A virtual machine group digital modeling method and device, electronic equipment and storage medium

Abstract

This invention relates to the field of virtual machine group technology, and more particularly to a method, apparatus, electronic device, and storage medium for digital modeling of virtual machine groups. It addresses the problems of traditional distributed management models, such as difficulty in achieving accurate instruction decomposition and response feedback, and inaccurate dynamic characteristic characterization and untimely response. The invention includes: collecting distributed heterogeneous resources; constructing a resource digital model of the distributed heterogeneous resources; establishing a spatial mapping relationship between the resource digital model and power grid topology nodes; and constructing a virtual machine group digital model based on the spatial mapping relationship, the resource digital model, and preset virtual machine group construction principles.

Description

Technical Field

[0001] This invention relates to the field of virtual machine group technology, and in particular to a method, apparatus, electronic device and storage medium for digital modeling of virtual machine groups. Background Technology

[0002] Currently, massive heterogeneous distributed resources exhibit significant differences in time response characteristics and geographical location. Virtual power plants, as a key means to support the construction of new power systems, are evolving from simple resource aggregation to refined control of massive heterogeneous resources. However, these resources exhibit significant differences and coupling complexities in time response characteristics, spatial geographical distribution, and physical operating mechanisms, posing severe challenges to the real-time sensing, simulation calculation, and simulation demonstration of the power grid.

[0003] Traditional distributed management models often focus on data aggregation on the logical side, lacking deep integration of resource physical characteristics and spatial environment. This makes it difficult to achieve accurate instruction decomposition and response feedback when facing high-frequency real-time instructions such as frequency adjustment, voltage adjustment and blockage mitigation, resulting in problems such as inaccurate dynamic characteristic characterization and untimely response. Summary of the Invention

[0004] This invention provides a method, apparatus, electronic device, and storage medium for digital modeling of virtual machine groups, which solves the problems of inaccurate instruction decomposition and response feedback in traditional distributed management models, as well as inaccurate dynamic characteristic characterization and untimely response.

[0005] This invention provides a method for digital modeling of virtual machine groups, comprising:

[0006] Collect distributed heterogeneous resources;

[0007] Construct a resource digital model for the distributed heterogeneous resources;

[0008] Establish the spatial mapping relationship between the resource digital model and the power grid topology nodes;

[0009] The virtual machine group digital model is constructed based on the spatial mapping relationship, the resource digital model, and the preset virtual machine group construction principles.

[0010] Optionally, the step of constructing the resource digital model of the distributed heterogeneous resource includes:

[0011] The distributed heterogeneous resources are decomposed into objects to obtain a set of geometric parameters, a set of physical constraints, a set of dynamic behavior functions, and a set of rule constraints.

[0012] The geometric parameter set, the physical constraint set, the dynamic behavior function set, and the rule constraint set are encapsulated into a standardized state vector;

[0013] A resource digital model is constructed using the standardized state vectors.

[0014] Optionally, the process of generating the geometric parameter set includes:

[0015] Collect the latitude, longitude, altitude coordinates, and grid connection point number of the distributed heterogeneous resources;

[0016] Spatial coordinates are generated using the latitude, longitude, and altitude coordinates;

[0017] Establish a three-dimensional structural model of the distributed heterogeneous resource device, and generate three-dimensional bounding box parameters based on the three-dimensional structural model of the device;

[0018] A set of geometric parameters is generated using the spatial coordinates, the grid connection point number, and the three-dimensional bounding box parameters.

[0019] Optionally, the process of generating the physical constraint set includes:

[0020] Read the rated capacity, maximum charging and discharging power, minimum charging and discharging power, conversion efficiency, upper energy limit, and lower energy limit of the distributed heterogeneous resource;

[0021] A set of physical constraints is constructed using the rated capacity, the maximum charge / discharge power, the minimum charge / discharge power, the conversion efficiency, the upper energy limit, and the lower energy limit.

[0022] Optionally, the process of generating the dynamic behavior function set includes:

[0023] Collect the actual response curves of the distributed heterogeneous resources under multiple preset scheduling instructions and environmental variables;

[0024] A set of dynamic behavior functions is generated based on the preset scheduling instructions, the environmental variables, and the actual response curve.

[0025] Optionally, the rule constraint set generation process includes:

[0026] Obtain the market clearing rules, SOC operating range, and response constraints of the distributed heterogeneous resources;

[0027] The market clearing rules, the SOC operating range, and the response constraints are used to generate a set of rule constraints.

[0028] Optionally, the step of constructing a virtual machine group digital model based on the spatial mapping relationship, the resource digital model, and the preset virtual machine group construction principles includes:

[0029] According to the preset virtual machine group construction principle, multiple initial virtual machine groups are constructed for the power grid, and the resource set of the initial virtual machine group is generated according to the spatial mapping relationship and the resource digital model.

[0030] Based on the resource set and the resource digital model, determine the adjustable power upper and lower limits, safe operating range constraints, power change rate constraints, line power flow and node operation restrictions;

[0031] Add the adjustable power upper and lower limits, the safe operating range constraints, the power change rate constraints, the line power flow and node operation restrictions to the initial virtual machine group to generate a digital model of the virtual machine group.

[0032] The present invention also provides a digital modeling apparatus for virtual machine groups, comprising:

[0033] The distributed heterogeneous resource acquisition module is used to acquire distributed heterogeneous resources.

[0034] A resource digital model construction module is used to construct a resource digital model of the distributed heterogeneous resources;

[0035] The spatial mapping relationship establishment module is used to establish the spatial mapping relationship between the resource digital model and the power grid topology nodes;

[0036] The virtual machine group digital model construction module is used to construct a virtual machine group digital model based on the spatial mapping relationship, the resource digital model, and the preset virtual machine group construction principles.

[0037] The present invention also provides an electronic device, the device comprising a processor and a memory:

[0038] The memory is used to store program code and transmit the program code to the processor;

[0039] The processor is configured to execute the virtual machine group digital modeling method as described above, according to instructions in the program code.

[0040] The present invention also provides a computer-readable storage medium for storing program code for executing the virtual machine group digital modeling method as described in any of the preceding claims.

[0041] As can be seen from the above technical solutions, the present invention has the following advantages: The present invention discloses a digital modeling method for virtual machine groups, and specifically discloses: collecting distributed heterogeneous resources; constructing a resource digital model of distributed heterogeneous resources; establishing a spatial mapping relationship between the resource digital model and the power grid topology nodes; and constructing a virtual machine group digital model based on the spatial mapping relationship, the resource digital model, and the preset virtual machine group construction principles.

[0042] This invention constructs a digital model of distributed heterogeneous resources and establishes a spatial mapping relationship between it and the power grid topology nodes. Then, based on the spatial mapping relationship and the preset virtual machine group construction principle, the distributed heterogeneous resources are distributed into different virtual machine groups. The different virtual machine groups are used to decompose instructions and provide response feedback, thereby achieving the accuracy of distributed resource regulation and the timeliness of response. Attached Figure Description

[0043] To more clearly illustrate the technical solutions in the embodiments of the present invention or the prior art, the drawings used in the description of the embodiments or the prior art will be briefly introduced below. Obviously, the drawings described below are only some embodiments of the present invention. For those skilled in the art, other drawings can be obtained based on these drawings without creative effort.

[0044] Figure 1 A flowchart illustrating the steps of a digital modeling method for virtual machine groups provided in this embodiment of the invention;

[0045] Figure 2 A flowchart illustrating the steps of a digital modeling method for virtual machine groups, as provided in another embodiment of the present invention;

[0046] Figure 3 A flowchart illustrating the modeling steps of a resource digital model provided in this embodiment of the invention;

[0047] Figure 4 A logical schematic diagram of a digital modeling method for virtual machine groups provided in an embodiment of the present invention;

[0048] Figure 5 This is a structural block diagram of a virtual machine group digital modeling device provided in an embodiment of the present invention. Detailed Implementation

[0049] This invention provides a method, apparatus, electronic device, and storage medium for digital modeling of virtual machine groups, which addresses the problems of inaccurate instruction decomposition and response feedback in traditional distributed management models, as well as inaccurate dynamic characteristic characterization and untimely response.

[0050] To make the objectives, features, and advantages of this invention more apparent and understandable, the technical solutions of the embodiments of this invention will be clearly and completely described below with reference to the accompanying drawings. Obviously, the embodiments described below are only some embodiments of this invention, and not all embodiments. Based on the embodiments of this invention, all other embodiments obtained by those skilled in the art without creative effort are within the scope of protection of this invention.

[0051] Please see Figure 1 , Figure 1 A flowchart illustrating the steps of a digital modeling method for virtual machine groups provided in an embodiment of the present invention.

[0052] The present invention provides a digital modeling method for virtual machine groups, which may specifically include the following steps:

[0053] Step 101: Collect distributed heterogeneous resources;

[0054] In this embodiment of the invention, distributed heterogeneous resources may include distributed energy storage, photovoltaics, smart buildings, electric vehicle charging stations, 5G base stations, industrial plants, distributed wind power stations, distributed air conditioning, and photovoltaic-storage-direct-drive-flexible resources.

[0055] Step 102: Construct a resource digital model for distributed heterogeneous resources;

[0056] A digital model is a virtual or physical model constructed using digital technology, used to simulate, analyze, or represent real-world objects, systems, or processes. Digital models are widely used in fields such as industrial design, education and training, and scientific research experiments.

[0057] After collecting distributed heterogeneous resources, a digital twin model spanning multiple dimensions (spatial and temporal) can be constructed using behavioral algorithm logic written in VS Code and a physical structure model built in 3D Max. This digital twin model serves not only for 3D visualization but also as the foundation for a structured description of the resources' states and the representation of their physical constraints. Specifically, each type of resource is abstracted into a multi-dimensional state-space model containing geometric parameters, physical operating parameters, dynamic response functions, and operational rule constraints, forming a digital twin across multiple dimensions—the resource digital model.

[0058] Step 103: Establish the spatial mapping relationship between the resource digital model and the power grid topology nodes;

[0059] After constructing the resource digital model, a spatial mapping relationship between the resource digital model and the power grid topology nodes can be established, thereby establishing a connection between distributed heterogeneous resources and power grid topology nodes, providing a foundation for the subsequent resource allocation of virtual machine groups.

[0060] Step 104: Construct a virtual machine group digital model based on spatial mapping relationships, resource digital models, and preset virtual machine group construction principles.

[0061] This invention constructs a digital model of distributed heterogeneous resources and establishes a spatial mapping relationship between it and the power grid topology nodes. Then, based on the spatial mapping relationship and the preset virtual machine group construction principle, the distributed heterogeneous resources are distributed into different virtual machine groups. The different virtual machine groups are used to decompose instructions and provide response feedback, thereby achieving the accuracy of distributed resource regulation and the timeliness of response.

[0062] Please see Figure 2 , Figure 2 A flowchart illustrating the steps of a digital modeling method for virtual machine groups, provided in another embodiment of the present invention.

[0063] This invention provides a method for digital modeling of virtual machine groups, which may specifically include the following steps:

[0064] Step 201: Collect distributed heterogeneous resources;

[0065] In this embodiment of the invention, distributed heterogeneous resources may include distributed energy storage, photovoltaics, smart buildings, electric vehicle charging stations, 5G base stations, industrial plants, distributed wind power stations, distributed air conditioning, and photovoltaic-storage-direct-drive-flexible resources.

[0066] Step 202: Decompose the distributed heterogeneous resources into objects to obtain a set of geometric parameters, a set of physical constraints, a set of dynamic behavior functions, and a set of rule constraints;

[0067] like Figure 3 As shown, in this embodiment of the invention, constructing a resource data model for distributed heterogeneous resources may include four stages: model abstraction, model expression, model construction, and model execution.

[0068] First, we will abstract the physical devices of distributed heterogeneous resources.

[0069] Model abstraction specifically refers to the objectification and decomposition of physical devices, dividing them into four categories of attribute fields: geometric parameter set, physical constraint set, dynamic behavior function set, and rule constraint set.

[0070] In one example, the process of generating the geometric parameter set includes:

[0071] S211, collect the latitude, longitude, altitude coordinates and grid connection point number of distributed heterogeneous resources;

[0072] S212 uses latitude, longitude, and altitude coordinates to generate spatial coordinates;

[0073] S213, Establish a three-dimensional structural model of the equipment for distributed heterogeneous resources, and generate three-dimensional bounding box parameters based on the three-dimensional structural model of the equipment;

[0074] S214 uses spatial coordinates, grid connection point numbers, and three-dimensional bounding box parameters to generate a set of geometric parameters.

[0075] In a practical implementation, a set of geometric parameters can be generated by constructing a geometric model (G) of the resource device.

[0076] Geometric Model (G): Defines the resource's 3D spatial coordinates, 3D bounding box dimensions, and GIS mount point anchoring information to support visualization. It is constructed by acquiring the resource's spatial coordinate information and device information parameters.

[0077] First, collect the WGS84 latitude and longitude coordinates, altitude coordinates, and grid node number of the resources. First, spatial positioning and grid connection point matching are completed through a GIS system. Second, based on equipment design drawings or on-site survey data, a three-dimensional structural model of the equipment is established in the 3DMax environment, generating three-dimensional bounding box parameters (length, width, height, etc.). The system then incorporates the rotational attitude matrix; finally, it encapsulates the spatial coordinates, bounding box dimensions, and topological anchoring node information into a unified set of geometric parameters.

[0078] ;

[0079] in, This model assigns node numbers to resources within the power grid. It provides the spatial mapping basis for subsequent topology analysis.

[0080] In one example, the process of generating the physical constraint set includes:

[0081] S221, read the rated capacity, maximum charging and discharging power, minimum charging and discharging power, conversion efficiency, upper energy limit and lower energy limit of the distributed heterogeneous resources;

[0082] S222 uses rated capacity, maximum charge / discharge power, minimum charge / discharge power, conversion efficiency, upper energy limit, and lower energy limit to construct a set of physical constraints.

[0083] In practical implementation, a physical model can be constructed ( The physical constraint set is constructed using a physical model (Φ). The physical model (Φ) characterizes inherent physical properties such as rated capacity, maximum power, and charge / discharge efficiency, serving as a rigid constraint for scheduling. The physical model can be constructed based on equipment nameplate parameters and historical operating data.

[0084] First, read the rated capacity of the distributed heterogeneous resources ( ), maximum and minimum charge / discharge power ( ), conversion efficiency ( ) and energy upper and lower limits ( Basic parameters such as , , and , are used; secondly, statistical analysis of the maximum adjustable margin is performed based on historical operating data to form a time-varying adjustable power range; finally, a set of physical constraints is constructed:

[0085] ;

[0086] Among them, the maximum and minimum charging and discharging power ( It can change dynamically over time.

[0087] In one example, the process of generating a set of dynamic behavior functions includes:

[0088] S231, collect the actual response curves of distributed heterogeneous resources under multiple preset scheduling instructions and environmental variables;

[0089] S232 generates a set of dynamic behavior functions based on preset scheduling instructions, environmental variables, and actual response curves.

[0090] In practical implementation, a behavioral model (B) can be constructed to obtain a set of dynamic response functions. The behavioral model uses a neural network algorithm to characterize response time delay, ramp rate, and load fluctuation patterns. This model can be obtained through training on historical operational data. First, actual response curves of resources under different load commands are collected to construct input-output sample pairs (scheduling command, environmental variables → actual power response). Second, supervised learning training is performed using a neural network algorithm (such as a multilayer perceptron or recurrent neural network) to fit the resource's response time delay function and ramp rate characteristics. After training, a set of dynamic response functions can be obtained.

[0091] ;

[0092] in, For scheduling instructions, This represents the current state of the resource. This model is used to characterize the resource's dynamic adjustment capability and response reachability boundary.

[0093] In one example, the rule constraint set generation process includes:

[0094] S241, obtain the market clearing rules, SOC operating range and response constraints of distributed heterogeneous resources;

[0095] S242 uses market clearing rules, SOC operating range, and response constraints to generate a set of rule constraints.

[0096] In practical implementation, this can be achieved through a rule model ( The rules for market clearing, SOC operating range, and response constraints are defined to obtain a set of rules and constraints.

[0097] Abstracting each resource into a set of state spaces for the four models mentioned above allows for a more refined characterization of resource properties across multiple time scales.

[0098] ;

[0099] Step 203: Encapsulate the geometric parameter set, physical constraint set, dynamic behavior function set, and rule constraint set into a standardized state vector;

[0100] After obtaining the geometric parameter set, physical constraint set, dynamic behavior function set, and rule constraint set, a unified data structure interface can be defined for these four sets of attributes. Then, these four types of attributes (geometric parameter set, physical constraint set, dynamic behavior function set, and rule constraint set) are encapsulated into a standardized state vector.

[0101] ;

[0102] At the same time, a unique mapping identifier (NodeID) is established between resources and power grid nodes.

[0103] The role of this stage is to transform multi-source heterogeneous data into a computable and callable structured data model, providing a unified data interface for subsequent entity construction and topology mapping.

[0104] By constructing a standardized state vector, it can be ensured that the parameters of each dimension are computable, comparable, and mappable in a unified coordinate system. This vector is organized in tensor form, preserving the topological structure and semantic association of the original constraints, and supporting subsequent policy generation, optimization solution, and real-time feedback loop.

[0105] Step 204: Construct a resource digital model using standardized state vectors;

[0106] In this embodiment of the invention, after completing the model abstraction of the physical device, the three stages of model expression, model construction, and model operation can be entered sequentially.

[0107] Model Representation: Abstract models are expressed using domain modeling languages, facilitating understanding of the model by target users and the runtime environment. Specifically, resource-level 3D rendering and interaction can be implemented using Three.js, and model state variables can be... The model is bound to real-time detection data and visualized feedback of physical parameters and dynamic behaviors through the front end. Simultaneously, the Cesium engine matches resource space coordinates with power grid topology nodes, forming a resource-node spatial mapping relationship. Finally, a glTF format model file adapted for the WebGL environment is generated. The core of this stage lies in combining the geometric model (G) with topology anchoring information, enabling the resource model to be visualized and located within the power grid spatial structure, providing a spatial verification basis for subsequent topology association calculations.

[0108] Model building refers to the assembly and verification of models using modeling tools. In its implementation, firstly, a device appearance structure model is built using 3ds Max, generating bounding box parameters and spatial attitude matrices to achieve a physical representation of the geometric model (G). Secondly, a runtime logic script is written in the VS Code environment, embedding power boundaries, energy constraints, and efficiency parameters from the physical model (Φ) into the model attribute fields. Simultaneously, the dynamic response function trained from the behavioral model (B) is bound to the model object via an interface, achieving a dynamic mapping between command input and power output. The rule model (Γ) is embedded into object attributes as a set of constraints for subsequent runtime verification. This stage completes the engineering integration of the four types of models, transforming resources from data descriptions into computable digital entities.

[0109] Model Execution: The designed resource digital model is run in an environment such as a simulator. By collecting resource operation data in real time, the adjustable power range and energy state variables in the physical model (Φ) are updated; the behavioral model (B) is invoked to predict responses to scheduling commands; the operational boundary is verified using the rule model (Γ); and the resource state is synchronized to the power grid topology by combining the node mapping information of the geometric model (G). This stage achieves dynamic model updates and constraint closed-loop verification, enabling the resource digital model to not only have visual representation capabilities but also the ability to participate in virtual machine group construction and scheduling calculations.

[0110] Furthermore, after establishing the resource digital model, a refined evaluation of the resource digital model can be achieved through the "real-time" evaluation index:

[0111] ;

[0112] in: For real-time measurement vectors on the physical side, This represents the simulated state of the resource digital model. The larger the value, the higher the modeling accuracy, the stronger the real-time synchronization, and the stronger the predictability.

[0113] Step 205: Establish the spatial mapping relationship between the resource digital model and the power grid topology nodes;

[0114] After establishing the resource digital model, it can be attached to the power grid topology nodes, thereby constructing a spatial mapping relationship between the resource digital model and the power grid topology nodes.

[0115] This spatial mapping relationship enables deep integration of resource digital models and power grid topology. Specifically, the mounting process requires ensuring that the attribute fields of each resource digital model match the parameter configurations of the corresponding nodes, thus providing fundamental support for subsequent dynamic scheduling and computation. Furthermore, this mapping relationship supports multi-level topology expansion, allowing for flexible adjustments to resource distribution in complex power grid environments. By updating the mapping information in real time, the visibility of power grid operation status and decision-making efficiency can be further improved, laying a solid technical foundation for the collaborative optimization of virtual machine groups.

[0116] Step 206: Construct a virtual machine group digital model based on spatial mapping relationships, resource digital models, and preset virtual machine group construction principles.

[0117] After the resource digital model is completed, the virtual machine group digital model can be constructed based on the spatial mapping relationship, the resource digital model, and the preset virtual machine group construction principles.

[0118] In one example, the steps of constructing a virtual machine group digital model based on spatial mapping relationships, resource digital models, and preset virtual machine group construction principles may include the following sub-steps:

[0119] S61, according to the preset virtual machine group construction principle, construct multiple initial virtual machine groups for the power grid, and generate the resource set of the initial virtual machine group according to the spatial mapping relationship and resource digital model;

[0120] S62, based on the resource set and resource digital model, determines the upper and lower limits of adjustable power, constraints on safe operating range, constraints on power change rate, line power flow and node operation restrictions;

[0121] S63 adds adjustable power upper and lower limits, safe operating range constraints, power change rate constraints, line power flow and node operation restrictions to the initial virtual machine group to generate a digital model of the virtual machine group.

[0122] In the specific implementation, the default principles for building virtual machine groups are as follows:

[0123] 1) Divide according to the "layered and zoned" results of the power grid - a 10kV feeder or a transformer area is a aggregation domain to avoid distortion of safety verification after crossing domains.

[0124] 2) Seal the connection according to "same aggregator, same grid connection point" - ensure consistency of rights and obligations and prevent "multiple entities in one virtual machine group" from causing chaos in scheduling instructions.

[0125] 3) Appropriate scale – too large and the power grid will be unstable; too small and there will be no flexibility. Generally, it is controlled in the range of 1-10MW to match the jurisdiction of the local dispatching authority.

[0126] 4) Resource characteristic matching - The maximum upward / downward adjustment capability, response speed, and response accuracy of resources within the same unit should be as consistent as possible to ensure the efficient operation of the virtual machine group.

[0127] The mathematical model for constructing virtual machine groups is as follows:

[0128] 1) Virtual machine group It consists of several adjustable resources, and its resource set is represented as:

[0129] ;

[0130] Among them, the distributed heterogeneous resources involved in the virtual machine group Based on spatial mapping relationships, it can include distributed energy storage, electric vehicle charging facilities, controllable loads, distributed photovoltaics, etc. The time scale is determined by discrete time periods. This indicates that the time step is... .

[0131] 2) Virtual machine groups in time periods The upper and lower limits of the equivalent adjustable power are obtained by superimposing the adjustable capabilities of its internal resources:

[0132] ; ;

[0133] in:

[0134] , Representing resources During the period Minimum and maximum adjustable power;

[0135] For bidirectional resources (such as energy storage and electric vehicles), the upper and lower power limits can be both positive and negative values.

[0136] For unidirectional resources (such as controllable loads or photovoltaics), the power boundary is constrained based on their physical properties.

[0137] The scheduling power of the virtual machine group must meet the following requirements:

[0138] ;

[0139] 3) For resources with energy constraints, such as energy storage and electric vehicles, virtual machine groups introduce intertemporal energy state variables. The state evolution relationship is as follows:

[0140] ;

[0141] in:

[0142] For resources Energy conversion efficiency;

[0143] For resources During the period The actual response power.

[0144] The energy status of the virtual machine group must meet the constraints of the safe operating range:

[0145] ;

[0146] This constraint ensures that the virtual machine group does not overspend or operate beyond its limits during continuous regulation.

[0147] 4) To describe the dynamic adjustment capability of the virtual machine group, a power change rate constraint is introduced, the expression of which is:

[0148] ;

[0149] Among them, the equivalent ramping capability of virtual machine groups It can be determined by a combination of internal resources, for example:

[0150] ;

[0151] The specific value selection method can be configured according to the control of security and conservatism to ensure that the virtual machine group can reliably track scheduling instructions.

[0152] 5) To ensure the feasibility of control actions within the physical power grid, the virtual machine group needs to be topologically anchored to the power grid nodes. Let the virtual machine group... Connected to the power grid node Then its injected power participates in the power flow calculation:

[0153] ;

[0154] And under grid constraints, it meets line power flow and node operation limitations, for example:

[0155] ; ;

[0156] in:

[0157] Indicates the power of the virtual machine group to the line Flow distribution factor;

[0158] This represents the maximum line capacity.

[0159] 6) After completing the construction of the virtual machine group digital model, in order to verify the executability and consistency of the model in actual power grid control scenarios, command decomposition and response allocation calculations can be performed based on the virtual machine group equivalent model. This optimization process belongs to the model application stage, and its solution object is the regulation output variable of the virtual machine group, rather than the virtual machine group model parameters themselves.

[0160] ;

[0161] Constraints (Power Balance and Node Voltage):

[0162] ;

[0163] Decomposed to the first Instruction power of a virtual machine group;

[0164] : No. The actual response power of each virtual machine group;

[0165] The economic cost or loss cost of the unit performing control actions;

[0166] Weighting coefficients are used to balance the preference between "response accuracy" and "economy"; The total control and dispatch demand issued by the power grid to the virtual power plant;

[0167] The node voltage function based on power flow calculation ensures that the control process does not trigger limit exceedance.

[0168] The virtual machine group digital model ensures that, in the face of massive resource calls, the challenges of balancing grid topology and strong uncertainty in response during distributed resource calls can be addressed. A multi-level grid model splicing method can be used to match the grid topology, constructing a hierarchical control model of terminal equipment-virtual machine group-virtual power plant, thereby achieving precise allocation of distributed resources from "station-line-transformer-customer". Simultaneously, based on machine learning and artificial intelligence, multi-timescale flexible resource aggregation and optimized control algorithms are developed to correct response deviations in real time. This supports virtual power plants in accurately tracking grid dispatch instructions at different levels (province, grid, and region) such as peak shaving, regional frequency regulation, reserve, voltage control, and congestion mitigation, enabling flexible aggregation of resources across virtual power plants.

[0169] In the hierarchical control model of terminal device-virtual machine group-virtual power plant, the virtual power plant layer is responsible for receiving grid control instructions and performing global power allocation, the virtual machine group layer acts as an intermediate execution unit to perform equivalent power coordination within its topology domain, and the terminal resource layer executes specific responses based on its own physical constraints and state conditions.

[0170] This invention constructs a digital model of distributed heterogeneous resources and establishes a spatial mapping relationship between it and the power grid topology nodes. Then, based on the spatial mapping relationship and the preset virtual machine group construction principle, the distributed heterogeneous resources are distributed into different virtual machine groups. The different virtual machine groups are used to decompose instructions and provide response feedback, thereby achieving the accuracy of distributed resource regulation and the timeliness of response.

[0171] Please see Figure 4 , Figure 4 This is a logical schematic diagram of a digital modeling method for virtual machine groups provided in an embodiment of the present invention.

[0172] like Figure 4 As shown, the embodiments of the present invention take cross-temporal and spatial adjustable resource coupling as the core and are divided into three progressive stages: mechanism research, digital modeling technology research, and construction of virtual machine group digital model, ultimately realizing the construction of virtual machine group digital model.

[0173] Phase 1: Research on the Coupling Mechanism of Spatiotemporally Adjustable Resources: This phase is the theoretical and data foundation layer. Through dual-dimensional analysis of data and models, the coupling law between distributed heterogeneous resources and the power grid is clarified.

[0174] The input module includes power grid model data and a multi-source adjustable resource model.

[0175] Power grid model data includes three core types of data: power grid topology, connection points, and power flow, which are used to characterize the physical structure and operating status of the power grid.

[0176] Based on the multi-variable adjustable resource (i.e. distributed heterogeneous resource) model: construct a four-dimensional model of geometry-physical-behavior-rules to describe the spatial morphology, physical attributes, dynamic response and rule constraints of resources respectively.

[0177] Specifically, this involves data analysis of power grid model data, combined with multivariate adjustable resource models to conduct model research, thereby generating a coupling mechanism for adapting massive heterogeneous distributed resources to the power grid, clarifying the spatiotemporal characteristics and response patterns of resources and their interaction with the power grid, and providing a theoretical foundation for subsequent digital resource modeling.

[0178] Phase 2: Research on Digital Modeling Technology for Adjustable Resources and Virtual Machine Groups: Based on the results of Phase 1, a visual modeling method is developed.

[0179] This phase focuses on technical research in two directions: characteristic analysis and fusion modeling. Specifically, it includes adjustable resource characteristic analysis and fusion modeling techniques.

[0180] Adjustable resource characteristic analysis: Based on four-dimensional model parameters, we conduct in-depth analysis of the load characteristics, spatiotemporal characteristics, and response characteristics of resources, and extract the key parameters required for modeling.

[0181] Fusion modeling technology: integrates technologies such as datasets, 3D modeling, GIS kernel, and power grid lines to achieve spatial fusion and visualization of resources and power grids.

[0182] Through research in the above two directions, a method for full-range visualization modeling of adjustable resources and virtual machine groups was finally developed, providing technical path and tool support for the construction of digital models of virtual machine groups.

[0183] Phase 3: Construction of the Virtual Machine Group Digital Model: The results of the first two phases are aggregated into a runnable digital model of the virtual machine group.

[0184] This phase builds upon the coupling mechanism of Phase ① and the modeling techniques of Phase ②, focusing on modeling typical distributed heterogeneous resources. Core resource types cover distributed energy storage, distributed photovoltaics, smart buildings, electric vehicle charging stations, 5G base stations, industrial plants, and distributed wind power plants. Ultimately, it achieves data integration, simulation calculations, and dynamic simulation display of the flow of data in the virtual machine group's 3D virtual scene and power grid topology, completing the transition from theory to an interactive digital twin system.

[0185] Please see Figure 5 , Figure 5 This is a structural block diagram of a virtual machine group digital modeling device provided in an embodiment of the present invention.

[0186] This invention provides a digital modeling apparatus for virtual machine groups, comprising:

[0187] Distributed heterogeneous resource acquisition module 501 is used to acquire distributed heterogeneous resources;

[0188] Resource digital model construction module 502 is used to construct resource digital models of distributed heterogeneous resources;

[0189] The spatial mapping relationship establishment module 503 is used to establish the spatial mapping relationship between the resource digital model and the power grid topology nodes;

[0190] The virtual machine group digital model construction module 504 is used to construct a virtual machine group digital model based on spatial mapping relationships, resource digital models, and preset virtual machine group construction principles.

[0191] In this embodiment of the invention, the resource digital model construction module 502 includes:

[0192] The object-oriented decomposition submodule is used to decompose distributed heterogeneous resources into objects, resulting in a set of geometric parameters, a set of physical constraints, a set of dynamic behavior functions, and a set of rule constraints.

[0193] The encapsulation submodule is used to encapsulate the geometric parameter set, physical constraint set, dynamic behavior function set, and rule constraint set into a standardized state vector;

[0194] The resource digital model construction submodule is used to construct a resource digital model using standardized state vectors.

[0195] In this embodiment of the invention, the process of generating the geometric parameter set includes:

[0196] The latitude, longitude, altitude coordinates and grid connection point number acquisition unit is used to collect the latitude, longitude, altitude coordinates and grid connection point number of distributed heterogeneous resources;

[0197] Spatial coordinate generation unit, used to generate spatial coordinates using latitude, longitude and altitude coordinates;

[0198] The 3D bounding box parameter generation unit is used to establish a 3D structural model of the equipment for distributed heterogeneous resources and generate 3D bounding box parameters based on the 3D structural model of the equipment.

[0199] The geometric parameter set generation unit is used to generate a geometric parameter set using spatial coordinates, grid point numbers, and 3D bounding box parameters.

[0200] In this embodiment of the invention, the process of generating the physical constraint set includes:

[0201] Rated capacity, maximum charge / discharge power, minimum charge / discharge power, conversion efficiency, upper energy limit and lower energy limit reading unit, used to read the rated capacity, maximum charge / discharge power, minimum charge / discharge power, conversion efficiency, upper energy limit and lower energy limit of distributed heterogeneous resources;

[0202] The physical constraint set construction unit is used to construct a physical constraint set using rated capacity, maximum charge / discharge power, minimum charge / discharge power, conversion efficiency, upper energy limit, and lower energy limit.

[0203] In this embodiment of the invention, the process of generating the dynamic behavior function set includes:

[0204] The actual response curve acquisition unit is used to acquire the actual response curves of distributed heterogeneous resources under multiple preset scheduling instructions and environmental variables.

[0205] The dynamic behavior function set generation unit is used to train and generate a dynamic behavior function set based on preset scheduling instructions, environmental variables, and actual response curves.

[0206] In this embodiment of the invention, the rule constraint set generation process includes:

[0207] The market clearing rules, SOC operating range, and response constraint limit acquisition unit is used to acquire the market clearing rules, SOC operating range, and response constraint limits of distributed heterogeneous resources.

[0208] The rule constraint set generation unit is used to generate a rule constraint set by adopting market clearing rules, SOC operating range, and response constraints.

[0209] In this embodiment of the invention, the virtual machine group digital model construction module 504 includes:

[0210] The initial virtual machine group construction and resource set generation submodule is used to construct multiple initial virtual machine groups for the power grid according to the preset virtual machine group construction principles, and generate the resource set of the initial virtual machine group according to the spatial mapping relationship and resource digital model.

[0211] The adjustable power upper and lower limits, safe operating range constraints, power change rate constraints, line power flow and node operation restrictions determination unit is used to determine the adjustable power upper and lower limits, safe operating range constraints, power change rate constraints, line power flow and node operation restrictions based on the resource set and resource digital model;

[0212] The virtual machine group digital model generation unit is used to add adjustable power upper and lower limits, safe operating range constraints, power change rate constraints, line power flow and node operation restrictions to the initial virtual machine group to generate a virtual machine group digital model.

[0213] This invention also provides an electronic device, which includes a processor and a memory:

[0214] The memory is used to store program code and transfer the program code to the processor;

[0215] The processor is used to execute the virtual machine group digital modeling method of this invention according to the instructions in the program code.

[0216] This invention also provides a computer-readable storage medium for storing program code for executing the virtual machine group digital modeling method of this invention.

[0217] Those skilled in the art will clearly understand that, for the sake of convenience and brevity, the specific working processes of the systems, devices, and units described above can be referred to the corresponding processes in the foregoing method embodiments, and will not be repeated here.

[0218] The various embodiments in this specification are described in a progressive manner, with each embodiment focusing on the differences from other embodiments. The same or similar parts between the various embodiments can be referred to each other.

[0219] Those skilled in the art will understand that embodiments of the present invention can be provided as methods, apparatus, or computer program products. Therefore, embodiments of the present invention can take the form of entirely hardware embodiments, entirely software embodiments, or embodiments combining software and hardware aspects. Furthermore, embodiments of the present invention can take the form of computer program products 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 code.

[0220] Embodiments of the present invention are described with reference to flowchart illustrations and / or block diagrams of methods, terminal devices (systems), and computer program products according to embodiments of the invention. It will be understood that each block of the flowchart illustrations and / or block diagrams, and combinations of blocks in the flowchart illustrations and / or block diagrams, can be implemented by computer program instructions. These computer program instructions can be provided to a processor of a general-purpose computer, special-purpose computer, embedded processor, or other programmable data processing terminal device to produce a machine, such that the instructions, which execute via the processor of the computer or other programmable data processing terminal device, generate instructions for implementing the flowchart illustrations and / or block diagrams. Figure 1 One or more processes and / or boxes Figure 1 A device that provides the functions specified in one or more boxes.

[0221] These computer program instructions may also be stored in a computer-readable storage medium that can direct a computer or other programmable data processing terminal device to operate in a particular manner, such that the instructions stored in the computer-readable storage medium produce an article of manufacture including instruction means, which are implemented in a process Figure 1 One or more processes and / or boxes Figure 1 The function specified in one or more boxes.

[0222] These computer program instructions can also be loaded onto a computer or other programmable data processing terminal equipment, causing a series of operational steps to be performed on the computer or other programmable terminal equipment to produce a computer-implemented process, thereby providing instructions that execute on the computer or other programmable terminal equipment for implementing the process. Figure 1 One or more processes and / or boxes Figure 1 The steps of the function specified in one or more boxes.

[0223] Although preferred embodiments of the present invention have been described, those skilled in the art, upon learning the basic inventive concept, can make other changes and modifications to these embodiments. Therefore, the appended claims are intended to be interpreted as including the preferred embodiments as well as all changes and modifications falling within the scope of the embodiments of the present invention.

[0224] It should be noted that the user information (including but not limited to user device information, user personal information, etc.) and data (including but not limited to data used for analysis, data stored, data displayed, etc.) involved in this application are all information and data authorized by the user or fully authorized by all parties. Furthermore, the collection, use and processing of the relevant data must comply with the relevant laws, regulations and standards of the relevant countries and regions, and corresponding operation entry points are provided for users to choose to authorize or refuse.

[0225] Finally, it should be noted that in this document, relational terms such as "first" and "second" are used only to distinguish one entity or operation from another, and do not necessarily require or imply any such actual relationship or order between these entities or operations. Furthermore, the terms "comprising," "including," or any other variations thereof are intended to cover non-exclusive inclusion, such that a process, method, article, or terminal device that comprises a list of elements includes not only those elements but also other elements not expressly listed, or elements inherent to such a process, method, article, or terminal device. Without further limitations, an element defined by the phrase "comprising one..." does not exclude the presence of other identical elements in the process, method, article, or terminal device that includes said element.

[0226] The above-described embodiments are only used to illustrate the technical solutions of the present invention, and are not intended to limit it. Although the present invention has been described in detail with reference to the foregoing embodiments, those skilled in the art should understand that modifications can still be made to the technical solutions described in the foregoing embodiments, or equivalent substitutions can be made to some of the technical features. Such modifications or substitutions do not cause the essence of the corresponding technical solutions to deviate from the spirit and scope of the technical solutions of the embodiments of the present invention.

Claims

1. A digital modeling method for virtual machine groups, characterized in that, include: Collect distributed heterogeneous resources; Construct a resource digital model for the distributed heterogeneous resources; Establish the spatial mapping relationship between the resource digital model and the power grid topology nodes; The virtual machine group digital model is constructed based on the spatial mapping relationship, the resource digital model, and the preset virtual machine group construction principles.

2. The method according to claim 1, characterized in that, The step of constructing the resource digital model of the distributed heterogeneous resource includes: The distributed heterogeneous resources are decomposed into objects to obtain a set of geometric parameters, a set of physical constraints, a set of dynamic behavior functions, and a set of rule constraints. The geometric parameter set, the physical constraint set, the dynamic behavior function set, and the rule constraint set are encapsulated into a standardized state vector; A resource digital model is constructed using the standardized state vectors.

3. The method according to claim 2, characterized in that, The process of generating the geometric parameter set includes: Collect the latitude, longitude, altitude coordinates, and grid connection point number of the distributed heterogeneous resources; Spatial coordinates are generated using the latitude, longitude, and altitude coordinates; Establish a three-dimensional structural model of the distributed heterogeneous resource device, and generate three-dimensional bounding box parameters based on the three-dimensional structural model of the device; A set of geometric parameters is generated using the spatial coordinates, the grid connection point number, and the three-dimensional bounding box parameters.

4. The method according to claim 2, characterized in that, The process of generating the physical constraint set includes: Read the rated capacity, maximum charging and discharging power, minimum charging and discharging power, conversion efficiency, upper energy limit, and lower energy limit of the distributed heterogeneous resource; A set of physical constraints is constructed using the rated capacity, the maximum charge / discharge power, the minimum charge / discharge power, the conversion efficiency, the upper energy limit, and the lower energy limit.

5. The method according to claim 2, characterized in that, The process of generating the dynamic behavior function set includes: Collect the actual response curves of the distributed heterogeneous resources under multiple preset scheduling instructions and environmental variables; A set of dynamic behavior functions is generated based on the preset scheduling instructions, the environmental variables, and the actual response curve.

6. The method according to claim 2, characterized in that, The process of generating the rule constraint set includes: Obtain the market clearing rules, SOC operating range, and response constraints of the distributed heterogeneous resources; The market clearing rules, the SOC operating range, and the response constraints are used to generate a set of rule constraints.

7. The method according to claim 1, characterized in that, The step of constructing a virtual machine group digital model based on the spatial mapping relationship, the resource digital model, and the preset virtual machine group construction principles includes: According to the preset virtual machine group construction principle, multiple initial virtual machine groups are constructed for the power grid, and the resource set of the initial virtual machine group is generated according to the spatial mapping relationship and the resource digital model. Based on the resource set and the resource digital model, determine the adjustable power upper and lower limits, safe operating range constraints, power change rate constraints, line power flow and node operation restrictions; Add the adjustable power upper and lower limits, the safe operating range constraints, the power change rate constraints, the line power flow and node operation restrictions to the initial virtual machine group to generate a digital model of the virtual machine group.

8. A digital modeling device for virtual machine groups, characterized in that, include: The distributed heterogeneous resource acquisition module is used to acquire distributed heterogeneous resources. A resource digital model construction module is used to construct a resource digital model of the distributed heterogeneous resources; The spatial mapping relationship establishment module is used to establish the spatial mapping relationship between the resource digital model and the power grid topology nodes; The virtual machine group digital model construction module is used to construct a virtual machine group digital model based on the spatial mapping relationship, the resource digital model, and the preset virtual machine group construction principles.

9. An electronic device, characterized in that, The device includes a processor and a memory: The memory is used to store program code and transmit the program code to the processor; The processor is configured to execute the virtual machine group digital modeling method according to any one of claims 1-7 according to the instructions in the program code.

10. A computer-readable storage medium, characterized in that, The computer-readable storage medium is used to store program code for executing the virtual machine group digital modeling method according to any one of claims 1-7.

Images