Building mechanical and electrical system simulation method, device and equipment based on directed graph clustering optimization

Abstract

The application provides a building mechanical and electrical system simulation method, device and equipment based on directed graph clustering optimization, which comprises the following steps: constructing a directed graph model of a building mechanical and electrical system; generating directed basic loops of the building mechanical and electrical system according to the directed graph model of the building mechanical and electrical system; performing clustering processing on the directed basic loops to obtain a plurality of clustering groups; merging the directed basic loops in each clustering group to generate a clustering loop; and performing simulation solving on the building mechanical and electrical system according to the clustering loop to obtain a simulation result of the building mechanical and electrical system. The method of the application realizes efficient simplification and equivalent fusion of a large number of structurally similar redundant basic loops, greatly reduces the calculation complexity and iteration scale of simulation solving, significantly improves the convergence speed and calculation efficiency of system simulation, and effectively solves the problems of calculation redundancy, large resource consumption and poor real-time performance of the traditional simulation method in a large-scale building mechanical and electrical system.

Description

Technical Field

[0001] This invention relates to the field of digital simulation technology for building energy systems, and in particular to a method, apparatus, and equipment for simulating building electromechanical systems based on directed graph clustering optimization. Background Technology

[0002] With the increasing scale and complexity of buildings, the demand for high-precision dynamic simulation of large-scale regional energy supply systems and electromechanical systems of super high-rise buildings is becoming increasingly urgent.

[0003] In related technologies, directed graph-based simulation methods abstract the system as a network of nodes and edges, and organize coupled solutions by identifying feedback loops in the network, which has become an effective technical approach. However, when applying such methods to truly large-scale systems, the system topology often contains a large number of basic loops with similar structures. Directly incorporating all basic loops into the iterative solution system will result in excessively large dimensions of iterative equations, severe redundancy in computational paths, consumption of large amounts of computational resources, and slow convergence, making it difficult to meet the efficiency requirements of scenarios such as design optimization and real-time analysis. Summary of the Invention

[0004] This invention provides a simulation method, apparatus, and device for building electromechanical systems based on directed graph clustering optimization. It generates directed basic loops of the building electromechanical system from a directed graph model and compresses hundreds or thousands of basic loops into a small number of clustered loops through clustering and merging. While fully preserving the topology and coupling characteristics of the building electromechanical system, it achieves efficient simplification and equivalent fusion of a large number of structurally similar redundant basic loops, significantly reducing the computational complexity and iteration scale of the simulation solution, and significantly improving the convergence speed and computational efficiency of the system simulation. Under the premise of ensuring controllable simulation accuracy, it effectively solves the problems of computational redundancy, high resource consumption, and poor real-time performance of traditional simulation methods in large-scale building electromechanical systems.

[0005] This invention provides a simulation method for building electromechanical systems based on directed graph clustering optimization, comprising the following steps: Construct a directed graph model of the building electromechanical system; the nodes in the directed graph model are used to represent the building electromechanical equipment, and the directed edges in the directed graph model are used to represent the physical connection relationship or information flow transmission relationship between the building electromechanical equipment; Based on the directed graph model of the building electromechanical system, generate the directed basic cycle of the building electromechanical system; Clustering is performed on the directed basic rings to obtain multiple cluster groups; The directed basic rings in each of the cluster groups are merged to generate a cluster ring; the cluster ring is used to characterize the topological and coupling properties of the cluster groups. The building electromechanical system is simulated and solved based on the clustering ring to obtain the simulation results of the building electromechanical system.

[0006] According to the present invention, a simulation method for building electromechanical systems based on directed graph clustering optimization is provided, wherein the directed basic rings are clustered to obtain multiple cluster groups, including: Based on the structural similarity between directed basic rings, the directed basic rings are clustered to obtain multiple cluster groups; wherein, the structural similarity of directed basic rings within each cluster group is higher than a threshold, and the structural similarity of directed basic rings between different cluster groups is lower than a threshold.

[0007] According to the present invention, a simulation method for building electromechanical systems based on directed graph clustering optimization is provided, wherein the directed basic rings are clustered according to the structural similarity between them to obtain multiple cluster groups, including: Based on the structural similarity between the directed basic rings, a similarity matrix is ​​obtained; The directed basic rings are clustered based on the similarity matrix to obtain the multiple cluster groups.

[0008] According to the present invention, a simulation method for building electromechanical systems based on directed graph clustering optimization is provided, wherein clustering the directed basic rings according to the similarity matrix to obtain the plurality of cluster groups includes: Based on the similarity matrix, the directed basic rings are clustered using a hierarchical clustering algorithm, and the distance changes during the clustering process are determined using the natural breakpoint method to determine the number of clusters and the multiple cluster groups.

[0009] According to the present invention, a simulation method for building electromechanical systems based on directed graph clustering optimization is provided, wherein merging the directed basic rings in each cluster group to generate a clustering ring includes: For each cluster group, the common nodes and common paths between directed basic rings within the cluster group are taken as the backbone, and the different paths between directed basic rings within the cluster group are taken as branches. The clustering ring is generated based on the main trunk and the branches.

[0010] According to the present invention, a simulation method for building electromechanical systems based on directed graph clustering optimization is provided, wherein the building electromechanical system includes at least one of the following: Energy pipeline network system, building air conditioning water system and building central refrigeration station system.

[0011] According to the present invention, a simulation method for building electromechanical systems based on directed graph clustering optimization is provided, wherein the building electromechanical equipment includes at least one of the following: Chillers, cooling towers, water pumps, air conditioning terminals and controllers.

[0012] The present invention also provides a building electromechanical system simulation device, comprising the following modules: A construction module is used to construct a directed graph model of a building electromechanical system; the nodes in the directed graph model are used to represent building electromechanical equipment, and the directed edges in the directed graph model are used to represent the physical connection relationship or information flow transmission relationship between building electromechanical equipment; The generation module is used to generate a directed basic loop of the building electromechanical system based on the directed graph model of the building electromechanical system. The clustering module is used to perform clustering processing on the directed basic rings to obtain multiple cluster groups; The merging module is used to merge the directed basic rings in each of the cluster groups to generate a cluster ring; the cluster ring is used to characterize the topological and coupling properties of the cluster groups. The simulation module is used to perform simulation solutions on the building electromechanical system based on the clustering ring, and obtain the simulation results of the building electromechanical system.

[0013] The present invention also provides an electronic device, including a memory, a processor, and a computer program stored in the memory and executable on the processor, wherein the processor executes the computer program to implement the building electromechanical system simulation method based on directed graph clustering optimization as described above.

[0014] The present invention also provides a non-transitory computer-readable storage medium having a computer program stored thereon, which, when executed by a processor, implements the building electromechanical system simulation method based on directed graph clustering optimization as described above.

[0015] The present invention also provides a computer program product, including a computer program that, when executed by a processor, implements the building electromechanical system simulation method based on directed graph clustering optimization as described above.

[0016] This invention provides a simulation method, apparatus, and equipment for building electromechanical systems based on directed graph clustering optimization. It generates directed basic loops of the building electromechanical system from a directed graph model and compresses hundreds or thousands of basic loops into a small number of clustered loops through clustering and merging. While fully preserving the topology and coupling characteristics of the building electromechanical system, it achieves efficient simplification and equivalent fusion of a large number of structurally similar redundant basic loops, significantly reducing the computational complexity and iteration scale of the simulation solution, and significantly improving the convergence speed and computational efficiency of the system simulation. Under the premise of ensuring controllable simulation accuracy, it effectively solves the problems of computational redundancy, high resource consumption, and poor real-time performance of traditional simulation methods in large-scale building electromechanical systems. Attached Figure Description

[0017] To more clearly illustrate the technical solutions in this 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 some embodiments of this invention. For those skilled in the art, other drawings can be obtained from these drawings without creative effort.

[0018] Figure 1 This is one of the flowcharts illustrating the building electromechanical system simulation method based on directed graph clustering optimization provided by this invention.

[0019] Figure 2 This is the second flowchart of the building electromechanical system simulation method based on directed graph clustering optimization provided by the present invention.

[0020] Figure 3 This is the directed topology graph of the cooling plant system provided by the present invention.

[0021] Figure 4 This is a simplified diagram of the directed graph of the cooling plant system topology after preprocessing and removing independent nodes, as provided by the present invention.

[0022] Figure 5 This is a schematic diagram of several structurally similar basic rings provided by the present invention.

[0023] Figure 6 This is a schematic diagram of the optimized clustered ring set generated by the basic ring grouping and merging provided by the present invention.

[0024] Figure 7 This is a schematic diagram of the building electromechanical system simulation device provided by the present invention.

[0025] Figure 8 This is a schematic diagram of the structure of the electronic device provided by the present invention. Detailed Implementation

[0026] To make the objectives, technical solutions, and advantages of this invention clearer, the technical solutions of this invention will be clearly and completely described below with reference to the accompanying drawings. Obviously, the described embodiments are only some, not all, of the embodiments of this invention. All other embodiments obtained by those skilled in the art based on the embodiments of this invention without creative effort are within the scope of protection of this invention.

[0027] The following is combined with Figures 1 to 8 This invention describes a method, apparatus, and equipment for simulating building electromechanical systems based on directed graph clustering optimization.

[0028] To facilitate a clearer understanding of the technical solutions of the various embodiments of this application, some technical content related to the various embodiments of this application will be introduced first.

[0029] With the increasing scale and complexity of buildings, the demand for high-precision dynamic simulation of large-scale regional energy supply systems and electromechanical systems of super high-rise buildings is becoming increasingly urgent. Directed graph-based simulation methods abstract the system into a network of nodes and edges, and organize coupled solutions by identifying feedback loops (directed loops) in the network, which has become an effective technical approach.

[0030] However, when applying such methods to truly large-scale systems, a significant bottleneck arises: the system topology often contains a large number of structurally similar basic loops. For example, a regional pipe network supplying cooling to ten buildings may contain more than ten hydraulic loops with highly similar structures (cold source-main pipe-building branch pipe-return pipe); the air conditioning water system of a high-rise building may contain similar all-air handling unit loops on each floor. Directly incorporating all these basic loops into the iterative solution system will result in excessively large dimensional iterative equations, severe redundancy in computational paths, excessive consumption of computational resources, and slow convergence, making it difficult to meet the efficiency requirements of scenarios such as design optimization and real-time analysis.

[0031] Therefore, while preserving the key physical coupling relationships of the system, how to intelligently simplify the loop structure and compress the solution scale has become a key technical challenge to improve the practicality of simulation of large-scale building electromechanical systems.

[0032] Figure 1 This is one of the flowcharts illustrating the building electromechanical system simulation method provided by the present invention, such as... Figure 1 As shown, the method includes the following: Step 101: Construct a directed graph model of the building electromechanical system; the nodes in the directed graph model are used to represent the building electromechanical equipment, and the directed edges in the directed graph model are used to represent the physical connection relationship or information flow transmission relationship between the building electromechanical equipment.

[0033] Specifically, in this embodiment, the building electromechanical system is abstractly modeled to obtain a directed graph model of the building electromechanical system, thereby effectively representing the physical topology and information interaction relationships of the building electromechanical system. Optionally, the nodes in the directed graph model of the building electromechanical system correspond to various building electromechanical equipment and control units such as chillers, cooling towers, water pumps, air conditioning terminals, and controllers; the directed edges in the directed graph model of the building electromechanical system accurately map the actual physical connections or information flow transmission relationships between the equipment, thus obtaining a directed graph model that can completely reflect the structure and coupling relationships of the building electromechanical system. The building electromechanical system in this embodiment includes, but is not limited to, energy pipeline systems, building air conditioning water systems, and building central chiller station systems.

[0034] Step 102: Generate the directed basic loop of the building electromechanical system based on the directed graph model of the building electromechanical system.

[0035] Specifically, after constructing the directed graph model of the building electromechanical system, this application can extract all directed basic cycles from the directed graph of the building electromechanical system. That is, a closed path that starts from a certain node, traverses along the directed edge, passes through each node only once, and finally returns to the starting node, forming an initial set of basic cycles. Thus, the accurate identification of all coupled closed loops in the building electromechanical system is achieved.

[0036] Step 103: Perform clustering on the directed basic rings to obtain multiple cluster groups.

[0037] Specifically, in the embodiments of this application, after generating the directed basic loops of the building electromechanical system based on the directed graph model of the building electromechanical system, cluster analysis can be performed on all directed basic loops. Basic loops with higher structural similarity are grouped into the same cluster group, thereby realizing the grouping of a large number of redundant loops with high structural similarity in the building electromechanical system into the same group, effectively solving the problem of large solution scale and computational redundancy caused by too many similar loops in traditional simulation.

[0038] Step 104: Merge the directed basic rings in each cluster group to generate a clustering ring; the clustering ring is used to characterize the topological and coupling properties of the cluster group.

[0039] Specifically, after clustering directed basic rings to obtain multiple cluster groups, this application can merge the directed basic rings in each cluster group to generate cluster rings, thereby effectively characterizing the overall topological structure and physical coupling characteristics of the corresponding cluster groups, realizing the equivalent merging of similar loops, compressing hundreds or thousands of directed basic rings into a small number of cluster rings, reducing the solution scale of the system by orders of magnitude, and fundamentally reducing the computational complexity of subsequent simulation solutions.

[0040] Step 105: Perform simulation solution on the building electromechanical system based on the clustering ring to obtain the simulation results of the building electromechanical system.

[0041] Specifically, this application merges the directed basic rings in each cluster group to generate cluster rings, and then performs collaborative iterative solutions to the building electromechanical system on a unit basis of cluster rings. Iterative calculations are performed at the cluster ring level, and the system node states are updated synchronously until the change in the physical parameter values ​​of each node in the system between two adjacent iterations is less than a preset convergence threshold. The system state obtained at this point is the simulation result of the building electromechanical system. It should be noted that this application effectively replaces the traditional full solution of all directed basic rings by merging basic rings with similar structures through clustering and iterative solution based on a simplified set of cluster rings. This significantly reduces redundant paths and computational complexity in iterative calculations, resulting in a significant reduction in the dimension of iterative equations, computational paths, and computational volume. The system convergence speed is greatly improved, effectively enhancing the computational efficiency and convergence speed of dynamic simulation of complex building electromechanical systems such as HVAC and hydraulic networks. It is suitable for large-scale system simulation, real-time optimization, and digital twin applications, significantly improving the simulation solution efficiency of building electromechanical systems.

[0042] The method described in the above embodiments generates directed basic loops of the building electromechanical system based on the directed graph model of the building electromechanical system. Through clustering and merging, hundreds or thousands of basic loops are compressed into a small number of clustered loops. While fully preserving the topology and coupling characteristics of the building electromechanical system, it achieves efficient simplification and equivalent fusion of a large number of structurally similar redundant basic loops, significantly reducing the computational complexity and iteration scale of the simulation solution, and significantly improving the convergence speed and computational efficiency of the system simulation. Under the premise of ensuring controllable simulation accuracy, it effectively solves the problems of computational redundancy, high resource consumption, and poor real-time performance of traditional simulation methods in large-scale building electromechanical systems.

[0043] In some embodiments, the directed basic rings are clustered to obtain multiple cluster groups, including: Based on the structural similarity between directed basic rings, the directed basic rings are clustered to obtain multiple cluster groups; among them, the structural similarity of directed basic rings within each cluster group is higher than a threshold, and the structural similarity of directed basic rings between different cluster groups is lower than a threshold.

[0044] Specifically, in this embodiment, for all directed basic loops extracted from the directed graph model of the building electromechanical system, the structural similarity between any two directed basic loops is calculated from the perspective of topological structural features. Using this structural similarity as the criterion, clustering is performed on all directed basic loops, grouping directed basic loops with similar structural features into the same cluster group. Simultaneously, it is ensured that the directed basic loops in different cluster groups have significant differences in structural features, ultimately resulting in multiple cluster groups with similar structures within each group and dissimilar structures between groups. It should be noted that this method can integrate a large number of highly similar redundant loops in the building electromechanical system into the same cluster group, effectively solving the technical problems of large solution scale and redundant calculation process caused by too many similar loops in traditional simulation methods.

[0045] The method described in the above embodiments clusters the directed basic rings into multiple cluster groups based on the structural similarity between them. This achieves accurate clustering and grouping of directed basic rings in building electromechanical systems, ensuring both the high similarity of the loop topology within the same cluster group and the significant differences in the loop structure between different cluster groups. By integrating a large number of highly similar redundant loops in the building electromechanical system into the same cluster group, the method effectively solves the problems of large solution scale and redundant calculation process caused by too many similar loops in traditional simulation methods.

[0046] In some embodiments, the directed basic rings are clustered based on the structural similarity between them to obtain multiple cluster groups, including: Based on the structural similarity between directed basic rings, the similarity matrix is ​​obtained; Clustering of directed basic rings based on the similarity matrix yields multiple cluster groups.

[0047] Specifically, in this embodiment, for all directed basic loops of the building electromechanical system, after calculating the structural similarity between any two directed basic loops, all similarity calculation results are structurally integrated in matrix form to construct a similarity matrix. Optionally, the rows and columns of the similarity matrix correspond to the directed basic loops in the system, and the value of each element in the matrix represents the structural similarity between the two directed basic loops in its corresponding row and column. This completely and orderly stores the quantitative similarity data between all basic loops, realizing the structured and standardized storage of the structural similarity data between all directed basic loops. It transforms the discrete similarity calculation results into a regular matrix data form, avoiding clustering analysis errors caused by disordered data. Optionally, after obtaining the similarity matrix based on the structural similarity between directed basic rings, the similarity values ​​of each element in the similarity matrix can be used as the criterion for clustering algorithms. Following the logic that high similarity results in grouping them into one group and low similarity results in grouping them into different groups, all directed basic rings are divided into multiple clustering groups. Finally, clustering results are obtained that satisfy the condition that the structural similarity within a group is higher than a threshold and the structural similarity between groups is lower than a threshold, thus ensuring the accuracy of clustering and grouping.

[0048] The method described above achieves structured and standardized storage of similarity data between directed basic rings by constructing a similarity matrix, effectively avoiding clustering errors caused by data clutter, ensuring the accuracy of clustering results, and improving the efficiency of directed basic ring clustering in building electromechanical systems.

[0049] In some embodiments, directed basic rings are clustered based on a similarity matrix to obtain multiple cluster groups, including: Based on the similarity matrix, a hierarchical clustering algorithm is used to cluster directed basic rings, and the distance change during the clustering process is determined by the natural breakpoint method to determine the number of clusters and multiple cluster groups.

[0050] Specifically, in this embodiment, a hierarchical clustering algorithm is used to cluster all directed basic loops of the building electromechanical system, forming a clustering result with a hierarchical structure, effectively ensuring the objectivity and accuracy of the clustering results. Furthermore, during the clustering process of the directed basic loops, this application analyzes the distance changes during the clustering process based on the natural breakpoint method to determine the optimal number of clusters k, dividing all basic loops into k cluster groups. This ensures that the loop structures within each group are highly similar, accurately determining the optimal number of clusters. This replaces the subjective method of manually pre-setting the number of clusters, effectively avoiding the problems of poor simplification due to too many clusters and loss of key structural features due to too few clusters. This ensures that the number of clusters highly matches the actual loop structure characteristics of the building electromechanical system, effectively integrating a large number of structurally similar redundant basic loops, significantly reducing the number of cluster groups, and avoiding over-clustering. This ensures that the key coupling relationships of the building electromechanical system are not lost, effectively guaranteeing simulation accuracy.

[0051] The method described in the above embodiments, through the combined application of hierarchical clustering algorithm and natural breakpoint method, makes the number of clusters highly matched with the actual loop structure characteristics of the building electromechanical system. This not only significantly reduces the number of cluster groups to simplify the simulation solution scale, but also avoids the loss of key structural features of the system due to over-clustering, effectively ensuring simulation accuracy and efficiency.

[0052] In some embodiments, the directed basic rings in each cluster group are merged to generate a cluster ring, including: For each cluster group, the common nodes and common paths between directed basic rings within the cluster group are taken as the backbone, and the different paths between directed basic rings within the cluster group are taken as branches. Generate clustering rings based on the main branches and branches.

[0053] Specifically, in this embodiment, common nodes and common paths shared by directed basic rings within a cluster group are identified and integrated into the backbone structure corresponding to that cluster group. At the same time, unique and non-common path segments of each directed basic ring within the cluster group are identified as differential paths and used as branch structures of the cluster rings. This effectively balances the simplicity and information integrity of the cluster rings, so that subsequent simulation solutions only need to be performed on a small number of cluster rings, significantly reducing the dimension and computational complexity of the iterative equations and improving the efficiency and convergence speed of iterative calculations.

[0054] The method described in the above embodiments significantly reduces the number of loops in the system by merging multiple similar basic loops in each cluster group into a single cluster loop. This allows subsequent simulations to be performed only on a small number of cluster loops, significantly reducing the dimensionality and computational complexity of the iterative equations and improving the efficiency and convergence speed of the iterative calculations.

[0055] For example, such as Figure 2 As shown in the figure, this application provides a simulation method for building electromechanical systems based on directed graph clustering optimization, as detailed below: Taking the simulation of a central chiller station system in a building as an example, the system includes equipment such as chiller units, cooling towers, chilled water pumps, cooling water pumps, air conditioning terminals and control modules, forming a coupled hydraulic and thermal system.

[0056] S1. Obtain the system model: Obtain the simulation directed graph model of the cooling plant system, such as Figure 3 As shown in the diagram. The nodes represent chillers, cooling towers, various water pumps, air conditioning terminals, controllers, etc., and the directed edges represent the water flow direction and the relationship between the control signal transmission.

[0057] S2. Identify the basic ring: The system is preprocessed by removing external boundary nodes and independent control nodes, resulting in the following: Figure 4 The simplified diagram is shown below. In this simplified diagram, all directed simple cycles are identified, forming the initial basic cycle set R = {R1, R2, …, R}. n}.like Figure 5 As shown, there are multiple basic loops with similar structures in the system. For example, multiple parallel air conditioning terminal branches and the chiller station form a similar hydraulic-thermal loop.

[0058] S3, Loop Clustering Optimization: Similarity calculation: For all identified basic cycles R, calculate the similarity between any two cycles R. i With R j The structural similarity between them is used to form a similarity matrix D.

[0059] Clustering Grouping: Based on the similarity matrix D, a hierarchical clustering algorithm is used to analyze the basic rings. By analyzing the natural discontinuities of distance changes during the clustering process, the optimal number of clusters k is determined, and all basic rings are divided into k clusters G = {G1, G2, …, G}. k This results in highly similar ring structures within groups and significant differences between groups.

[0060] Loop merging: For each cluster group G p (p=1,…,k), perform a merge operation: extract the common nodes and paths of all rings within the group to form the backbone, and integrate the different paths of each ring into branches. This ultimately generates a clustered ring representing the coupling characteristics of the group. After merging, an optimized set of clustered rings is obtained, such as... Figure 6 As shown, multiple similar rings are merged into a few representative clustering rings, significantly simplifying the system structure.

[0061] S4. Solving based on clustering ring sets: The optimized cluster ring set is used as a description of the system coupling relationship, and a cooperative iterative solution is performed. After initializing the state of each node, a global iterative calculation is performed at the cluster ring level to update the output of each node until the system state meets the convergence condition.

[0062] S5. State integration and simulation advancement: Once the collaborative iterative solution is complete, the final states of all nodes are updated in the simulation directed graph model G. At this point, the state of the system at the current simulation time t is completely determined. Subsequently, the simulation time is advanced by one step Δt to t+Δt, and the process returns to step S1 to begin the calculation for the next time step, thus achieving continuous time-domain simulation of the dynamic processes of the building electromechanical system.

[0063] It should be noted that the building electromechanical system simulation method based on directed graph clustering optimization in this application compresses hundreds or thousands of basic rings into a small number of clustered rings through cluster merging. This results in an order-of-magnitude reduction in the dimensionality of the iterative equations and the computational load, leading to a revolutionary improvement in solution efficiency, making it particularly suitable for ultra-large-scale system simulation. Furthermore, the similarity calculation and merging strategies in this application are based on rigorous mathematical definitions, ensuring the equivalence of the system before and after optimization in terms of key coupling mechanisms and input-output relationships, thus maintaining controllable simulation accuracy. In addition, the entire clustering optimization process can be completed automatically without manual intervention, and can be integrated as a standard preprocessing module into various graph-based simulation platforms. This provides a feasible technical foundation for scenarios with extreme requirements for simulation speed, such as digital twins, real-time full-network optimization, and iterative design of ultra-large-scale systems.

[0064] The method described above introduces an innovative "ring clustering optimization" layer between basic ring identification and overall iterative solution. This layer measures the structural similarity of basic rings, aggregates a large number of similar rings into groups, and merges them into a few more representative "clustered rings," thereby mathematically constructing a smaller and more refined optimization coupling model, ultimately achieving an order-of-magnitude improvement in simulation efficiency.

[0065] The following describes the building electromechanical system simulation device provided by the present invention. The building electromechanical system simulation device described below can be referred to in correspondence with the building electromechanical system simulation method based on directed graph clustering optimization described above. Optionally, as... Figure 7 As shown, the building electromechanical system simulation device includes: Module 710 is used to construct a directed graph model of the building electromechanical system; the nodes in the directed graph model are used to represent the building electromechanical equipment, and the directed edges in the directed graph model are used to represent the physical connection relationship or information flow transmission relationship between the building electromechanical equipment; The generation module 720 is used to generate the directed basic loop of the building electromechanical system based on the directed graph model of the building electromechanical system. Clustering module 730 is used to cluster directed basic rings to obtain multiple cluster groups; The merging module 740 is used to merge the directed basic rings in each cluster group to generate a cluster ring; the cluster ring is used to characterize the topological and coupling properties of the cluster group. Simulation module 750 is used to perform simulation solutions on building electromechanical systems based on clustering rings, and obtain simulation results of building electromechanical systems.

[0066] Figure 8 An example is a schematic diagram of the physical structure of an electronic device, such as... Figure 8As shown, the electronic device may include: a processor 810, a communication interface 820, a memory 830, and a communication bus 840. The processor 810, communication interface 820, and memory 830 communicate with each other via the communication bus 840. The processor 810 can call logical instructions in the memory 830 to execute a building electromechanical system simulation method based on directed graph clustering optimization. This method includes: constructing a directed graph model of the building electromechanical system; nodes in the directed graph model represent building electromechanical equipment, and directed edges in the directed graph model represent the physical connection relationships or information flow transmission relationships between building electromechanical equipment; generating directed basic loops of the building electromechanical system based on the directed graph model; performing clustering processing on the directed basic loops to obtain multiple cluster groups; merging the directed basic loops in each cluster group to generate a cluster ring; the cluster ring is used to represent the topology and coupling characteristics of the cluster groups; and performing simulation solving on the building electromechanical system based on the cluster ring to obtain the simulation results of the building electromechanical system.

[0067] Furthermore, the logical instructions in the aforementioned memory 830 can be implemented as software functional units and, when sold or used as independent products, can be stored in a computer-readable storage medium. Based on this understanding, the technical solution of the present invention, or the part that contributes to the prior art, or a part of the technical solution, can be embodied in the form of a software product. This computer software product is stored in a storage medium and includes several instructions to cause a computer device (which may be a personal computer, server, or network device, etc.) to execute all or part of the steps of the methods described in the various embodiments of the present invention. The aforementioned storage medium includes various media capable of storing program code, such as USB flash drives, portable hard drives, read-only memory (ROM), random access memory (RAM), magnetic disks, or optical disks.

[0068] On the other hand, the present invention also provides a computer program product, which includes a computer program that can be stored on a non-transitory computer-readable storage medium. When the computer program is executed by a processor, the computer can execute the building electromechanical system simulation method based on directed graph clustering optimization provided by the above methods. The method includes: constructing a directed graph model of the building electromechanical system; nodes in the directed graph model are used to represent building electromechanical equipment, and directed edges in the directed graph model are used to represent the physical connection relationship or information flow transmission relationship between building electromechanical equipment; generating directed basic loops of the building electromechanical system according to the directed graph model of the building electromechanical system; performing clustering processing on the directed basic loops to obtain multiple cluster groups; merging the directed basic loops in each cluster group to generate a cluster ring; the cluster ring is used to represent the topology and coupling characteristics of the cluster group; and performing simulation solving on the building electromechanical system according to the cluster ring to obtain the simulation result of the building electromechanical system.

[0069] In another aspect, the present invention also provides a non-transitory computer-readable storage medium storing a computer program thereon, which, when executed by a processor, implements the building electromechanical system simulation method based on directed graph clustering optimization provided by the above methods. This method includes: constructing a directed graph model of the building electromechanical system; nodes in the directed graph model representing building electromechanical equipment, and directed edges in the directed graph model representing physical connection relationships or information flow transmission relationships between building electromechanical equipment; generating directed basic loops of the building electromechanical system based on the directed graph model; performing clustering processing on the directed basic loops to obtain multiple cluster groups; merging the directed basic loops in each cluster group to generate a clustering ring; the clustering ring representing the topology and coupling characteristics of the cluster groups; and performing simulation solving on the building electromechanical system based on the clustering ring to obtain the simulation results of the building electromechanical system.

[0070] The device embodiments described above are merely illustrative. The units described as separate components may or may not be physically separate. The components shown as units may or may not be physical units; that is, they may be located in one place or distributed across multiple network units. Some or all of the modules can be selected to achieve the purpose of this embodiment according to actual needs. Those skilled in the art can understand and implement this without any creative effort.

[0071] Through the above description of the embodiments, those skilled in the art can clearly understand that each embodiment can be implemented by means of software plus necessary general-purpose hardware platforms, and of course, it can also be implemented by hardware. Based on this understanding, the above technical solutions, in essence or the part that contributes to the prior art, can be embodied in the form of a software product. This computer software product can be stored in a computer-readable storage medium, such as ROM / RAM, magnetic disk, optical disk, etc., and includes several instructions to cause a computer device (which may be a personal computer, server, or network device, etc.) to execute the methods described in the various embodiments or some parts of the embodiments.

[0072] Finally, it should be noted that the above embodiments are only used to illustrate the technical solutions of the present invention, and not to limit them; 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; and these 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 simulation method for building electromechanical systems based on directed graph clustering optimization, characterized in that, include: Construct a directed graph model of the building's electromechanical system; The nodes in the directed graph model are used to represent building electromechanical equipment, and the directed edges in the directed graph model are used to represent the physical connection relationship or information flow transmission relationship between building electromechanical equipment. Based on the directed graph model of the building electromechanical system, generate the directed basic cycle of the building electromechanical system; Clustering is performed on the directed basic rings to obtain multiple cluster groups; The directed basic rings in each of the cluster groups are merged to generate a cluster ring; The clustering ring is used to characterize the topological and coupling properties of the cluster group; The building electromechanical system is simulated and solved based on the clustering ring to obtain the simulation results of the building electromechanical system.

2. The simulation method for building electromechanical systems based on directed graph clustering optimization according to claim 1, characterized in that, The clustering process performed on the directed basic rings yields multiple cluster groups, including: Based on the structural similarity between directed basic rings, the directed basic rings are clustered to obtain multiple cluster groups; wherein, the structural similarity of directed basic rings within each cluster group is higher than a threshold, and the structural similarity of directed basic rings between different cluster groups is lower than a threshold.

3. The building electromechanical system simulation method based on directed graph clustering optimization according to claim 2, characterized in that, The directed basic rings are clustered based on their structural similarity to obtain multiple cluster groups, including: Based on the structural similarity between the directed basic rings, a similarity matrix is ​​obtained; The directed basic rings are clustered based on the similarity matrix to obtain the multiple cluster groups.

4. The simulation method for building electromechanical systems based on directed graph clustering optimization according to claim 3, characterized in that, The step of clustering the directed basic rings based on the similarity matrix to obtain the plurality of cluster groups includes: Based on the similarity matrix, the directed basic rings are clustered using a hierarchical clustering algorithm, and the distance changes during the clustering process are determined using the natural breakpoint method to determine the number of clusters and the multiple cluster groups.

5. The simulation method for building electromechanical systems based on directed graph clustering optimization according to any one of claims 1-4, characterized in that, The step of merging the directed basic rings in each of the cluster groups to generate a cluster ring includes: For each cluster group, the common nodes and common paths between directed basic rings within the cluster group are taken as the backbone, and the different paths between directed basic rings within the cluster group are taken as branches. The clustering ring is generated based on the main trunk and the branches.

6. The simulation method for building electromechanical systems based on directed graph clustering optimization according to any one of claims 1-4, characterized in that, The building electromechanical system includes at least one of the following: Energy pipeline network system, building air conditioning water system and building central refrigeration station system.

7. The simulation method for building electromechanical systems based on directed graph clustering optimization according to any one of claims 1-4, characterized in that, The building electromechanical equipment includes at least one of the following: Chillers, cooling towers, water pumps, air conditioning terminals and controllers.

8. A simulation device for building electromechanical systems based on directed graph clustering optimization, characterized in that, include: The building module is used to construct directed graph models of building electromechanical systems; The nodes in the directed graph model are used to represent building electromechanical equipment, and the directed edges in the directed graph model are used to represent the physical connection relationship or information flow transmission relationship between building electromechanical equipment. The generation module is used to generate a directed basic loop of the building electromechanical system based on the directed graph model of the building electromechanical system. The clustering module is used to perform clustering processing on the directed basic rings to obtain multiple cluster groups; The merging module is used to merge the directed basic rings in each of the cluster groups to generate a cluster ring; The clustering ring is used to characterize the topological and coupling properties of the cluster group; The simulation module is used to perform simulation solutions on the building electromechanical system based on the clustering ring, and obtain the simulation results of the building electromechanical system.

9. An electronic device comprising a memory, a processor, and a computer program stored in the memory and running on the processor, characterized in that, When the processor executes the computer program, it implements the building electromechanical system simulation method based on directed graph clustering optimization as described in any one of claims 1 to 7.

10. A non-transitory computer-readable storage medium having a computer program stored thereon, characterized in that, When the computer program is executed by the processor, it implements the building electromechanical system simulation method based on directed graph clustering optimization as described in any one of claims 1 to 7.

Images