Multi-energy IDR scheduling method and system based on energy element digital twin

Abstract

The present disclosure provides a multi-energy IDR scheduling method and system based on energy element digital twins, which belongs to the field of energy optimization scheduling technology. The scheme designs digital twin intelligent entities corresponding to typical energy elements of physical entity systems through model mapping and data mapping between digital environment and physical entity system, so as to establish flexible resource twin mapping; and on this basis, conducts subject behavior simulation design including value orientation and social behavior of energy elements in the digital environment, constructs digital twins that can simulate the behavioral characteristics of massive flexible resources, and then completes IDR scheduling, so that the scheduling method can effectively meet user needs, and at the same time, meet low-carbon goals to a certain extent, and reduce scheduling costs.

Description

Technical Field

[0001] The present disclosure belongs to the technical field of energy optimization scheduling, and in particular relates to a multi-energy IDR scheduling method and system based on energy element digital twins. Background Art

[0002] The statements in this section merely provide background information related to the present disclosure and do not necessarily constitute prior art.

[0003] Traditional power system dispatching models can be broadly categorized into centralized optimization and distributed, decentralized, or weakly centralized dispatching. Centralized optimization requires a dispatch center to collect information such as electricity demand, power generation, and line constraints. After centralized optimization, these instructions are then distributed to dispatched end-users. Real-time data collection allows the dispatch center to monitor the execution of these instructions and inform future decisions. Based on a review of the work of load aggregators at home and abroad, some researchers have studied the dispatching of small and medium-sized loads, such as residential and commercial loads, and proposed a hierarchical load management architecture.

[0004] The inventors found that the above research relies more on the passive control of energy elements (LA: Load Aggergator) units, and does not emphasize the active interaction of energy elements; considering the diversity of subject behaviors in multi-energy systems, the cross-border uncertainty between information-physics-society-subject behaviors, and the coupling relationship between multiple complex networks, this is difficult for current simulation systems based on physical modeling to handle; in addition, the decision-making of autonomous groups, the generation and evolution of grid bodies, and the interaction between energy elements are all a process of successive recursion and dynamic optimization evolution from abstract to concrete, from fuzzy to accurate, and there is a possibility of trial and error. The concept of digital twin (DT) was first proposed by Michael Grieves. With increasingly complex power system models and massive amounts of data, fully utilizing existing grid resources has become challenging. However, grid DT, as a powerful analysis and design-aided platform, can meet the ever-changing demands of both power generation and consumption with minimal grid enhancements. While existing research based on digital twin technology has achieved some success in data-driven power system modeling, with increasing user initiative and the rise of demand response, research on data-driven models for member interaction is still lacking. Summary of the Invention

[0005] In order to solve the above problems, the present disclosure provides a multi-energy IDR scheduling method and system based on energy element digital twins. The scheme designs digital twin intelligent entities corresponding to typical energy elements of physical entity systems through model mapping and data mapping between digital environment and physical entity system, so as to establish flexible resource twin mapping; and on this basis, conducts subject behavior simulation design including value orientation and social behavior of energy elements in the digital environment, constructs digital twins that can simulate the behavioral characteristics of massive flexible resources, and then completes IDR scheduling, so that the scheduling method can effectively meet user needs, and at the same time, meet low-carbon goals to a certain extent, and reduce scheduling costs.

[0006] According to a first aspect of an embodiment of the present disclosure, a multi-energy IDR scheduling method based on an energy element digital twin is provided, comprising:

[0007] Based on the physical model of the equipment in the integrated energy system and its corresponding initial state and constraints, a virtual mapping of the integrated energy system is created to realize the construction of the energy element digital twin model; based on the historical power generation data of the integrated energy system, a deep neural network is used to predict the load and power generation data on similar days;

[0008] The energy element digital twin model is modified based on the parameters in the physical model of the integrated energy system and the predicted similar daily load and power generation data; wherein, during the simulation operation process, the energy element digital twin model adjusts the coefficients of the simulation operation model based on the differences between the simulation operation and the physical entity of the equipment to achieve synchronization between the digital twin and the physical entity; at the same time, feedback is provided to the physical entity to achieve optimized operation of the physical entity; and in the energy element digital twin, the willingness of each energy element in the integrated energy system to participate in demand response scheduling behavior is measured by calculating the influence value of the energy element;

[0009] For energy elements involved in grid dispatching tasks, based on electricity prices in different time periods and preset constraints, multi-objective optimization decisions are made through the revised digital twin of the energy element to obtain the optimal Pareto solution set; based on the Pareto solution set, the charging and discharging power of the energy storage device in the integrated energy system, the output power of each unit and the power of the interconnecting line are obtained.

[0010] Furthermore, the calculation of the influence value of the energy element is specifically the weighted sum of the contribution capability value, participation capability value, privacy budget value and activity value of the energy element, wherein the contribution capability value is determined based on the user's maximum adjustable capability, the participation capability value is determined based on the external environmental conditions that affect the user's decision and the user's satisfaction, the privacy budget value is determined based on the privacy data contributed by the user, and the activity value is determined based on the user's historical influence performance.

[0011] Furthermore, the optimization objectives of the multi-objective optimization decision include the maintenance costs of distributed energy, the transaction costs with the power grid, natural gas grid and load, and the environmental protection costs of emitting CO2, SO2 and NOx.

[0012] Furthermore, the multi-objective optimization decision is performed through the modified energy element digital twin, and specifically the NSGA-II algorithm is used for the multi-objective optimization decision.

[0013] Furthermore, the integrated energy system includes a variety of energy conversion equipment and communication equipment to achieve the coupling of different energy subsystems such as electricity, heat, natural gas and hydrogen, and output to hydrogen load, electricity load and heat load.

[0014] According to a second aspect of an embodiment of the present disclosure, a multi-energy IDR scheduling system based on an energy element digital twin is provided, comprising:

[0015] A digital twin model construction unit, which is used to create a virtual mapping of the integrated energy system based on the physical model of the equipment in the integrated energy system and its corresponding initial state and constraints, thereby realizing the construction of the energy element digital twin model;

[0016] A prediction unit, which is used to predict the load and power generation data of similar days based on the historical power generation data of the integrated energy system using a deep neural network;

[0017] A correction unit, configured to correct the energy element digital twin model based on parameters in the physical model of the integrated energy system and predicted similar daily load and power generation data; wherein, during the simulation operation process, the energy element digital twin model adjusts the coefficients of the simulation operation model based on the differences between the simulation operation and the physical entity of the equipment to achieve synchronization between the digital twin and the physical entity; at the same time, feedback is provided to the physical entity to achieve optimized operation of the physical entity; and in the energy element digital twin, the willingness of each energy element in the integrated energy system to participate in demand response scheduling behavior is measured by calculating the influence value of the energy element;

[0018] The optimization scheduling unit is used to perform multi-objective optimization decisions on the energy elements participating in the grid scheduling task based on the electricity prices in different time periods and preset constraints through the modified digital twin of the energy element to obtain the optimal Pareto solution set; based on the said Pareto solution set, the charging and discharging power of the energy storage device in the integrated energy system, the output power of each unit and the power of the interconnection line are obtained.

[0019] According to the third aspect of an embodiment of the present disclosure, an electronic device is provided, comprising a memory, a processor, and a computer program stored and running on the memory, wherein when the processor executes the program, the multi-energy IDR scheduling method based on the energy element digital twin is implemented.

[0020] According to the fourth aspect of the embodiment of the present disclosure, a non-transitory computer-readable storage medium is provided, on which a computer program is stored. When the program is executed by a processor, the multi-energy IDR scheduling method based on the energy element digital twin is implemented.

[0021] Compared with the prior art, the present invention has the following advantages:

[0022] The solution disclosed in the present invention provides a multi-energy IDR (Integrated Demand Response) scheduling method and system based on the digital twin of energy elements. The solution designs a digital twin intelligent entity corresponding to the typical energy elements of the physical entity system through model mapping and data mapping between the digital environment and the physical entity system, so as to establish a flexible resource twin mapping; and on this basis, conducts subject behavior simulation design including the value orientation and social behavior of the energy elements in the digital environment, constructs a digital twin that can simulate the behavioral characteristics of massive flexible resources, and then completes IDR scheduling, so that the scheduling method can effectively meet user needs, and at the same time, meet the low-carbon goals to a certain extent, and reduce scheduling costs.

[0023] Advantages of additional aspects of the present disclosure will be given in part in the following description and in part will become apparent from the following description or learned through practice of the present disclosure. BRIEF DESCRIPTION OF THE DRAWINGS

[0024] The accompanying drawings, which constitute a part of the present disclosure, are used to provide a further understanding of the present disclosure. The exemplary embodiments of the present disclosure and their descriptions are used to explain the present disclosure and do not constitute an improper limitation to the present disclosure.

[0025] Figure 1 Schematic diagram of the design mechanism of the energy element digital twin described in the embodiment of the present disclosure;

[0026] Figure 2 Schematic diagram of the virtual space of a multi-energy system based on the energy element digital twin according to an embodiment of the present disclosure;

[0027] Figure 3 This is a schematic diagram of the daily multi-energy demand described in the embodiments of the present disclosure;

[0028] Figure 4 Schematic diagram of the multi-energy system structure in the simulation experiment described in the embodiments of the present disclosure;

[0029] Figure 5 A schematic diagram comparing the thermal supply and demand relationship under different coupling conditions described in the embodiments of the present disclosure;

[0030] Figure 6Schematic diagram comparing multi-energy load reduction and response costs under different demand response mechanisms described in the embodiments of the present disclosure;

[0031] Figure 7 This is a flow chart of a multi-energy IDR scheduling method based on energy element digital twins described in an embodiment of the present disclosure. DETAILED DESCRIPTION

[0032] The present disclosure will be further described below with reference to the accompanying drawings and embodiments.

[0033] It should be noted that the following detailed descriptions are illustrative and intended to provide further explanation of the present disclosure. Unless otherwise specified, all technical and scientific terms used herein have the same meaning as commonly understood by those skilled in the art to which the present disclosure belongs.

[0034] It should be noted that the terms used herein are only for describing specific embodiments and are not intended to limit the exemplary embodiments according to the present disclosure. As used herein, unless the context clearly indicates otherwise, the singular form is intended to include the plural form. In addition, it should be understood that when the terms "comprise" and / or "include" are used in this specification, they indicate the presence of features, steps, operations, devices, components and / or combinations thereof.

[0035] In the absence of conflict, the embodiments of the present disclosure and the features thereof may be combined with each other.

[0036] Example 1:

[0037] The purpose of this embodiment is to provide a multi-energy IDR scheduling method based on energy element digital twins.

[0038] A multi-energy IDR scheduling method based on energy element digital twins, including:

[0039] Based on the physical model of the equipment in the integrated energy system and its corresponding initial state and constraints, a virtual mapping of the integrated energy system is created to realize the construction of the energy element digital twin model; based on the historical power generation data of the integrated energy system, a deep neural network is used to predict the load and power generation data on similar days;

[0040] The energy element digital twin model is modified based on the parameters in the physical model of the integrated energy system and the predicted similar daily load and power generation data; wherein, during the simulation operation process, the energy element digital twin model adjusts the coefficients of the simulation operation model based on the differences between the simulation operation and the physical entity of the equipment to achieve synchronization between the digital twin and the physical entity; at the same time, feedback is provided to the physical entity to achieve optimized operation of the physical entity; and in the energy element digital twin, the willingness of each energy element in the integrated energy system to participate in demand response scheduling behavior is measured by calculating the influence value of the energy element;

[0041] For energy elements involved in grid dispatching tasks, based on electricity prices in different time periods and preset constraints, multi-objective optimization decisions are made through the revised digital twin of the energy element to obtain the optimal Pareto solution set; based on the Pareto solution set, the charging and discharging power of the energy storage device in the integrated energy system, the output power of each unit and the power of the interconnecting line are obtained.

[0042] Furthermore, the calculation of the influence value of the energy element is specifically the weighted sum of the contribution capability value, participation capability value, privacy budget value and activity value of the energy element, wherein the contribution capability value is determined based on the user's maximum adjustable capability, the participation capability value is determined based on the external environmental conditions that affect the user's decision and the user's satisfaction, the privacy budget value is determined based on the privacy data contributed by the user, and the activity value is determined based on the user's historical influence performance.

[0043] Furthermore, the optimization objectives of the multi-objective optimization decision include the maintenance costs of distributed energy, the transaction costs with the power grid, natural gas grid and load, and the environmental protection costs of emitting CO2, SO2 and NOx.

[0044] Furthermore, the multi-objective optimization decision is performed through the modified energy element digital twin, and specifically the NSGA-II algorithm is used for the multi-objective optimization decision.

[0045] Furthermore, the integrated energy system includes a variety of energy conversion equipment and communication equipment to achieve the coupling of different energy subsystems such as electricity, heat, natural gas and hydrogen, and output to hydrogen load, electricity load and heat load.

[0046] Specifically, the solution of this embodiment is described in detail below with reference to the accompanying drawings and specific examples:

[0047] The solution described in this embodiment addresses the problem that existing methods only obtain data-driven models of existing multi-energy physical systems from big data, without modeling the activeness and interaction models of energy elements, such as Figure 7As shown in the figure, a multi-energy IDR scheduling method based on digital twins of energy elements is proposed. It adopts the following technical concepts: through model mapping and data mapping between the digital environment and the physical entity system, a digital twin intelligent agent corresponding to the typical energy elements of the physical entity system is designed to establish a flexible resource twin mapping. On this basis, a subject behavior simulation module containing the value orientation and social behavior of energy elements is developed in the digital environment, and a digital twin that can simulate the behavioral characteristics of massive flexible resources is constructed to complete IDR scheduling. The specific plan is detailed from the following aspects:

[0048] (1) Construction of the digital twin model of the energy element of the integrated energy system

[0049] The key to digital twins is to build high-fidelity virtual entities of physical entities based on virtual space to simulate real-world behavior, and to predict and optimize future behavior trends based on the corresponding information. During the simulation process, the difference between the simulation and the physical entity is used to adjust the coefficients of the simulation model to achieve synchronization between the digital twin and the physical entity. The digital twin can also provide feedback to the physical entity to achieve optimized operation of the physical entity. The design mechanism of the energy element digital twin model is as follows: Figure 1 shown.

[0050] Based on the digital twin, the virtual space test entity generates comprehensive information on device status, network framework topology, line parameters, and electrical, thermal, gas, and hydrogen energy flows. The simulation optimization results are then fed into the control device for testing. The actual operating status of the device can also be fed back into the twin for improvement and optimization. Furthermore, the knowledge-driven user initiative model continuously improves the data-driven model, thereby achieving self-adaptation and improvement of the energy element digital twin.

[0051] (2) Member (Energy Element) Interaction Model

[0052] This embodiment proposes an influence model that can fully describe the characteristics of multi-energy system members. Taking the performance of flexible loads in demand response as an example, the higher the influence value, the greater the willingness to participate in demand response scheduling and other behaviors. The influence of a member is composed of four parts. That is, the influence value of a member is weighted by four parts: contribution ability value, participation ability value, privacy budget value, and activity value. Specifically:

[0053] 1) Contribution Capacity: This refers to the maximum contribution of a user (or flexible load, the same below). This can be understood as the user's maximum adjustable capacity. In actual multi-energy systems, this value carries the greatest weight.

[0054] 2) Participation Capacity: This refers to the external environmental conditions and user satisfaction that can influence user decisions. These factors are influenced by factors such as market policies, weather, and system stability. The more favorable the environment and the higher the satisfaction, the greater the value of this component.

[0055] 3) Privacy Budget: Assume that demand response is initiated by the distribution system administrator. In the incentive mechanism designed later, in addition to compensation related to demand response, the distribution system administrator should also compensate users for the private data they contribute based on their privacy budget. Users with larger privacy budgets receive higher rewards from the distribution system administrator and are therefore more willing to participate in scheduling tasks that risk privacy leaks. Each user will design their own privacy budget to maximize their own utility.

[0056] 4) Activity Value: This reflects the user's historical influence and helps prevent inappropriate data from appearing at a specific moment. To encourage user activity during scheduling, the weight of this value should be neither too high nor too low. The greater the historical influence value and the more times a user has participated, the larger the value of this value.

[0057] Assume that N is the total number of users in the study case. Influence value I i The description is as follows:

[0058] I i =a i I C,i +b i I P,i +c i I A,i +d i I B,i (1)

[0059] Where i∈{1,2,…,N}, I i is the influence value of the flexible load i, a i ,bi,ci and di are to satisfy a i +b i +c i +d i =1 linear weight parameter; I C,i ,I P,i ,I A,i ,I B,i ∈[0,1] (per unit value) represent the contribution capability value, participation capability value, activity level and privacy budget of the elastic load i. The characteristics of the flexible load can be expressed as [I C,i ,I P,i ,I A,i ,I B,i ] TThe linear weight parameters in different regions are different, and different parameters reflect different member characteristics, which reflects the flexibility and applicability of the model.

[0060] (3) Data-driven multi-energy system scheduling model

[0061] Establishing a virtual space of multi-energy system based on twins Figure 2 As shown, the system integrates electricity, heat, gas, and hydrogen networks through various energy conversion and communication devices, connecting the system to the power grid and natural gas grid. It includes photovoltaic (PV), wind turbines (WT), combined heat and power (CHP) systems (micro gas turbines), gas boilers (GB), power-to-hydrogen (P2H) units, hydrogen storage tanks (HT), fuel cells (FC), thermal energy storage (TT), and batteries (SB).

[0062] The power flow model in the multi-energy system is constructed using the traditional AC power flow model. Based on the node power balance equation, this paper uses the Newton-Raphson algorithm to iteratively solve the Jacobian matrix by constructing it, calculating the state quantity of each node, and thus obtaining the power flow distribution of the power network. The calculation formula is:

[0063]

[0064] Where, P i and Q i represent the injected active and reactive power of node i, respectively. represents the node voltage, and Y is the node admittance matrix.

[0065] Unlike power networks, thermal networks do not follow electromagnetic transient laws, but rather heat migration and conduction processes, with time scales of minutes or hours. Heat transfer in a pipe is represented by the change in water temperature at position x over time t. Ignoring static heat conduction within the water flow, the thermal transfer equation can be expressed as:

[0066]

[0067] φ=cmT (4)

[0068] The first two terms on the left side of the equation represent convective heat transfer in the supply and return pipes, respectively, and the third term represents pipe heat loss. T(x,t) is the temperature difference between the water flow at position x in the pipe and the reference temperature at time t, and is a function of x and t; m is the mass flow rate of the water flow and can be assumed to be constant; c is the specific heat capacity of water; ρ is the density of water; λ is the thermal conductivity of the pipe; S h is the cross-sectional area of ​​the thermal branch pipe, and Q(x,t) represents the heat flow power. Combining the two equations, we can obtain an equation with a format similar to the power network formula:

[0069]

[0070]

[0071] Isothermal natural gas is transported under pressure, and the gas flow obeys the law of conservation of mass and Bernoulli's law for non-ideal gases. The transport process is generally described by the continuity equation and momentum equation, using pressure p(x, t) and flow rate q(x, t) as state variables. Ignoring the partial derivatives that describe the time-varying flow rate, the natural gas state equation can be expressed as follows:

[0072]

[0073]

[0074] Where p is the pressure of the gas flow at the pipeline position x at time t; q is the volume flow rate of the gas flow at the pipeline position x at time t (m 3 / s, all measured under standard conditions, i.e. 1 atmosphere pressure and temperature of 25°C); v a is the gas sound velocity; w is the average flow velocity in the pipeline; D is the inner diameter of the pipeline; λ g is the pipeline friction coefficient; S g is the cross-sectional area of ​​the natural gas branch pipe. In addition, let the natural gas constant be R g , the pipe temperature is T g , the flow rate and pressure have the following relationship:

[0075]

[0076] The energy coupling device is designed as follows:

[0077] (1) Grid-natural gas grid: micro gas turbine (or cogeneration equipment)

[0078] The fuel curve describes the relationship between generator output and natural gas consumption, as shown below.

[0079]

[0080] in, Indicates the gas consumption rate of MT (m 3 / s), c eg Indicates the slope of the fuel curve (m 3 / (kW·s)), Indicates the electrical power output of MT, in kW.

[0081] (2) Grid-heat network: micro gas turbine (or cogeneration equipment)

[0082] When MT generates electricity, it emits high-temperature flue gas as a byproduct. This waste heat is recovered to provide heat. If the MT operates in a power-to-heat mode, the calorific value can be expressed as follows.

[0083]

[0084] Where, κ is the gas heat recovery rate, is the thermal output of MT (kW), LHV is the lower heating value (MJ / kg), ρ g It is the density of gas (kg / m3).

[0085] (3) Natural gas network - heat network: For gas boilers, the relationship between output power and gas consumption is shown in the following formula.

[0086]

[0087] Among them, η b is the efficiency of GB, is the thermal power output of GB (kW), is the gas consumption rate of GB (m 3 / hr).

[0088] (4) Mobile hydrogen energy storage network - power grid: charging piles

[0089]

[0090] Among them, P t H is the grid-side output power of the charging pile connected to the mobile hydrogen energy storage, η pc is the efficiency of the charging pile, η FC is the fuel cell power generation efficiency.

[0091] (IV) Optimizing scheduling strategies

[0092] When the integrated energy system is economically operated, it is necessary to consider the maintenance costs of distributed energy, the transaction costs with the power grid, natural gas grid and load, and the emissions of CO2, SO2 and NO x Environmental protection costs, etc.

[0093] (1) Maintenance cost.

[0094]

[0095] Among them, c i,t is the operation and maintenance cost coefficient of distributed energy i at time t; P i,t is the output power of micro source i at time t;

[0096] (2)Energy costs.

[0097] f2=c buy,t P buy,t +c gas,t G buy,t -c sell,t P sell,t (15)

[0098] Among them, c buy,t and c sell,t is the electricity purchase price and electricity sales price at time t; P buy,t and P sell,t It is the electricity purchase and sales of the integrated energy system; c gas,t is the price of natural gas purchased at time t; G buy,t is the amount of natural gas purchased.

[0099] (3) Environmental protection costs.

[0100]

[0101] Among them, c i,k The pollutant type (CO2, SO2 and NO x ), λ i,k is the unit treatment cost of the kth type of pollutant; P i,t is the emission coefficient of the pollutant.

[0102] The specific optimization steps are as follows:

[0103] Step 1: First, input the panoramic information such as load, wind energy, photovoltaic power generation history data, meteorological data, etc. into the database management module. Set the initial state and constraints of each device to create a virtual image of the integrated energy system;

[0104] Step 2: Based on the deep neural network algorithm, load and wind power data are predicted, and the energy element digital twin model is modified according to the physical model and similar daily data;

[0105] Step 3: The power grid dispatch center issues a task, and the energy element digital twin accepts the task;

[0106] Step 4: Based on the electricity price and constraints for each time period, the twin uses the NSGA-II algorithm to make a multi-objective optimization decision. Finally, based on the optimal Pareto solution set, the charging and discharging power of the energy storage device, the output power of each unit, and the power of the tie line are determined.

[0107] Furthermore, in order to prove the effectiveness of the solution described in this embodiment, the following corresponding experiments were carried out:

[0108] The experimental environment is an Intel Core i7-10870H CPU 2.21GHz processor with 32GB RAM. The effectiveness of the proposed method is demonstrated using an integrated energy system in a region of northern China during winter. The region has two CCHPs (combined cooling, heating, and power) and eight large-scale flexible loads (or load nodes), each managed by an LSO. Typical load curves for electricity, heating, and cooling are shown in Figure 2. Figure 3 The load limit is 40MW at all times. The district heating network topology is shown in Figure 4 As shown in Figure 2, we can assume that the proportion of the electric load of each node in each time period is always constant, and thus assume that the proportions of the electric load of the eight nodes are: 20%, 15%, 10%, 5%, 20%, 15%, 10%, and 5%.

[0109] By solving the optimization model with twin agents, the impact of total load reduction of multiple energy coupling can be analyzed. Figure 5 It can be seen that when coupling is not considered, the thermal network often produces excess heat, resulting in a certain amount of energy waste. However, when coupling is considered, some electricity is converted into heat, and traditional thermal equipment such as gas boilers can meet user heating needs at a lower output. Therefore, the proposed IDR based on multi-energy coupling can meet low-carbon goals to a certain extent and also provides the possibility of access to clean energy.

[0110] Further, Figure 6 The paper demonstrates the cooling, heating, and electricity load reductions achieved throughout the system through IDR over a single day, comparing the cost curves of this method with those using demand response (DR) without considering cooling and heating coupling. During the daytime (8:00-16:00), DR reduces more load, resulting in higher values ​​for both cost curves. However, because multi-energy coupling avoids network congestion and energy waste, the curves with coupling are generally lower than those without. In the evening (17:00-18:00), due to the reduced load, the output changes or startup and shutdown of cooling and heating equipment incur additional costs, resulting in a slightly lower cost curve without coupling. However, overall, the established coupling model has a greater advantage in terms of DR costs, further demonstrating the effectiveness of the proposed twin agent.

[0111] Example 2:

[0112] The purpose of this embodiment is to provide a multi-energy IDR scheduling system based on energy element digital twins.

[0113] A multi-energy IDR scheduling system based on energy element digital twins, including:

[0114] A digital twin model construction unit, which is used to create a virtual mapping of the integrated energy system based on the physical model of the equipment in the integrated energy system and its corresponding initial state and constraints, thereby realizing the construction of the energy element digital twin model;

[0115] A prediction unit, which is used to predict the load and power generation data of similar days based on the historical power generation data of the integrated energy system using a deep neural network;

[0116] A correction unit, configured to correct the energy element digital twin model based on parameters in the physical model of the integrated energy system and predicted similar daily load and power generation data; wherein, during the simulation operation process, the energy element digital twin model adjusts the coefficients of the simulation operation model based on the differences between the simulation operation and the physical entity of the equipment to achieve synchronization between the digital twin and the physical entity; at the same time, feedback is provided to the physical entity to achieve optimized operation of the physical entity; and in the energy element digital twin, the willingness of each energy element in the integrated energy system to participate in demand response scheduling behavior is measured by calculating the influence value of the energy element;

[0117] The optimization scheduling unit is used to perform multi-objective optimization decisions on the energy elements participating in the grid scheduling task based on the electricity prices in different time periods and preset constraints through the modified digital twin of the energy element to obtain the optimal Pareto solution set; based on the said Pareto solution set, the charging and discharging power of the energy storage device in the integrated energy system, the output power of each unit and the power of the interconnection line are obtained.

[0118] Furthermore, the system described in this embodiment corresponds to the method described in Example 1, and its technical details have been described in detail in Example 1, so they will not be repeated here.

[0119] In further embodiments, there is also provided:

[0120] An electronic device includes a memory and a processor, and computer instructions stored in the memory and executed by the processor. When the computer instructions are executed by the processor, the method described in Example 1 is performed. For the sake of brevity, no further details are given here.

[0121] It should be understood that in this embodiment, the processor may be a central processing unit (CPU), or may be other general-purpose processors, digital signal processors (DSP), application-specific integrated circuits (ASIC), off-the-shelf field-programmable gate arrays (FPGA), or other programmable logic devices, discrete gate or transistor logic devices, discrete hardware components, etc. The general-purpose processor may be a microprocessor or any conventional processor, etc.

[0122] The memory may include a read-only memory and a random access memory, and provides instructions and data to the processor. A portion of the memory may also include a non-volatile random access memory. For example, the memory may also store information about the device type.

[0123] A computer-readable storage medium is used to store computer instructions, and when the computer instructions are executed by a processor, the method described in embodiment 1 is performed.

[0124] The method in Example 1 can be directly implemented as being executed by a hardware processor, or by a combination of hardware and software modules within the processor. The software module can be located in a storage medium well-established in the art, such as random access memory, flash memory, read-only memory, programmable read-only memory, electrically erasable programmable memory, or registers. The storage medium is located in the memory, and the processor reads the information in the memory and, in conjunction with its hardware, completes the steps of the above method. To avoid repetition, a detailed description is not given here.

[0125] Those skilled in the art will appreciate that the units, i.e., algorithm steps, of the various examples described in this embodiment can be implemented using electronic hardware or a combination of computer software and electronic hardware. Whether these functions are implemented in hardware or software depends on the specific application and design constraints of the technical solution. Professionals and technicians may use different methods to implement the described functions for each specific application, but such implementation should not be considered beyond the scope of this disclosure.

[0126] The multi-energy IDR scheduling method and system based on energy element digital twins provided in the above embodiment can be implemented and has broad application prospects.

[0127] The foregoing description is merely a preferred embodiment of the present disclosure and is not intended to limit the present disclosure. Those skilled in the art will readily appreciate that various modifications and variations are possible. Any modifications, equivalent substitutions, or improvements made within the spirit and principles of the present disclosure shall be included within the scope of protection of the present disclosure.

Claims

1. A multi-energy IDR scheduling method based on energy element digital twin, characterized by: include: Based on the physical model of the equipment in the integrated energy system and its corresponding initial state and constraints, a virtual mapping of the integrated energy system is created to realize the construction of the energy element digital twin model; based on the historical power generation data of the integrated energy system, a deep neural network is used to predict the load and power generation data on similar days; The energy element digital twin model is modified based on the parameters in the physical model of the integrated energy system and the predicted similar daily load and power generation data; wherein, during the simulation operation process, the energy element digital twin model adjusts the coefficients of the simulation operation model based on the differences between the simulation operation and the physical entity of the equipment to achieve synchronization between the digital twin and the physical entity; at the same time, feedback is provided to the physical entity to achieve optimized operation of the physical entity; and in the energy element digital twin, the willingness of each energy element in the integrated energy system to participate in demand response scheduling behavior is measured by calculating the influence value of the energy element; For energy elements involved in grid dispatching tasks, based on electricity prices in different time periods and preset constraints, multi-objective optimization decisions are made through the revised digital twin of the energy element to obtain the optimal Pareto solution set; based on the Pareto solution set, the charging and discharging power of the energy storage device in the integrated energy system, the output power of each unit and the power of the interconnecting line are obtained.

2. The multi-energy IDR scheduling method based on energy element digital twin according to claim 1 is characterized in that: The calculation of the influence value of the energy element is specifically the weighted sum of the contribution capability value, participation capability value, privacy budget value and activity value of the energy element, wherein the contribution capability value is determined based on the user's maximum adjustable capability, the participation capability value is determined based on the external environmental conditions that affect the user's decision and the user's satisfaction, the privacy budget value is determined based on the privacy data contributed by the user, and the activity value is determined based on the user's historical influence performance.

3. The multi-energy IDR scheduling method based on energy element digital twin according to claim 1 is characterized in that: The optimization objectives of the multi-objective optimization decision include the maintenance cost of distributed energy, the transaction cost with the power grid, natural gas grid and load, and the environmental protection cost of emitting CO2, SO2 and NOx.

4. The multi-energy IDR scheduling method based on energy element digital twin according to claim 1 is characterized in that: The multi-objective optimization decision is performed through the modified energy element digital twin, and specifically the NSGA-II algorithm is used for the multi-objective optimization decision.

5. The multi-energy IDR scheduling method based on energy element digital twin according to claim 1 is characterized in that: The integrated energy system includes a variety of energy conversion equipment and communication equipment to achieve the coupling of different energy subsystems such as electricity, heat, natural gas and hydrogen, and output to hydrogen load, electricity load and heat load.

6. A multi-energy IDR scheduling system based on energy element digital twin, characterized by: include: A digital twin model construction unit, which is used to create a virtual mapping of the integrated energy system based on the physical model of the equipment in the integrated energy system and its corresponding initial state and constraints, thereby realizing the construction of the energy element digital twin model; A prediction unit, which is used to predict the load and power generation data of similar days based on the historical power generation data of the integrated energy system using a deep neural network; A correction unit, configured to correct the energy element digital twin model based on parameters in the physical model of the integrated energy system and predicted similar daily load and power generation data; wherein, during the simulation operation process, the energy element digital twin model adjusts the coefficients of the simulation operation model based on the differences between the simulation operation and the physical entity of the equipment to achieve synchronization between the digital twin and the physical entity; at the same time, feedback is provided to the physical entity to achieve optimized operation of the physical entity; and in the energy element digital twin, the willingness of each energy element in the integrated energy system to participate in demand response scheduling behavior is measured by calculating the influence value of the energy element; The optimization scheduling unit is used to perform multi-objective optimization decisions on the energy elements participating in the grid scheduling task based on the electricity prices in different time periods and preset constraints through the modified digital twin of the energy element to obtain the optimal Pareto solution set; based on the said Pareto solution set, the charging and discharging power of the energy storage device in the integrated energy system, the output power of each unit and the power of the interconnection line are obtained.

7. The multi-energy IDR scheduling system based on energy element digital twin according to claim 1 is characterized in that: The calculation of the influence value of the energy element is specifically the weighted sum of the contribution capability value, participation capability value, privacy budget value and activity value of the energy element, wherein the contribution capability value is determined based on the user's maximum adjustable capability, the participation capability value is determined based on the external environmental conditions that affect the user's decision and the user's satisfaction, the privacy budget value is determined based on the privacy data contributed by the user, and the activity value is determined based on the user's historical influence performance.

8. The multi-energy IDR scheduling system based on energy element digital twin according to claim 1, characterized in that: The optimization objectives of the multi-objective optimization decision include the maintenance cost of distributed energy, the transaction cost with the power grid, natural gas grid and load, and the environmental protection cost of emitting CO2, SO2 and NOx.

9. An electronic device comprising a memory, a processor, and a computer program stored and running on the memory, characterized in that: When the processor executes the program, it implements a multi-energy IDR scheduling method based on energy element digital twins as described in any one of claims 1-5.

10. A non-transitory computer-readable storage medium having a computer program stored thereon, characterized in that: When the program is executed by a processor, it implements a multi-energy IDR scheduling method based on energy element digital twins as described in any one of claims 1 to 5.

Images