A gas pipeline network node division and simulation method

Abstract

The present invention relates to a gas pipeline network node partitioning and simulation method, comprising: step S1: obtaining monitoring data and pipeline network node attribute information of a gas transmission pipeline network; step S2: splitting the pipeline network node attributes into multiple sub-attribute sets; and partitioning the pipeline network nodes into multiple sets based on the sub-attribute sets and the monitoring data. During the gas pipeline network node partitioning process, the present invention fully utilizes multi-dimensional information, such as attribute dimension information and monitoring data dimension information, integrating this multi-dimensional information into the set optimization and determination process, ultimately forming a gas node set with practical analytical significance for modeling and simulation.

Description

Technical field

[0001] The present invention belongs to the technical field of gas pipe network simulation, and in particular relates to a gas pipe network node division and simulation method and system. [Background Technology]

[0002] The use of natural gas has improved residents' living conditions and reduced the storage and transportation of solid fuels and waste. This not only protects the ecological environment but also saves energy and offers significant economic benefits. To facilitate the transport of liquids, gases, and loose solids, numerous types of underground pipelines are laid, forming a complex underground pipeline network. As a critical infrastructure, relevant departments need to compile and maintain basic information about underground pipelines. For example, information about underground pipelines beneath roads is crucial for road maintenance. Therefore, understanding the operation of natural gas pipelines is crucial before, during, and during construction. For example, during pipeline renovation and expansion, a reasonable valve shutoff strategy must be developed based on the location of the pipeline opening to shut off gas. A corresponding valve shutoff strategy consists of a minimum number of valves that meet the following conditions. This information, which cannot be directly collected, requires simulation software based on the gas pipeline network structure and real-time data collection.

[0003] However, the reality is that, on the one hand, the physical environment in which the pipeline network is erected is very complex, and on the other hand, the structure of the pipeline network itself is also very complex, and the types of information collected are also very diverse. At this time, during the simulation process, for large-scale pipeline networks, or pipeline network structures involving complex data, the search, simulation, and analysis operations can be very time-consuming. In addition to being time-consuming, the desired results may not be obtained in the end. Therefore, classifying the monitoring and collection nodes of the natural gas transmission pipeline network, creating and dividing similar node sets, and then simulating them is a way to solve the problem. However, in the existing technology, the monitoring nodes are often divided according to a single dimension of node attributes, for example, the node's affiliation is often used to classify all nodes in a cell into one set. This division method is obviously not conducive to regional joint simulation and large-scale simulation, and it is also quite disadvantageous for the full utilization of other types of data. When the simulation model targets a large area, the traditional method of constructing the simulation model will expose many problems. How to improve the homogeneity within the node and the heterogeneity between the division ranges during the node division process is a problem that must be solved and is also the key to the problem.

[0004] In the process of dividing the gas pipeline network nodes, the present invention makes full use of multi-dimensional information such as multiple different attribute dimension information and monitoring data dimension, cross-integrates the multi-dimensional data into the optimization and determination process of node division, and finally forms a gas node set with practical analysis significance for modeling and simulation. [Summary of the invention]

[0005] In order to solve the above problems in the prior art, the present invention proposes a gas network node division and simulation method, the gas network node division method comprising:

[0006] Step S1: Obtaining monitoring data of the gas transmission network and network node attribute information;

[0007] Step S2: splitting the pipe network node attributes into multiple sub-attribute sets; dividing the pipe network nodes into multiple sets based on the sub-attribute sets and monitoring data;

[0008] The method of dividing the pipe network nodes into multiple sets based on the sub-attribute set and the monitoring data specifically comprises the following steps:

[0009] Step SubA1: selecting an attribute in a sub-attribute cluster as a representative sub-attribute of the sub-attribute cluster; multiple sub-attribute clusters correspond to multiple representative sub-attributes; based on each representative sub-attribute, selecting one pipe network node from all pipe network nodes as an initial node;

[0010] Step SubA2: selecting one pipe network node from all pipe network nodes as an initial node based on the monitoring data;

[0011] Step SubA3: Merge all initial nodes, and remove duplication and similarity from the merged initial nodes to form a seed node set;

[0012] Step SubA4: clustering the onset nodes from the seed node set and obtaining multiple sets corresponding to the seed nodes;

[0013] Step SubA5: Determine the first condition for any two sets, and merge the sets that meet the first condition;

[0014] Step SubA6: re-determine the set attribute label based on the first condition;

[0015] Step SubA7: Calculate the monitoring data labels of the set;

[0016] Step SubA8: Re-partition the nodes based on the attribute labels of the set;

[0017] Step SubA9: Calculate the partition evaluation value of the set; determine whether the partition evaluation value is lower than the optimization threshold; if so, end step S2; otherwise, return to step SubA5.

[0018] Furthermore, the monitoring data includes pressure, flow, temperature, sound, and valve status.

[0019] Furthermore, the monitoring data is historical monitoring data.

[0020] Furthermore, the gas transmission pipeline network is a natural gas transmission pipeline network.

[0021] Based on the same inventive concept, the present invention provides a gas network node simulation method, comprising:

[0022] Step S1: Obtaining monitoring data of the gas transmission network and network node attribute information;

[0023] Step S2: splitting the pipe network node attributes into multiple sub-attribute sets; dividing the pipe network nodes into multiple sets based on the sub-attribute sets and monitoring data;

[0024] The method of dividing the pipe network nodes into multiple sets based on the sub-attribute set and the monitoring data specifically comprises the following steps:

[0025] Step SubA1: selecting an attribute in a sub-attribute cluster as a representative sub-attribute of the sub-attribute cluster; multiple sub-attribute clusters correspond to multiple representative sub-attributes; based on each representative sub-attribute, selecting one pipe network node from all pipe network nodes as an initial node;

[0026] Step SubA2: selecting one pipe network node from all pipe network nodes as an initial node based on the monitoring data;

[0027] Step SubA3: Merge all initial nodes, and remove duplication and similarity from the merged initial nodes to form a seed node set;

[0028] Step SubA4: clustering the onset nodes from the seed node set and obtaining multiple sets corresponding to the seed nodes;

[0029] Step SubA5: Determine the first condition for any two sets, and merge the sets that meet the first condition;

[0030] Step SubA6: re-determine the set attribute label based on the first condition;

[0031] Step SubA7: Calculate the monitoring data labels of the set;

[0032] Step SubA8: Re-partition the nodes based on the attribute labels of the set;

[0033] Step SubA9: Calculate the partition evaluation value of the set; determine whether the partition evaluation value is lower than the optimization threshold; if so, end step S2; otherwise, return to step SubA5;

[0034] Step S3: Select a representative node from each set, determine the attribute value of the representative node, set up a simulation model based on the attribute value of the representative node and its connection relationship; input the representative node and the monitoring data collected on site into the simulation model to obtain simulation results.

[0035] Furthermore, the gas transmission pipeline network is a natural gas transmission pipeline network.

[0036] Based on the same inventive concept, the present invention provides a big data computing node, which is used to execute the above-mentioned gas pipeline network node division method and the above-mentioned gas pipeline network node simulation method.

[0037] Based on the same inventive concept, the present invention provides a processor, which is used to run a program, wherein the program executes the gas pipeline network node division method and the gas pipeline network node simulation method when running.

[0038] Based on the same inventive concept, the present invention provides a computer-readable storage medium, comprising a program, which, when executed on a computer, enables the computer to execute the gas network node division method and the gas network node simulation method.

[0039] Based on the same inventive concept, the present invention provides an execution device, including a processor, the processor is coupled to a memory, the memory stores program instructions, and when the program instructions stored in the memory are executed by the processor, the gas pipeline network node division method and the gas pipeline network node simulation method are implemented.

[0040] The beneficial effects of the present invention include:

[0041] (1) Considering the differences between the gas pipeline network and other types of network structures, when dividing the analysis set of monitoring nodes, the method of "relaxing the attributes to set the target conditions and tightening the conditions for iterative optimization" is used to fully utilize the multi-dimensional information such as the attribute dimension information and the monitoring data dimension, and integrate the multi-dimensional information into the optimization and determination process of the set, and finally form a gas node set with practical analysis significance;

[0042] (2) Rapid selection of seed nodes from multiple dimensions not limited to monitoring data accelerates clustering speed and global homogeneity of node attributes within the cluster, breaks the problem of fixed analysis mode caused by set partitioning based on a single dimension, and reduces the number of simulation nodes.

Brief Description of the Drawings

[0043] The drawings described herein are used to provide a further understanding of the present invention and constitute a part of this application, but do not constitute an improper limitation of the present invention. In the drawings:

[0044] Figure 1 Schematic diagram of the gas network node simulation method of the present invention. [Specific implementation method]

[0045] The present invention will be described in detail below with reference to the accompanying drawings and specific embodiments, wherein the exemplary embodiments and descriptions are only used to explain the present invention but are not intended to limit the present invention.

[0046] As attached Figure 1 As shown, the present invention proposes a gas network node division method, which includes the following steps:

[0047] Step S1: Obtaining monitoring data of the gas transmission network and network node attribute information;

[0048] The monitoring data includes pressure, flow, temperature, sound, valve status, etc.; the pipe network node attribute information includes node location, node ownership, node type, node height, etc. When the node is a pipe segment, the attribute information also includes pipe segment length, pipe diameter, service age, degree of decay, material, loss, expected service life, etc. The attributes can include the same attribute type that changes over time or the same attribute type that changes over space, such as construction age, service age, maximum pipe diameter, average pipe diameter, highest position, average position, lowest position, etc.

[0049] Interchangeable: The monitoring data includes node location, node ownership, node type, etc., and the node attributes include pressure, flow, temperature, sound, valve status, etc.; that is, when conducting multi-dimensional attribute analysis, the monitoring data and attributes are used as the basis for division, and their roles are interchangeable. Whether this interchangeability is also determined by the integrity and availability of the data;

[0050] Preferably, the monitoring data is historical monitoring data, and the monitoring data includes multiple types;

[0051] Preferably, the gas pipeline network is a natural gas pipeline network;

[0052] Step S2: splitting the pipe network node attributes into multiple sub-attribute sets; dividing the pipe network nodes into multiple sets based on the sub-attribute sets and monitoring data;

[0053] The method of splitting the network node attributes into multiple sub-attributes is as follows: dividing the node attributes into one or more sub-attribute clusters according to the similarity of the attributes; wherein each sub-attribute cluster represents an important attribute of an aspect; that is, firstly dividing the attributes into multiple attribute dimensions according to their descriptive ability and description scope; then dividing the network nodes based on the combination of the multiple attribute dimensions and the monitoring data dimension;

[0054] The method of dividing the pipe network nodes into multiple sets based on the sub-attribute set and the monitoring data specifically comprises the following steps:

[0055] Step SubA1: Select one attribute from a sub-attribute cluster as the representative sub-attribute of the sub-attribute cluster; multiple sub-attribute clusters correspond to multiple representative sub-attributes; based on each representative sub-attribute, select I pipe network nodes from all pipe network nodes as initial nodes; the selection method is to maximize the difference in the representative sub-attributes between the I initial nodes or to evenly distribute the values; for example, with respect to the position coordinate sub-attribute, the positions of the selected I nodes are evenly distributed, such as in a grid distribution; in this case, for J representative sub-attributes, I×J nodes are ultimately selected, of which there may be duplicate nodes;

[0056] Preferred: When there is only one attribute in the sub-attribute cluster, directly select this attribute as the representative sub-attribute. Of course, many attributes may not contain many sub-attributes. However, the more sub-attributes that are split, the more three-dimensional the pipe network description may be, and finally a more homogenized effect can be achieved.

[0057] Step SubA2: Based on the monitoring data, select I pipe network nodes from all pipe network nodes as initial nodes; the selection method is to maximize the difference in monitoring data between the initial nodes or to evenly distribute the values; after completing the above two sub-steps, when the number of sub-attribute clusters is J, the number of initial nodes is I×(J+1);

[0058] Alternatively: the selection method is random selection;

[0059] Of course, the types of monitoring data are often diverse, and we can focus on selecting monitoring data of various types. The basis for selection can be the best data integrity. After all, the historical integrity of monitoring data is often the main problem. One expansion method is to select I×T pipeline network nodes from all pipeline network nodes as initial nodes based on multiple monitoring data types. Where: T is the number of monitoring data types. The selection method is to maximize the difference or sum of the differences of various types of monitoring data between the initial nodes. At this time, after completing the above two sub-steps, when the number of sub-attribute clusters is J, the number of initial nodes is (I×T)+(I×J); the number of initial nodes is still controllable.

[0060] Step SubA3: Merge all initial nodes, and perform deduplication and desimilarization on the merged initial nodes to form a seed node set. Specifically, for multiple nodes with identical or similar monitoring data and network node attributes, select one node to perform deduplication and desimilarization. Merge the deduplicated and desimilarized initial nodes to form a seed node set. The size of the seed node set is less than or equal to I×(J+1).

[0061] Step SubA4: clustering the onset nodes from the seed node set and obtaining multiple sets corresponding to the seed nodes; various common clustering methods can be used here;

[0062] Preferably: clustering is performed based on one attribute among multiple attributes and / or monitoring data; thereby reducing the difficulty of the initial clustering operation; if only one attribute is selected for clustering, the difficulty of clustering can be greatly reduced;

[0063] When considering multiple attributes and monitoring data, the distance calculation of nodes in the clustering process can consider both the data value and the attribute value of the monitoring data, and consider the attributes or values of different dimensions at the same time through weighted summation;

[0064] Step SubA5: Determine a first condition for any two sets, and merge the sets that meet the first condition. Specifically, when nodes in two sets meet the first condition, the two sets are merged; otherwise, the two sets are not merged. The first condition is that the attribute values of the preset attribute type of the nodes exceeding a first preset ratio are the same. For example, when the preset attribute type is location, the same attribute value may be the same location area, such as being located in ** street, ** enterprise, etc.

[0065] Preferably: the first preset ratio is 95%;

[0066] Determining the first condition specifically includes the following steps:

[0067] Step SubA51: When entering this step for the first time, a first condition is determined based on the attribute information of one of the two sets; important attributes are determined from the attributes of the one set, and the attribute values of the important attributes of the first set are expanded to serve as the attribute values of the preset attribute type; the expansion method here is to expand the specific attribute value into a larger attribute value range and then serve as the attribute value of the preset attribute type; for example, a specific address value can be expanded into an address range, etc., and an appropriate expansion method can be selected according to the form of the attribute value; another example is to expand a specific data value into a numerical range; wherein the important attributes can be pre-set, or all attributes can be set as important attributes;

[0068] When determining the important attribute from the attributes of the set, it is determined based on clustering information that the nodes in the cluster set must have certain similarities, and their label attributes can be used as important attributes;

[0069] Step SubA52: If this step is not entered for the first time, the first condition is tightened as a new first condition by increasing the first preset ratio value and tightening the attribute value of the preset attribute type;

[0070] Step SubA6: re-determine the set attribute label based on the first condition; specifically, set the preset attribute types involved in the first condition and their identical attribute values as the attribute label of the set; then, the attribute label now involves one or more attribute types;

[0071] Step SubA7: Calculate the monitoring data label of the set; specifically, based on the values of all monitoring data in the set, calculate the mean of the monitoring data as the monitoring data label of the set;

[0072] Step SubA8: Re-partitioning the nodes based on the attribute labels of the set; specifically, re-partitioning some of the nodes in the set that do not meet the first condition;

[0073] Preferably, the part of nodes is a second preset proportion of nodes; for example, 1%;

[0074] Preferably: the second preset ratio < (1-first preset ratio);

[0075] Preferably, the repartitioning can be done by dividing into other sets or leaving them as scattered points. When dividing into other sets, the more identical or similar sets can be selected based on the sameness or similarity of all attributes. If no such set exists, the nodes can be left as scattered points.

[0076] For a gas pipeline network, even if the data values of the monitoring data of the nodes are very different, the nodes may still have great analytical similarities. They are just nodes with different functions within the same similarity range. For example, for different nodes in a cell, their pressure values or flow values may vary greatly, but in fact, putting them in the same analysis set is still very meaningful and valuable for analysis. The present invention takes into account the differences between gas pipeline networks and other types of network structures. When dividing the analysis set of monitoring nodes, it uses attribute dimension information and monitoring data dimension information in combination, and through continuous iterative optimization, it finally determines the gas node set with practical analytical significance.

[0077] Step SubA9: Calculate the partition evaluation value of the set; determine whether the partition evaluation value is lower than the optimization threshold; if so, end step S2; otherwise, return to step SubA5;

[0078]

[0079] Where: m is the number of sets, i and j are set numbers, d_MD(i,j) is the distance between the monitoring data label values of set i and set j; σ i is the average distance between all nodes in set i and the monitoring data label value; σ j is the average distance between all nodes in set j and the monitoring data label values of set j;

[0080] Preferably, if the partition evaluation value is not lower than the optimization threshold, if no set merging occurs in step SubA5 and no node repartitioning occurs in step SubA8, step S2 ends. At this point, although there is no optimal monitoring node set, there is no point in performing optimization.

[0081] Compared with the method of selecting initial nodes based solely on the grid, the present invention can quickly select seed nodes based on multiple dimensions of monitoring data, which speeds up clustering speed and global homogeneity of node attributes within the cluster, breaking the current situation of fixed analysis mode caused by set partitioning based on a single dimension.

[0082] Preferably, the method further comprises the following steps:

[0083] Step S3: Selecting a representative node from each set, determining the attribute value of the representative node, and setting a simulation model based on the attribute value of the representative node and its connection relationship; inputting the representative node and the monitoring data collected on-site into the simulation model to set and adjust the simulation model; simulating the simulation model to obtain simulation results;

[0084] Determining the attribute value of the representative node specifically comprises: selecting a plurality of nodes with different degrees of difference as representative nodes according to the degree of difference of the node monitoring data in the set, and setting the attribute value of the representative node to the attribute value of the node itself; for example, selecting three nodes with the largest, middle, and smallest flow monitoring values as representative nodes; when setting the attribute value, the attribute value maintains the original attribute value of the node itself; the existence of the difference degree means that the difference degree is greater than a preset value;

[0085] The representative nodes may not be directly connected but indirectly connected. When there is no other representative node between two representative nodes in the set, the two representative nodes are set to be directly connected to establish a connection relationship between the nodes.

[0086] Alternatively, step S3 includes setting a virtual node for each set, setting parameters of the virtual node based on the set attribute label and the monitoring data label, setting a connection relationship of the virtual node based on the flow direction of natural gas in the virtual node, and inputting the connection relationship, virtual node and its parameters into the simulation model for simulation; when there is no clear flow direction between two virtual nodes, no connection relationship is set;

[0087] Based on the same inventive concept, the present invention also provides a big data computing node, which includes a first big data node and a second big data node, wherein: the first big data node is used to implement the above-mentioned gas pipeline network node division method, and the second big data node is used to implement the above-mentioned gas pipeline network node simulation method.

[0088] Based on the same inventive concept, the present invention also provides a cloud server, which includes a first large cloud server and a second cloud server, wherein: the first cloud server is used to implement the above-mentioned gas pipeline network node division method, and the second cloud server is used to implement the above-mentioned gas pipeline network node simulation method.

[0089] A computer program (also referred to as a program, software, software application, script, or code) can be written in any form of programming language, including assembly or interpreted languages, declarative or procedural languages, and it can be deployed in any form, including as a stand-alone program or as a module, component, subroutine, object, or other unit suitable for use in a computing environment. A computer program may, but need not, correspond to a file in a file system. A program can be stored in a portion of a file that holds other programs or data (e.g., one or more scripts stored in a markup language document), in a single file dedicated to the program, or in multiple collaborative files (e.g., files storing one or more modules, subroutines, or code portions). A computer program can be deployed to execute on one computer or on multiple computers located at one site or distributed across multiple sites and interconnected by a communication network.

[0090] It will be understood by those skilled in the art that embodiments of the present invention may be provided as methods, systems, or computer program products. Thus, the present invention may take the form of an entirely hardware embodiment, an entirely software embodiment, or an embodiment combining software and hardware. Furthermore, the present invention may take the form of a computer program product implemented on one or more computer-usable storage media (including but not limited to magnetic disk storage, CD-ROM, optical storage, etc.) containing computer-usable program code.

[0091] The present invention is described with reference to the flowcharts and / or block diagrams of the methods, devices (systems), and computer program products according to the embodiments of the present application. It should be understood that each process and / or block in the flowchart and / or block diagram, as well as the combination of the processes and / or blocks in the flowchart and / or block diagram, can be implemented by computer program instructions. These computer program instructions can be provided to a processor of a general-purpose computer, a special-purpose computer, an embedded processor, or other programmable data processing device to produce a machine, so that the instructions executed by the processor of the computer or other programmable data processing device generate instructions for implementing the processes in the flowchart and / or block diagram. Figure 1 a process or multiple processes and / or boxes Figure 1 A device that provides the functions specified in a block or multiple blocks.

[0092] These computer program instructions may also be stored in a computer readable memory that can direct a computer or other programmable data processing device to work in a specific manner, so that the instructions stored in the computer readable memory produce an article of manufacture comprising an instruction device, which implements the process Figure 1 a process or multiple processes and / or boxes Figure 1 The function specified in one or more boxes.

[0093] These computer program instructions can also be loaded onto a computer or other programmable data processing device so that a series of operational steps are executed on the computer or other programmable device to produce a computer-implemented process, thereby providing the instructions executed on the computer or other programmable device for implementing the process. Figure 1 a process or multiple processes and / or boxes Figure 1 The steps for the function specified in one or more boxes.

[0094] 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 it. Although the present invention has been described in detail with reference to the above embodiments, ordinary technicians in the field should understand that the specific implementation methods of the present invention can still be modified or replaced by equivalents. Any modification or equivalent replacement that does not depart from the spirit and scope of the present invention should be covered by the scope of protection of the claims of the present invention.

Claims

1. A method for dividing gas network nodes, characterized in that: include: Step S1: Obtaining monitoring data of the gas transmission network and network node attribute information; Step S2: splitting the pipe network node attributes into multiple sub-attribute sets; dividing the pipe network nodes into multiple sets based on the sub-attribute sets and monitoring data; The method of dividing the pipe network nodes into multiple sets based on the sub-attribute set and the monitoring data specifically comprises the following steps: Step SubA1: selecting an attribute in a sub-attribute cluster as a representative sub-attribute of the sub-attribute cluster; multiple sub-attribute clusters correspond to multiple representative sub-attributes; based on each representative sub-attribute, selecting one pipe network node from all pipe network nodes as an initial node; Step SubA2: selecting one pipe network node from all pipe network nodes as an initial node based on the monitoring data; Step SubA3: Merge all initial nodes, and remove duplication and similarity from the merged initial nodes to form a seed node set; Step SubA4: clustering the onset nodes from the seed node set and obtaining multiple sets corresponding to the seed nodes; Step SubA5: determining a first condition for any two sets, and merging the sets that meet the first condition; the first condition is that the attribute values of the preset attribute type of the nodes exceeding a first preset ratio are the same; Step SubA6: re-determine the set attribute label based on the first condition; Step SubA7: Calculate the monitoring data labels of the set; Step SubA8: Re-partition the nodes based on the attribute labels of the set; Step SubA9: Calculate the partition evaluation value of the set; determine whether the partition evaluation value is lower than the optimization threshold; if so, end step S2; otherwise, return to step SubA5; ； Where: m is the number of sets, i and j are set numbers, is the distance between the monitoring data label values of set i and set j; is the average distance between all nodes in set i and the monitoring data label value; It is the average distance between all nodes in set j and the monitoring data label values of set j.

2. The gas network node division method according to claim 1, characterized in that: The monitoring data includes pressure, flow, temperature, sound, and valve status.

3. The gas network node division method according to claim 2, characterized in that: The monitoring data is historical monitoring data.

4. The gas network node division method according to claim 3, characterized in that: The gas transmission pipeline network is a natural gas transmission pipeline network.

5. A gas network node simulation method, characterized in that: include: Step S1: Obtaining monitoring data of the gas transmission network and network node attribute information; Step S2: splitting the pipe network node attributes into multiple sub-attribute sets; dividing the pipe network nodes into multiple sets based on the sub-attribute sets and monitoring data; The method of dividing the pipe network nodes into multiple sets based on the sub-attribute set and the monitoring data specifically comprises the following steps: Step SubA1: selecting an attribute in a sub-attribute cluster as a representative sub-attribute of the sub-attribute cluster; multiple sub-attribute clusters correspond to multiple representative sub-attributes; based on each representative sub-attribute, selecting one pipe network node from all pipe network nodes as an initial node; Step SubA2: selecting one pipe network node from all pipe network nodes as an initial node based on the monitoring data; Step SubA3: Merge all initial nodes, and remove duplication and similarity from the merged initial nodes to form a seed node set; Step SubA4: clustering the onset nodes from the seed node set and obtaining multiple sets corresponding to the seed nodes; Step SubA5: determining a first condition for any two sets, and merging the sets that meet the first condition; the first condition is that the attribute values of the preset attribute type of the nodes exceeding a first preset ratio are the same; Step SubA6: re-determine the set attribute label based on the first condition; Step SubA7: Calculate the monitoring data labels of the set; Step SubA8: Re-partition the nodes based on the attribute labels of the set; Step SubA9: Calculate the partition evaluation value of the set; determine whether the partition evaluation value is lower than the optimization threshold; if so, end step S2; otherwise, return to step SubA5; ； Where: m is the number of sets, i and j are set numbers, is the distance between the monitoring data label values of set i and set j; is the average distance between all nodes in set i and the monitoring data label value; is the average distance between all nodes in set j and the monitoring data label values of set j; Step S3: Select a representative node from each set, determine the attribute value of the representative node, set up a simulation model based on the attribute value of the representative node and its connection relationship; input the representative node and the monitoring data collected on site into the simulation model to obtain simulation results.

6. The gas network node simulation method according to claim 5, characterized in that: The gas transmission pipeline network is a natural gas transmission pipeline network.

7. A big data computing node, characterized in that: The big data computing node is used to execute the gas pipeline network node division method described in any one of claims 1-4 and the gas pipeline network node simulation method described in any one of claims 5-6.

8. A processor, characterized in that: The processor is used to run a program, wherein when the program is run, the gas pipe network node division method described in any one of claims 1-4 and the gas pipe network node simulation method described in any one of claims 5-6 are executed.

9. A computer-readable storage medium, characterized in that The invention comprises a program which, when running on a computer, enables the computer to execute the gas pipe network node division method according to any one of claims 1 to 4 and the gas pipe network node simulation method according to any one of claims 5 to 6.

10. An execution device, characterized in that: It includes a processor, which is coupled to a memory, and the memory stores program instructions. When the program instructions stored in the memory are executed by the processor, the gas pipeline network node division method described in any one of claims 1 to 4 and the gas pipeline network node simulation method described in any one of claims 5 to 6 are implemented.

Images