Green energy digital twin simulation method, system, medium and electronic device

Abstract

The application provides a green energy digital twin simulation method, system, medium and electronic equipment, and the method comprises the following steps: constructing a green energy digital twin static model subsystem; the green energy digital twin static model subsystem is based on a physical model of a physical device and uses a builder mode as a construction method; a green energy digital twin dynamic model subsystem is constructed, the green energy digital twin dynamic model subsystem takes a current action value of an intelligent agent as input, and generates next state information and a reward value as output. The green energy digital twin simulation method, system, medium and electronic equipment can effectively support the research of artificial intelligence operation and control optimization technology, AI prediction and early warning and diagnosis technology.

Description

Technical Field

[0001] This invention relates to the technical field of digital twin simulation, and in particular to a green energy digital twin simulation method, system, medium, and electronic device. Background Technology

[0002] Green energy systems are typically integrated systems with multiple energy coupling and complementarity, involving numerous controllable intelligent devices and high complexity. Due to the differences in the development of each subsystem, they are usually planned and designed separately, resulting in problems such as unclear multi-energy synergy and integration mechanisms, insufficient efficiency of integrated operation and control strategies, and poor system dynamic adaptive capabilities, leading to poor system coordination and low energy utilization. Summary of the Invention

[0003] In view of the shortcomings of the prior art described above, the purpose of this invention is to provide a green energy digital twin simulation method, system, medium, and electronic device that can effectively support research on artificial intelligence operation and control optimization technology, AI prediction and early warning, and diagnostic technology.

[0004] In a first aspect, the present invention provides a green energy digital twin simulation method, the method comprising the following steps: constructing a green energy digital twin static model subsystem; the green energy digital twin static model subsystem is based on the physical model of the physical equipment and uses the builder mode as the construction method; constructing a green energy digital twin dynamic model subsystem, the green energy digital twin dynamic model subsystem taking the current action value of the agent as input and generating the next state information and reward value as output.

[0005] In one implementation of the first aspect, constructing a green energy digital twin static model subsystem includes the following steps:

[0006] Define the basic physical model of a green energy system; the basic physical model includes a photovoltaic power generation model, an electrolyzer model, an energy storage lithium battery model, a hydrogen storage tank model, and a compressor;

[0007] Based on the basic physical model of physical entities, a component mechanism model is defined; the component mechanism model includes the output power of the photovoltaic power generation model, the hydrogen production flow rate of the electrolyzer model, the state changes of the energy storage lithium battery model, the state changes of the hydrogen storage tank model, and the power of the compressor.

[0008] Based on the basic physical model of the physical entity and the green energy digital twin static model subsystem, the builder pattern is used iteratively to define complex green energy digital twin static model subsystems of various scales required for simulation.

[0009] In one implementation of the first aspect, the output power of the photovoltaic power generation model Where YPV This indicates the power output of the photovoltaic panel under standard test conditions; f PV This indicates the derating factor for photovoltaic panels; This represents the solar radiation incident on the photovoltaic array at the current time step; α represents incident radiation under standard test conditions. P T represents the power temperature coefficient; c T represents the temperature of the photovoltaic array at the current time step; c,STC This indicates the temperature of the photovoltaic array under standard test conditions;

[0010] The hydrogen production flow rate F of the electrolyzer model ele (t)=P ele_total ×η ele / HHV H2 ,in F ele (t) represents the hydrogen flow rate output from the electrolyzer at time t; η represents the power of the electrolyzer at time t; ele HHV represents the efficiency of the electrolyzer. H2 P represents the higher heating value of hydrogen. batt This indicates the real-time charging and discharging power of the battery.

[0011] The state changes of the energy storage lithium battery model Where S batt (t+1) represents the charge of the lithium battery at time t+1, S batt (t) represents the charge of the lithium battery at time t, P batt (t) represents the charging and discharging power of the battery at time t, η batt Indicates charge / discharge efficiency;

[0012] The state changes of the hydrogen storage tank model Where S hydro (t+1) represents the amount of hydrogen stored in the hydrogen storage tank at time t+1, S hydro (t) represents the amount of hydrogen stored in the hydrogen storage tank at time t; F hydro (t) represents the hydrogen charging / discharging rate of the hydrogen storage tank at time t; η hydro For real-time hydrogen charging and discharging efficiency;

[0013] The power of the compressor in T is the specific heat capacity of hydrogen. comp η is the gas temperature at the compressor inlet. cp Where is the compressor efficiency, K is the specific heat ratio of hydrogen under standard conditions, P1 and P2 are the compressor inlet and outlet pressures respectively, and W is... comp This indicates the gas flow rate at the compressor outlet.

[0014] In one implementation of the first aspect, constructing a green energy digital twin dynamic model subsystem includes the following steps:

[0015] The green energy digital twin dynamic model subsystem is defined to include a next state generation module, an environmental variable iteration module, a state observation module, and a reward generation module;

[0016] During the operation of the green energy digital twin simulation system, the state-space variables are correlated with the system's state variables;

[0017] Based on the agent's current state, select the corresponding action in the action space, constrain each action, and input the final constrained action value as the power setpoint of each component into each physical model;

[0018] The system obtains auxiliary variables that are unrelated to the sensing data of physical entities within the system based on the environmental variable iteration module;

[0019] The state observation module selects feature values ​​from the auxiliary variables and the next state information to characterize the state variables that the agent can observe;

[0020] The next state generation module outputs the next state information based on the current action value, the current environment state, and the auxiliary variables.

[0021] The reward generation module simulates and outputs the corresponding reward value based on the current action value, the auxiliary variable, and the next state information;

[0022] The actions are constrained to conform to their actual physical meaning;

[0023] For physical entities or systems with unknown mechanisms, a corresponding dynamic operating model is obtained by training using a data-driven approach.

[0024] To address the external environmental drivers of a green energy digital twin simulation system, a data-driven approach is used to train and obtain dynamic prediction values.

[0025] In one implementation of the first aspect, the step of the reward generation module simulating and outputting a corresponding reward value based on the current action value, the auxiliary variable, and the next state information includes the following steps:

[0026] Determine the hydrogen flow path;

[0027] Calculate the hydrogen float value H2 at time t. fluc ;

[0028] Calculate reward value

[0029] In one implementation of the first aspect, the hydrogen float value H2 at time t is calculated.fluc include:

[0030] in, Target represents the target hydrogen load, F ele (t) represents the hydrogen production flow rate of the electrolyzer model.

[0031] In one implementation of the first aspect, the next state generation module automatically iteratively calculates and generates next state information based on physical model mechanisms and a data-based temporal deep neural network.

[0032] Secondly, the present invention provides a green energy digital twin simulation system, the system comprising a first building module and a second building module;

[0033] The first construction module is used to construct a green energy digital twin static model subsystem; the green energy digital twin static model subsystem is based on the physical model of the physical equipment and uses the builder mode as the construction method;

[0034] The second building module is used to build a green energy digital twin dynamic model subsystem. The green energy digital twin dynamic model subsystem takes the current action value of the agent as input and generates the next state information and reward value as output.

[0035] Thirdly, the present invention provides a storage medium on which a computer program is stored, which, when executed by a processor, implements the above-described green energy digital twin simulation method.

[0036] Fourthly, the present invention provides an electronic device, comprising: a processor and a memory;

[0037] The memory is used to store computer programs;

[0038] The processor is used to execute the computer program stored in the memory, so that the electronic device performs the green energy digital twin simulation method described above.

[0039] As described above, the green energy digital twin simulation method, system, medium, and electronic device of the present invention have the following beneficial effects:

[0040] (1) For the first time, a green energy digital twin simulation system that can be used for deep reinforcement learning is defined in a scalable manner, enabling the training of deep reinforcement learning control optimization strategies to cope with complex and ever-changing real-world situations;

[0041] (2) A green energy digital twin static model subsystem based on the builder pattern is proposed. By using the builder pattern, the green energy system to be simulated can be flexibly customized.

[0042] (3) A mechanism and data-driven green energy digital twin dynamic model subsystem was proposed. Based on the mechanism model of the physical device, the dynamic working model of the physical device was trained by historical data, which can better meet the simulation requirements of various real scenarios.

[0043] (4) The green energy digital twin simulation system can interact with different intelligent agents to simulate and compare different simulation effects under the current situation, which greatly improves the rationality, effectiveness and safety of operation in the intelligent control optimization scenario of green energy system. Attached Figure Description

[0044] Figure 1 The flowchart shown is an embodiment of the green energy digital twin simulation method of the present invention;

[0045] Figure 2 The diagram shown is a structural schematic of the basic physical model of the present invention in one embodiment.

[0046] Figure 3 The diagram shown is a structural schematic of the green energy digital twin dynamic model subsystem of the present invention in one embodiment;

[0047] Figure 4 The diagram shows the hydrogen flow path in one embodiment of the present invention;

[0048] Figure 5 The diagram shown is a structural schematic of the green energy digital twin simulation system of the present invention in one embodiment;

[0049] Figure 6 The diagram shown is a structural schematic of an embodiment of the electronic device of the present invention. Detailed Implementation

[0050] The following specific examples illustrate the implementation of the present invention. Those skilled in the art can easily understand other advantages and effects of the present invention from the content disclosed in this specification. The present invention can also be implemented or applied through other different specific embodiments, and various details in this specification can also be modified or changed based on different viewpoints and applications without departing from the spirit of the present invention. It should be noted that, unless otherwise specified, the following embodiments and features described therein can be combined with each other.

[0051] It should be noted that the illustrations provided in the following embodiments are only schematic representations of the basic concept of the present invention. Therefore, the drawings only show the components related to the present invention and are not drawn according to the actual number, shape and size of the components in the actual implementation. In the actual implementation, the form, quantity and proportion of each component can be arbitrarily changed, and the layout of the components may also be more complex.

[0052] The green energy digital twin simulation method, system, medium, and electronic equipment of this invention provide a configurable, multi-scale green energy digital twin simulation technology driven by mechanism and data coupling and based on the builder pattern. It can effectively support the research of artificial intelligence operation and control optimization technology, AI prediction, early warning and diagnostic technology, and empower the high proportion of new energy consumption in the new generation of power systems with new energy as the core.

[0053] The technical solutions of the present invention will now be described in detail with reference to the accompanying drawings.

[0054] like Figure 1 As shown, in one embodiment, the green energy digital twin simulation method of the present invention includes steps 1-2.

[0055] Step S1: Construct a green energy digital twin static model subsystem; the green energy digital twin static model subsystem is based on the physical model of the physical equipment and uses the builder mode as the construction method.

[0056] Specifically, the green energy digital twin static model subsystem is an iterative modeling method based on the physical model of the physical equipment and using the builder pattern as the construction method. By defining multiple builders, multi-scale complex green energy digital twin static model subsystems can be constructed to meet the customized simulation needs of various green energy digital twin static model subsystems.

[0057] The multi-scale complex green energy digital twin static model subsystem can include a physical model of each physical entity and a simple green energy system defined using the builder pattern based on the physical models. Through the builder pattern, it enables the customization of the complex green energy digital twin static model subsystem to be simulated. This customization capability not only includes basic physical entities but also various simple green energy digital twin static model subsystems implemented through the builder pattern, including different types and numbers of physical entities and already constructed simple green energy digital twin static model subsystems. The simple green energy digital twin static model subsystem is customizablely constructed from a set of physical models of specific physical entities using the builder pattern. This customizability includes the basic attributes of the included physical entities, the types of physical entities, and their quantities.

[0058] In one embodiment, constructing a green energy digital twin static model subsystem includes the following steps:

[0059] 11) Define the basic physical model of the green energy system; the basic physical model includes a photovoltaic power generation model, an electrolyzer model, an energy storage lithium battery model, a hydrogen storage tank model, and a compressor.

[0060] like Figure 2 As shown, the physical model mainly includes a photovoltaic power generation model, an electrolyzer model, an energy storage lithium battery model, a hydrogen storage tank model, a compressor model, etc. For ease of description, f0, f1, and f2 in the figure refer to the physical models of the photovoltaic, compressor, and electrolyzer, respectively. g1 refers to the calculation formula for calculating the hydrogen charging rate by the compressor power, and g2 refers to the calculation formula for calculating the total power of the electrolyzer by the electrolysis hydrogen flow rate. Specifically, in the physical model, solar radiation shines on the power generation panel in the photovoltaic power generation module to generate electricity. The electricity generated by the photovoltaic has the following two flow paths: (1) The photovoltaic module generates electricity at a certain power P. ele (t)(P ele (t)>0) Power is supplied to the electrolyzer, which electrolyzes to produce hydrogen and outputs it; (2) The battery action P given by the intelligent agent. batt (t)(P batt (t)>0), which determines that a portion of the electrical energy flows into the lithium battery storage. The electrical energy required for electrolysis in the electrolytic cell comes from the following two sources: (1) the photovoltaic power generation module, which generates electricity through the electrolytic cell action P given by the intelligent agent. ele (t)(P ele (t)>0), decide to provide a portion of the electricity generated by photovoltaic power generation to the electrolytic cell; (2) energy storage lithium battery, through the battery action P given by the intelligent agent. batt (t)(P batt (t)<0), so it is decided to supply a portion of the electrical energy in the battery to the electrolyzer. The hydrogen produced by the electrolysis of the electrolyzer has the following two flow paths: (1) directly output as the hydrogen load at the output end F ele (t); (2) Action F via hydrogen storage tank hydro (t)(F hydro (t)>0), which determines that a portion of the hydrogen is compressed by the compressor and stored in the hydrogen storage tank. The hydrogen load at the output end has the following two sources: (1) F obtained by electrolysis in the electrolyzer. ele (t); (2) Hydrogen storage tank, through the action F of the hydrogen storage tank hydro (t)(F hydro If (t) < 0, a portion of the hydrogen in the hydrogen storage tank will be released. Three actions P... ele (t), P batt (t), F hydro (t) is given by the agent, which autonomously decides to perform the actions of electrolysis, energy storage or discharge, hydrogen storage or hydrogen release based on the current state.

[0061] 12) Based on the basic physical model of the physical entity, define the component mechanism model; the component mechanism model includes the output power of the photovoltaic power generation model, the hydrogen production flow rate of the electrolyzer model, the state change of the energy storage lithium battery model, the state change of the hydrogen storage tank model, and the power of the compressor.

[0062] The output power of the photovoltaic power generation model Where Y PV This indicates the power output of the photovoltaic panel under standard test conditions (i.e., a rated power of 2000kW); f PV This indicates the derating factor for photovoltaic panels, with a default value of 80%. This represents the solar radiation incident on the photovoltaic array at the current time step; α represents incident radiation under standard test conditions. P T represents the power temperature coefficient; c T represents the temperature of the photovoltaic array at the current time step; c，STC This indicates the temperature of the photovoltaic array under standard test conditions.

[0063] The hydrogen production flow rate F of the electrolyzer model ele (t)=P ele_total ×η ele / HHV H2 ,in F ele (t) represents the hydrogen flow rate output from the electrolyzer at time t; η represents the power of the electrolytic cell at time t. ele The efficiency of the electrolyzer is indicated. In this invention, an alkaline electrolyzer is used, and the efficiency is set to 70%. HHV H2 This indicates the higher heating value of hydrogen, which is 39.4 kWh / kg. batt This indicates the real-time charge / discharge power of the battery. The output hydrogen pressure of the electrolyzer is 3 MPa (stable).

[0064] The state changes of the energy storage lithium battery model Where S batt (t+1) represents the charge of the lithium battery at time t+1, S batt (t) represents the charge of the lithium battery at time t, P batt (t) represents the charging and discharging power of the battery at time t, η batt This indicates the charge / discharge efficiency, with a default value of 90%. The charge / discharge power of the lithium battery must not exceed the maximum charge / discharge power, and simultaneous charging and discharging of the batteries is not allowed at any given time. The battery capacity must meet the following requirements:

[0065] SOC batt_min ≤SOC batt (t)≤SOC batt_max

[0066]

[0067] Among them, SOC batt(t) represents the state of charge (S) of the lithium battery, defined as the ratio of the battery's stored capacity to its rated capacity at time t; the rated capacity S of the lithium battery... batt_rated The upper and lower limits of the battery state of charge are [20%, 100%].

[0068] The state changes of the hydrogen storage tank model Where S hydro (t+1) represents the amount of hydrogen stored in the hydrogen storage tank at time t+1, S hydro (t) represents the amount of hydrogen stored in the hydrogen storage tank at time t; F hydro (t) represents the hydrogen charging / discharging rate of the hydrogen storage tank at time t; η hydro To ensure real-time hydrogen charging and discharging efficiency, the hydrogen charge state of the storage tank must meet the following requirements:

[0069] SOC hydro_min ≤SOC hydro (t)≤SOC hydro_max

[0070] SOC hydro (t)=S hydro (t) / S hydro_rated

[0071] Analogous to the state of charge of a battery, SOC hydro (t) represents the hydrogen charge state of the hydrogen storage tank; the rated capacity S of the hydrogen storage tank. hydro_rated The hydrogen storage tank has a rated pressure of 30 MPa and a hydrogen load side pressure requirement of 3 MPa. Therefore, the minimum hydrogen load of the hydrogen storage tank is not less than 10% of the rated capacity. That is, the upper and lower limits of the hydrogen load state of the hydrogen storage tank are [10%, 100%].

[0072] The power of the compressor in This refers to the specific heat capacity of hydrogen. T comp This refers to the gas temperature at the compressor inlet, approximately equal to the ambient temperature of 298K. η cp For the efficiency of the compressor, η comp =0.75. K is the specific heat ratio of hydrogen under standard conditions, K = 1.4. P1 and P2 are the inlet and outlet pressures of the compressor, respectively, P1 = 3 MPa, P2 = 30 MPa. W comp This refers to the gas velocity at the compressor outlet, expressed in kg / s. The compressor only operates during the hydrogen charging process (F...). hydro It works when (t)≥0).

[0073] 13) Based on the basic physical model of the physical entity and the green energy digital twin static model subsystem, the builder pattern is used iteratively to define complex green energy digital twin static model subsystems of various scales required for simulation.

[0074] Among these features is the customizability of complex green energy digital twin static model subsystems that can be simulated using the builder pattern. This customizability extends beyond basic physical entities; it can also include various simple green energy digital twin static model subsystems implemented through the builder pattern, encompassing different types and numbers of physical entities and already constructed simple green energy digital twin static model subsystems.

[0075] Step S2: Construct a green energy digital twin dynamic model subsystem. The green energy digital twin dynamic model subsystem takes the current action value of the agent as input and generates the next state information and reward value as output.

[0076] Specifically, the green energy digital twin dynamic model subsystem is a behavioral simulation modeling process based on a white-box mechanistic model and assisted by an algorithm model trained with black-box historical data. This is referred to as the mechanism and data-coupled driven dynamic behavioral modeling method. The green energy digital twin dynamic model subsystem can be used to train a deep reinforcement learning agent model, taking the agent's current action value as input and the generated next state information and reward value as output.

[0077] In one embodiment, constructing a green energy digital twin dynamic model subsystem includes the following steps:

[0078] 21) For example Figure 3 As shown, the green energy digital twin dynamic model subsystem is configured to include a next state generation module (next_state()), an environment variable iteration module (next_vars()), a state observation module (observation()), and a reward generation module (reward()).

[0079] 22) During the operation of the green energy digital twin simulation system, the state-space variables are mapped to the system's state variables. These states include the photovoltaic power generation at various times, the state of charge of the lithium battery, and the state of charge of the hydrogen storage tank. The state space can be represented as: S = [P pv (t), S batt (t), S hydro (t)].

[0080] 23) Based on the agent's current state, it selects appropriate actions in the action space according to the policy, constrains each action to conform to actual physical meaning, and inputs the final constrained action values ​​as the power setpoints of each component into each physical model. The action space can be represented as: A = [P...] batt (t), P ele (t), F hydro (t)].

[0081] 24) Obtain auxiliary variables that are independent of sensor data from internal physical entities of systems such as photovoltaic power generation, wind power generation, and energy storage batteries based on the environment variable iteration module next_vars().

[0082] 25) Based on the state observation module (observation()), feature values ​​are selected from the auxiliary variables and next state information to characterize the state variables that the agent can observe, including predicted radiation intensity, user load information at the prediction end, etc. Here, "observation" is a figurative term used to describe the state data of the green energy digital twin simulation system that the agent can access and obtain during training. The observed variables in this invention include the current environmental state, auxiliary variables, current action values, etc.

[0083] 26) The next state generation module (next_state()) outputs the next state information based on the current action value, the current environment state, and the auxiliary variables. The next state generation module automatically iteratively calculates and generates the next state information based on the physical model mechanism and a data-driven temporal deep neural network.

[0084] 27) Based on the reward generation module reward(), the corresponding reward value r(t) is simulated and output according to the current action value, the auxiliary variable and the next state information.

[0085] First, the hydrogen flow path is determined, such as... Figure 4 As shown. Next, the hydrogen fluctuation value at time t is calculated. in, Target represents the target hydrogen load, F ele (t) represents the hydrogen production flow rate of the electrolyzer model. Then, the reward value is calculated.

[0086] 28) Constrain the actions to conform to actual physical meaning. These constraints are based on the fundamental mechanisms of each component, ensuring the actions remain within reasonable limits and do not exceed boundaries. Exceeding boundaries includes, for example, the battery being unable to continue charging after reaching its upper limit, or the battery being unable to continue discharging after reaching its lower limit. The principle of the hydrogen storage tank is the same. The specific implementation steps are shown in the following pseudocode:

[0087]

[0088]

[0089]

[0090]

[0091] 29) For physical entities or systems with unknown mechanisms, a corresponding dynamic operating model is obtained through data-driven training. For example, for photovoltaic power generation, a neural network model is trained based on data to predict power generation.

[0092] 210) For the external environmental driving factors of the green energy digital twin simulation system, dynamic prediction values ​​are obtained by training based on data-driven methods. For example, user load can be predicted by training a neural network based on historical data.

[0093] The scope of protection of the green energy digital twin simulation method described in this embodiment is not limited to the execution order of the steps listed in this embodiment. Any solution implemented by adding, subtracting, or replacing steps in the prior art based on the principle of this invention is included within the scope of protection of this invention.

[0094] This invention also provides a green energy digital twin simulation system, which can implement the green energy digital twin simulation method described in this invention. However, the implementation device of the green energy digital twin simulation system described in this invention includes, but is not limited to, the structure of the green energy digital twin simulation system listed in this embodiment. All structural modifications and substitutions of the prior art made according to the principles of this invention are included within the protection scope of this invention.

[0095] like Figure 5 As shown, in one embodiment, the green energy digital twin simulation system of the present invention includes a first building module 51 and a second building module 52.

[0096] The first construction module 51 is used to construct a green energy digital twin static model subsystem; the green energy digital twin static model subsystem is based on the physical model of the physical equipment and uses the builder mode as the construction method.

[0097] The second construction module 52 is used to construct a green energy digital twin dynamic model subsystem. The green energy digital twin dynamic model subsystem takes the current action value of the agent as input and generates the next state information and reward value as output.

[0098] The structure and principle of the first building module 51 and the second building module 52 correspond one-to-one with the steps in the above-mentioned green energy digital twin simulation method, so they will not be described again here.

[0099] In the embodiments provided by this invention, it should be understood that the disclosed systems, apparatuses, or methods can be implemented in other ways. For example, the apparatus embodiments described above are merely illustrative. For instance, the division of modules / units is only a logical functional division, and in actual implementation, there may be other division methods. For example, multiple modules or units may be combined or integrated into another system, or some features may be ignored or not executed. Furthermore, the coupling or direct coupling or communication connection shown or discussed may be through some interfaces; the indirect coupling or communication connection of apparatuses or modules or units may be electrical, mechanical, or other forms.

[0100] The modules / units described as separate components may or may not be physically separate. The components shown as modules / units may or may not be physical modules; that is, they may be located in one place or distributed across multiple network units. Some or all of the modules / units can be selected to achieve the objectives of the embodiments of the present invention, depending on actual needs. For example, the functional modules / units in the various embodiments of the present invention may be integrated into one processing module, or each module / unit may exist physically separately, or two or more modules / units may be integrated into one module / unit.

[0101] Those skilled in the art will further recognize that the units and algorithm steps of the various examples described in conjunction with the embodiments disclosed herein can be implemented in electronic hardware, computer software, or a combination of both. To clearly illustrate the interchangeability of hardware and software, the components and steps of the various examples have been generally described in terms of functionality in the foregoing description. Whether these functions are implemented in hardware or software depends on the specific application and design constraints of the technical solution. Those skilled in the art can use different methods to implement the described functions for each specific application, but such implementations should not be considered beyond the scope of this invention.

[0102] This invention also provides a computer-readable storage medium. Those skilled in the art will understand that all or part of the steps in the green energy digital twin simulation method of the above embodiments can be executed by a program instructing a processor. The program can be stored in a computer-readable storage medium, which is a non-transitory medium, such as random access memory, read-only memory, flash memory, hard disk, solid-state drive, magnetic tape, floppy disk, optical disc, and any combination thereof. The storage medium can be any available medium accessible to a computer or a data storage device such as a server or data center that integrates one or more available media. This available medium can be a magnetic medium (e.g., floppy disk, hard disk, magnetic tape), an optical medium (e.g., digital video disc (DVD)), or a semiconductor medium (e.g., solid-state drive (SSD)).

[0103] This invention also provides an electronic device. The electronic device includes a processor and a memory.

[0104] The memory is used to store computer programs.

[0105] The memory includes various media capable of storing program code, such as ROM, RAM, magnetic disk, USB flash drive, memory card, or optical disk.

[0106] The processor is connected to the memory and is used to execute the computer program stored in the memory, so that the electronic device performs the green energy digital twin simulation method described above.

[0107] Preferably, the processor can be a general-purpose processor, including a central processing unit (CPU), a network processor (NP), etc.; it can also be a digital signal processor (DSP), an application-specific integrated circuit (ASIC), a field-programmable gate array (FPGA), or other programmable logic devices, discrete gate or transistor logic devices, or discrete hardware components.

[0108] like Figure 6As shown, the electronic device of the present invention is embodied in the form of a general-purpose computing device. The components of the electronic device may include, but are not limited to: one or more processors or processing units 61, a memory 62, and a bus 63 connecting different system components (including the memory 62 and the processing unit 61).

[0109] Bus 63 represents one or more of several bus architectures, including a memory bus or memory controller, a peripheral bus, a graphics acceleration port, a processor, or a local bus using any of the various bus architectures. For example, these architectures include, but are not limited to, the Industry Standard Architecture (ISA) bus, the Micro Channel Architecture (MAC) bus, the Enhanced ISA bus, the Video Electronics Standards Association (VESA) local bus, and the Peripheral Component Interconnect (PCI) bus.

[0110] Electronic devices typically include a variety of computer-readable media. These media can be any available media that can be accessed by the electronic device, including volatile and non-volatile media, and removable and non-removable media.

[0111] Memory 62 may include computer system readable media in the form of volatile memory, such as random access memory (RAM) 621 and / or cache memory 622. The electronic device may further include other removable / non-removable, volatile / non-volatile computer system storage media. By way of example only, storage system 623 may be used to read and write non-removable, non-volatile magnetic media (…). Figure 6 Not shown; usually referred to as a "hard drive"). Although Figure 6 Not shown, a disk drive for reading and writing to a removable non-volatile disk (e.g., a "floppy disk") and an optical disk drive for reading and writing to a removable non-volatile optical disk (e.g., a CD-ROM, DVD-ROM, or other optical media) may be provided. In these cases, each drive may be connected to bus 63 via one or more data media interfaces. Memory 62 may include at least one program product having a set (e.g., at least one) of program modules configured to perform the functions of the embodiments of the present invention.

[0112] A program / utility 624 having a set (at least one) of program modules 6241 may be stored, for example, in memory 62. Such program modules 6241 include, but are not limited to, an operating system, one or more application programs, other program modules, and program data. Each or some combination of these examples may include an implementation of a network environment. Program modules 6241 typically perform the functions and / or methods described in the embodiments of the present invention.

[0113] The electronic device can also communicate with one or more external devices (e.g., keyboard, pointing device, display, etc.), one or more devices that enable a user to interact with the electronic device, and / or any device that enables the electronic device to communicate with one or more other computing devices (e.g., network interface card, modem, etc.). This communication can be performed through input / output (I / O) interface 64. Furthermore, the electronic device can also communicate with one or more networks (e.g., local area network (LAN), wide area network (WAN), and / or public networks, such as the Internet) through network adapter 65. Figure 6 As shown, network adapter 65 communicates with other modules of the electronic device via bus 63. It should be understood that, although not shown in the figure, other hardware and / or software modules may be used in conjunction with the electronic device, including but not limited to: microcode, device drivers, redundant processing units, external disk drive arrays, RAID systems, tape drives, and data backup storage systems.

[0114] The above embodiments are merely illustrative of the principles and effects of the present invention and are not intended to limit the invention. Any person skilled in the art can modify or alter the above embodiments without departing from the spirit and scope of the present invention. Therefore, all equivalent modifications or alterations made by those skilled in the art without departing from the spirit and technical concept disclosed in the present invention should still be covered by the claims of the present invention.

Claims

1. A green energy digital twin simulation method, characterized in that: The method includes the following steps: A green energy digital twin static model subsystem is constructed; the green energy digital twin static model subsystem is based on the physical model of the physical equipment and uses the builder mode as the construction method; A green energy digital twin dynamic model subsystem is constructed, wherein the green energy digital twin dynamic model subsystem takes the current action value of the agent as input and generates the next state information and reward value as output; The construction of a green energy digital twin dynamic model subsystem includes the following steps: The green energy digital twin dynamic model subsystem is defined to include a next state generation module, an environmental variable iteration module, a state observation module, and a reward generation module; During the operation of the green energy digital twin simulation system, the state-space variables are correlated with the system's state variables; Based on the agent's current state, select the corresponding action in the action space, constrain each action, and input the final constrained action value as the power setpoint of each component into each physical model; The system obtains auxiliary variables that are unrelated to the sensing data of physical entities within the system based on the environmental variable iteration module; The state observation module selects feature values ​​from the auxiliary variables and the next state information to characterize the state variables that the agent can observe; The next state generation module outputs the next state information based on the current action value, the current environment state, and the auxiliary variables. The reward generation module simulates and outputs the corresponding reward value based on the current action value, the auxiliary variable, and the next state information; The actions are constrained to conform to their actual physical meaning; For physical entities or systems with unknown mechanisms, a corresponding dynamic operating model is obtained by training using a data-driven approach. To address the external environmental driving factors of a green energy digital twin simulation system, a data-driven approach is used to train and obtain dynamic prediction values. The reward generation module simulates and outputs the corresponding reward value based on the current action value, the auxiliary variable, and the next state information, including the following steps: Determine the hydrogen flow path; Calculate the hydrogen fluctuation value at time t. ; Calculate reward value ; Calculate the hydrogen fluctuation value at time t. include: ,in, , Indicates the target hydrogen load. This represents the hydrogen production flow rate of the electrolyzer model. This indicates the rate at which the hydrogen storage tank is filled or discharged.

2. The green energy digital twin simulation method according to claim 1, characterized in that: The construction of a green energy digital twin static model subsystem includes the following steps: Define the basic physical model of a green energy system; the basic physical model includes a photovoltaic power generation model, an electrolyzer model, an energy storage lithium battery model, a hydrogen storage tank model, and a compressor; Based on the basic physical model of physical entities, a component mechanism model is defined; the component mechanism model includes the output power of the photovoltaic power generation model, the hydrogen production flow rate of the electrolyzer model, the state changes of the energy storage lithium battery model, the state changes of the hydrogen storage tank model, and the power of the compressor. Based on the basic physical model of the physical entity and the green energy digital twin static model subsystem, the builder pattern is used iteratively to define complex green energy digital twin static model subsystems of various scales required for simulation.

3. The green energy digital twin simulation method according to claim 1, characterized in that: The output power of the photovoltaic power generation model ,in This indicates the power output of the photovoltaic panel under standard test conditions; This indicates the derating factor for photovoltaic panels; This represents the solar radiation incident on the photovoltaic array at the current time step; Indicates incident radiation under standard test conditions; Indicates the power temperature coefficient; This indicates the temperature of the photovoltaic array at the current time step; This indicates the temperature of the photovoltaic array under standard test conditions; Hydrogen production flow rate of the electrolyzer model ,in , This represents the hydrogen flow rate output from the electrolyzer at time t; This represents the power of the electrolytic cell at time t; Indicates the efficiency of the electrolytic cell. This indicates the higher heating value of hydrogen. This indicates the real-time charging and discharging power of the battery. The state changes of the energy storage lithium battery model ,in The charge level of the lithium battery at time t+1. The charge level of the lithium battery at time t. Let t be the charge / discharge power of the battery. Indicates charge / discharge efficiency; The state changes of the hydrogen storage tank model ,in This represents the amount of hydrogen stored in the hydrogen storage tank at time t+1. The amount of hydrogen stored in the hydrogen storage tank at time t; The hydrogen filling and discharging rate of the hydrogen storage tank at time t; For real-time hydrogen charging and discharging efficiency; The power of the compressor ,in This refers to the specific heat capacity of hydrogen. This refers to the gas temperature at the compressor inlet. For the efficiency of the compressor, This is the specific heat ratio of hydrogen under standard conditions. and These are the pressures at the compressor inlet and outlet, respectively. This indicates the gas flow rate at the compressor outlet.

4. The green energy digital twin simulation method according to claim 1, characterized in that: The next state generation module automatically iteratively calculates and generates next state information based on physical model mechanisms and data-based temporal deep neural networks.

5. A green energy digital twin simulation system, characterized in that: The system includes a first building module and a second building module; The first construction module is used to construct a green energy digital twin static model subsystem; the green energy digital twin static model subsystem is based on the physical model of the physical equipment and uses the builder mode as the construction method; The second building module is used to build a green energy digital twin dynamic model subsystem. The green energy digital twin dynamic model subsystem takes the current action value of the agent as input and generates the next state information and reward value as output. The construction of a green energy digital twin dynamic model subsystem includes the following steps: The green energy digital twin dynamic model subsystem is defined to include a next state generation module, an environmental variable iteration module, a state observation module, and a reward generation module; During the operation of the green energy digital twin simulation system, the state-space variables are correlated with the system's state variables; Based on the agent's current state, select the corresponding action in the action space, constrain each action, and input the final constrained action value as the power setpoint of each component into each physical model; The system obtains auxiliary variables that are unrelated to the sensing data of physical entities within the system based on the environmental variable iteration module; The state observation module selects feature values ​​from the auxiliary variables and the next state information to characterize the state variables that the agent can observe; The next state generation module outputs the next state information based on the current action value, the current environment state, and the auxiliary variables. The reward generation module simulates and outputs the corresponding reward value based on the current action value, the auxiliary variable, and the next state information; The actions are constrained to conform to their actual physical meaning; For physical entities or systems with unknown mechanisms, a corresponding dynamic operating model is obtained by training using a data-driven approach. To address the external environmental driving factors of a green energy digital twin simulation system, a data-driven approach is used to train and obtain dynamic prediction values. The reward generation module simulates and outputs the corresponding reward value based on the current action value, the auxiliary variable, and the next state information, including the following steps: Determine the hydrogen flow path; Calculate the hydrogen fluctuation value at time t. ; Calculate reward value ; Calculate the hydrogen fluctuation value at time t. include: ,in, , Indicates the target hydrogen load. This represents the hydrogen production flow rate of the electrolyzer model. This indicates the rate at which the hydrogen storage tank is filled or discharged.

6. A storage medium having a computer program stored thereon, characterized in that, When the program is executed by the processor, it implements the green energy digital twin simulation method as described in any one of claims 1 to 4.

7. An electronic device, characterized in that, include: Processor and memory; The memory is used to store computer programs; The processor is used to execute the computer program stored in the memory to cause the electronic device to perform the green energy digital twin simulation method according to any one of claims 1 to 4.

Images