CN116522795A - Comprehensive energy system simulation method and system based on digital twin model - Google Patents
Comprehensive energy system simulation method and system based on digital twin model Download PDFInfo
- Publication number
- CN116522795A CN116522795A CN202310572283.6A CN202310572283A CN116522795A CN 116522795 A CN116522795 A CN 116522795A CN 202310572283 A CN202310572283 A CN 202310572283A CN 116522795 A CN116522795 A CN 116522795A
- Authority
- CN
- China
- Prior art keywords
- training
- model
- digital twin
- energy
- comprehensive energy
- 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
- 238000004088 simulation Methods 0.000 title claims abstract description 44
- 238000000034 method Methods 0.000 title claims abstract description 42
- 238000012549 training Methods 0.000 claims abstract description 72
- 238000013499 data model Methods 0.000 claims abstract description 52
- 238000013136 deep learning model Methods 0.000 claims abstract description 18
- 238000005516 engineering process Methods 0.000 claims abstract description 9
- 238000013528 artificial neural network Methods 0.000 claims description 34
- 238000004146 energy storage Methods 0.000 claims description 28
- 230000006870 function Effects 0.000 claims description 22
- 210000002569 neuron Anatomy 0.000 claims description 12
- 238000003860 storage Methods 0.000 claims description 8
- 238000005286 illumination Methods 0.000 claims description 7
- 238000005070 sampling Methods 0.000 claims description 7
- 238000004458 analytical method Methods 0.000 claims description 6
- 230000008569 process Effects 0.000 claims description 5
- 238000004590 computer program Methods 0.000 claims description 4
- 230000003993 interaction Effects 0.000 description 7
- 238000012937 correction Methods 0.000 description 6
- 230000007246 mechanism Effects 0.000 description 5
- 238000010586 diagram Methods 0.000 description 4
- 238000013178 mathematical model Methods 0.000 description 4
- 238000011160 research Methods 0.000 description 3
- 238000012546 transfer Methods 0.000 description 3
- 230000003044 adaptive effect Effects 0.000 description 2
- 230000005540 biological transmission Effects 0.000 description 2
- 238000010276 construction Methods 0.000 description 2
- 230000007547 defect Effects 0.000 description 2
- 238000013461 design Methods 0.000 description 2
- 230000006872 improvement Effects 0.000 description 2
- 238000012986 modification Methods 0.000 description 2
- 230000004048 modification Effects 0.000 description 2
- 238000005457 optimization Methods 0.000 description 2
- 238000013473 artificial intelligence Methods 0.000 description 1
- 230000009286 beneficial effect Effects 0.000 description 1
- 230000008878 coupling Effects 0.000 description 1
- 238000010168 coupling process Methods 0.000 description 1
- 238000005859 coupling reaction Methods 0.000 description 1
- 230000005611 electricity Effects 0.000 description 1
- 238000005338 heat storage Methods 0.000 description 1
- 238000004519 manufacturing process Methods 0.000 description 1
- 238000012544 monitoring process Methods 0.000 description 1
- 230000001537 neural effect Effects 0.000 description 1
- 238000012545 processing Methods 0.000 description 1
- 238000011084 recovery Methods 0.000 description 1
Classifications
-
- G—PHYSICS
- G06—COMPUTING; CALCULATING OR COUNTING
- G06F—ELECTRIC DIGITAL DATA PROCESSING
- G06F30/00—Computer-aided design [CAD]
- G06F30/20—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
- G06N3/0464—Convolutional networks [CNN, ConvNet]
-
- G—PHYSICS
- G06—COMPUTING; CALCULATING OR COUNTING
- G06N—COMPUTING ARRANGEMENTS BASED ON SPECIFIC COMPUTATIONAL MODELS
- G06N3/00—Computing arrangements based on biological models
- G06N3/02—Neural networks
- G06N3/08—Learning methods
- G06N3/084—Backpropagation, e.g. using gradient descent
-
- G—PHYSICS
- G06—COMPUTING; CALCULATING OR COUNTING
- G06Q—INFORMATION AND COMMUNICATION TECHNOLOGY [ICT] SPECIALLY ADAPTED FOR ADMINISTRATIVE, COMMERCIAL, FINANCIAL, MANAGERIAL OR SUPERVISORY PURPOSES; SYSTEMS OR METHODS SPECIALLY ADAPTED FOR ADMINISTRATIVE, COMMERCIAL, FINANCIAL, MANAGERIAL OR SUPERVISORY PURPOSES, NOT OTHERWISE PROVIDED FOR
- G06Q50/00—Information and communication technology [ICT] specially adapted for implementation of business processes of specific business sectors, e.g. utilities or tourism
- G06Q50/06—Energy or water supply
-
- G—PHYSICS
- G06—COMPUTING; CALCULATING OR COUNTING
- G06F—ELECTRIC DIGITAL DATA PROCESSING
- G06F2111/00—Details relating to CAD techniques
- G06F2111/10—Numerical modelling
Landscapes
- Engineering & Computer Science (AREA)
- Physics & Mathematics (AREA)
- Theoretical Computer Science (AREA)
- Health & Medical Sciences (AREA)
- Evolutionary Computation (AREA)
- General Physics & Mathematics (AREA)
- Software Systems (AREA)
- Artificial Intelligence (AREA)
- General Health & Medical Sciences (AREA)
- General Engineering & Computer Science (AREA)
- Business, Economics & Management (AREA)
- Life Sciences & Earth Sciences (AREA)
- Economics (AREA)
- Mathematical Physics (AREA)
- Biomedical Technology (AREA)
- Biophysics (AREA)
- Computational Linguistics (AREA)
- Data Mining & Analysis (AREA)
- Computing Systems (AREA)
- Molecular Biology (AREA)
- Geometry (AREA)
- Computer Hardware Design (AREA)
- Medical Informatics (AREA)
- Computer Vision & Pattern Recognition (AREA)
- Public Health (AREA)
- Water Supply & Treatment (AREA)
- Human Resources & Organizations (AREA)
- Marketing (AREA)
- Primary Health Care (AREA)
- Strategic Management (AREA)
- Tourism & Hospitality (AREA)
- General Business, Economics & Management (AREA)
- Supply And Distribution Of Alternating Current (AREA)
Abstract
The invention provides a comprehensive energy system simulation method and system based on a digital twin model, wherein the scheme comprises the following steps: acquiring historical data of each energy device of the comprehensive energy system; training the deep learning model by taking the historical data as an initial sample set to obtain a data model fitting each comprehensive energy device; based on a digital twin technology, periodically acquiring real-time parameters of all comprehensive energy equipment, and adaptively growing an initial sample set based on the acquired real-time parameters; performing secondary training on the deep learning model by using the increased sample set to obtain a digital twin data model corresponding to each energy device; and the simulation of the comprehensive energy system is realized based on the digital twin data model corresponding to each energy device.
Description
Technical Field
The invention belongs to the technical field of comprehensive energy system simulation, and particularly relates to a comprehensive energy system simulation method and system based on a digital twin model.
Background
The statements in this section merely provide background information related to the present disclosure and may not necessarily constitute prior art.
The comprehensive energy system taking the electric power as the core comprises various energy production, transmission, storage and consumption networks, has complex structure, various devices and complex technology, and has typical nonlinear random characteristics and multi-scale dynamic characteristics. However, the conventional mathematical model has difficulty in meeting the requirements of planning design, monitoring analysis and operation optimization of the ies (I ntegrated energy system), and further improvement of the modeling accuracy of the energy equipment in the ies is required; the high-precision modeling of the I ES energy equipment can be realized by analyzing mass system data through an artificial intelligent algorithm, and the simulation model can be continuously optimized by collecting real-time data of the physical equipment. The artificial intelligence algorithm is an important supporting technology for constructing the digital twin model of the I ES, and provides a digital and intelligent foundation for accurately constructing the digital twin simulation model of the I ES energy equipment.
The inventor finds that most of the existing methods are I ES energy equipment mathematical modeling methods with lower accuracy, only the capacity configuration, the optimal scheduling and other researches of a steady-state system can be performed, and the time scale is longer and the error is larger; in addition, the neural network modeling method mentioned by the existing method can only realize the construction of a data model, and does not consider the realization of real-time optimization and updating of the data model through the adaptive growth of a sample set so as to achieve the real-time data interaction of a physical system and a digital twin model.
Disclosure of Invention
In order to overcome the defects of the prior art, the invention provides a comprehensive energy system simulation method and system based on a digital twin model, wherein the scheme adopts a CNN-BP neural network algorithm to carry out data modeling on energy equipment of an I ES, and realizes the self-adaptive growth of a sample set through the real-time data interaction with physical equipment, so as to further optimize the data model of the energy equipment, realize the establishment of the digital twin model of the I ES, effectively improve the modeling precision of the digital model, and further improve the simulation accuracy of the comprehensive energy system.
According to a first aspect of the embodiment of the present invention, there is provided a comprehensive energy system simulation method based on a digital twin model, including:
acquiring historical data of each energy device of the comprehensive energy system, wherein the historical data comprise illumination intensity and temperature corresponding to photovoltaic devices, wind speed corresponding to fans, inlet temperature, inlet pressure and inlet flow of compressors corresponding to gas turbines, and energy storage state and energy storage capacity corresponding to energy storage devices;
training the deep learning model by taking the historical data as an initial sample set to obtain a data model fitting each comprehensive energy device;
based on a digital twin technology, periodically acquiring real-time parameters of all comprehensive energy equipment, and adaptively growing an initial sample set based on the acquired real-time parameters;
performing secondary training on the deep learning model by using the increased sample set to obtain a digital twin data model corresponding to each energy device; and the simulation of the comprehensive energy system is realized based on the digital twin data model corresponding to each energy device.
Further, the deep learning model adopts a CNN-BP neural network, and in the training process of the CNN-BP neural network, the obtained historical data of each energy device of the comprehensive energy system is used as an initial training set in advance for training, and after training is completed, a data model which is subjected to preliminary training is stored; acquiring real-time data of each energy device of the comprehensive energy system, which are acquired according to a preset sampling interval within a certain period of time, adaptively increasing an initial training set, and performing secondary training on the stored model subjected to primary training by using the increased training set.
Further, the CNN-BP neural network comprises an input layer for receiving a plurality of attribute parameters of the energy equipment, wherein the attribute parameters in the input layer are sequentially input into neurons of a first hidden layer and a second hidden layer, and the characteristics processed by the neurons are subjected to output layer to obtain a plurality of output results; the output result is the size of the active power and the reactive power output by the energy equipment.
Furthermore, the training of the CNN-BP neural network adopts a traposs function as a training function and a learngdm function as a learning function.
Further, for each energy device in the integrated energy system, an independent data model and a digital twin data model need to be trained.
Further, the energy devices in the integrated energy system include, but are not limited to, photovoltaic devices, fans, gas turbines, and energy storage devices.
A second aspect of the present invention provides a digital twin model-based integrated energy system simulation system, comprising:
the system comprises a historical data acquisition unit, a power supply unit and an energy storage unit, wherein the historical data acquisition unit is used for acquiring historical data of each energy device of the comprehensive energy system, wherein the historical data comprise illumination intensity and temperature corresponding to photovoltaic devices, wind speed corresponding to fans, inlet temperature, inlet pressure and inlet flow of compressors corresponding to gas turbines, and energy storage state and energy storage capacity corresponding to energy storage devices;
the data model training unit is used for training the deep learning model by taking the historical data as an initial sample set to obtain a data model fitting each comprehensive energy device;
the sample set self-adaptive growth unit is used for periodically acquiring real-time parameters of all the comprehensive energy devices based on a digital twin technology and carrying out self-adaptive growth on an initial sample set based on the acquired real-time parameters;
the model training and simulation analysis unit is used for carrying out secondary training on the deep learning model by utilizing the increased sample set to obtain a digital twin data model corresponding to each energy device; and the simulation of the comprehensive energy system is realized based on the digital twin data model corresponding to each energy device.
According to a third aspect of the disclosed embodiments, there is provided an electronic device, including a memory, a processor and a computer program running on the memory, where the processor implements the integrated energy system simulation method based on a digital twin model when executing the program.
According to a fourth aspect of embodiments of the present disclosure, there is provided a non-transitory computer readable storage medium having stored thereon a computer program which, when executed by a processor, implements the method of integrated energy system simulation based on a digital twin model.
The one or more of the above technical solutions have the following beneficial effects:
(1) The invention provides a comprehensive energy system simulation method and system based on a digital twin model, wherein the scheme adopts a CNN-BP neural network algorithm to carry out data modeling on energy equipment of an IES, and realizes the self-adaptive growth of a sample set through real-time data interaction with physical equipment, so as to further optimize the data model of the energy equipment, realize the establishment of the IES digital twin model, effectively improve the modeling precision of the digital model and further improve the simulation accuracy of the comprehensive energy system.
(2) According to the invention, the historical data (initial sample set) of the IES energy equipment is trained through the CNN-BP neural network, a data model fitting the physical equipment is built, and the problems of low accuracy of the mathematical model of the energy equipment and difficult modeling of the mechanism model in the comprehensive energy system are solved; meanwhile, the self-adaptive growth of the sample set is realized through the real-time data interaction of the data model and the physical equipment, the data model of the energy equipment is further optimized, the establishment of the digital twin model of the IES energy equipment is realized, the model precision is further improved, and the application range and the research depth of the model in the IES are improved.
Additional aspects of the invention will be set forth in part in the description which follows and, in part, will be obvious from the description, or may be learned by practice of the invention.
Drawings
The accompanying drawings, which are included to provide a further understanding 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 the invention.
FIG. 1 is a schematic diagram of a modeling framework of a digital twin model-based integrated energy system simulation method according to an embodiment of the present invention;
FIG. 2 is a schematic diagram of a CNN-BP (Convolutional Neural Network-back propagation) neural network with two hidden layers according to an embodiment of the present invention;
FIG. 3 is a training flow chart of a CNN-BP neural network according to an embodiment of the invention;
fig. 4 is a schematic diagram of a digital twin modeling flow of an IES energy device according to an embodiment of the present invention.
Detailed Description
It should be noted that the following detailed description is exemplary and is intended to provide further explanation of the invention. Unless defined otherwise, all technical and scientific terms used herein have the same meaning as commonly understood by one of ordinary skill in the art to which this invention belongs.
It is noted that the terminology used herein is for the purpose of describing particular embodiments only and is not intended to be limiting of exemplary embodiments according to the present invention.
Embodiments of the invention and features of the embodiments may be combined with each other without conflict.
Example 1
The embodiment provides a comprehensive energy system simulation method based on a digital twin model.
A comprehensive energy system simulation method based on a digital twin model comprises the following steps:
acquiring historical data of each energy device of the comprehensive energy system, wherein the historical data comprise illumination intensity and temperature corresponding to photovoltaic devices, wind speed corresponding to fans, inlet temperature, inlet pressure and inlet flow of compressors corresponding to gas turbines, and energy storage state and energy storage capacity corresponding to energy storage devices;
training the deep learning model by taking the historical data as an initial sample set to obtain a data model fitting each comprehensive energy device;
based on a digital twin technology, periodically acquiring real-time parameters of all comprehensive energy equipment, and adaptively growing an initial sample set based on the acquired real-time parameters;
performing secondary training on the deep learning model by using the increased sample set to obtain a digital twin data model corresponding to each energy device; and the simulation of the comprehensive energy system is realized based on the digital twin data model corresponding to each energy device.
In specific real time, the deep learning model adopts a CNN-BP neural network, and in the training process of the CNN-BP neural network, the obtained historical data of each energy device of the comprehensive energy system is used as an initial training set in advance for training, and after training is completed, a data model for primarily completing training is stored; acquiring real-time data of each energy device of the comprehensive energy system, which are acquired according to a preset sampling interval within a certain period of time, adaptively increasing an initial training set, and performing secondary training on the stored model subjected to primary training by using the increased training set.
The CNN-BP neural network comprises an input layer for receiving a plurality of attribute parameters of the energy equipment, wherein the attribute parameters in the input layer are sequentially input into neurons of a first hidden layer and a second hidden layer, and the characteristics processed by the neurons obtain a plurality of output results through an output layer; the output result is the size of the active power and the reactive power output by the energy equipment.
The training of the CNN-BP neural network adopts a traposs function as a training function and a learnddm function as a learning function.
In a specific implementation, for each energy device in the integrated energy system, an independent data model and a digital twin data model need to be trained; the energy devices in the integrated energy system include, but are not limited to, photovoltaic devices, fans, gas turbines, and energy storage devices.
For easy understanding, the following detailed description of the embodiments will be given with reference to the accompanying drawings:
the comprehensive energy system (Integrated energy system, IES) is a coupling system integrating source network charge storage and containing multiple energy sources such as electricity, heat, gas and the like, the traditional mathematical modeling method has low simulation precision and rough model, and has no application value in actual engineering; the mechanism model with higher simulation precision has a plurality of parameters, the modeling complexity is higher, the mechanism model can not interact with the physical equipment in the simulation operation, the real-time updating of the model parameters is realized, and the simulation precision can be gradually reduced along with the increase of the operation time. Therefore, the embodiment adopts a CNN-BP neural network algorithm to carry out data modeling on the energy equipment of the IES, and realizes the self-adaptive growth of the sample set through the real-time data interaction with the physical equipment, so as to further optimize the data model of the energy equipment and realize the establishment of the digital twin model of the IES.
The IES energy devices are of a wide variety and include power system distributed energy devices such as Photovoltaic (PV), wind Turbine (WT); thermodynamic system devices such as Gas Turbines (GT), heat recovery boilers (HR), gas Boilers (GB), electric Boilers (EB); refrigerating equipment such as an air source heat pump (Air Source Heat Pump, AP), an Electric refrigerator (EC); storage battery, heat storage tank and ice cold-storage etc. energy storage equipment. The IES energy equipment belongs to different system types, and various energies are mutually coupled, so that in order to reduce modeling difficulty, a mathematical modeling method is generally adopted, and a simulation model established by the method is simple in structure and low in precision and can only be simply researched and analyzed. In order to solve the defects of low accuracy of an IES energy equipment mathematical model and difficult modeling of a mechanism model, the embodiment provides a comprehensive energy system simulation method based on a digital twin model, and the scheme adopts a comprehensive energy system digital twin modeling strategy considering the self-adaptive growth of a sample set, and specifically comprises the following steps:
firstly, determining initial parameters of a CNN-BP neural network; and training historical data (initial sample set) of the IES energy equipment through a CNN-BP neural network, and constructing a data model fitting the physical equipment.
The composition structure of the CNN-BP neural network is generally divided into three parts, namely an input layer, an hidden layer and an output layer, wherein the input layer and the output layer are respectively one layer, and the hidden layer can be arranged into one layer or multiple layers according to actual requirements.
Fig. 2 is a diagram of a CNN-BP neural network with two hidden layers according to the embodiment. First, M input signals, denoted as X, are provided to an input layer 1 ，X 2 ，...，X m The method comprises the steps of carrying out a first treatment on the surface of the Then M signals are respectively and sequentially transmitted into I neurons in the hidden layer I and j neurons in the hidden layer II, and are respectively marked as I 1 ，I 2 ，...，I i And J 1 ，J 2 ，...，J j The method comprises the steps of carrying out a first treatment on the surface of the Finally, through iterative training, N output results are obtained at the output layer, which are Y respectively 1 ，Y 2 ，...，Y n 。
In order to realize the adaptive growth of the sample set, the scheme of the embodiment converts the data model into a digital twin model, so that the physical equipment performs real-time data interaction with the data model, and the input signal of the CNN-BP neural network input layer is changed into M+T 0 X n, where T 0 Representing the sampling interval, n represents the number of samples in between model updates. Through the self-adaptive growth of the sample set, the data model of the energy equipment is further optimized and updated, the construction of the digital twin model of the I ES energy equipment is realized, and the specific flow is as follows:
step 1: through the data interface of the sensor, according to the set sampling time T 0 The method comprises the steps of collecting the data of the I ES energy equipment in real time, transmitting the equipment information through network transmission and storing the equipment information into a database;
step 2: reading historical data of the I ES energy equipment in the database, and taking the historical data as an initial sample set;
step 3: initial parameters of the CNN-BP neural network are set:
(1) input and output parameters: different energy devices have different input parameters, and the input parameters of the photovoltaic devices include illumination intensity, temperature and the like; the fan input parameters include wind speed and the like; the input parameters of the gas turbine include the inlet temperature of the gas compressor, the inlet pressure of the gas compressor, the inlet flow of the gas compressor and the like; the input parameters of the energy storage equipment are energy storage state, energy storage capacity and the like. For each energy device of the IES, the output parameters are the active power and the reactive power.
(2) Operating parameters: training error is 0.0001, learning rate is 0.01, and maximum iteration number is 500;
(3) hidden layer parameters: the number of hidden layers is 2, and the number of neurons in the hidden layers is 6;
(4) transfer function: the transfer function of the hidden layer node selects a tan function, and the transfer function of the output layer node selects a purelin function;
(5) training function: selecting a trapeziss algorithm as a training function;
(6) learning function: the learngdm function is selected as the learning function.
Step 4: assume that all input samples of CNN-BP neural network are x= [ X 1 ,X 2 ,...,X M ]Corresponding training history data sample set and output value of X k ＝[x k1 ,x k2 ,...,x km ]And Y k ＝[y k1 ,y k2 ,...,y kn ] T The desired output is d k ＝[d k1 ,d k2 ,...,d kn ] T The neuron input is u, the neuron output is v, and the deep analysis on the signal which is transmitted forward by the CNN-BP neural network can obtain:
step 5: the error signal e can be calculated by the analysis of step 4 kn Sum of errors E (n):
e ky (n)＝d ky (n)-y ky (n)
step 6: according to the error signal and the error sum obtained in the step 5, the CNN-BP neural network carries out reverse conduction and weight correction:
step 7: according to the delta learning rule, the correction value of the weight is as follows:
where eta represents the step size of learning,for equivalent representation under delta learning rule, expressed as
Step 8: the correction result of the hidden layer to output layer weight can be obtained as follows:
w jy (n+1)＝w jy (n)+Δw jy (n)
step 9: after obtaining the correction weights from the hidden layers to the output layers, the next step needs to continue to calculate the correction weights w between the hidden layers ij The method comprises the steps of carrying out a first treatment on the surface of the And a correction weight w between the input layer and the hidden layer xi ：
Step 10: from the steps ofAnd 8 and 9, obtaining w after correcting the CNN-BP neural network ij (n+1) and w xi And (n+1), recalculating the neuron output and the final total output of each layer according to the corrected weight, repeating the steps until the result error is within a reasonable range, finishing training of the single energy equipment data model, and storing the data model subjected to preliminary training.
Step 11: reading real-time data of a single energy device in a database, adaptively increasing a sample set, and inputting a sample X= [ X ] 1 ,X 2 ,...,X M ,...,X Mx ]Wherein mx=m+t 0 X n, wherein T 0 Representing the sampling interval, n represents the number of samples in between model updates.
Step 12: and re-inputting the sample set with the self-adaptive growth into the CNN-BP neural network for the next iteration, so as to update and optimize the data model and realize digital twin modeling of single I ES energy equipment. The training flow of the CNN-BP neural network is shown in figure 3.
Step 13: and selecting historical data of the next I ES energy equipment as an initial sample, and repeating the steps 3 to 12 to finish digital twin modeling of the I ES energy equipment.
Step 14: and similarly, digital twin modeling of different energy devices in the I ES is realized. The digital twin modeling flow of the IES energy device is shown in figure 4.
According to the invention, the historical data (initial sample set) of the I ES energy equipment is trained through the CNN-BP neural network, a data model fitting the physical equipment is built, and the problems of low accuracy of the mathematical model of the energy equipment and difficult modeling of the mechanism model in the comprehensive energy system are solved; in addition, the invention realizes the self-adaptive growth of the sample set through the real-time data interaction of the data model and the physical equipment, further optimizes the data model of the energy equipment, realizes the establishment of the digital twin model of the I ES energy equipment, further improves the model precision, and expands the application range and the research depth of the digital twin model in the I ES.
Example two
The embodiment provides a comprehensive energy system simulation system based on a digital twin model.
A digital twin model-based integrated energy system simulation system, comprising:
the system comprises a historical data acquisition unit, a power supply unit and an energy storage unit, wherein the historical data acquisition unit is used for acquiring historical data of each energy device of the comprehensive energy system, wherein the historical data comprise illumination intensity and temperature corresponding to photovoltaic devices, wind speed corresponding to fans, inlet temperature, inlet pressure and inlet flow of compressors corresponding to gas turbines, and energy storage state and energy storage capacity corresponding to energy storage devices;
the data model training unit is used for training the deep learning model by taking the historical data as an initial sample set to obtain a data model fitting each comprehensive energy device;
the sample set self-adaptive growth unit is used for periodically acquiring real-time parameters of all the comprehensive energy devices based on a digital twin technology and carrying out self-adaptive growth on an initial sample set based on the acquired real-time parameters;
the model training and simulation analysis unit is used for carrying out secondary training on the deep learning model by utilizing the increased sample set to obtain a digital twin data model corresponding to each energy device; and the simulation of the comprehensive energy system is realized based on the digital twin data model corresponding to each energy device.
It should be noted that, each module in the embodiment corresponds to each step in the first embodiment one to one, and the implementation process is the same, which is not described here.
In further embodiments, there is also provided:
an electronic device comprising a memory and a processor and computer instructions stored on the memory and running on the processor, which when executed by the processor, perform the method of embodiment one. For brevity, the description is omitted here.
It should be understood that in this embodiment, the processor may be a central processing unit CPU, and the processor may also be other general purpose processors, digital signal processors DSP, application specific integrated circuits ASIC, off-the-shelf programmable gate array FPGA or other programmable logic device, discrete gate or transistor logic devices, discrete hardware components, or the like. A general purpose processor may be a microprocessor or the processor may be any conventional processor or the like.
The memory may include read only memory and random access memory and provide instructions and data to the processor, and a portion of the memory may also include non-volatile random access memory. For example, the memory may also store information of the device type.
A computer readable storage medium storing computer instructions which, when executed by a processor, perform the method of embodiment one.
The method in the first embodiment may be directly implemented as a hardware processor executing or implemented by a combination of hardware and software modules in the processor. The software modules may be located in a random access memory, flash memory, read only memory, programmable read only memory, or electrically erasable programmable memory, registers, etc. as well known in the art. The storage medium is located in a memory, and the processor reads the information in the memory and, in combination with its hardware, performs the steps of the above method. To avoid repetition, a detailed description is not provided herein.
Those of ordinary skill in the art will appreciate that the elements of the various examples described in connection with the present embodiments, i.e., the algorithm steps, can be implemented as electronic hardware or combinations of computer software and electronic hardware. Whether such functionality is implemented as hardware or software depends upon the particular application and design constraints imposed on the solution. Skilled artisans may implement the described functionality in varying ways for each particular application, but such implementation decisions should not be interpreted as causing a departure from the scope of the present disclosure.
The comprehensive energy system simulation method and system based on the digital twin model provided by the embodiment can be realized, and has wide application prospect.
The foregoing description of the preferred embodiments of the present disclosure is provided only and not intended to limit the disclosure so that various modifications and changes may be made to the present disclosure by those skilled in the art. Any modification, equivalent replacement, improvement, etc. made within the spirit and principle of the present disclosure should be included in the protection scope of the present disclosure.
Claims (10)
1. The comprehensive energy system simulation method based on the digital twin model is characterized by comprising the following steps of:
acquiring historical data of each energy device of the comprehensive energy system, wherein the historical data comprise illumination intensity and temperature corresponding to photovoltaic devices, wind speed corresponding to fans, inlet temperature, inlet pressure and inlet flow of compressors corresponding to gas turbines, and energy storage state and energy storage capacity corresponding to energy storage devices;
training the deep learning model by taking the historical data as an initial sample set to obtain a data model fitting each comprehensive energy device;
based on a digital twin technology, periodically acquiring real-time parameters of all comprehensive energy equipment, and adaptively growing an initial sample set based on the acquired real-time parameters;
performing secondary training on the deep learning model by using the increased sample set to obtain a digital twin data model corresponding to each energy device; and the simulation of the comprehensive energy system is realized based on the digital twin data model corresponding to each energy device.
2. The comprehensive energy system simulation method based on the digital twin model as claimed in claim 1, wherein the deep learning model adopts a CNN-BP neural network, and in the training process of the CNN-BP neural network, the obtained historical data of each energy device of the comprehensive energy system is used as an initial training set for training, and after the training is completed, a data model for primarily completing the training is stored; acquiring real-time data of each energy device of the comprehensive energy system, which are acquired according to a preset sampling interval within a certain period of time, adaptively increasing an initial training set, and performing secondary training on the stored model subjected to primary training by using the increased training set.
3. The comprehensive energy system simulation method based on the digital twin model as claimed in claim 2, wherein the CNN-BP neural network comprises an input layer for receiving a plurality of attribute parameters of the energy equipment, wherein the plurality of attribute parameters in the input layer are sequentially input into neurons of a first hidden layer and a second hidden layer, and the characteristics processed by the neurons obtain a plurality of output results through an output layer; the output result is the size of the active power and the reactive power output by the energy equipment.
4. The method for simulating a comprehensive energy system based on a digital twin model according to claim 2, wherein the training of the CNN-BP neural network adopts a trainos function as a training function and a learnddm function as a learning function.
5. The method for simulating a comprehensive energy system based on a digital twin model according to claim 1, wherein for each energy device in the comprehensive energy system, an independent data model and a digital twin data model are trained.
6. The method for simulating a comprehensive energy system based on a digital twin model according to claim 1, wherein the energy devices in the comprehensive energy system include, but are not limited to, photovoltaic devices, fans, gas turbines and energy storage devices.
7. A digital twin model-based integrated energy system simulation system, comprising:
the system comprises a historical data acquisition unit, a power supply unit and an energy storage unit, wherein the historical data acquisition unit is used for acquiring historical data of each energy device of the comprehensive energy system, wherein the historical data comprise illumination intensity and temperature corresponding to photovoltaic devices, wind speed corresponding to fans, inlet temperature, inlet pressure and inlet flow of compressors corresponding to gas turbines, and energy storage state and energy storage capacity corresponding to energy storage devices;
the data model training unit is used for training the deep learning model by taking the historical data as an initial sample set to obtain a data model fitting each comprehensive energy device;
the sample set self-adaptive growth unit is used for periodically acquiring real-time parameters of all the comprehensive energy devices based on a digital twin technology and carrying out self-adaptive growth on an initial sample set based on the acquired real-time parameters;
the model training and simulation analysis unit is used for carrying out secondary training on the deep learning model by utilizing the increased sample set to obtain a digital twin data model corresponding to each energy device; and the simulation of the comprehensive energy system is realized based on the digital twin data model corresponding to each energy device.
8. The comprehensive energy system simulation system based on the digital twin model as claimed in claim 7, wherein the deep learning model adopts a CNN-BP neural network, and in the training process of the CNN-BP neural network, the obtained historical data of each energy device of the comprehensive energy system is used as an initial training set for training, and after the training is completed, a data model for primarily completing the training is stored; acquiring real-time data of each energy device of the comprehensive energy system, which are acquired according to a preset sampling interval within a certain period of time, adaptively increasing an initial training set, and performing secondary training on the stored model subjected to primary training by using the increased training set.
9. An electronic device comprising a memory, a processor and a computer program stored for execution on the memory, wherein the processor, when executing the program, implements a digital twin model based integrated energy system simulation method as claimed in any one of claims 1 to 6.
10. A non-transitory computer readable storage medium having stored thereon a computer program, which when executed by a processor implements a digital twin model based integrated energy system simulation method according to any of claims 1-6.
Priority Applications (1)
| Application Number | Priority Date | Filing Date | Title |
|---|---|---|---|
| CN202310572283.6A CN116522795A (en) | 2023-05-18 | 2023-05-18 | Comprehensive energy system simulation method and system based on digital twin model |
Applications Claiming Priority (1)
| Application Number | Priority Date | Filing Date | Title |
|---|---|---|---|
| CN202310572283.6A CN116522795A (en) | 2023-05-18 | 2023-05-18 | Comprehensive energy system simulation method and system based on digital twin model |
Publications (1)
| Publication Number | Publication Date |
|---|---|
| CN116522795A true CN116522795A (en) | 2023-08-01 |
Family
ID=87399398
Family Applications (1)
| Application Number | Title | Priority Date | Filing Date |
|---|---|---|---|
| CN202310572283.6A Pending CN116522795A (en) | 2023-05-18 | 2023-05-18 | Comprehensive energy system simulation method and system based on digital twin model |
Country Status (1)
| Country | Link |
|---|---|
| CN (1) | CN116522795A (en) |
Cited By (2)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN116757875A (en) * | 2023-08-18 | 2023-09-15 | 国网智能电网研究院有限公司 | Source-charge storage multi-twin body cooperative interaction method, device, equipment and storage medium |
| CN116992779A (en) * | 2023-09-22 | 2023-11-03 | 北京国科恒通数字能源技术有限公司 | Simulation method and system of photovoltaic energy storage system based on digital twin model |
-
2023
- 2023-05-18 CN CN202310572283.6A patent/CN116522795A/en active Pending
Cited By (4)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN116757875A (en) * | 2023-08-18 | 2023-09-15 | 国网智能电网研究院有限公司 | Source-charge storage multi-twin body cooperative interaction method, device, equipment and storage medium |
| CN116757875B (en) * | 2023-08-18 | 2023-10-24 | 国网智能电网研究院有限公司 | Source-charge storage multi-twin body cooperative interaction method, device, equipment and storage medium |
| CN116992779A (en) * | 2023-09-22 | 2023-11-03 | 北京国科恒通数字能源技术有限公司 | Simulation method and system of photovoltaic energy storage system based on digital twin model |
| CN116992779B (en) * | 2023-09-22 | 2024-01-05 | 北京国科恒通数字能源技术有限公司 | Simulation method and system of photovoltaic energy storage system based on digital twin model |
Similar Documents
| Publication | Publication Date | Title |
|---|---|---|
| CN116522795A (en) | Comprehensive energy system simulation method and system based on digital twin model | |
| CN110264012B (en) | Renewable energy power combination prediction method and system based on empirical mode decomposition | |
| CN111754030B (en) | Thermal power generating unit power supply coal consumption optimization method based on HAC and RF-GA | |
| CN109193756B (en) | Scene decoupling dynamic economic dispatching model solving method of wind power access system | |
| CN111144663A (en) | Ultra-short-term wind power prediction method for offshore wind farm considering output fluctuation process | |
| CN116014715A (en) | Digital twinning-based comprehensive energy control method and system | |
| CN113107626A (en) | Combined cycle generator set load prediction method based on multivariable LSTM | |
| CN111915079B (en) | Hybrid KNN wind power prediction method and system | |
| CN114626573A (en) | Load prediction method for optimizing extreme learning machine based on improved multivariate universe algorithm | |
| CN113887141A (en) | Micro-grid group operation strategy evolution method based on federal learning | |
| CN115995810A (en) | Wind power prediction method and system considering weather fluctuation self-adaptive matching | |
| CN111897240A (en) | Simulation method and system based on nuclear power system operation | |
| CN113435595B (en) | Two-stage optimization method for network parameters of extreme learning machine based on natural evolution strategy | |
| CN111401659A (en) | Ultra-short-term or short-term photovoltaic power generation power prediction method based on case reasoning | |
| CN110598947A (en) | Load prediction method based on improved cuckoo-neural network algorithm | |
| CN112052987B (en) | Comprehensive energy system optimization planning method and system considering wind power | |
| CN110276478B (en) | Short-term wind power prediction method based on segmented ant colony algorithm optimization SVM | |
| CN116862077A (en) | Electric heating operation cost prediction method and medium based on multi-mode combination model | |
| CN109359671B (en) | Classification intelligent extraction method for hydropower station reservoir dispatching rules | |
| CN117057523A (en) | Power distribution network energy storage double-layer planning method based on load prediction | |
| CN116360266A (en) | Pig house temperature energy-saving control method based on multi-objective optimization algorithm | |
| CN103336829B (en) | query optimization method based on simulated annealing algorithm | |
| CN115712976A (en) | Heat energy and electric load optimization method based on multi-element heat supply unit and related equipment | |
| CN112487723B (en) | Multi-parameter-based optimized design method for reclaimed water heat source pump system | |
| Sun et al. | Optimization Design of Wind Turbine Blade Based on an Improved Particle Swarm Optimization Algorithm Combined with Non‐Gaussian Distribution |
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 |