system dynamic frequency prediction model is built based on a long-short-time memory neural network, the long-short-time memory neural network comprising a forgetting gate, an input gate and an output gate:
in the method, in the process of the invention,o t indicating the output gate, W o 、b o Respectively represento t And the weight matrix and bias of sigma is a sigmod activation function,x t 、h t-1 respectively representing the node state information input by the forgetting gate at the current moment and the hidden layer state of the last moment stored by the memory cell.
5. The frequency prediction method of claim 1, wherein the adaptive neural fuzzy inference system comprises a fuzzification layer, a fuzzy rule layer, a normalization layer, an input connection layer, and an output layer.
6. The method of claim 5, wherein inputting the first dynamic frequency prediction value and the second dynamic frequency prediction value into an adaptive neural fuzzy inference system to obtain the frequency after disturbance of the wind-storage combined system comprises:
and sequentially inputting the first dynamic frequency predicted value and the second dynamic frequency predicted value into a fuzzification layer, a fuzzy rule layer, a normalization layer, an input connection layer and an output layer of the self-adaptive neural fuzzy inference system to obtain the frequency after the wind power storage combined system is disturbed.
7. The method of claim 6, wherein sequentially inputting the first dynamic frequency prediction value and the second dynamic frequency prediction value into a fuzzification layer, a fuzzy rule layer, a normalization layer, an input connection layer, and an output layer of the adaptive neural fuzzy inference system to obtain the frequency after disturbance of the wind-storage combined system comprises:
the blurring layer is adopted to carry out blurring operation on the first dynamic frequency predicted value and the second dynamic frequency predicted value, and a first characteristic value and a second characteristic value of the first dynamic frequency predicted value and the second dynamic frequency predicted value which are subjected to blurring are respectively output;
inputting the first characteristic value and the second characteristic value into the fuzzy rule layer for combination, and outputting a plurality of fuzzy rule intensities after the first characteristic value and the second characteristic value are combined;
inputting the plurality of fuzzy rule intensities combined by the first characteristic value and the second characteristic value to a normalization layer, and outputting the plurality of normalized fuzzy rule intensities;
inputting the normalized multiple fuzzy rule intensities, the first dynamic frequency predicted value and the second dynamic frequency predicted value to the input connection layer, and outputting the proportion of each fuzzy rule intensity in the frequency after the disturbance of the wind-storage combined system;
and inputting an output result of the input connection layer to an output layer to obtain the frequency of the wind-storage combined system after disturbance.
8. A system for predicting frequency after disturbance based on a wind-storage combined system, comprising:
the first output unit is used for acquiring disturbance power of the power system power disturbance instant wind-storage combined power system, inputting the disturbance power into a pre-built wind-storage combined system frequency response model and outputting a disturbed first dynamic frequency predicted value;
the second output unit is used for acquiring node state information of the wind storage combined system at the moment before and after power disturbance of the power system, inputting the node state information into a pre-constructed post-disturbance wind storage combined system dynamic frequency prediction model, and outputting a post-disturbance second dynamic frequency prediction value;
the obtaining unit is used for inputting the first dynamic frequency predicted value and the second dynamic frequency predicted value into the adaptive neural fuzzy inference system to obtain the frequency after the wind-storage combined system is disturbed.
9. The frequency prediction system of claim 8, wherein the adaptive neural fuzzy inference system comprises a fuzzification layer, a fuzzy rule layer, a normalization layer, an input connection layer, and an output layer.
10. The frequency prediction system according to claim 9, wherein the obtaining unit is configured to:
and sequentially inputting the first dynamic frequency predicted value and the second dynamic frequency predicted value into a fuzzification layer, a fuzzy rule layer, a normalization layer, an input connection layer and an output layer of the self-adaptive neural fuzzy inference system to obtain the frequency after the wind power storage combined system is disturbed.
11. The frequency prediction system according to claim 10, wherein the obtaining unit is configured to:
the blurring layer is adopted to carry out blurring operation on the first dynamic frequency predicted value and the second dynamic frequency predicted value, and a first characteristic value and a second characteristic value of the first dynamic frequency predicted value and the second dynamic frequency predicted value which are subjected to blurring are respectively output;
inputting the first characteristic value and the second characteristic value into the fuzzy rule layer for combination, and outputting a plurality of fuzzy rule intensities after the first characteristic value and the second characteristic value are combined;
inputting the plurality of fuzzy rule intensities combined by the first characteristic value and the second characteristic value to a normalization layer, and outputting the plurality of normalized fuzzy rule intensities;
inputting the normalized multiple fuzzy rule intensities, the first dynamic frequency predicted value and the second dynamic frequency predicted value to the input connection layer, and outputting the proportion of each fuzzy rule intensity in the frequency after the disturbance of the wind-storage combined system;
and inputting an output result of the input connection layer to an output layer to obtain the frequency of the wind-storage combined system after disturbance.
12. An electronic device comprising a memory, a processor and a computer program stored on the memory and executable on the processor, characterized in that the processor implements the steps of the frequency prediction method according to any of claims 1-7 when the program is executed by the processor.
13. A non-transitory computer readable storage medium, on which a computer program is stored, characterized in that the computer program, when being executed by a processor, implements the steps of the frequency prediction method according to any of claims 1-7.
Priority Applications (1)
| Application Number | Priority Date | Filing Date | Title |
|---|---|---|---|
| CN202311615224.9A CN117349998A (en) | 2023-11-29 | 2023-11-29 | Frequency prediction method, system and medium based on wind-storage combined system disturbance |
Applications Claiming Priority (1)
| Application Number | Priority Date | Filing Date | Title |
|---|---|---|---|
| CN202311615224.9A CN117349998A (en) | 2023-11-29 | 2023-11-29 | Frequency prediction method, system and medium based on wind-storage combined system disturbance |
Publications (1)
| Publication Number | Publication Date |
|---|---|
| CN117349998A true CN117349998A (en) | 2024-01-05 |
Family
ID=89359812
Family Applications (1)
| Application Number | Title | Priority Date | Filing Date |
|---|---|---|---|
| CN202311615224.9A Pending CN117349998A (en) | 2023-11-29 | 2023-11-29 | Frequency prediction method, system and medium based on wind-storage combined system disturbance |
Country Status (1)
| Country | Link |
|---|---|
| CN (1) | CN117349998A (en) |
-
2023
- 2023-11-29 CN CN202311615224.9A patent/CN117349998A/en active Pending
Similar Documents
| Publication | Publication Date | Title |
|---|---|---|
| Kim et al. | Length-adaptive transformer: Train once with length drop, use anytime with search | |
| Lu et al. | The PID Controller Based on the Artificial Neural Network and the Differential Evolution Algorithm. | |
| Ponce et al. | Doubly fed induction generator (DFIG) wind turbine controlled by artificial organic networks | |
| CN112310980B (en) | Safety and stability evaluation method and system for direct-current blocking frequency of alternating-current and direct-current series-parallel power grid | |
| CN109412161B (en) | Power system probability load flow calculation method and system | |
| CN110009141B (en) | Climbing event prediction method and system based on SDAE feature extraction and SVM classification model | |
| CN110634082A (en) | Low-frequency load shedding system operation stage prediction method based on deep learning | |
| Wen et al. | Data‐driven transient frequency stability assessment: A deep learning method with combined estimation‐correction framework | |
| Jaber et al. | A new parameters identification of single area power system based LFC using Segmentation Particle Swarm Optimization (SePSO) algorithm | |
| de Jesús Rubio | Analytic neural network model of a wind turbine | |
| CN111401792A (en) | Dynamic safety assessment method based on extreme gradient lifting decision tree | |
| Ouada et al. | Neuro-fuzzy sliding mode controller based on a brushless doubly fed induction generator | |
| Kiran et al. | Online training of a generalized neuron with particle swarm optimization | |
| Sahoo et al. | Torque and pitch angle control of a wind turbine using multiple adaptive neuro-fuzzy control | |
| Wang et al. | Modeling of a 5-cell direct methanol fuel cell using adaptive-network-based fuzzy inference systems | |
| Razmi et al. | Neural network based on a genetic algorithm for power system loading margin estimation | |
| Vargas et al. | Data mining techniques for very short term prediction of wind power | |
| CN117349998A (en) | Frequency prediction method, system and medium based on wind-storage combined system disturbance | |
| CN115528750B (en) | Power grid safety and stability oriented data model hybrid drive unit combination method | |
| Mohammed et al. | Design of a load frequency controller based on artificial neural network for single-area power system | |
| Zhang et al. | An adaptive fuzzy PID control of hydro-turbine governor | |
| Xiao et al. | Deep learning for predicting the operation of under-frequency load shedding systems | |
| Dameshghi et al. | A new strategy for short-term power-curve prediction of wind turbine based on PSO-LS-WSVM | |
| Bin et al. | Simple and effective fault diagnosis method of power lithium-ion battery based on GWA-DBN | |
| CN110207871B (en) | Method, device, storage medium and system for stress prediction of wind turbine generator |
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 |