Digital twin model simulation method, device and equipment for electric power pipe gallery, storage medium and product

Abstract

The invention relates to a digital twin model simulation method, device and equipment for an electric power pipe gallery, a storage medium and a product. The method is applied to a simulation main node, and comprises the following steps: determining a plurality of model simulation layers corresponding to a digital twin model of an electric power pipe gallery, the plurality of model simulation layers being generated according to multi-level attribute information of the digital twin model, the multi-level attribute information is obtained by fusing multi-source heterogeneous data of a multi-dimensional physical field collected by various sensors; according to simulation attribute characteristics of each model simulation layer, a corresponding simulation task is allocated to each model simulation layer, and the simulation attribute characteristics at least represent one of simulation time nodes and simulation updating frequencies of the model simulation layers; and simulating the digital twin model by executing a plurality of simulation tasks to obtain a simulation result of the digital twin model. By adopting the method, the simulation effect of the digital twin model simulation of the electric power pipe gallery is improved.

Description

Technical Field

[0001] The present application relates to the field of digital twin technology, and in particular to a method, apparatus, computer equipment, computer-readable storage medium, and computer program product for simulating a digital twin model of a power pipeline corridor. Background Art

[0002] With the development of science and technology, digital twin technology has been widely used in many fields such as manufacturing and transportation. Through digital twin technology, real-time mapping of virtual models and physical entities can be established, thereby realizing dynamic, real-time and closed-loop information interaction and automatic control of physical entities and virtual twins. Therefore, digital twin models will also be applied in the management and maintenance of power pipelines.

[0003] Currently, in the digital twin model simulation process of power pipeline corridors, multiple digital twin models are usually constructed for different equipment in the power pipeline corridor, and unified management, analysis and operation and maintenance are carried out. However, due to the complex structure and large number of equipment in the power pipeline corridor, the simulation results obtained cannot be evaluated in line with the actual scenario, which makes it easy for the simulation to take a long time or have poor simulation accuracy. Therefore, the current simulation effect of the digital twin model simulation of the power pipeline corridor is poor. Summary of the Invention

[0004] Based on this, it is necessary to provide a digital twin model simulation method, device, computer equipment, computer-readable storage medium and computer program product for power pipeline corridors to improve the simulation effect of digital twin simulation of power pipeline corridors in response to the above technical problems.

[0005] In a first aspect, the present application provides a digital twin model simulation method for a power pipeline corridor, which is applied to a simulation master node and includes:

[0006] Determining multiple model simulation layers corresponding to the digital twin model of the power pipeline corridor, wherein the multiple model simulation layers are generated based on multi-level attribute information of the digital twin model, and the multi-level attribute information is obtained by fusing multi-source heterogeneous data of a multi-dimensional physical field collected by multiple sensors;

[0007] According to the simulation attribute characteristics of each model simulation layer, each model simulation layer is assigned a corresponding simulation task, wherein the simulation attribute characteristics represent at least one of the simulation time node and the simulation update frequency of the model simulation layer;

[0008] By executing multiple simulation tasks, the digital twin model is simulated to obtain a digital twin model simulation result.

[0009] In one embodiment, simulating the digital twin model by executing multiple simulation tasks to obtain a digital twin model simulation result includes:

[0010] Determine a plurality of simulation slave nodes in a simulation node cluster to which the simulation master node belongs;

[0011] Selecting step: selecting a target simulation task from the plurality of simulation tasks;

[0012] Matching a target simulation slave node for the target simulation task among all simulation slave nodes according to the corresponding relationship between the resource requirement information of the target simulation task and the resource load information of the plurality of simulation slave nodes;

[0013] The target simulation task is executed at the target simulation slave node, and the selection step is returned to be executed until the task simulation results of all simulation tasks are obtained, and the digital twin simulation result is obtained by integrating multiple task simulation results.

[0014] In one embodiment, selecting a target simulation task from the plurality of simulation tasks includes:

[0015] Determine a first execution priority and a second execution priority corresponding to each of the multiple simulation tasks, wherein the first execution priority is the execution priority of the model simulation layer where any simulation task is located, and the second execution priority is the execution priority of any simulation task within the model simulation layer where it is located;

[0016] Sorting the plurality of simulation tasks according to the plurality of first execution priorities and the plurality of second execution priorities to obtain an execution priority sorting result;

[0017] The target simulation task is selected from the multiple simulation tasks according to the execution priority sorting result.

[0018] In one embodiment, matching a target simulation slave node for the target simulation task among all simulation slave nodes according to the correspondence between the resource requirement information of the target simulation task and the resource load information of the plurality of simulation slave nodes includes:

[0019] According to the resource requirement information and the plurality of resource load information, a plurality of candidate simulation slave nodes are screened from the plurality of simulation slave nodes, wherein the candidate simulation slave nodes are simulation slave nodes that meet the execution resource requirements of the target simulation task;

[0020] The target simulation slave node is screened from the multiple candidate simulation slave nodes according to resource idle information of the multiple candidate simulation slave nodes, wherein the resource idle information is used to represent idle scheduling resources of the candidate simulation slave nodes after executing the target simulation task.

[0021] In one embodiment, the method further comprises at least one of the following:

[0022] updating the load scheduling resources of the target simulation slave node according to the target simulation task matched by the target simulation slave node;

[0023] When it is detected that the target simulation task is overloaded, rematching the target simulation slave node for the target simulation task among all simulation slave nodes;

[0024] When it is detected that the number of tasks to be executed on the simulation slave node is greater than a preset task amount threshold, the target simulation slave node is re-matched for the tasks to be executed on the simulation slave node.

[0025] In one embodiment, the multiple model simulation layers include a model base layer, a model structure layer, a model function layer, and a model behavior layer in a layer-by-layer manner; the step of determining the multiple model simulation layers set for the digital twin model of the power pipeline corridor includes:

[0026] performing standard processing on the point cloud data of the power pipeline corridor to obtain standard point cloud data, and performing base layer modeling on the digital twin model of the power pipeline corridor according to the classification result of the standard point cloud data to obtain the model base layer;

[0027] Converting the point cloud standard data into a geometric model of the power pipeline corridor, and performing structural layer modeling on the geometric model according to preset structural parameters and the model base layer to obtain the model structure layer;

[0028] Constructing a functional knowledge graph of the power pipeline corridor, and generating the model function layer according to the functional knowledge graph and the model structure layer;

[0029] According to the actual operation data of the power pipeline corridor and the simulated operation data of the digital twin model of the power pipeline corridor, the digital twin model of the power pipeline corridor is modeled at a behavior layer to obtain the model behavior layer.

[0030] In a second aspect, the present application also provides a digital twin model simulation device for a power pipeline corridor, which is applied to simulate a master node and includes:

[0031] a determination module, configured to determine a plurality of model simulation layers corresponding to the digital twin model of the power pipeline corridor, wherein the plurality of model simulation layers are generated based on multi-level attribute information of the digital twin model, and the multi-level attribute information is obtained by fusing multi-source heterogeneous data of a multi-dimensional physical field acquired by a plurality of sensors;

[0032] an allocation module, configured to allocate a corresponding simulation task to each of the model simulation layers according to a simulation attribute feature of each of the model simulation layers, wherein the simulation attribute feature represents at least one of a simulation time node and a simulation update frequency of the model simulation layer;

[0033] The simulation module is used to simulate the digital twin model by executing multiple simulation tasks to obtain the digital twin model simulation results.

[0034] In a third aspect, the present application further provides a computer device comprising a memory and a processor, wherein the memory stores a computer program, and when the processor executes the computer program, the following steps are implemented:

[0035] Determine multiple model simulation layers corresponding to the digital twin model of the power pipeline corridor, wherein the multiple model simulation layers are generated based on the multi-level attribute information of the digital twin model, and the multi-level attribute information is obtained by fusion of multi-source heterogeneous data of multi-dimensional physical fields collected by multiple sensors; according to the simulation attribute characteristics of each of the model simulation layers, assign corresponding simulation tasks to each of the model simulation layers, wherein the simulation attribute characteristics at least characterize one of the simulation time node and simulation update frequency of the model simulation layer; simulate the digital twin model by executing multiple simulation tasks to obtain a digital twin model simulation result.

[0036] In a fourth aspect, the present application further provides a computer-readable storage medium having a computer program stored thereon, wherein when the computer program is executed by a processor, the following steps are implemented:

[0037] Determine multiple model simulation layers corresponding to the digital twin model of the power pipeline corridor, wherein the multiple model simulation layers are generated based on the multi-level attribute information of the digital twin model, and the multi-level attribute information is obtained by fusion of multi-source heterogeneous data of multi-dimensional physical fields collected by multiple sensors; according to the simulation attribute characteristics of each of the model simulation layers, assign corresponding simulation tasks to each of the model simulation layers, wherein the simulation attribute characteristics at least characterize one of the simulation time node and simulation update frequency of the model simulation layer; simulate the digital twin model by executing multiple simulation tasks to obtain a digital twin model simulation result.

[0038] In a fifth aspect, the present application further provides a computer program product, comprising a computer program, which, when executed by a processor, implements the following steps:

[0039] Determine multiple model simulation layers corresponding to the digital twin model of the power pipeline corridor, wherein the multiple model simulation layers are generated based on the multi-level attribute information of the digital twin model, and the multi-level attribute information is obtained by fusion of multi-source heterogeneous data of multi-dimensional physical fields collected by multiple sensors; according to the simulation attribute characteristics of each of the model simulation layers, assign corresponding simulation tasks to each of the model simulation layers, wherein the simulation attribute characteristics at least characterize one of the simulation time node and simulation update frequency of the model simulation layer; simulate the digital twin model by executing multiple simulation tasks to obtain a digital twin model simulation result.

[0040] The above-mentioned digital twin model simulation method, device, computer equipment, computer-readable storage medium and computer program product of the power pipeline corridor first determine the multiple model simulation layers corresponding to the digital twin model of the power pipeline corridor, wherein the multiple model simulation layers are generated according to the multi-level attribute information of the digital twin model, and then based on the simulation attribute characteristics of each model simulation layer, respectively assign corresponding simulation tasks to each model simulation layer, wherein the simulation attribute characteristics at least characterize one of the simulation time node and simulation update frequency of the model simulation layer, and finally simulate the digital twin model of the power pipeline corridor by executing multiple simulation tasks to obtain the digital twin model simulation result. Since the multiple model simulation layers are generated according to the multi-level attribute information of the digital twin model, the multi-level attribute information is obtained by fusion of multi-source heterogeneous data of multi-dimensional physical fields collected by multiple sensors, and then there is an inter-layer relationship between the multiple model simulation layers, so by determining the multiple model simulation layers corresponding to the digital twin model, the multi-level characteristics of the digital twin model can be reflected as a whole to adapt to the digital twin. A model is generated, and the simulation tasks corresponding to each model simulation layer are assigned according to the simulation attribute characteristics of each model simulation layer, where the simulation attribute characteristics characterize at least one of the simulation time nodes and simulation update frequency of the model simulation layer. Therefore, the simulation attribute characteristics can locally reflect the specific details and operating characteristics of the digital twin model of the power pipeline corridor, and then the simulation tasks assigned to each model simulation layer through the simulation attribute characteristics are accurate. Finally, by executing multiple simulation tasks, the digital twin simulation results obtained by simulating the digital twin model of the power pipeline corridor can fit the actual scene, and the purpose of simulating the digital twin model of the power pipeline corridor in a complex scene can be achieved, rather than only being able to integrate multiple digital twin models for unified management, analysis and operation and maintenance. Therefore, the technical defects of the complex structure and numerous equipment of the power pipeline corridor, which lead to the inability of the simulation result evaluation to fit the actual scene, and thus easily lead to long simulation time or poor simulation accuracy, etc., are overcome. Therefore, the simulation effect of the digital twin model simulation of the power pipeline corridor is improved. BRIEF DESCRIPTION OF THE DRAWINGS

[0041] In order to more clearly illustrate the technical solutions in the embodiments of the present application or related technologies, the following briefly introduces the drawings required for use in the embodiments or related technical descriptions. Obviously, the drawings described below are only some embodiments of the present application. For ordinary technicians in this field, other drawings can be obtained based on these drawings without paying any creative work.

[0042] Figure 1 1 is a flow chart of a digital twin model simulation method for a power pipeline corridor in one embodiment;

[0043] Figure 21 is a flow chart of a digital twin model simulation method for a power pipeline corridor in another embodiment;

[0044] Figure 3 A schematic diagram of scheduling and executing multiple simulation tasks of a digital twin model simulation method for a power pipeline corridor in one embodiment;

[0045] Figure 4 1 is a structural block diagram of a digital twin model simulation device for a power pipeline corridor in one embodiment;

[0046] Figure 5 FIG. 1 is a diagram showing the internal structure of a computer device in one embodiment. DETAILED DESCRIPTION

[0047] In order to make the purpose, technical solutions and advantages of this application more clear, the following further describes this application in detail with reference to the accompanying drawings and embodiments. It should be understood that the specific embodiments described herein are only used to explain this application and are not intended to limit this application.

[0048] First, it should be understood that power transmission corridors are critical infrastructure for ensuring the normal operation of cities. Traditional maintenance methods for power transmission corridor management and maintenance often rely on manual inspections and static monitoring. However, these methods struggle to reflect the status of transmission corridors in real time, leading to potential problems such as inefficient maintenance and omissions. With the advancement of technology, digital twin technology has provided new insights into power transmission corridor operation and maintenance. Digital twin technology integrates physics and information to construct a digital virtual twin that fully reflects the physical operating mechanisms of physical entities, enabling dynamic, real-time, closed-loop information exchange and automatic control between the physical entity and the virtual twin. Digital twin technology was first used in spacecraft maintenance and simulation. In recent years, with the rapid development of technologies such as the Internet of Things, cloud computing, and artificial intelligence, digital twin technology has been widely applied and studied globally. Currently, the main research directions for power transmission corridor applications are as follows: 1) integrated transmission corridor operation and maintenance management; 2) development and application of digital twin platforms; 3) automated inspection and intelligent monitoring systems; and 4) digital twin technology for oil and gas drilling and production. Consequently, the application of digital twin technology in power transmission corridors is becoming increasingly frequent.

[0049] However, the current digital twin model simulation process of power pipeline corridors can only be applied to simple scenarios under power pipeline corridors. In addition, there is still a lack of simple and effective digital twin technology application cases in simple scenarios. In complex scenarios, digital twin technology has the following problems: 1) Data island problem. Different monitoring and detection equipment are difficult to form a unified management, analysis and display, and operation and maintenance are relatively difficult; 2) Digital twin model creation is difficult. In existing technologies, the creation of digital twin models often relies on a lot of manual intervention, especially in complex application scenarios, such as power pipeline corridors, which have complex structures and equipment. 3) Insufficient real-time performance. The existing power pipeline corridor monitoring technology data update and response time are not timely, and it is unable to cope with emergencies. In general, due to the complex structure and numerous equipment of the power pipeline corridor, the obtained simulation result evaluation cannot fit the actual scenario, which makes it easy for the simulation to take a long time or have poor simulation accuracy. Therefore, there is an urgent need for a digital twin model simulation method for the power pipeline corridor that can improve the simulation effect of the digital twin model simulation of the power pipeline corridor.

[0050] In one embodiment, Figure 1As shown, a digital twin model simulation method for a power pipeline corridor is provided. This embodiment takes the method applied to a simulation master node as an example. The simulation master node is deployed on a terminal, and the terminal includes but is not limited to a personal computer, a laptop computer, a smart phone, and a tablet computer. The simulation master node can be understood as a core node in the simulation system responsible for coordinating, managing, and controlling other simulation nodes. The simulation master node includes a determination module, an allocation module, and a simulation module. The determination module is used to determine multiple model simulation layers corresponding to the digital twin model of the power pipeline corridor, wherein the multiple model simulation layers are generated based on the multi-level attribute information of the digital twin model, and the multi-level attribute information is obtained by fusion of multi-source heterogeneous data of a multi-dimensional physical field collected by multiple sensors; the allocation module is used to allocate corresponding simulation tasks to each model simulation layer according to the simulation attribute characteristics of each model simulation layer, wherein the simulation attribute characteristics At least one of the simulation time nodes and simulation update frequency of the model simulation layer is characterized; the simulation module is used to simulate the digital twin model by executing multiple simulation tasks to obtain the secondary simulation results of the digital twin model. By determining the information interaction between the module, the allocation module and the simulation module, it is possible to reflect the multi-level characteristics and comprehensive performance of the digital twin model of the power pipeline corridor as a whole through multiple model simulation layers, and to reflect the specific details and operation characteristics of the digital twin model of the power pipeline corridor locally through the simulation attribute characteristics of different model simulation layers, so as to simulate the purpose of obtaining the simulation results of the digital twin model of the power pipeline corridor in complex scenarios. Therefore, it is possible to improve the simulation effect of the digital twin model simulation of the power pipeline corridor. It is understandable that this method can also be applied to the server, and can also be applied to the system including the terminal and the server, and is implemented through the interaction between the terminal and the server. In this embodiment, the method includes the following steps:

[0051] Step 202: determine multiple model simulation layers corresponding to the digital twin model of the power pipeline corridor, wherein the multiple model simulation layers are generated based on the multi-level attribute information of the digital twin model, and the multi-level attribute information is obtained by fusing multi-source heterogeneous data of multi-dimensional physical fields collected by multiple sensors.

[0052] It should be noted that multi-level attribute information is used to characterize the inter-layer attributes of the simulation layer in the digital twin model, which is obtained by fusion of multi-source heterogeneous data of multi-dimensional physical fields collected by multiple sensors. Among them, multi-dimensional physical field refers to the simultaneous existence of multiple mutually coupled physical fields in space. Physical fields can be electric fields, magnetic fields, temperature fields, etc. In the power pipeline corridor scenario, multi-dimensional physical field is specifically a collection of multiple physical effects that exist and interact with each other in the power pipeline corridor, which may include electric fields, magnetic fields, temperature fields, vibration fields, fluid fields and stress fields. Among them, the electric field has the electric potential distribution data generated by cables, switchgear, etc., the temperature field has the heating data of cables, transformers and other equipment during operation, the vibration field has the vibration data of transformers or fans, the fluid field has the airflow distribution data of the ventilation system, and the stress field has the mechanical stress data borne by the pipeline corridor walls and cable supports; the internal environment of the power pipeline corridor is complex and is collected by multiple sensors. The data may specifically include electrical data, mechanical data, environmental data and fluid data. The electrical data may specifically include voltage, current, power factor and harmonics, etc., which are used to reflect the operating status of the equipment. The mechanical data may specifically include vibration, displacement, stress and temperature gradient, etc., which are used to monitor the health of the structure. The environmental data may specifically include temperature, humidity and gas concentration, etc., which are used to ensure operational safety. The fluid data may specifically include pressure, flow rate and flow, etc., which are used to monitor the status of the pipeline medium. The various sensors may specifically include electrical parameter sensors, mechanical parameter sensors, environmental parameter sensors and fluid parameter sensors. Among them, the electrical parameter sensors may specifically include voltage transformers, current transformers, power factor sensors and harmonic analyzers, etc. The mechanical parameter sensors may specifically include vibration sensors, displacement sensors, stress sensors and infrared thermal imagers, etc. The environmental parameter sensors may specifically include temperature and humidity sensors, gas sensors (such as 、 Concentration detection) and smoke alarms, etc. Fluid parameter sensors may include pressure sensors, flow meters and flow rate sensors. The power pipeline corridor is divided into multiple model simulation layers in a hierarchical and progressive manner. Multiple model simulation layers are progressively constructed layer by layer to gradually build a digital twin model. Different modeling strategies are adopted at different levels, which can not only ensure the accuracy of the digital twin model, but also improve the efficiency of modeling. The model simulation layer is used to characterize the simulation characteristics of the digital twin model at different levels. Among them, the simulation characteristics can be specifically physical structure, functional behavior and performance optimization, etc. The model simulation layer can be specifically the model base layer, model structure Layer, model function layer or model behavior layer, among which the model base layer is the underlying support for the entire simulation system, providing the basic environment, data, algorithms and tools required for model operation, the model structure layer focuses on components and topology, the model function layer is used to support algorithm logic and function implementation, and the model behavior layer focuses on dynamic characteristics. For example, in an implementable way, for the digital twin model of the power pipeline corridor, a total of three layers are set, among which the first layer, the second layer and the third layer are progressive, the first layer focuses on the physical structure, the second layer focuses on functional behavior, and the third layer focuses on performance optimization, thereby gradually generating a complete digital twin model.

[0053] As an example, step 202 includes: determining multiple model simulation layers required to construct a digital twin model of the power pipeline corridor, wherein the multiple model simulation layers are generated based on multi-level attribute information of the digital twin model.

[0054] Step 204 : assigning corresponding simulation tasks to each model simulation layer according to simulation attribute characteristics of each model simulation layer, wherein the simulation attribute characteristics represent at least one of the simulation time node and the simulation update frequency of the model simulation layer.

[0055] It should be noted that the simulation attribute characteristics at least characterize one of the simulation time node and the simulation update frequency of the model simulation layer, wherein the simulation time node is used to identify the simulation time of the model simulation layer, and the simulation update frequency is used to identify the update frequency of the model simulation layer. For example, in an implementable manner, it is assumed that multiple model simulation layers include a model base layer, a model structure layer, and a model behavior layer, wherein the simulation attribute characteristics of the model base layer and the model structure layer characterize that their simulations are mainly performed when the digital twin model is created to ensure the initial accuracy and structural integrity of the digital twin model, while the simulation of the model behavior layer characterizes that it needs to be dynamically updated in real time to reflect the actual operating status of the equipment, environmental changes and fault predictions. Therefore, the simulation of the model behavior layer will continue, and the model will be adjusted through real-time data to keep the power corridor consistent with the actual situation.

[0056] It should be noted that different simulation tasks can be created in the simulation master node, where one simulation task corresponds to one model simulation layer. It can be understood that different simulation tasks can be used to implement simulation requirements for different model simulation layers. For example, simulation task A is used to implement device simulation of the model base layer, and simulation task B is used to implement device simulation of the model function layer. Different simulation tasks can also be used to implement simulation requirements for the same model simulation layer. For example, simulation task C is used to implement device simulation of the model base layer, and simulation task D is used to implement pipeline simulation of the model base layer.

[0057] As an example, step 204 includes: using the simulation attribute characteristics of each model simulation layer as an index, querying the corresponding simulation tasks for each model simulation layer, and allocating multiple simulation tasks to the corresponding model simulation layers.

[0058] Step 206: Simulate the digital twin model by executing multiple simulation tasks to obtain a digital twin model simulation result.

[0059] It should be noted that after multiple simulation tasks are executed, the simulation results under different simulation tasks can be collected regularly through the simulation master node, and through data synchronization, the simulation results under different simulation tasks can be synthesized to obtain the digital twin model simulation results, wherein the digital twin model simulation results can specifically be a complete three-dimensional visualization image. It can be understood that the digital twin model simulation results can not only feedback the complete digital twin model, but also feedback the intra-layer data of multiple model simulation layers under the digital twin model. For example, the intra-layer data can specifically include the position, status and mutual relationship of each structure in the model simulation layer, etc., wherein the simulation tasks can specifically be computing tasks and rendering tasks, etc.

[0060] As an example, step 206 includes: simulating multiple model simulation layers of the digital twin model by executing multiple simulation tasks in parallel, obtaining multiple layer simulation results, and synthesizing the multiple layer simulation results into a digital twin model simulation result.

[0061] In the above-mentioned digital twin model simulation method of the power pipeline corridor, first, multiple model simulation layers corresponding to the digital twin model of the power pipeline corridor are determined, wherein the multiple model simulation layers are generated according to the multi-level attribute information of the digital twin model, and then based on the simulation attribute characteristics of each model simulation layer, corresponding simulation tasks are assigned to each model simulation layer, wherein the simulation attribute characteristics at least characterize one of the simulation time node and simulation update frequency of the model simulation layer, and finally, by executing multiple simulation tasks, the digital twin model of the power pipeline corridor is simulated to obtain the digital twin model simulation result. Since the multiple model simulation layers are generated according to the multi-level attribute information of the digital twin model, and the multiple model simulation layers have an inter-layer relationship, by determining the multiple model simulation layers corresponding to the digital twin model, the multi-level characteristics of the digital twin model can be reflected as a whole to adapt to the digital twin model, and the simulation tasks corresponding to each model simulation layer are based on each model simulation layer. The simulation attribute characteristics of the real layer are assigned, among which the simulation attribute characteristics at least characterize one of the simulation time nodes and simulation update frequency of the model simulation layer. Therefore, the simulation attribute characteristics can locally reflect the specific details and operating characteristics of the digital twin model of the power pipeline corridor, and then the simulation tasks assigned to each model simulation layer through the simulation attribute characteristics are accurate. Finally, by executing multiple simulation tasks, the digital twin simulation results obtained by simulating the digital twin model of the power pipeline corridor can fit the actual scene, and the purpose of simulating the digital twin model of the power pipeline corridor in a complex scene can be achieved, rather than only being able to integrate multiple digital twin models for unified management, analysis and operation and maintenance. Therefore, the technical defects that the simulation result evaluation cannot fit the actual scene due to the complex structure and numerous equipment of the power pipeline corridor, which makes it easy to have long simulation time or poor simulation accuracy, etc., are overcome. Therefore, the simulation effect of the digital twin model simulation of the power pipeline corridor is improved.

[0062] In one embodiment, Figure 2 As shown in the figure, by executing multiple simulation tasks, the digital twin model is simulated to obtain the simulation results of the digital twin model, including:

[0063] Step 302, determining a plurality of simulation slave nodes in the simulation node cluster to which the simulation master node belongs;

[0064] It should be noted that due to the limited computing power of traditional technology, it is impossible to achieve large-scale real-time simulation and high-refresh-rate visual rendering during the simulation of the digital twin model of the power pipeline corridor. Therefore, in order to improve the simulation efficiency of the digital twin model of the power pipeline corridor, multi-GPU cluster technology can be adopted to process large-scale simulation tasks, that is, to build a high-performance distributed multi-GPU cluster architecture to obtain a simulation node cluster, wherein the simulation node cluster includes a simulation master node and multiple simulation slave nodes, and the simulation master node is used to perform task allocation and resource scheduling, and different simulation tasks are assigned to different simulation slave nodes to achieve efficient parallel computing and rendering. For example, in an implementable method, the simulation node cluster can be specifically a high-performance distributed multi-GPU cluster, wherein independent servers serve as nodes, and each node is interconnected through a high-speed network to ensure low latency and bandwidth of data transmission, thereby meeting the needs of real-time simulation and rendering.

[0065] As an example, step 302 includes: querying the simulation node cluster to which the simulation master node belongs according to the cluster identifier of the simulation master node, and determining a plurality of simulation slave nodes in the simulation node cluster.

[0066] Step 304, a selection step: selecting a target simulation task from a plurality of simulation tasks.

[0067] It should be noted that in the process of relying on multiple simulation slave nodes to collaboratively complete the execution of multiple simulation tasks, the problem of task allocation is involved. Therefore, when simulating the digital twin model, it is necessary to execute the target simulation task selection step, where the target simulation task refers to a simulation task selected from multiple simulation tasks, and the target simulation task can be randomly selected from multiple simulation tasks.

[0068] As an example, step 304 includes: a selection step: randomly selecting any simulation task from multiple simulation tasks as a target simulation task.

[0069] Step 306 : Match a target simulation slave node for the target simulation task among all simulation slave nodes according to the correspondence between the resource requirement information of the target simulation task and the resource load information of the plurality of simulation slave nodes.

[0070] It should be noted that in the process of simulating the digital twin model, in addition to the task allocation problem, the allocation of scheduling resources is also involved. By completing resource scheduling for multiple simulation slave nodes, the matching of simulation tasks and simulation slave nodes can be completed. Among them, resource demand information is used to characterize the resources required to execute the target simulation task, and resource load information is used to characterize the resources currently loaded on the simulation slave node. For example, in one feasible method, assuming that all simulation slave nodes do not have idle resources to execute the target simulation task, a simulation slave node with idle resources greater than a first resource threshold and load resources less than a second resource threshold can be selected from multiple simulation slave nodes as the target simulation slave node.

[0071] As an example, step 306 includes: determining a first resource threshold based on the resource requirement information of the target simulation task, and determining a first size relationship between the idle resources determined based on the resource load information of multiple simulation slave nodes and the first resource threshold, and determining a second size relationship between the load resources of multiple simulation slave nodes and the second resource threshold based on the resource requirement information and the resource load information of multiple simulation slave nodes, and matching the target simulation slave node for the target simulation task among all simulation slave nodes based on the first size relationship and the second size relationship.

[0072] Step 308: execute the target simulation task at the target simulation slave node, and return to execute the selection step until the task simulation results of all simulation tasks are obtained, and obtain the digital twin simulation result by integrating multiple task simulation results.

[0073] As an example, step 308 includes: executing the target simulation task at the target simulation slave node, and returning to execute the selection step until the task simulation results of all simulation tasks are obtained, and obtaining the digital twin simulation result by integrating multiple task simulation results.

[0074] In the above-mentioned simulation method of the digital twin model, the simulation node cluster to which the simulation master node belongs is first determined based on the simulation master node, and then multiple simulation slave nodes in the simulation node cluster are determined, and a selection step is performed: a target simulation task is selected from multiple simulation tasks, and then a target simulation slave node is matched for the target simulation task in all simulation slave nodes through the correspondence between the resource requirement information of the target simulation task and the resource load information of multiple simulation slave nodes. Finally, the target simulation slave node executes the target simulation task, and the selection step is returned until the task simulation results of all simulation tasks are obtained, and the digital twin simulation results are obtained by integrating the simulation results of multiple tasks. That is, the allocation of simulation tasks and the resource allocation of multiple simulation slave nodes are completed under the simulation node cluster architecture, so that the simulation of the digital twin model in the large-scale power pipeline corridor scenario is completed with the help of multiple simulation slave nodes, rather than relying on the single capability of the simulation master node for digital twin model simulation. Therefore, while laying the foundation for improving the simulation effect of the digital twin model simulation of the power pipeline corridor, the simulation efficiency of the digital twin model simulation of the power pipeline corridor is improved.

[0075] In one embodiment, selecting a target simulation task from a plurality of simulation tasks includes:

[0076] Determine the first execution priority and the second execution priority corresponding to each of the multiple simulation tasks, wherein the first execution priority is the execution priority of the model simulation layer in which any simulation task is located, and the second execution priority is the execution priority of any simulation task within the model simulation layer in which it is located; sort the execution priorities of the multiple simulation tasks according to the multiple first execution priorities and the multiple second execution priorities to obtain an execution priority sorting result; select a target simulation task from the multiple simulation tasks according to the execution priority sorting result.

[0077] It should be noted that, in the process of selecting the target simulation task, it can be selected randomly or based on the execution priority of the simulation task. For example, in one feasible method, the simulation task of the behavior layer is set as a high-priority simulation task, the simulation task of the structure layer is set as a medium-priority simulation task, and the simulation task of the foundation layer is set as a low-priority simulation task. It can be understood that in the process of determining the execution priority of the simulation task, it is necessary to simultaneously consider the execution priority between the model simulation layers and the execution priority within the model simulation layer, that is, the first execution priority and the second execution priority, wherein the first execution priority is the execution priority of the model simulation layer where any simulation task is located, and the second execution priority is the execution priority of any simulation task within the model simulation layer where it is located. After knowing the first execution priority and the second execution priority of a simulation task, the specific position of the simulation task among multiple simulation tasks can be clarified.

[0078] As an example, determine the first execution priority corresponding to each of the multiple simulation tasks, and determine the second execution priority corresponding to each of the multiple simulation tasks; determine the total execution priority of the multiple simulation tasks based on the multiple first execution priorities and the multiple second execution priorities; sort the execution priorities of the multiple simulation tasks based on the multiple total execution priorities to obtain the execution priority sorting results, wherein the execution priority sorting results can specifically be an array; select the target simulation task from the multiple simulation tasks based on the execution priority sorting results. In the process of selecting the target simulation task, this embodiment relies on the execution priority between the model simulation layers and the execution priority within the model simulation layer where each simulation task is located, thereby completing the execution priority division of different simulation tasks, and finally selecting the target simulation task from the multiple simulation tasks based on the execution priority sorting results of the multiple simulation tasks, thereby achieving the purpose of sequentially matching the simulation slave nodes for the multiple simulation tasks based on the importance of the simulation tasks, and thus further laying the foundation for improving the simulation effect of the digital twin model of the power pipeline corridor.

[0079] In one embodiment, matching a target simulation slave node for the target simulation task among all simulation slave nodes according to the correspondence between the resource requirement information of the target simulation task and the resource load information of the plurality of simulation slave nodes includes:

[0080] Based on resource demand information and multiple resource load information, multiple candidate simulation slave nodes are screened from multiple simulation slave nodes, wherein the candidate simulation slave nodes are simulation slave nodes that meet the execution resource requirements of the target simulation task; based on resource idle information of the multiple candidate simulation slave nodes, the target simulation slave node is screened from the multiple candidate simulation slave nodes, wherein the resource idle information is used to characterize the idle scheduling resources of the candidate simulation slave node after executing the target simulation task.

[0081] It should be noted that, in the process of matching the target simulation slave node for the target simulation task from all simulation slave nodes, a specific task scheduling algorithm can be set to select the target simulation slave node with the highest degree of adaptability to the target simulation task, that is, first, through resource demand information and multiple resource load information, a candidate simulation slave node that can meet the execution resource requirements of the target simulation task is selected from multiple simulation slave nodes, and then by comparing the resource idleness of different candidate simulation slave nodes, the target simulation slave node is screened from multiple simulation slave nodes. For example, in an implementable manner, the implementation of the task scheduling algorithm is as follows: 1) Initialization, when the system starts, a list of all GPU nodes in the simulation node cluster is determined GPU_No des[], initialize the status of each node, including computing power Compute_Power[i], current load Load[i], and task queue Task_Queue[i]; 2) Task classification and priority setting, divide all simulation tasks into different priorities Priority[], among which the model behavior layer is set to high priority, the model structure layer is set to medium priority, and the model foundation layer is set to low priority; 3) Task allocation, for each newly arrived simulation task Task_j, allocate it according to the following steps: traverse all GPU nodes GPU_Nodes[i], calculate the current load Load[i] of each node, select the node with the lightest load Node_min, and ensure that:

[0082] Load[Node_min]+Compute_Needed_j Compute_Power[Node_min], that is, before assigning a new task to the node with the lightest load (Node_min), it is necessary to ensure that the current load of the node (Load[Node_min]) plus the computing resources required for the new task (Compute_Needed_j) does not exceed the computing power of the node (Compute_Power[Node_min]), so that task Task_j is assigned to Node_min, where the candidate simulation slave node is a simulation slave node that meets the execution resource requirements of the target simulation task, and the resource idle information is used to characterize the idle scheduling information of the candidate simulation slave node after executing the target simulation task.

[0083] As an example, based on multiple resource load information, the idle resources of multiple simulation slave nodes are determined, and the simulation slave nodes whose idle resources are greater than the required resources identified by the resource demand information are selected as candidate simulation slave nodes; based on the resource idle information of multiple candidate simulation slave nodes, the candidate simulation slave node with the largest idle resources is selected from the multiple candidate simulation slave nodes as the target simulation slave node. This embodiment uses resource demand information and resource load information to screen candidate simulation slave nodes that meet the execution resource requirements of the target simulation task from multiple simulation slave nodes, completing a primary screening of the simulation slave nodes, and then based on the resource idle information of the candidate simulation slave nodes, screen the target simulation slave node from multiple candidate simulation slave nodes, completing a secondary screening of the simulation slave nodes, thereby achieving the purpose of matching the most suitable target simulation slave node for the target simulation task based on a specific task scheduling algorithm, thereby laying the foundation for further improving the simulation effect of the digital twin model of the power pipeline corridor.

[0084] In one embodiment, the method further comprises at least one of the following:

[0085] According to the target simulation task matched by the target simulation slave node, the load scheduling resources of the target simulation slave node are updated; when it is detected that the target simulation task is overloaded, the target simulation slave node is rematched for the target simulation task among all simulation slave nodes; when it is detected that the number of tasks to be executed on the simulation slave node is greater than the preset task amount threshold, the target simulation slave node is rematched for the tasks to be executed on the simulation slave node.

[0086] It should be noted that in addition to the task and resource allocation capabilities, the simulation master node also has the macro-control capabilities of the entire simulation node cluster. For example, in addition to assigning task Task_j to Node_min, the simulation master node can also update the load Load[Node_min]+Compute_Needed_j of the target simulation slave node; the simulation master node can also perform real-time load monitoring and dynamic adjustment. During the task execution process, the load Load[i] and task completion status of each GPU node can be monitored in real time. If a simulation slave node is overloaded (that is, Load[i] exceeds its computing power Cpmpute_Power[i]), or the task queue is overloaded, task reallocation will be triggered, and the low-priority tasks of the overloaded node will be suspended and reallocated to nodes with lighter loads.

[0087] As an example, the target simulation task matched by the target simulation slave node is determined, and the current load scheduling resources of the target simulation slave node are updated to the sum of the current load resources and the demand resources; when it is detected that the current load resources of the target simulation slave node corresponding to the target simulation task are greater than the preset load resource threshold, the target simulation slave node is re-matched for the target simulation task in all simulation slave nodes; when it is detected that the number of tasks to be executed on the simulation slave node is greater than the preset task amount threshold, the target simulation slave node is re-matched for the tasks to be executed on all simulation slave nodes. When simulating the digital twin model, this embodiment synchronously sets the load update, real-time load monitoring and dynamic adjustment capabilities of the simulation slave node, so as to ensure the normal and efficient progress of the simulation process, and therefore lays the foundation for further improving the simulation effect of the digital twin model.

[0088] In one practicable manner, referring to Figure 3 , Figure 3 A schematic diagram showing the scheduling and execution of multiple simulation tasks, which includes task classification and priority setting, matching of target simulation tasks and target simulation slave nodes based on resource capabilities, and real-time load monitoring and dynamic adjustment of simulation slave nodes.

[0089] In one embodiment, the multiple model simulation layers include a model base layer, a model structure layer, a model function layer, and a model behavior layer in a layer-by-layer manner; determining the multiple model simulation layers set for the digital twin model of the power pipeline corridor includes:

[0090] The point cloud data of the power pipeline corridor is processed in a standard manner to obtain point cloud standard data, and based on the classification results of the point cloud standard data, the base layer of the digital twin model of the power pipeline corridor is modeled to obtain the model base layer; the point cloud standard data is converted into a geometric model of the power pipeline corridor, and the structural layer of the geometric model is modeled based on the preset structural parameters and the model base layer to obtain the model structure layer; a functional knowledge graph of the power pipeline corridor is constructed, and a model function layer is generated based on the functional knowledge graph and the model structure layer; based on the actual operation data of the power pipeline corridor and the simulated operation data of the digital twin model of the power pipeline corridor, the behavior layer of the digital twin model of the power pipeline corridor is modeled to obtain the model behavior layer.

[0091] It should be noted that different model simulation layers can rely on different means in the modeling process. The model simulation layer includes the model base layer, model structure layer, model function layer and model behavior layer in a layer-by-layer manner. By sequentially constructing the model base layer, model structure layer, model function layer and model behavior layer of the power pipeline corridor, a complete digital twin model is gradually generated. 1) The model base layer modeling first uses mobile lidar scanning, drone lidar scanning and other technologies to quickly determine the large-scale point cloud data of the power pipeline corridor, and combines the high-precision GPS positioning system to generate a basic geographic information model; further, the collected point cloud data is subjected to denoising, deduplication and coordinate conversion processing to ensure the accuracy and consistency of the data, and is preliminarily classified through clustering algorithms to divide the point cloud data into categories such as structures, equipment, and pipelines; 2) In the model structure layer modeling, a simplified modeling method is first adopted in the structure layer, and the complex The point cloud data is converted into a lightweight geometric model. Using plane and surface simplification algorithms, complex building structures are simplified into key geometric shapes such as faces, columns, and pipes. Pre-designed parametric templates are then used to abstractly model typical structures and equipment within the power corridor. By matching this with the underlying layer data, a structural model that conforms to the actual situation is generated. 3) Modeling at the functional layer is automatically constructed based on the knowledge graph. First, a functional knowledge graph of the power corridor is constructed, combining the design drawings and equipment manuals. This knowledge graph contains the functions, performance indicators, and operating rules of various types of equipment within the corridor. Based on the knowledge graph and the structural layer model, functional models of various types of equipment within the corridor are automatically generated. This process is achieved through rule-based reasoning and parameter matching, reducing the need for manual intervention. 4) Modeling at the behavioral layer dynamically updates the corridor's behavioral model using real-time sensor data, historical operation and maintenance data, and simulation data. Using a data-driven approach, time series analysis and machine learning algorithms are used to simulate equipment operating status and predict faults. Furthermore, the parameters of the behavioral model are optimized based on on-site operation and maintenance feedback and simulation results to better reflect actual operating conditions.

[0092] As an example, the point cloud data of the power pipeline corridor is subjected to noise reduction, deduplication, and coordinate transformation to obtain standard point cloud data, and the standard point cloud data is classified by a clustering algorithm to obtain classification results. Based on the classification results, the digital twin model of the power pipeline corridor is modeled at the base layer to obtain the model base layer; the standard point cloud data is converted into a geometric model of the power pipeline corridor, and the geometric model is abstractly modeled using a pre-designed parametric template, and the model structure layer is generated by matching it with the data of the model base layer; a functional knowledge graph of the power pipeline corridor is constructed, and a model function layer is generated based on the functional knowledge graph and the model structure layer model; based on the real-time operation data, historical operation and maintenance data, and historical simulation data of the power pipeline corridor, the digital twin model of the power pipeline corridor is modeled at the behavior layer to obtain the model behavior layer. This embodiment divides the digital twin model into a model base layer, a model structure layer, a model function layer, and a model behavior layer, and then adopts different modeling methods to respectively construct the model base layer, model structure layer, model function layer, and model behavior layer, thereby laying the foundation for the subsequent improvement of the simulation effect of the digital twin model of the power pipeline corridor.

[0093] In one feasible method, a model base layer, a model structure layer, a model function layer and a model behavior layer are first set up in a layer-by-layer progressive manner, wherein the point cloud data of the power pipeline corridor is subjected to standard processing to obtain point cloud standard data, and based on the classification results of the point cloud standard data, the digital twin model of the power pipeline corridor is modeled at the base layer to obtain the model base layer; the point cloud standard data is converted into a geometric model of the power pipeline corridor, and based on the preset structural parameters and the model base layer, the geometric model is modeled at the structure layer to obtain the model structure layer; a functional knowledge graph of the power pipeline corridor is constructed, and based on the functional knowledge graph and the model structure layer, a model function layer is generated; based on the actual operation data of the power pipeline corridor and the simulated operation data of the digital twin model of the power pipeline corridor, the digital twin model of the power pipeline corridor is modeled at the behavior layer to obtain the model behavior layer.

[0094] Furthermore, according to the simulation attribute characteristics of the model base layer, the model structure layer, the model function layer and the model behavior layer, corresponding simulation tasks are assigned to the multiple model simulation layers; and then in the process of simulating the digital twin model, the multiple simulation slave nodes in the simulation node cluster to which the simulation master node belongs are first determined, and the first execution priority and the second execution priority corresponding to the multiple simulation tasks are determined, and the multiple simulation tasks are sorted according to the multiple first execution priorities and the multiple second execution priorities to obtain the execution priority sorting results, and the target simulation task is selected from the multiple simulation tasks based on the execution priority sorting results, and then according to the resource demand information and the multiple resource load information, multiple candidate simulation slave nodes are screened from the multiple simulation slave nodes, and according to the resource idle information of the multiple candidate simulation slave nodes, the target simulation slave node is screened from the multiple candidate simulation slave nodes, and finally the target simulation task is executed on the target simulation slave node, and the execution selection step is returned until the task simulation results of all simulation tasks are obtained, and the digital twin simulation result is obtained by integrating the multiple task simulation results.

[0095] Since multiple model simulation layers are generated based on the multi-level attribute information of the digital twin model, and thus there is an inter-layer relationship between the multiple model simulation layers, by determining the multiple model simulation layers corresponding to the digital twin model, the multi-level characteristics of the digital twin model can be reflected as a whole to adapt to the digital twin model, and the simulation tasks corresponding to each model simulation layer are allocated according to the simulation attribute characteristics of each model simulation layer, wherein the simulation attribute characteristics at least characterize one of the simulation time nodes and simulation update frequency of the model simulation layer, so the simulation attribute characteristics can locally reflect the specific details and operating characteristics of the digital twin model of the power pipeline corridor, and then through the simulation attribute characteristics The simulation tasks assigned to each model simulation layer are accurate. Finally, by executing multiple simulation tasks, the digital twin simulation results obtained by simulating the digital twin model of the power pipeline corridor can fit the actual scenario, thereby achieving the purpose of simulating the digital twin model simulation results of the power pipeline corridor under complex scenarios, rather than only integrating multiple digital twin models for unified management, analysis and operation and maintenance. Therefore, it overcomes the technical defects that the simulation result evaluation cannot fit the actual scenario due to the complex structure and large number of equipment of the power pipeline corridor, which makes it easy to have long simulation time or poor simulation accuracy. Therefore, the simulation effect of the digital twin model simulation of the power pipeline corridor is improved.

[0096] It should be understood that, although the steps in the flowcharts of the above embodiments are shown in sequence as indicated by the arrows, these steps are not necessarily performed in the order indicated by the arrows. Unless otherwise specified herein, there is no strict order restriction on the execution of these steps, and these steps can be performed in other orders. Moreover, at least a portion of the steps in the flowcharts of the above embodiments may include multiple steps or multiple stages, and these steps or stages are not necessarily performed at the same time, but can be performed at different times. The execution order of these steps or stages is not necessarily to be performed in sequence, but can be performed in turn or alternately with other steps or at least a portion of steps or stages in other steps.

[0097] Based on the same inventive concept, the present application also provides a digital twin model simulation device for a power pipeline corridor for implementing the aforementioned digital twin model simulation method for a power pipeline corridor. The solution provided by this device is similar to the solution described in the aforementioned method. Therefore, the specific limitations of one or more embodiments of the digital twin model simulation device for a power pipeline corridor provided below can be found in the above-mentioned limitations of the digital twin model simulation method for a power pipeline corridor, and will not be repeated here.

[0098] In an exemplary embodiment, Figure 4 As shown, a digital twin model simulation device for a power pipeline corridor is provided, including: a determination module 401, an allocation module 402 and a simulation module 403, wherein:

[0099] A determination module 401 is configured to determine a plurality of model simulation layers corresponding to a digital twin model of a power pipeline corridor, wherein the plurality of model simulation layers are generated based on multi-level attribute information of the digital twin model, the multi-level attribute information being obtained by fusing multi-source heterogeneous data of a multi-dimensional physical field acquired by a plurality of sensors;

[0100] an allocation module 402 for allocating corresponding simulation tasks to each of the model simulation layers according to simulation attribute characteristics of each of the model simulation layers, wherein the simulation attribute characteristics represent at least one of a simulation time node and a simulation update frequency of the model simulation layer;

[0101] The simulation module 403 is used to simulate the digital twin model by executing multiple simulation tasks to obtain a digital twin model simulation result.

[0102] In one embodiment, the simulation module 403 is further configured to:

[0103] Determine multiple simulation slave nodes in the simulation node cluster to which the simulation master node belongs; selection step: select a target simulation task from the multiple simulation tasks; match a target simulation slave node for the target simulation task in all simulation slave nodes according to the correspondence between the resource requirement information of the target simulation task and the resource load information of the multiple simulation slave nodes; execute the target simulation task at the target simulation slave node, and return to execute the selection step until the task simulation results of all simulation tasks are obtained, and the digital twin simulation result is obtained by integrating multiple task simulation results.

[0104] In one embodiment, the simulation module 403 is further configured to:

[0105] Determine the first execution priority and the second execution priority corresponding to each of the multiple simulation tasks, wherein the first execution priority is the execution priority of the model simulation layer where any simulation task is located, and the second execution priority is the execution priority of any of the simulation tasks within the model simulation layer where it is located; sort the multiple simulation tasks according to the multiple first execution priorities and the multiple second execution priorities to obtain an execution priority sorting result; select the target simulation task from the multiple simulation tasks according to the execution priority sorting result.

[0106] In one embodiment, the simulation module 403 is further configured to:

[0107] Based on the resource demand information and multiple resource load information, multiple candidate simulation slave nodes are screened from the multiple simulation slave nodes, wherein the candidate simulation slave nodes are simulation slave nodes that meet the execution resource requirements of the target simulation task; based on the resource idle information of the multiple candidate simulation slave nodes, the target simulation slave node is screened from the multiple candidate simulation slave nodes, wherein the resource idle information is used to characterize the idle scheduling resources of the candidate simulation slave nodes after executing the target simulation task.

[0108] In one embodiment, the digital twin model simulation device of the power pipeline corridor is further used to:

[0109] According to the target simulation task matched by the target simulation slave node, the load scheduling resources of the target simulation slave node are updated; when it is detected that the target simulation task is overloaded, the target simulation slave node is rematched for the target simulation task among all simulation slave nodes; when it is detected that the number of tasks to be executed on the simulation slave node is greater than a preset task amount threshold, the target simulation slave node is rematched for the tasks to be executed on the simulation slave node.

[0110] In one embodiment, the multiple model simulation layers include a model base layer, a model structure layer, a model function layer, and a model behavior layer in a layer-by-layer manner; the determination module 401 is further configured to:

[0111] The point cloud data of the power pipeline corridor is subjected to standard processing to obtain point cloud standard data, and based on the classification results of the point cloud standard data, the base layer of the digital twin model of the power pipeline corridor is modeled to obtain the model base layer; the point cloud standard data is converted into a geometric model of the power pipeline corridor, and the structural layer of the geometric model is modeled based on preset structural parameters and the model base layer to obtain the model structure layer; a functional knowledge graph of the power pipeline corridor is constructed, and the model functional layer is generated based on the functional knowledge graph and the model structure layer; the behavior layer of the digital twin model of the power pipeline corridor is modeled based on the actual operation data of the power pipeline corridor and the simulated operation data of the digital twin model of the power pipeline corridor to obtain the model behavior layer.

[0112] Each module in the aforementioned digital twin model simulation device for power pipeline corridors can be implemented in whole or in part through software, hardware, or a combination thereof. Each module can be embedded in or independent of a processor within a computer device as hardware, or stored in a computer device's memory as software, allowing the processor to call and execute the corresponding operations of each module.

[0113] In an exemplary embodiment, a computer device is provided. The computer device may be a terminal, and its internal structure diagram may be as shown in FIG. Figure 5 As shown. The computer device includes a processor, a memory, an input / output interface, a communication interface, a display unit and an input device. The processor, the memory and the input / output interface are connected via a system bus, and the communication interface, the display unit and the input device are connected to the system bus via the input / output interface. The processor of the computer device is used to provide computing and control capabilities. The memory of the computer device includes a non-volatile storage medium and an internal memory. The non-volatile storage medium stores an operating system and a computer program. The internal memory provides an environment for the operation of the operating system and the computer program in the non-volatile storage medium. The input / output interface of the computer device is used to exchange information between the processor and an external device. The communication interface of the computer device is used to communicate with an external terminal in a wired or wireless manner, and the wireless manner can be achieved through WIFI, a mobile cellular network, NFC (near field communication) or other technologies. When the computer program is executed by the processor, it realizes a digital twin model simulation method for a power pipeline corridor. Those skilled in the art can understand that Figure 5The structure shown in the figure is only a block diagram of a part of the structure related to the solution of the present application, and does not constitute a limitation on the computer device to which the solution of the present application is applied. The specific computer device may include more or fewer components than shown in the figure, or combine certain components, or have a different component arrangement.

[0114] In one embodiment, a computer device is further provided, including a memory and a processor. The memory stores a computer program, and the processor implements the steps in the above method embodiments when executing the computer program.

[0115] In one embodiment, a computer-readable storage medium is provided, on which a computer program is stored. When the computer program is executed by a processor, the steps in the above-mentioned method embodiments are implemented.

[0116] In one embodiment, a computer program product is provided, including a computer program, which implements the steps in the above method embodiments when executed by a processor.

[0117] Those skilled in the art will appreciate that all or part of the processes in the above-mentioned embodiments can be implemented by instructing the relevant hardware through a computer program. The computer program can be stored in a non-volatile computer-readable storage medium. When the computer program is executed, it can include the processes of the above-mentioned embodiments. In particular, any reference to memory, database, or other media used in the embodiments provided in this application can include at least one of non-volatile and volatile memory. Non-volatile memory can include read-only memory (ROM), magnetic tape, floppy disk, flash memory, optical memory, high-density embedded non-volatile memory, resistive random access memory (ReRAM), magnetic random access memory (MRAM), ferroelectric random access memory (FRAM), phase change memory (PCM), graphene memory, etc. Volatile memory can include random access memory (RAM) or external cache memory, etc. By way of illustration and not limitation, RAM can take various forms, such as static random access memory (SRAM) or dynamic random access memory (DRAM). The databases involved in the various embodiments provided herein may include at least one of a relational database and a non-relational database. Non-relational databases may include, but are not limited to, distributed databases based on blockchains. The processors involved in the various embodiments provided herein may be, but are not limited to, general-purpose processors, central processing units (CPUs), graphics processing units (GPUs), digital signal processors (DSPs), programmable logic devices (PLDs), data processing logic devices based on quantum computing, and the like.

[0118] The technical features of the above embodiments can be combined arbitrarily. To make the description concise, not all possible combinations of the technical features in the above embodiments are described. However, as long as there is no contradiction in the combination of these technical features, they should be considered to be within the scope of this specification.

[0119] The above-described embodiments merely represent several implementation methods of the present application. While the descriptions are relatively specific and detailed, they should not be construed as limiting the scope of the present application. It should be noted that a person of ordinary skill in the art may make various modifications and improvements without departing from the spirit of the present application, and these modifications and improvements fall within the scope of protection of the present application. Therefore, the scope of protection of the present application shall be determined by the appended claims.

Claims

1. A digital twin model simulation method for a power pipeline corridor, characterized in that: Applied to the simulation master node, the method includes: Determining multiple model simulation layers corresponding to the digital twin model of the power pipeline corridor, wherein the multiple model simulation layers are generated based on multi-level attribute information of the digital twin model, and the multi-level attribute information is obtained by fusing multi-source heterogeneous data of a multi-dimensional physical field collected by multiple sensors; According to the simulation attribute characteristics of each model simulation layer, each model simulation layer is assigned a corresponding simulation task, wherein the simulation attribute characteristics represent at least one of the simulation time node and the simulation update frequency of the model simulation layer; By executing multiple simulation tasks, the digital twin model is simulated to obtain a digital twin model simulation result.

2. The method according to claim 1, characterized in that The digital twin model is simulated by executing multiple simulation tasks to obtain a digital twin model simulation result, including: Determine a plurality of simulation slave nodes in a simulation node cluster to which the simulation master node belongs; Selecting step: selecting a target simulation task from the plurality of simulation tasks; Matching a target simulation slave node for the target simulation task among all simulation slave nodes according to the corresponding relationship between the resource requirement information of the target simulation task and the resource load information of the plurality of simulation slave nodes; The target simulation task is executed at the target simulation slave node, and the selection step is returned to be executed until the task simulation results of all simulation tasks are obtained, and the digital twin simulation result is obtained by integrating multiple task simulation results.

3. The method according to claim 2, characterized in that The selecting a target simulation task from the plurality of simulation tasks comprises: Determine a first execution priority and a second execution priority corresponding to each of the multiple simulation tasks, wherein the first execution priority is the execution priority of the model simulation layer where any simulation task is located, and the second execution priority is the execution priority of any simulation task within the model simulation layer where it is located; Sorting the plurality of simulation tasks according to the plurality of first execution priorities and the plurality of second execution priorities to obtain an execution priority sorting result; The target simulation task is selected from the multiple simulation tasks according to the execution priority sorting result.

4. The method according to claim 2, characterized in that The matching of a target simulation slave node for the target simulation task among all simulation slave nodes according to the correspondence between the resource requirement information of the target simulation task and the resource load information of the plurality of simulation slave nodes comprises: According to the resource requirement information and the plurality of resource load information, a plurality of candidate simulation slave nodes are screened from the plurality of simulation slave nodes, wherein the candidate simulation slave nodes are simulation slave nodes that meet the execution resource requirements of the target simulation task; The target simulation slave node is screened from the multiple candidate simulation slave nodes according to resource idle information of the multiple candidate simulation slave nodes, wherein the resource idle information is used to represent idle scheduling resources of the candidate simulation slave nodes after executing the target simulation task.

5. The method according to claim 4, characterized in that The method further comprises at least one of the following: updating the load scheduling resources of the target simulation slave node according to the target simulation task matched by the target simulation slave node; When it is detected that the target simulation task is overloaded, rematching the target simulation slave node for the target simulation task among all simulation slave nodes; When it is detected that the number of tasks to be executed on the simulation slave node is greater than a preset task amount threshold, the target simulation slave node is re-matched for the tasks to be executed on the simulation slave node.

6. The method according to claim 1, characterized in that The multiple model simulation layers include a model foundation layer, a model structure layer, a model function layer and a model behavior layer in a progressive manner; The step of determining multiple model simulation layers for the digital twin model of the power pipeline corridor includes: performing standard processing on the point cloud data of the power pipeline corridor to obtain standard point cloud data, and performing base layer modeling on the digital twin model of the power pipeline corridor according to the classification result of the standard point cloud data to obtain the model base layer; Converting the point cloud standard data into a geometric model of the power pipeline corridor, and performing structural layer modeling on the geometric model according to preset structural parameters and the model base layer to obtain the model structure layer; Constructing a functional knowledge graph of the power pipeline corridor, and generating the model function layer according to the functional knowledge graph and the model structure layer; According to the actual operation data of the power pipeline corridor and the simulated operation data of the digital twin model of the power pipeline corridor, the digital twin model of the power pipeline corridor is modeled at a behavior layer to obtain the model behavior layer.

7. A digital twin model simulation device for a power pipeline corridor, characterized in that: Applied to simulating a master node, the device comprises: a determination module, configured to determine a plurality of model simulation layers corresponding to the digital twin model of the power pipeline corridor, wherein the plurality of model simulation layers are generated based on multi-level attribute information of the digital twin model, and the multi-level attribute information is obtained by fusing multi-source heterogeneous data of a multi-dimensional physical field acquired by a plurality of sensors; an allocation module, configured to allocate a corresponding simulation task to each of the model simulation layers according to a simulation attribute feature of each of the model simulation layers, wherein the simulation attribute feature represents at least one of a simulation time node and a simulation update frequency of the model simulation layer; The simulation module is used to simulate the digital twin model by executing multiple simulation tasks to obtain the digital twin model simulation results.

8. A computer device comprising a memory and a processor, wherein the memory stores a computer program, wherein: When the processor executes the computer program, the steps of the method according to any one of claims 1 to 6 are implemented.

9. A computer-readable storage medium having a computer program stored thereon, characterized in that: When the computer program is executed by a processor, the steps of the method according to any one of claims 1 to 6 are implemented.

10. A computer program product comprising a computer program, characterized in that When the computer program is executed by a processor, the steps of the method according to any one of claims 1 to 6 are implemented.

Images