CN113675863B - Digital twin-based micro-grid frequency secondary cooperative control method - Google Patents
Digital twin-based micro-grid frequency secondary cooperative control method Download PDFInfo
- Publication number
- CN113675863B CN113675863B CN202110967214.6A CN202110967214A CN113675863B CN 113675863 B CN113675863 B CN 113675863B CN 202110967214 A CN202110967214 A CN 202110967214A CN 113675863 B CN113675863 B CN 113675863B
- Authority
- CN
- China
- Prior art keywords
- micro
- frequency
- grid
- digital twin
- neural network
- Prior art date
- Legal status (The legal status is an assumption and is not a legal conclusion. Google has not performed a legal analysis and makes no representation as to the accuracy of the status listed.)
- Active
Links
- 238000000034 method Methods 0.000 title claims abstract description 28
- 230000003993 interaction Effects 0.000 claims abstract description 12
- 238000007665 sagging Methods 0.000 claims abstract description 10
- 238000004422 calculation algorithm Methods 0.000 claims abstract description 7
- 238000013528 artificial neural network Methods 0.000 claims description 33
- 230000006870 function Effects 0.000 claims description 20
- 210000002569 neuron Anatomy 0.000 claims description 18
- 230000002159 abnormal effect Effects 0.000 claims description 8
- 230000004913 activation Effects 0.000 claims description 5
- 238000010606 normalization Methods 0.000 claims description 5
- 238000012549 training Methods 0.000 claims description 5
- 238000010220 Pearson correlation analysis Methods 0.000 claims description 4
- 238000004458 analytical method Methods 0.000 claims description 4
- 238000004364 calculation method Methods 0.000 claims description 4
- 238000012545 processing Methods 0.000 claims description 4
- 238000007781 pre-processing Methods 0.000 claims description 3
- 238000003062 neural network model Methods 0.000 claims description 2
- 125000003275 alpha amino acid group Chemical group 0.000 claims 1
- 150000001875 compounds Chemical class 0.000 claims 1
- 238000001514 detection method Methods 0.000 claims 1
- 230000006872 improvement Effects 0.000 description 9
- 238000005516 engineering process Methods 0.000 description 6
- 230000008569 process Effects 0.000 description 4
- 238000004088 simulation Methods 0.000 description 4
- 238000010586 diagram Methods 0.000 description 3
- 238000004519 manufacturing process Methods 0.000 description 3
- 230000002411 adverse Effects 0.000 description 2
- 230000002457 bidirectional effect Effects 0.000 description 2
- 238000011217 control strategy Methods 0.000 description 2
- 230000000694 effects Effects 0.000 description 2
- 238000004146 energy storage Methods 0.000 description 2
- 238000013507 mapping Methods 0.000 description 2
- 238000010248 power generation Methods 0.000 description 2
- 230000008859 change Effects 0.000 description 1
- 230000001419 dependent effect Effects 0.000 description 1
- 238000013461 design Methods 0.000 description 1
- 238000011161 development Methods 0.000 description 1
- 238000009826 distribution Methods 0.000 description 1
- 230000007613 environmental effect Effects 0.000 description 1
- 230000007246 mechanism Effects 0.000 description 1
- 238000012986 modification Methods 0.000 description 1
- 230000004048 modification Effects 0.000 description 1
- 238000013450 outlier detection Methods 0.000 description 1
- 230000000704 physical effect Effects 0.000 description 1
- 238000011084 recovery Methods 0.000 description 1
- 230000001105 regulatory effect Effects 0.000 description 1
- 230000000087 stabilizing effect Effects 0.000 description 1
- 238000006467 substitution reaction Methods 0.000 description 1
Classifications
-
- H—ELECTRICITY
- H02—GENERATION; CONVERSION OR DISTRIBUTION OF ELECTRIC POWER
- H02J—CIRCUIT ARRANGEMENTS OR SYSTEMS FOR SUPPLYING OR DISTRIBUTING ELECTRIC POWER; SYSTEMS FOR STORING ELECTRIC ENERGY
- H02J3/00—Circuit arrangements for ac mains or ac distribution networks
- H02J3/24—Arrangements for preventing or reducing oscillations of power in networks
- H02J3/241—The oscillation concerning frequency
-
- H—ELECTRICITY
- H02—GENERATION; CONVERSION OR DISTRIBUTION OF ELECTRIC POWER
- H02J—CIRCUIT ARRANGEMENTS OR SYSTEMS FOR SUPPLYING OR DISTRIBUTING ELECTRIC POWER; SYSTEMS FOR STORING ELECTRIC ENERGY
- H02J3/00—Circuit arrangements for ac mains or ac distribution networks
- H02J3/002—Flicker reduction, e.g. compensation of flicker introduced by non-linear load
-
- 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
- H02J2203/10—Power transmission or distribution systems management focussing at grid-level, e.g. load flow analysis, node profile computation, meshed network optimisation, active network management or spinning reserve management
-
- 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)
- Power Engineering (AREA)
- Physics & Mathematics (AREA)
- Nonlinear Science (AREA)
- Supply And Distribution Of Alternating Current (AREA)
Abstract
A digital twin-based micro-grid frequency secondary cooperative control method belongs to the technical field of micro-grid control and solves the problem that parameters in traditional droop control-based micro-grid frequency secondary cooperative control cannot be dynamically adjusted; the method comprises the steps of solving the problem of correction of the running state of a micro-grid system through digital twin, acquiring running data in the micro-grid system in real time, transmitting the running data of a power grid to a digital twin model in real time through a data interaction interface, analyzing and predicting the data through the digital twin model, feeding back a control instruction to the micro-grid system for secondary control, and correcting the frequency of the micro-grid system to enable the frequency to be stabilized near a rated frequency; compared with the traditional secondary control algorithm based on sagging, the digital twin has a logic rule base, can quickly respond to the micro-grid system, and improves the control precision of the system frequency.
Description
Technical Field
The invention belongs to the technical field of micro-grid control, and relates to a micro-grid frequency secondary cooperative control method based on digital twin.
Background
With the increasing exhaustion of traditional fossil energy sources in the global scope, new energy power generation technology in micro-grids is increasingly widely applied. However, since the new energy power generation is easily affected by various environmental factors, the output power has the characteristics of intermittence, volatility and randomness, and especially when the micro-grid is in an island operation mode, the frequency of the system is adversely affected, so that the electric energy quality is affected.
The traditional frequency adjustment means is mainly based on mathematical modeling and mechanism modeling, but with the increasing complexity of a micro-grid system, the problems of inaccurate model and the like exist, and the control effect is further affected. The literature 'distributed fixed time secondary coordination control of an island micro-grid' (Cheng just, chongqing university) aims at that the sagging control strategy of the island micro-grid can lead the frequency and the voltage of a system steady state to deviate from rated values, and provides a distributed fixed time secondary coordination control strategy to realize the recovery control of the system frequency and the voltage and realize the expected active power distribution. The control method can complete the secondary control target within a fixed time without depending on the initial state of the system, so that the offline presetting of the setting time according to the task requirement is possible. However, this document does not solve the problem that the parameters in the conventional droop-based secondary control algorithm cannot be dynamically adjusted.
The Digital Twin (Digital Twin) is a simulation process integrating multiple disciplines, multiple physical quantities, multiple scales and multiple probabilities by fully utilizing data such as a physical model, sensor updating, operation history and the like, and mapping is completed in a virtual space, so that a full life cycle process of corresponding entity equipment is reflected. Digital twinning is a beyond-the-reality concept that can be seen as a digital mapping system of one or more important, mutually dependent equipment systems.
The digital twin concept is put forward for the first time in 2003, and the digital twin concept does not attract high importance to domestic and foreign scholars until 2011, and is continuously developed in 2016-2018 by the most authoritative information technology consultation company in the world, namely Gartner, which is the current top strategic technology development direction. The national science and technology academy of intellectual manufacturing association of 12 months 2017 has twinned digital as one of ten technological advances in world intellectual manufacturing at the world intellectual manufacturing society. To date, the digital twinning definition widely accepted by the industry is given by Glaessegen and Star-gel in 2012: the complex product simulation model integrating multiple physical properties, multiple scales and probability can reflect the state of a real product in real time. As a technology which fully utilizes models, data and intelligence and integrates multiple disciplines, digital twinning is oriented to the whole life cycle process of products, plays the role of bridges and ties connecting the physical world and the information world, and provides more real-time, efficient and intelligent service.
Therefore, the invention utilizes digital twin technology to carry out secondary cooperative control on the micro-grid frequency. And a large amount of data generated in the running process of the micro-grid is fully mined through the data driving model, so that real-time interaction of the data between the digital twin model and the physical entity of the micro-grid is realized, and the running state of the micro-grid is further adjusted, so that the system frequency is ensured to be always maintained near the rated frequency.
Disclosure of Invention
The invention aims to design a digital twin-based micro-grid frequency secondary cooperative control method and system so as to solve the problem that parameters in the traditional droop control-based micro-grid frequency secondary cooperative control cannot be dynamically adjusted.
The invention solves the technical problems through the following technical scheme:
a digital twin-based micro-grid frequency secondary cooperative control method comprises the following steps:
s1, preprocessing an offline data set: through Pearson correlation analysis, selecting influence factors of micro-grid frequency as input variables to calculate correlation coefficients, filling missing values and detecting abnormal values of a data set, and carrying out normalization processing on input features in the data set;
s2, building a digital twin model: training the BP neural network based on the data set obtained in the step S1 by constructing the BP neural network, constructing a logic rule base, analyzing the running state of the micro-grid system, and if the micro-grid system enters a steady state and has larger deviation in frequency, starting the BP neural network for prediction, otherwise, keeping secondary control parameters unchanged;
s3, optimizing control of the micro-grid system: the method comprises the steps of establishing a secondary control model based on droop control, transmitting current operation data to a digital twin model through a data interaction interface by a micro-grid system, analyzing the operation data of the micro-grid by the digital twin model, feeding back an obtained control instruction to the micro-grid system through the data interaction interface, and further adjusting the frequency of the system.
The invention solves the problem of correcting the running state of the micro-grid system through digital twin, acquires running data in the micro-grid system in real time, transmits the running data of the power grid to a digital twin model in real time through a data interaction interface, analyzes and predicts the data through the digital twin model, feeds back a control instruction to the micro-grid system for secondary control, and corrects the frequency of the micro-grid system to be stabilized near the rated frequency; compared with the traditional secondary control algorithm based on sagging, the digital twin has a logic rule base, can quickly respond to the micro-grid system, and improves the control precision of the system frequency.
As a further improvement of the technical solution of the present invention, the formula for calculating the correlation coefficient by selecting the influencing factor of the micro-grid frequency as the input variable in step S1 is as follows:
wherein r is xy Representing the correlation coefficient, x and y respectively represent n-dimensional phasors,representing the average value of the input variables.
As a further improvement of the technical scheme of the invention, the missing value filling method in the step S1 comprises the following steps: and periodically collecting the power of each distributed power supply and the voltage at a bus in the micro-grid system, collecting the exchange power of a connecting line, and filling the missing value by constructing a cubic spline interpolation function between every two discrete points.
As a further improvement of the technical scheme of the invention, the cubic spline interpolation function is defined as follows:
y＝ax 3 +bx 2 +cx+d (2)
wherein a, b, c, d each represents a coefficient value of each of the functions of degree 3.
As a further improvement of the technical scheme of the present invention, the method for detecting the abnormal value in the step S1 is as follows: calculating the abnormal value score of each sample based on the isolated forest theory, wherein the calculation formula is as follows:
where s (γ, ψ) represents an anomaly score, γ represents a single sample, h (γ) is the height of γ in each tree, E (h (γ)) is the expectation of the path length of sample γ in a batch of isolated trees, c (ψ) is the average of the path lengths at a given sample number ψ, for normalizing the path length h (γ) of sample γ;
the calculation formula of c (ψ) is as follows:
where H (ψ -1) is a harmonic number, which can be estimated from ln (ψ -1) +0.5772156649 (Euler constant).
As a further improvement of the technical scheme of the present invention, the formula for normalizing the input features in the dataset in step S1 is as follows:
wherein x is min And x max Representing the minimum and maximum values in the data, respectively, normalizing x' to [ -1,1]And in the interval, so that the characteristics of the input data are reserved.
As a further improvement of the technical scheme of the invention, the method for constructing the BP neural network in the step S2 is as follows:
the output layer has only one neuron, the output variable is the frequency minimum of the sagging curve, and the number of neurons of the hidden layer is determined according to an empirical formula (6):
wherein q represents the number of hidden layer neurons; m represents the number of neurons in the input layer; n represents the number of neurons in the output layer; a is a constant of 1-10, and the number of hidden layers is adjusted according to analysis requirements.
As a further improvement of the technical scheme of the invention, the method for training the BP neural network based on the data set obtained in the step S1 in the step S2 comprises the following steps: setting an activation function of an hidden layer as a relu function, updating parameters of a BP neural network model through a random gradient descent algorithm, and storing the trained parameters, wherein an updating formula of the parameters is as follows:
in the formula (7), θ represents a network parameter of the BP neural network, η represents a learning rate, J represents a loss function,representing the gradient of the network parameter.
As a further improvement of the technical scheme of the invention, the prediction formula of the BP neural network in the step S2 is as follows:
wherein u (s, θ) represents the prediction result output by the BP neural network, and k represents the layer number of the BP neural network; s is the input of the BP neural network;representing the activation function of the layer i neurons in the BP neural network.
As a further improvement of the technical scheme of the present invention, the formula of the secondary control model based on droop control in step S3 is as follows:
wherein omega i Representing the output frequency of the ith controllable power supply; omega ni Representing the rated frequency of the ith controllable power supply; δω i Is a secondary frequency adjustment term; k (k) pf And k if Respectively representing the proportional and integral coefficients of the secondary frequency controller.
The invention has the advantages that:
the invention solves the problem of correcting the running state of the micro-grid system through digital twin, acquires running data in the micro-grid system in real time, transmits the running data of the power grid to a digital twin model in real time through a data interaction interface, analyzes and predicts the data through the digital twin model, feeds back a control instruction to the micro-grid system for secondary control, and corrects the frequency of the micro-grid system to be stabilized near the rated frequency; compared with the traditional secondary control algorithm based on sagging, the digital twin has a logic rule base, can quickly respond to the micro-grid system, and improves the control precision of the system frequency.
Drawings
FIG. 1 is a flow chart of digital twin-based micro-grid frequency secondary cooperative control in an embodiment of the invention;
fig. 2 is a topology structure diagram of a BP neural network according to an embodiment of the present invention;
FIG. 3 is a schematic diagram of bidirectional data interaction between a digital twin model and a micro-grid system according to an embodiment of the present invention;
FIG. 4 is a block diagram of a simulation model of a digital twin-based micro-grid frequency secondary cooperative control method according to an embodiment of the present invention;
FIG. 5 is a graph of the frequency variation of a micro-grid system based on a droop-based conventional secondary control model;
fig. 6 is a graph of frequency variation of a digital twin-based micro grid system according to an embodiment of the present invention.
Detailed Description
For the purpose of making the objects, technical solutions and advantages of the embodiments of the present invention more apparent, the technical solutions in the embodiments of the present invention will be clearly and completely described in the following in conjunction with the embodiments of the present invention, and it is apparent that the described embodiments are some embodiments of the present invention, but not all embodiments. All other embodiments, which can be made by those skilled in the art based on the embodiments of the invention without making any inventive effort, are intended to be within the scope of the invention.
The technical scheme of the invention is further described below with reference to the attached drawings and specific embodiments:
example 1
As shown in fig. 1, a digital twin-based micro-grid frequency secondary cooperative control method includes:
1. preprocessing offline data sets
1.1 Pearson correlation analysis
And selecting variables such as active power, reactive power, bus voltage and the like of each distributed power supply in the micro-grid system as input variables. Considering that excessive input variables can cause problems of increased complexity of a model, slow convergence speed and the like, through Pearson correlation analysis, several factors with the greatest influence on the frequency of the micro-grid are selected as the input variables, and the correlation coefficients are calculated, namely:
in the formula (1), x and y respectively represent n-dimensional phasors,representing the average value of the input variables.
1.2 missing value filling
The power of each distributed power supply, the voltage at the bus and the exchange power of the connecting lines in the micro-grid system are collected every 3 seconds, and the missing values in the data are caused by considering that the equipment possibly has faults, and the missing values are finally filled by constructing a cubic spline interpolation function between every two discrete points, wherein the cubic spline interpolation function is defined as follows:
y＝ax 3 +bx 2 +cx+d (2)
in the formula (2), a, b, c, and d represent coefficient values of the 3-degree functions, respectively.
1.3 outlier detection
Considering that abnormal values may exist in the sample set, the subsequent analysis is adversely affected, and calculating the abnormal value score of each sample based on the isolated forest theory includes:
in the formula (3), s (gamma, ψ) represents an anomaly score, gamma represents a single sample, h (gamma) is gamma at the height of each tree, E (gamma) is the expectation of the path length of the sample gamma in a batch of isolated trees, c (ψ) is the average value of the path lengths given the sample number ψ, and is used for carrying out normalization processing on the path length h (gamma) of the sample gamma;
in the formula (4), H (ψ -1) is a harmonic number, which can be estimated from ln (ψ -1) +0.5772156649 (Euler constant).
1.4 normalization of the data set
Carrying out normalization processing and dimensionalization on input features in a data set, namely:
in the formula (5), x min And x max Representing the minimum and maximum values in the data, respectively, normalizing x' to [ -1,1]The characteristics of the input data are preserved as much as possible within the interval.
2. Building digital twin model
2.1, as shown in fig. 2, constructing a BP neural network, wherein an output layer has only one neuron, the output variable is the frequency minimum value of a sagging curve, and the number of neurons of an hidden layer is determined according to a formula (6):
wherein q represents the number of hidden layer neurons; m represents the number of neurons in the input layer; n represents the number of neurons in the output layer; a is a constant of 1-10, and the number of hidden layers is adjusted according to analysis requirements.
Based on the offline data set obtained in the step 1, training the BP neural network, setting an activation function of an implicit layer as a relu function, updating model parameters through a random gradient descent algorithm, and saving the trained BP neural network parameters, so that the subsequent calling is convenient. The parameter update formula is as follows:
in the formula (7), θ represents a network parameter of the BP neural network, η represents a learning rate, J represents a loss function,representing the gradient of the network parameter.
2.2, constructing a logic rule base, analyzing the running state of the micro-grid system, if the system enters a steady state and the frequency deviation is large, starting a BP neural network to predict, otherwise, keeping secondary control parameters unchanged; the output prediction formula of the BP neural network is as follows:
wherein u (s, θ) represents the prediction result output by the BP neural network, and k represents the layer number of the BP neural network; s is the input of the BP neural network;representing the activation function of the layer i neurons in the BP neural network.
3. Optimized control of micro-grid systems
3.1, establishing a secondary control model based on sagging control as follows:
wherein omega i Representing the output frequency of the ith controllable power supply; omega ni Representing the rated frequency of the ith controllable power supply; δω i Is a secondary frequency adjustment term; k (k) pf And k if Respectively representing the proportional and integral coefficients of the secondary frequency controller.
And 3.2, based on the digital twin model built in the step 2, realizing bidirectional flow of data between the micro-grid system and the digital twin model through a data interaction interface, and finally stabilizing the system frequency near a rated value.
As shown in fig. 3, the micro-grid system transmits current operation data to the digital twin model through the data interaction interface, the digital twin model analyzes the operation data of the micro-grid, and the obtained control command is fed back to the micro-grid system through the data interaction interface to further adjust the system frequency.
As shown in fig. 4, a simulation model of the micro-grid system is established, 2 distributed energy storage power supplies exist in the system, the output power ranges of the distributed energy storage power supplies are 0 MW-0.08 MW and 0 MW-0.04 MW respectively, the active power of two loads is 0.04MW and 0.02MW respectively, the micro-grid system is connected with a main network at the initial moment, the micro-grid system is separated from the main network at 0.5s, and load shedding operation is performed at 2 s.
As shown in fig. 5 and 6, the frequency change graphs of the conventional secondary control model based on sagging and the system based on digital twin are shown respectively, it can be seen from fig. 5 that under the effect of the conventional secondary control model, the frequency of the system is stabilized at 49.90HZ after entering a steady state, the deviation from the rated frequency is 0.1HZ, and it can be seen from fig. 6 that after the digital twin detects that the micro grid system enters the steady state, a certain frequency deviation exists, at this time, a control command is output to the micro grid through the digital twin model to regulate the frequency of the micro grid system, and the regulated frequency is stabilized at 49.96HZ and is closer to the rated frequency.
The above embodiments are only for illustrating the technical solution of the present invention, and are not limiting; although the invention has been described in detail with reference to the foregoing embodiments, it will be understood by those of ordinary skill in the art that: the technical scheme described in the foregoing embodiments can be modified or some technical features thereof can be replaced by equivalents; such modifications and substitutions do not depart from the spirit and scope of the technical solutions of the embodiments of the present invention.
Claims (6)
1. The digital twin-based micro-grid frequency secondary cooperative control method is characterized by comprising the following steps of:
s1, preprocessing an offline data set: through Pearson correlation analysis, selecting influence factors of micro-grid frequency as input variables to calculate correlation coefficients, filling missing values and detecting abnormal values of a data set, and carrying out normalization processing on input features in the data set;
the formula for calculating the correlation coefficient by taking the influence factors of the micro-grid frequency as the input variables is as follows:
（1）
wherein r is xy Representing the correlation coefficient, x and y respectively represent n-dimensional phasors,、/>representing an average value of the input variables;
the missing value filling method comprises the following steps: periodically collecting the power of each distributed power supply and the voltage at a bus in the micro-grid system, collecting the exchange power of a connecting line, and filling the missing value by constructing a cubic spline interpolation function between every two discrete points;
the abnormal value detection method comprises the following steps: calculating the abnormal value score of each sample based on the isolated forest theory, wherein the calculation formula is as follows:
（3）
wherein s is%ψ) represents the anomaly score, ++>Representing a single sample, +.>Is->At the height of each tree, +.>For sample->The desire of path length in a collection of orphaned trees, < >>For a given number of samples->Average value of time path length for sample +.>Path length of->Carrying out standardization treatment;
the calculation formula of (2) is as follows:
（4）
where H (ψ -1) is a harmonic number, which can be estimated from ln (ψ -1) +0.5772156649 (Euler constant);
s2, building a digital twin model: training the BP neural network based on the data set obtained in the step S1 by constructing the BP neural network, constructing a logic rule base, analyzing the running state of the micro-grid system, and if the micro-grid system enters a steady state and the frequency has deviation, starting the BP neural network to predict, otherwise, keeping the secondary control parameters unchanged;
s3, optimizing control of the micro-grid system: establishing a secondary control model based on droop control, transmitting current operation data to a digital twin model through a data interaction interface by a micro-grid system, analyzing the operation data of the micro-grid by the digital twin model, feeding back an obtained control instruction to the micro-grid system through the data interaction interface, and further adjusting the frequency of the system;
the formula of the secondary control model based on sagging control is as follows:
（9）
wherein,indicate->The output frequency of the controllable power supply; />Indicate->The nominal frequency of the controllable power supply; />Is a secondary frequency adjustment term; />And->Respectively representing the proportional and integral coefficients of the secondary frequency controller.
2. The digital twin-based micro-grid frequency secondary cooperative control method according to claim 1, wherein the cubic spline interpolation function is defined as follows:
（2）
wherein a, b, c, d each represents a coefficient value of each of the functions of degree 3.
3. The digital twin-based micro-grid frequency secondary cooperative control method according to claim 2, wherein the formula for normalizing the input features in the data set in step S1 is as follows:
（5）
wherein,and->Representing the minimum and maximum values in the data, respectively, +.>Normalized to [ -1,1]And in the interval, so that the characteristics of the input data are reserved.
4. The digital twin-based micro-grid frequency secondary cooperative control method according to claim 3, wherein the method for constructing the BP neural network in step S2 is as follows:
the output layer has only one neuron, the output variable is the frequency minimum of the sagging curve, and the number of neurons of the hidden layer is determined according to an empirical formula (6):
（6）
wherein q represents the number of hidden layer neurons; m represents the number of neurons in the input layer; n represents the number of neurons in the output layer; a is a constant of 1-10, and the number of hidden layers is adjusted according to analysis requirements.
5. The digital twin-based micro-grid frequency secondary cooperative control method according to claim 4, wherein the method for training the BP neural network based on the data set obtained in step S1 in step S2 is as follows: setting an activation function of an hidden layer as a relu function, updating parameters of a BP neural network model through a random gradient descent algorithm, and storing the trained parameters, wherein an updating formula of the parameters is as follows:
（7）
in the formula (7), the amino acid sequence of the compound,network parameters representing BP neural network, +.>Indicates learning rate,/->Representing a loss function->Representing the gradient of the network parameter.
6. The digital twin-based micro-grid frequency secondary cooperative control method according to claim 5, wherein the prediction formula of the BP neural network in step S2 is as follows:
（8）
wherein,represents the predicted result output by the BP neural network,krepresenting the number of layers of the BP neural network; />Is the input of BP neural network; />Representing the th in BP neural networklActivation function of layer neurons.
Priority Applications (1)
| Application Number | Priority Date | Filing Date | Title |
|---|---|---|---|
| CN202110967214.6A CN113675863B (en) | 2021-08-23 | 2021-08-23 | Digital twin-based micro-grid frequency secondary cooperative control method |
Applications Claiming Priority (1)
| Application Number | Priority Date | Filing Date | Title |
|---|---|---|---|
| CN202110967214.6A CN113675863B (en) | 2021-08-23 | 2021-08-23 | Digital twin-based micro-grid frequency secondary cooperative control method |
Publications (2)
| Publication Number | Publication Date |
|---|---|
| CN113675863A CN113675863A (en) | 2021-11-19 |
| CN113675863B true CN113675863B (en) | 2024-02-06 |
Family
ID=78544989
Family Applications (1)
| Application Number | Title | Priority Date | Filing Date |
|---|---|---|---|
| CN202110967214.6A Active CN113675863B (en) | 2021-08-23 | 2021-08-23 | Digital twin-based micro-grid frequency secondary cooperative control method |
Country Status (1)
| Country | Link |
|---|---|
| CN (1) | CN113675863B (en) |
Families Citing this family (3)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN115224698B (en) * | 2022-07-20 | 2023-06-30 | 南京理工大学 | Reactive power-voltage optimization control method for new energy power system based on digital twin |
| CN115859700B (en) * | 2023-03-02 | 2023-05-05 | 国网湖北省电力有限公司电力科学研究院 | Power grid modeling method based on digital twin technology |
| CN116231871B (en) * | 2023-04-28 | 2023-07-28 | 深圳市三和电力科技有限公司 | Power grid situation supervision method, system and storage medium based on digital twinning |
Citations (6)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| WO2019178919A1 (en) * | 2018-03-20 | 2019-09-26 | 东南大学 | Micro-grid distributed controller parameter determination method based on linear quadratic optimization |
| CN112332444A (en) * | 2020-09-14 | 2021-02-05 | 华北电力大学（保定） | Microgrid energy management system based on digital twins |
| CN112464418A (en) * | 2020-11-17 | 2021-03-09 | 海南省电力学校(海南省电力技工学校) | Universal digital twin body construction method of distributed energy resources |
| CN112531694A (en) * | 2020-11-27 | 2021-03-19 | 国网重庆市电力公司电力科学研究院 | AC/DC hybrid power grid universe real-time simulation method based on digital twinning technology |
| CN113077101A (en) * | 2021-04-16 | 2021-07-06 | 华北电力大学 | Energy internet allocation management-oriented digital system and method |
| CN113221456A (en) * | 2021-05-11 | 2021-08-06 | 上海交通大学 | Digital twin modeling and multi-agent coordination control method for smart microgrid |
-
2021
- 2021-08-23 CN CN202110967214.6A patent/CN113675863B/en active Active
Patent Citations (6)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| WO2019178919A1 (en) * | 2018-03-20 | 2019-09-26 | 东南大学 | Micro-grid distributed controller parameter determination method based on linear quadratic optimization |
| CN112332444A (en) * | 2020-09-14 | 2021-02-05 | 华北电力大学（保定） | Microgrid energy management system based on digital twins |
| CN112464418A (en) * | 2020-11-17 | 2021-03-09 | 海南省电力学校(海南省电力技工学校) | Universal digital twin body construction method of distributed energy resources |
| CN112531694A (en) * | 2020-11-27 | 2021-03-19 | 国网重庆市电力公司电力科学研究院 | AC/DC hybrid power grid universe real-time simulation method based on digital twinning technology |
| CN113077101A (en) * | 2021-04-16 | 2021-07-06 | 华北电力大学 | Energy internet allocation management-oriented digital system and method |
| CN113221456A (en) * | 2021-05-11 | 2021-08-06 | 上海交通大学 | Digital twin modeling and multi-agent coordination control method for smart microgrid |
Also Published As
| Publication number | Publication date |
|---|---|
| CN113675863A (en) | 2021-11-19 |
Similar Documents
| Publication | Publication Date | Title |
|---|---|---|
| CN113675863B (en) | Digital twin-based micro-grid frequency secondary cooperative control method | |
| CN109523084A (en) | A kind of ultrashort-term wind power prediction method based on pivot analysis and machine learning | |
| CN110888317A (en) | PID controller parameter intelligent optimization method | |
| CN110212551B (en) | Micro-grid reactive power automatic control method based on convolutional neural network | |
| CN116596286B (en) | Optimized scheduling method, device and equipment for virtual power plant and storage medium | |
| CN110165714B (en) | Micro-grid integrated scheduling and control method based on extreme dynamic programming algorithm and computer readable storage medium | |
| CN111198550A (en) | Cloud intelligent production optimization scheduling on-line decision method and system based on case reasoning | |
| CN115425680A (en) | Power prediction model construction and prediction method of multi-energy combined power generation system | |
| CN115115127A (en) | Low-voltage transformer area intelligent regulation and control method and system based on deep learning | |
| Wang et al. | A data-centric predictive control approach for nonlinear chemical processes | |
| CN114430165A (en) | Micro-grid group intelligent coordination control method and device based on depth model prediction | |
| CN110231808B (en) | Production process energy efficiency trans-scale intelligent cooperative control system and method | |
| CN115795992A (en) | Park energy Internet online scheduling method based on virtual deduction of operation situation | |
| CN114722693A (en) | Optimization method of two-type fuzzy control parameter of water turbine regulating system | |
| CN114119289A (en) | Method and device for processing comprehensive energy monitoring data | |
| Wang et al. | Short-term wind power prediction based on DBSCAN clustering and support vector machine regression | |
| CN117638939A (en) | Water-light complementary optimization scheduling method based on Adam algorithm consideration | |
| CN117375097A (en) | Photovoltaic coordination autonomous method based on multi-agent coordination control strategy and reinforcement learning | |
| CN116307526B (en) | Intelligent factory productivity analysis system based on mathematical model | |
| CN109578264B (en) | Pressure stabilizing method, system and device of air compressor for chip production and storage medium | |
| EP4027474A1 (en) | Power control device and power control method | |
| CN116154875A (en) | Photovoltaic power station active power optimization distribution method based on TCN and error function | |
| CN114301062A (en) | Distributed energy optimization treatment device | |
| CN108009686B (en) | Photovoltaic power generation power prediction method, device and system | |
| CN112348235A (en) | Wind-solar bus load self-adaptive prediction method and device and computer equipment |
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 |