Low-carbon intelligent energy scheduling method and system based on virtual power distribution network and element universe

Abstract

The invention relates to a low-carbon intelligent energy scheduling method and system based on a virtual power distribution network and a universe, and the method comprises the following steps: obtaining the operation state data and environment parameters of all distributed energy equipment in real time, and constructing a virtual twinborn body of the distributed energy equipment; on the basis of the virtual twins of the distributed energy equipment, a virtual power distribution network is formed through aggregation, and an optimal scheduling model is constructed with carbon emission minimization; establishing a real-time evaluation index system based on the virtual power distribution network; and based on the real-time evaluation index system, constructing a target decision scheduling model in combination with the optimal scheduling model, and performing low-carbon intelligent energy scheduling based on the target decision scheduling model to complete the scheduling process. Compared with the prior art, the method has the advantages of improving the intelligent energy scheduling level, realizing efficient utilization of renewable energy sources and the like.

Description

Technical Field

[0001] The present invention relates to the field of power grid technology, and in particular to a low-carbon intelligent energy dispatching method based on a virtual distribution network and a metaverse. Background Art

[0002] With the global emphasis on sustainable development and low-carbon economy, the power system is facing tremendous transformation pressure. Traditional power systems mainly rely on fossil fuels for energy production, and their carbon emissions are significant, leading to the intensification of global warming and environmental pollution. Therefore, how to effectively use renewable energy to achieve low-carbon and sustainable development has become an important issue in the current power system management. In terms of distributed energy management, existing technologies usually adopt a single data collection and monitoring method, which makes it difficult to achieve comprehensive status monitoring of distributed energy equipment (such as photovoltaic power generation, wind power generation and energy storage systems). This single monitoring method not only limits the real-time understanding of the equipment's operating status, but also lacks flexible scheduling capabilities when facing dynamically changing power demand. In addition, traditional optimization scheduling methods often rely on static models and cannot be adaptively adjusted according to real-time data, resulting in insufficient flexibility of the system in low-carbon scheduling. On the other hand, digital twin technology, as an emerging method, can provide real-time status monitoring and prediction capabilities for equipment, but it still has shortcomings in existing applications. Specifically, the application of digital twin technology in distributed energy scheduling management has not been fully explored, especially in multi-scenario simulation verification, and a mature solution has not yet been formed. This limits its potential in optimizing scheduling, reducing carbon emissions and other fields.

[0003] In summary, in the existing technology of distributed energy scheduling management, it is difficult to achieve comprehensive monitoring of equipment status and adaptive optimization scheduling through digital twin technology, resulting in insufficient flexibility of the system in low-carbon scheduling. Therefore, it is urgent to develop a low-carbon intelligent energy scheduling management method to achieve the goal of efficient utilization of renewable energy and low-carbon operation. Summary of the invention

[0004] The purpose of the present invention is to provide a low-carbon intelligent energy scheduling method based on a virtual distribution network and a metaverse to improve the flexibility of low-carbon scheduling.

[0005] The purpose of the present invention can be achieved by the following technical solutions:

[0006] A low-carbon intelligent energy dispatching method based on a virtual distribution network and a metaverse comprises the following steps:

[0007] Obtain the operating status data and environmental parameters of each distributed energy device in real time and build a virtual twin of the distributed energy device;

[0008] Based on the virtual twins of the distributed energy devices, a virtual distribution network is aggregated and an optimized dispatching model is constructed with carbon emission minimization;

[0009] Based on the virtual distribution network, a real-time evaluation index system is established;

[0010] Based on the real-time evaluation index system, a target decision scheduling model is constructed in combination with the optimization scheduling model, and low-carbon intelligent energy scheduling is performed based on the target decision scheduling model to complete the scheduling process.

[0011] Furthermore, the step of constructing a virtual twin of a distributed energy device includes:

[0012] Obtain historical operating status data of each distributed energy device;

[0013] Based on historical operating status data, combined with real-time operating status data and environmental parameters, a state space model of each distributed energy device is constructed;

[0014] A virtual twin of a distributed energy device is modeled based on the state space model.

[0015] Furthermore, the expression of the state space model is:

[0016] X t+1 =AX t +BU t +W t

[0017] In the formula, X t+1 is the state vector at time t+1, X t is the state vector at time t, representing the current state, A is the state transfer matrix determined based on the historical operation state data, and B is the input matrix, describing the external input U t Impact on status, U t For external input, including environmental factors or changes in control signals, W t is the process noise, representing unpredictable random disturbances.

[0018] Furthermore, the formation process of the virtual distribution network includes:

[0019] Based on the virtual twins of the distributed energy devices, aggregating to form a virtual power plant;

[0020] The virtual power plants are further aggregated to form a virtual distribution network.

[0021] Furthermore, the expression of the optimization scheduling model is:

[0022]

[0023] In the formula, C total is the total carbon emissions, C j is the cost coefficient of the j-th energy source, P j,t Represents the dispatch power of the j-th energy at time t.

[0024] Furthermore, the steps of constructing the real-time evaluation index system include:

[0025] Determining indicators of multiple dimensions based on the virtual distribution network;

[0026] The indicators of the multiple dimensions are weighted to form a real-time evaluation indicator system, wherein the weighting step includes:

[0027] Based on expert opinions and experience, the subjective weights of multiple dimensional indicators are determined, where the calculation expression of subjective weights is:

[0028]

[0029] Where W subjective is the subjective weight of the indicator, w i is the weight of the ith data under the indicator, S i is the expert's rating;

[0030] The CRITIC method is used to calculate the objective weights of multiple dimensional indicators, where the calculation expression of objective weights is:

[0031]

[0032] Where W objective is the objective weight of the indicator, C j is the information content of the jth data under the indicator;

[0033] The subjective weighting results and the objective weighting results are combined to obtain the final comprehensive index weight, completing the construction process of the real-time evaluation index system, where the calculation expression of the comprehensive index weight is:

[0034] W final =αW subjective +(1-α)W objective

[0035] Where W final is the comprehensive indicator weight, and α is the balance coefficient between subjective weighting and objective weighting.

[0036] Furthermore, the indicators of the multiple dimensions include energy production indicators, energy storage and demand indicators, environment and operating condition indicators, and user satisfaction indicators.

[0037] The energy production index includes the power output and energy conversion efficiency of the distributed energy equipment, wherein the calculation expressions of the power output and the energy conversion efficiency are respectively:

[0038] P t =P pv,t +P wind,t +P storage,t

[0039]

[0040] Where P t is the actual power output of the distributed energy device at time t, P pv,t is the power output of photovoltaic power generation, P wind,t is the power output of wind power generation, P storage,t is the power output of the energy storage device, η t is the energy conversion efficiency, E input,t is the input energy of the distributed energy device at time t;

[0041] The energy storage and demand indicators include the energy storage state and load demand of the distributed energy equipment, wherein the calculation expressions of the energy storage state and load demand are:

[0042] E t =E t-1 +ΔE t

[0043]

[0044] In the formula, E t 、E t-1 are the energy storage states at time t and time t-1, ΔE t represents the energy change during time t, D t is the load demand, D k,t is the power demand of the kth user or device at time t;

[0045] The environment and operating condition indicators include external environmental factors and equipment operating status.

[0046] Furthermore, the target decision scheduling model aims to minimize operating costs and carbon emissions, and includes an objective function and constraints. The objective function is:

[0047]

[0048] The constraints are:

[0049] P j ≤P max,j ,

[0050] E t ≤E capacity ,

[0051]

[0052] In the formula, Z is the comprehensive value of system operation cost and carbon emission, C j is the cost coefficient of the j-th energy source, P j is the dispatch power of the jth energy source, λ is the weight coefficient of carbon emissions, CO2 j is the carbon emission of the jth energy source, P max,j is the maximum dispatch power of the jth energy source, E t is the storage state of energy at time t, E capacity is the maximum power storage capacity of the energy storage system, D t is the energy load demand at time t, D k,t is the power requirement of the kth user or device at time t.

[0053] Furthermore, it also includes evaluating the energy dispatch result by calculating the carbon emissions of the actual operation after the energy dispatch, wherein the calculation expression of the carbon emissions of the actual operation is:

[0054]

[0055] In the formula, CO2 j is the carbon emission of the jth energy source, P j is the dispatch power of the jth type of energy, and m is the number of energy types.

[0056] The present invention also provides a low-carbon intelligent energy dispatching system based on a virtual distribution network and a metaverse, comprising:

[0057] Virtual twin construction module: used to obtain the operating status data and environmental parameters of each distributed energy device in real time and build a virtual twin of the distributed energy device;

[0058] A virtual distribution network construction module is used to aggregate and form a virtual distribution network based on the virtual twin of the distributed energy equipment, and to construct an optimization scheduling model with the goal of minimizing carbon emissions;

[0059] A real-time evaluation index system building module is used to establish a real-time evaluation index system based on the virtual distribution network;

[0060] Energy scheduling module: used to build a target decision scheduling model based on the real-time evaluation index system and the optimization scheduling model, and perform low-carbon intelligent energy scheduling based on the target decision scheduling model to complete the scheduling process.

[0061] Compared with the prior art, the present invention has the following beneficial effects:

[0062] (1) The present invention constructs a virtual twin and aggregation operation through real-time data of each distributed energy device, and constructs an evaluation index system in real time. It combines the evaluation index and carbon emission minimization to construct an optimization scheduling model to construct a final target decision scheduling model. The present invention can realize real-time dynamic adjustment and resource scheduling through a real-time processing process, which solves the limitations of the prior art that relies on static models and improves the flexibility of low-carbon scheduling.

[0063] (2) The present invention uses metaverse technology to construct virtual twins and aggregate operations, which can digitize and map multi-energy systems into a virtual environment. It can not only realize comprehensive status monitoring of distributed energy equipment, but also realize a panoramic display of different energy scenarios, breaking through the physical limitations of traditional power plants. Through energy scheduling optimization, it can intuitively schedule energy systems in different regions and time periods, thereby improving the visualization and global control capabilities of energy scheduling management.

[0064] (3) The target decision-making scheduling model of the present invention aims to minimize carbon emissions and cost operations, thereby minimizing operating costs while minimizing low carbon emissions. BRIEF DESCRIPTION OF THE DRAWINGS

[0065] Figure 1 It is a schematic diagram of the method flow of the present invention;

[0066] Figure 2 This is a diagram of the hierarchical partition management architecture of a multi-agent system according to an embodiment of the present invention. DETAILED DESCRIPTION

[0067] The present invention is described in detail below in conjunction with the accompanying drawings and specific embodiments. This embodiment is implemented based on the technical solution of the present invention, and provides a detailed implementation method and specific operation process, but the protection scope of the present invention is not limited to the following embodiments.

[0068] Example 1

[0069] This embodiment provides a low-carbon intelligent energy scheduling method based on a virtual distribution network and a metaverse. Figure 1 As shown, the method comprises the following steps:

[0070] Step 1: Create a virtual twin of distributed energy.

[0071] The present invention first constructs a virtual twin of distributed energy equipment (such as photovoltaic power generation, wind power generation and energy storage equipment). The implementation process of this step includes the following key links:

[0072] Step 1.1: Data collection and feature modeling, by installing sensors on distributed energy equipment, the operating status and environmental parameters of the equipment are collected in real time.

[0073] Key parameters include:

[0074] (1)P t : Power output of the device at time t;

[0075] (2)E t : The energy storage state of the device at time t (e.g., the battery charge state);

[0076] (3)D t : The load demand of the equipment at time t (such as the real-time power demand of the electrical equipment);

[0077] (4)H t : External environmental factors, such as temperature, light intensity, wind speed, etc.;

[0078] The calculation relationship of equipment power output can be expressed as:

[0079] P t =f(E t ,D t ,H t ) (1)

[0080] The function f represents the complex relationship between power output and the storage state of the device, load demand and external environment. By establishing a regression model or other prediction model, it is possible to predict P t accurate predictions.

[0081] Step 1.2: Construction of virtual twin.

[0082] Based on real-time data collection and combined with historical operation data, a virtual model of the equipment is created. The model should include the following features:

[0083] (1) Dynamic response capability: The model can automatically adjust according to real-time data to reflect changes in equipment status.

[0084] (2) Multidimensional data fusion: Integrate the historical performance data of the equipment and the external environment data to provide comprehensive information support for the model.

[0085] (3) Simulation function: Ability to simulate the behavior and performance of equipment under different operating conditions and environmental changes.

[0086] For example, a virtual twin can be modeled using a state-space model, enabling it to capture dynamic changes in a time series:

[0087] X t+1 =AXt +BU t +W t (2)

[0088] Among them, X t is the state vector, A is the state transfer matrix, B is the input matrix, U t is the control input, W t is the process noise.

[0089] Step 1.3: Dynamic monitoring and feedback mechanism.

[0090] After the virtual twin is created, the system will implement dynamic monitoring and continuously collect real-time data from the device. The monitoring content includes:

[0091] (1) Real-time power output P t changes in

[0092] (2) Storage state E t changes in the charge and discharge process;

[0093] (3) External environmental factors t changes in the environment, such as changes in light and temperature.

[0094] For example, a virtual twin can be modeled using a state-space model, enabling it to capture dynamic changes in a time series:

[0095] X t+1 =AX t +BU t +W t (2)

[0096] Among them, X t is the state vector, A is the state transfer matrix, B is the input matrix, U t is the control input, W t is the process noise.

[0097] Step 2: Aggregate the virtual twins into a virtual distribution network.

[0098] After creating virtual twins of distributed energy resources, the next step is to aggregate these virtual twins into a virtual power plant to achieve unified management and coordinated scheduling of various distributed energy resources. The implementation process of this step includes the following key links, which reflects the layer-by-layer aggregation process from the device level to the virtual power plant level and then to the distribution network level.

[0099] Step 2.1: Data integration and resource identification.

[0100] like Figure 2As shown in the figure, at this stage, the real-time data collected by multiple distributed energy virtual twins (such as photovoltaic power generation, wind power generation, energy storage equipment, etc.) are integrated to form a virtual power plant twin; multiple virtual power plant twins will be further aggregated to form a distribution network twin. The key to this process is to achieve hierarchical and partitioned management at the device level, virtual power plant level, and distribution network level.

[0101] (1) Equipment level: Each energy device collects operating status and environmental parameters through sensors and monitors key indicators in real time, such as power output P t , Energy storage state E t and load demand D t .

[0102] (2) Virtual power plant level: By aggregating and processing the data at the equipment level, the overall status of the virtual power plant can be obtained. The formula is as follows:

[0103]

[0104] Where: P i,t Represents the power output of the i-th virtual twin at time t.

[0105] (3) Distribution network level: Ultimately, the data of the virtual power plant is combined with the operating information of the distribution network to form a dynamic, globally optimized energy management system to achieve overall scheduling and coordination of distributed energy.

[0106] Step 2.2: Establishment of optimization scheduling model.

[0107] Based on the integrated real-time data, an optimization scheduling model is established to achieve dynamic scheduling of various energy resources. This model takes into account the characteristics and relationships of each virtual twin to ensure that carbon emissions can be minimized while meeting load requirements. The model can be expressed as:

[0108]

[0109] Where: C j represents the cost coefficient of the j-th energy type, P j,t Represents the dispatch power of the j-th energy at time t.

[0110] Step 2.3: Real-time feedback and adjustment mechanism.

[0111] During the operation of the virtual power plant model, the system needs to continuously monitor real-time data and make feedback adjustments. By building a dynamic monitoring and feedback mechanism, the system can respond promptly to sudden load changes, environmental changes, etc. For example, when external environmental factors H t When power output is affected by changes in weather conditions, the system will adjust the scheduling strategy in real time to deal with:

[0112] E t =E t-1 +ΔE t (5)

[0113] When H t When ΔE changes t Updates can ensure the stability and flexibility of virtual power plants under different conditions.

[0114] Step 3: Establish a real-time evaluation indicator system.

[0115] After the virtual power plant successfully aggregates the virtual twin of distributed energy, establishing a real-time evaluation index system is an important link to ensure the efficient operation of the system and decision support. The core of this system is to conduct a comprehensive and accurate assessment of the operating status of the power system through scientific evaluation indicators to support the implementation of low-carbon intelligent decision-making.

[0116] Step 3.1: Construction of indicator system.

[0117] The real-time evaluation index system should cover indicators in multiple dimensions, mainly including the following aspects:

[0118] (1) Energy production index: an index reflecting energy production capacity and efficiency

[0119] Power output P t : The actual power output at time t can be expressed by the following formula:

[0120] P t =P pv,t +P wind,t +P storage,t (6)

[0121] Among them, P pv,t is the power output of photovoltaic power generation, P wind,t is the power output of wind power generation, P storage,t is the power output of the energy storage device.

[0122] Energy conversion efficiency η t : Indicates the efficiency of the device in converting input energy into electrical energy. The calculation formula is:

[0123]

[0124] Among them, E input,t is the input energy of the device at time t.

[0125] (2) Energy storage and demand indicators: indicators for evaluating energy storage status and load demand

[0126] Energy storage state E t: The charging and discharging status of the energy storage device can be monitored by the following formula:

[0127] E t =E t-1 +ΔE t (8)

[0128] Where, ΔE t represents the energy change during time t.

[0129] Load demand D t : Real-time load demand changes, expressed as:

[0130]

[0131] Among them, D k,t is the power requirement of the kth user or device at time t.

[0132] (3) Environmental and operating condition indicators: indicators for monitoring external environmental factors and equipment operating conditions

[0133] External environmental factors t : Such as temperature T t , humidity RH t , light intensity I t Etc. These factors will affect the performance of the equipment.

[0134] Equipment operating status monitoring indicators: such as operating current I t , operating voltage V t , which can be collected in real time through sensors.

[0135] (4) User satisfaction index: an index reflecting the user's satisfaction with power services

[0136] User feedback rating S t : Collect user satisfaction scores on electricity supply through surveys, usually between 1 and 5

[0137] Step 3.2: Indicator weights and comprehensive evaluation.

[0138] To ensure the comprehensiveness and scientificity of the evaluation, each indicator is weighted. By combining subjective and objective weighting methods (such as CRITIC method and hierarchical analysis method), a comprehensive weight value is obtained, thereby achieving a comprehensive evaluation of multiple indicators. The specific steps include:

[0139] (1) Subjective weighting: Based on expert opinions and experience, the indicators are preliminarily weighted and the weights of the indicators are calculated using the weighted sum method. The formula is as follows:

[0140]

[0141] Among them, w i is the weight of the ith indicator, S i It is the rating given by the experts.

[0142] (2) Use the correlation between data to calculate the objective weight of the indicator, usually using the CRITIC method. The objective weight can be expressed as:

[0143]

[0144] Among them, C j is the information content of the jth indicator.

[0145] (3) Combine the subjective and objective weighting results to obtain the final comprehensive indicator weight, the formula is as follows:

[0146] W final =αW subjective +(1-α)W objective (12)

[0147] Among them, α is the balance coefficient between subjective weighting and objective weighting, which is usually adjusted between 0 and 1.

[0148] By establishing a real-time evaluation index system, the virtual power plant can effectively monitor and evaluate the operating status of various distributed energy sources, providing strong data support for subsequent scheduling decisions and optimization management.

[0149] Step 4: Low-carbon intelligent decision-making and scheduling based on evaluation indicators.

[0150] After establishing a real-time evaluation index system, making low-carbon intelligent decisions based on these indicators is an important step to ensure the efficient operation and low-carbonization of virtual power plants. This step aims to achieve optimal scheduling and management of energy resources through scientific data analysis and decision-making algorithms, thereby reducing carbon emissions.

[0151] Step 4.1: Construction of scheduling decision support mechanism.

[0152] Using the real-time evaluation index system, an integrated scheduling decision support mechanism is constructed, including the following:

[0153] (1) Data input: Collect real-time data from each virtual twin and sensor as a basis for decision making. This data includes power output, load demand, energy storage status, environmental factors, etc.

[0154] (2) Decision analysis: Based on the collected data, a target decision scheduling model is constructed, and a variety of intelligent algorithms (such as linear programming, genetic algorithms, deep learning, etc.) are applied for decision analysis. The main steps include:

[0155] Objective function setting: Setting optimization goals, such as minimizing the system’s operating costs and carbon emissions:

[0156]

[0157] Constraint setting: Ensure that the decision results meet the actual operational constraints, such as:

[0158]

[0159] ·Decision output: Based on the results of decision analysis, output the optimized dispatch plan, including dispatch strategies, operating parameters and adjustment suggestions for various energy sources.

[0160] Step 4.2: Intelligent scheduling and optimization.

[0161] Based on the evaluation index system in step 3, intelligent scheduling and optimization are implemented using a decision support system. By real-time monitoring of data in multiple dimensions such as energy production, energy storage status, load demand, environmental conditions, and user satisfaction, the intelligent algorithm prioritizes the scheduling of renewable energy or traditional energy according to the changes in these indicators to ensure efficient resource utilization and minimize carbon emissions. For example, during peak loads, the system prioritizes the scheduling of photovoltaic and wind power by monitoring power output, load demand, and user satisfaction indicators. During unpredictable lows, the energy storage system is called in a timely manner using energy storage status indicators, and user satisfaction with power supply is evaluated in real time. If satisfaction decreases, the system will adjust the scheduling strategy based on user feedback data and historical records to improve power supply quality and user experience, thereby ensuring the stability and efficiency of the power system and maximizing user satisfaction.

[0162] Step 4.3: Low carbon performance assessment.

[0163] Regularly conduct low-carbon performance evaluation on the scheduling results to verify the effectiveness of system operation.

[0164] Key metrics include:

[0165] (1) Carbon emissions: Evaluate the effectiveness of low-carbon strategies by calculating actual carbon emissions.

[0166]

[0167] (2) Economic benefits: By evaluating operating costs and benefits, the economic benefits of low-carbonization measures are analyzed to ensure that economic feasibility is maintained while reducing carbon emissions.

[0168] Step 4.4: Decision optimization and learning.

[0169] Use machine learning algorithms to analyze historical decision-making data, summarize operating experience, and optimize decision-making strategies. The system can continuously adjust model parameters based on historical operating data to improve the accuracy and adaptability of decision-making.

[0170] This embodiment is applied in an actual scenario according to the above method, including the following steps:

[0171] Step 1): Create a virtual twin of distributed energy. By installing sensors on distributed energy equipment such as photovoltaic power generation, wind power generation, and energy storage equipment, the operating status data of the equipment (including power output, energy storage status, and external environmental factors) is collected in real time, and a corresponding virtual model is constructed to dynamically reflect the performance of the equipment;

[0172] Step 2): Aggregate virtual twins into virtual power plants. Through the integration of real-time data, the data of various distributed energy virtual twins are aggregated to form a unified virtual power plant model. On this basis, an optimization scheduling model is constructed to achieve dynamic scheduling of energy resources to ensure that load demand is met while reducing carbon emissions;

[0173] Step 3): Establish a real-time evaluation index system. Construct a multi-dimensional evaluation index system including energy production, storage and demand, environment and operating conditions, and user satisfaction. Through real-time data monitoring and analysis, calculate the weights of various indicators, and use the comprehensive weight optimization method to obtain the final comprehensive index to support the subsequent decision-making process;

[0174] Step 4): Low-carbon intelligent decision-making based on evaluation indicators. Using the established decision support system, intelligent scheduling and optimization are carried out according to real-time evaluation indicators. In this process, optimization goals are set, such as minimizing operating costs and carbon emissions, and priority scheduling of various energy sources is achieved through intelligent algorithms, and real-time monitoring and feedback are provided to ensure optimal resource utilization under the premise of low carbonization.

[0175] In summary, in order to meet the existing challenges, this embodiment combines virtual power plants (VPPs) with metaverse technology to provide a new management idea for power systems. Virtual power plants achieve unified management and scheduling by integrating a variety of distributed energy resources, while metaverse technology provides users with a visual and interactive management environment. This combination not only helps to improve the visualization capabilities of energy management, but also enhances the application of real-time data, making the power system more flexible in scheduling optimization and low-carbon operation.

[0176] Example 2

[0177] This embodiment provides a low-carbon intelligent energy dispatching system based on a virtual distribution network and a metaverse, including:

[0178] Virtual twin construction module: used to obtain the operating status data and environmental parameters of each distributed energy device in real time and build a virtual twin of the distributed energy device;

[0179] A virtual distribution network construction module is used to aggregate and form a virtual distribution network based on the virtual twin of the distributed energy equipment, and to construct an optimization scheduling model with the goal of minimizing carbon emissions;

[0180] A real-time evaluation index system building module is used to establish a real-time evaluation index system based on the virtual distribution network;

[0181] Energy scheduling module: used to build a target decision scheduling model based on the real-time evaluation index system and the optimization scheduling model, and perform low-carbon intelligent energy scheduling based on the target decision scheduling model to complete the scheduling process.

[0182] The rest is the same as in Example 1.

[0183] If the above functions are implemented in the form of software functional units and sold or used as independent products, they can be stored in a computer-readable storage medium. Based on this understanding, the technical solution of the present invention, or the part that contributes to the prior art, or the part of the technical solution, can be embodied in the form of a software product. The computer software product is stored in a storage medium, including several instructions for a computer device (which can be a personal computer, a server, or a network device, etc.) to perform all or part of the steps of the method described in each embodiment of the present invention. The aforementioned storage medium includes: U disk, mobile hard disk, read-only memory (ROM, Read-Only Memory), random access memory (RAM, Random Access Memory), disk or optical disk, etc., which can store program code.

[0184] It will be appreciated by those skilled in the art that embodiments of the present invention may be provided as methods, systems, or computer program products. Therefore, the present invention may take the form of a complete hardware embodiment, a complete software embodiment, or an embodiment combining software and hardware. Moreover, the present invention may take the form of a computer program product implemented on one or more computer-usable storage media (including but not limited to disk storage, CD-ROM, optical storage, etc.) containing computer-usable program codes. The schemes in the embodiments of the present invention may be implemented in various computer languages, for example, object-oriented programming language Java and literal scripting language JavaScript, etc.

[0185] The present invention is described with reference to flowcharts and / or block diagrams of methods, devices (systems), and computer program products according to embodiments of the present invention. It should be understood that each process and / or block in the flowchart and / or block diagram, as well as the combination of processes and / or blocks in the flowchart and / or block diagram, can be implemented by computer program instructions. These computer program instructions can be provided to a processor of a general-purpose computer, a special-purpose computer, an embedded processor, or other programmable data processing device to produce a machine, so that the instructions executed by the processor of the computer or other programmable data processing device generate instructions for implementing the processes in the flowchart and / or block diagram. Figure 1 A process or multiple processes and / or boxes Figure 1 A device that provides the functions specified in a block or multiple blocks.

[0186] These computer program instructions may also be stored in a computer-readable memory capable of directing a computer or other programmable data processing device to operate in a specific manner, so that the instructions stored in the computer-readable memory produce an article of manufacture comprising an instruction device, which implements the process Figure 1 A process or multiple processes and / or boxes Figure 1 A function specified in one or more boxes.

[0187] These computer program instructions can also be loaded onto a computer or other programmable data processing device so that a series of operating steps are executed on the computer or other programmable device to produce a computer-implemented process, thereby providing instructions for implementing the process in the computer or other programmable device. Figure 1 A process or multiple processes and / or boxes Figure 1 The steps for the functions specified in one or more boxes.

[0188] Although the preferred embodiments of the present invention have been described, those skilled in the art may make other changes and modifications to these embodiments once they have learned the basic creative concept. Therefore, the appended claims are intended to be interpreted as including the preferred embodiments and all changes and modifications that fall within the scope of the present invention.

[0189] Obviously, those skilled in the art can make various changes and modifications to the present invention without departing from the spirit and scope of the present invention. Thus, if these modifications and variations of the present invention fall within the scope of the claims of the present invention and their equivalents, the present invention is also intended to include these modifications and variations.

Claims

1. A low-carbon intelligent energy dispatching method based on virtual distribution network and metaverse, characterized in that: The following steps are involved: Obtain the operating status data and environmental parameters of each distributed energy device in real time and build a virtual twin of the distributed energy device; Based on the virtual twins of the distributed energy devices, a virtual distribution network is aggregated and an optimized dispatching model is constructed with carbon emission minimization; Based on the virtual distribution network, a real-time evaluation index system is established; Based on the real-time evaluation index system, a target decision scheduling model is constructed in combination with the optimization scheduling model, and low-carbon intelligent energy scheduling is performed based on the target decision scheduling model to complete the scheduling process.

2. A low-carbon intelligent energy dispatching method based on virtual distribution network and metaverse according to claim 1, characterized in that: The steps of constructing a virtual twin of a distributed energy device include: Obtain historical operating status data of each distributed energy device; Based on historical operating status data, combined with real-time operating status data and environmental parameters, a state space model of each distributed energy device is constructed; A virtual twin of a distributed energy device is modeled based on the state space model.

3. According to claim 2, a low-carbon intelligent energy dispatching method based on virtual distribution network and metaverse is characterized in that: The expression of the state space model is: X t+1 =AX t +BU t +W t Where, X t+1 is the state vector at time t+1, X t is the state vector at time t, representing the current state, A is the state transfer matrix determined based on the historical operation state data, and B is the input matrix, describing the external input U t Impact on status, U t For external input, including environmental factors or changes in control signals, W t is the process noise, representing unpredictable random disturbances.

4. A low-carbon intelligent energy dispatching method based on virtual distribution network and metaverse according to claim 1, characterized in that: The formation process of the virtual distribution network includes: Based on the virtual twins of the distributed energy devices, aggregating to form a virtual power plant; The virtual power plants are further aggregated to form a virtual distribution network.

5. According to claim 1, a low-carbon intelligent energy dispatching method based on virtual distribution network and metaverse is characterized in that: The expression of the optimization scheduling model is: In the formula, C total is the total carbon emissions, C j is the cost coefficient of the j-th energy source, P j,t Represents the dispatch power of the j-th energy at time t.

6. A low-carbon intelligent energy dispatching method based on virtual distribution network and metaverse according to claim 1, characterized in that: The steps of constructing the real-time evaluation index system include: Determining indicators of multiple dimensions based on the virtual distribution network; The indicators of the multiple dimensions are weighted to form a real-time evaluation indicator system, wherein the weighting step includes: Based on expert opinions and experience, the subjective weights of multiple dimensional indicators are determined, where the calculation expression of subjective weights is: Where W subjective is the subjective weight of the indicator, w i is the weight of the i-th data under the indicator, S i is the expert's rating; The CRITIC method is used to calculate the objective weights of multiple dimensional indicators, where the calculation expression of objective weights is: Where W objective is the objective weight of the indicator, C j is the information content of the jth data under the indicator; The subjective weighting results and the objective weighting results are combined to obtain the final comprehensive index weight, completing the construction process of the real-time evaluation index system, where the calculation expression of the comprehensive index weight is: W final =αW subjective +(1-α)W objective Where W final is the comprehensive indicator weight, and α is the balance coefficient between subjective weighting and objective weighting.

7. A low-carbon intelligent energy dispatching method based on virtual distribution network and metaverse according to claim 6, characterized in that: The indicators in the multiple dimensions include energy production indicators, energy storage and demand indicators, environment and operating condition indicators, and user satisfaction indicators. The energy production index includes the power output and energy conversion efficiency of the distributed energy equipment, wherein the calculation expressions of the power output and the energy conversion efficiency are respectively: P t =P pv,t +P wind,t +P storage,t Where P t is the actual power output of the distributed energy device at time t, P pv,t is the power output of photovoltaic power generation, P wind,t is the power output of wind power generation, P storage,t is the power output of the energy storage device, η t is the energy conversion efficiency, E input,t is the input energy of the distributed energy device at time t; The energy storage and demand indicators include the energy storage state and load demand of the distributed energy equipment, wherein the calculation expressions of the energy storage state and load demand are: E t =E t-1 +ΔE t In the formula, E t 、E t-1 are the energy storage states at time t and time t-1, ΔE t represents the energy change during time t, D t is the load demand, D k,t is the power demand of the kth user or device at time t; The environment and operating condition indicators include external environmental factors and equipment operating status.

8. A low-carbon intelligent energy dispatching method based on virtual distribution network and metaverse according to claim 1, characterized in that: The target decision scheduling model aims to minimize operating costs and carbon emissions, and includes an objective function and constraints. The objective function is: The constraints are: P j ≤P max,j , AND t ≤E capacity , In the formula, Z is the comprehensive value of system operation cost and carbon emission, C j is the cost coefficient of the j-th energy source, P j is the dispatch power of the jth energy source, λ is the weight coefficient of carbon emissions, CO2 j is the carbon emission of the jth energy source, P max,j is the maximum dispatch power of the jth energy source, E t is the storage state of energy at time t, E capacity is the maximum power storage capacity of the energy storage system, D t is the energy load demand at time t, D k,t is the power requirement of the kth user or device at time t.

9. A low-carbon intelligent energy dispatching method based on virtual distribution network and metaverse according to claim 1, characterized in that: It also includes evaluating the energy dispatch results by calculating the carbon emissions of actual operation after energy dispatch, where the calculation expression of the carbon emissions of actual operation is: In the formula, CO2 j is the carbon emission of the jth energy source, P j is the dispatch power of the jth type of energy, and m is the number of energy types.

10. A low-carbon intelligent energy dispatching system based on virtual distribution network and metaverse, characterized in that: include: Virtual twin construction module: used to obtain the operating status data and environmental parameters of each distributed energy device in real time and build a virtual twin of the distributed energy device; A virtual distribution network construction module is used to aggregate and form a virtual distribution network based on the virtual twin of the distributed energy equipment, and to construct an optimization scheduling model with the goal of minimizing carbon emissions; A real-time evaluation index system building module is used to establish a real-time evaluation index system based on the virtual distribution network; Energy scheduling module: used to build a target decision scheduling model based on the real-time evaluation index system and the optimization scheduling model, and perform low-carbon intelligent energy scheduling based on the target decision scheduling model to complete the scheduling process.

Images