CN117938863A - Cluster-based joint simulation implementation method, system, equipment and storage medium - Google Patents
Cluster-based joint simulation implementation method, system, equipment and storage medium Download PDFInfo
- Publication number
- CN117938863A CN117938863A CN202410327528.3A CN202410327528A CN117938863A CN 117938863 A CN117938863 A CN 117938863A CN 202410327528 A CN202410327528 A CN 202410327528A CN 117938863 A CN117938863 A CN 117938863A
- Authority
- CN
- China
- Prior art keywords
- node
- working node
- message
- simulation
- working
- Prior art date
- Legal status (The legal status is an assumption and is not a legal conclusion. Google has not performed a legal analysis and makes no representation as to the accuracy of the status listed.)
- Granted
Links
- 238000004088 simulation Methods 0.000 title claims abstract description 203
- 238000000034 method Methods 0.000 title claims abstract description 57
- 238000003860 storage Methods 0.000 title claims abstract description 20
- 238000004891 communication Methods 0.000 claims abstract description 110
- 238000004519 manufacturing process Methods 0.000 claims abstract description 36
- 238000012549 training Methods 0.000 claims abstract description 33
- 230000008569 process Effects 0.000 claims description 21
- 230000005540 biological transmission Effects 0.000 claims description 14
- 238000004590 computer program Methods 0.000 claims description 14
- 238000012545 processing Methods 0.000 claims description 6
- 238000010276 construction Methods 0.000 claims description 4
- 238000009826 distribution Methods 0.000 claims description 4
- 238000010586 diagram Methods 0.000 description 7
- 238000005516 engineering process Methods 0.000 description 5
- 230000007246 mechanism Effects 0.000 description 4
- 238000012546 transfer Methods 0.000 description 4
- 238000012544 monitoring process Methods 0.000 description 3
- 230000008901 benefit Effects 0.000 description 2
- 230000008878 coupling Effects 0.000 description 2
- 238000010168 coupling process Methods 0.000 description 2
- 238000005859 coupling reaction Methods 0.000 description 2
- 238000011161 development Methods 0.000 description 2
- 238000012423 maintenance Methods 0.000 description 2
- 230000001360 synchronised effect Effects 0.000 description 2
- 238000004364 calculation method Methods 0.000 description 1
- 239000004973 liquid crystal related substance Substances 0.000 description 1
- 238000012986 modification Methods 0.000 description 1
- 230000004048 modification Effects 0.000 description 1
- 230000003068 static effect Effects 0.000 description 1
Landscapes
- Debugging And Monitoring (AREA)
Abstract
The application relates to a cluster-based joint simulation implementation method, a system, equipment and a storage medium. The method comprises the following steps: and constructing a joint simulation resource training network based on the clusters. The simulation application of the first working node establishes a first communication long connection with the management node, and actively searches the management node for a second working node where the message production queue is located. The management node obtains the state information of the first working node through the first communication long connection to configure the load balancing strategy, and the sending message context is obtained. The simulation application of the first working node sends simulation data to the message production queue of the second working node according to the message sending context and the first communication length connection to complete message sending. The simulation application of the second working node pulls simulation data from the message consumption queue of the first working node according to the received message context and the connection of the second communication length to finish message receiving. In a large-scale simulation entity environment, the method can realize high-efficiency and high-speed parallel computation.
Description
Technical Field
The present application relates to the field of computer technologies, and in particular, to a cluster-based joint simulation implementation method, system, device, and storage medium.
Background
The diversity of the application scene of the distributed simulation technology enables a high-level architecture (HLA) to have lower instantaneity when accessors are increased and the data transmission scale is larger, and can not be applied to the simulation scene of virtual-real combination. In addition, most simulation platforms adopting an operation support environment (RTI) adopt single-machine simulation, when the number of mass simulation entities is faced, the real-time memory resource calling capability is reduced, the operation speed is obviously slowed, and parallel calculation cannot be realized in a large-data-volume environment; meanwhile, the RTI simulation system has poor compatibility among different software and hardware platforms, and the expandability and maintainability of the RTI simulation system are reduced.
Disclosure of Invention
In view of the foregoing, it is desirable to provide a cluster-based joint simulation implementation method, system, device and storage medium capable of implementing efficient high-speed parallel computation in a large-scale simulation entity environment.
A cluster-based joint simulation implementation method, the method comprising:
In the distributed joint simulation operation process, a joint simulation resource training network is constructed based on the clusters. The joint simulation resource training network comprises a management console and a cluster, wherein the cluster comprises a management node and a plurality of working nodes.
The working nodes are divided into a first working node and a second working node according to the communication domain, the simulation application of the first working node calls an API interface to establish a first communication long connection with the management node, and the second working node where the message production queue is located is actively searched for from the management node.
The management node obtains the state information of the first working node through the first communication long connection, and configures a load balancing strategy according to the state information of the first working node to obtain a transmission message context of the first working node connected with the second working node.
The simulation application of the first working node sends simulation data to the message production queue of the second working node according to the message sending context and the first communication length connection to complete message sending.
And the simulation application of the second working node calls the API interface to establish a second communication long connection with the management node, and actively searches the first working node of the message consumption queue from the management node.
The management node acquires the state information of the second working node through the second communication long connection, and configures a load balancing strategy according to the state information of the second working node to acquire a receiving message context of the second working node connected with the first working node.
The simulation application of the second working node pulls simulation data from the message consumption queue of the first working node according to the received message context and the connection of the second communication length to finish message receiving.
In one embodiment, the method further comprises: in the distributed joint simulation running process, a joint simulation resource training network is built by starting a management node in one cluster and a management console outside the cluster based on the cluster.
In one embodiment, a management node includes: a communication subsystem, a service processing subsystem and a storage subsystem. The simulation application of the first working node acts as a simulation unit for the message producer. The simulation application of the second working node acts as a simulation unit for the message consumer. The simulation unit of the message producer directly establishes a load balancing distribution strategy of the message queue in the cluster through the communication subsystem of the management node to realize message transmission.
In one embodiment, the method further comprises: the management console accesses RESTful service of the communication subsystem through the remote management API to acquire remote management authority of the management cluster.
In one embodiment, the method further comprises: the simulation application of the first working node calls an API interface to establish a first communication long connection with the management node, the first working node reports the state information of the first working node and the registration information of the simulation application of the first working node to the management node through the first communication long connection, and the second working node of the message production queue is actively searched for from the management node.
In one embodiment, the method further comprises: and the sending application of the simulation application of the first working node periodically inquires the management node about the load balance of the message production queue, and updates the working nodes in the cluster distributed by the management node.
In one embodiment, the method further comprises: and the receiving application of the simulation application of the second working node queries the management node for the load balance of the message consumption queue at regular time, and updates the message consumption queue distributed by the management node and the working nodes in the cluster corresponding to the message consumption queue.
A cluster-based joint simulation implementation system, the system comprising:
And the joint simulation training network construction module is used for constructing a joint simulation resource training network based on the clusters in the distributed joint simulation operation process. The joint simulation resource training network comprises a management console and a cluster, wherein the cluster comprises a management node and a plurality of working nodes.
The message production queue node searching module is used for dividing the working nodes into a first working node and a second working node according to the communication domain, enabling the simulation application of the first working node to call an API interface to establish a first communication long connection with the management node, and actively searching the second working node where the message production queue is located from the management node.
The message sending load balancing module is used for the management node to acquire the state information of the first working node through the first communication long connection, and configures a load balancing strategy according to the state information of the first working node to acquire a message sending context of the first working node connected with the second working node.
And the foreign-domain node message sending module is used for the simulation application of the first working node to send simulation data to the message production queue of the second working node according to the message sending context and the first communication long connection to finish message sending.
And the message consumption queue node searching module is used for calling the API interface by the simulation application of the second working node to establish a second communication long connection with the management node and actively searching the first working node of the message consumption queue from the management node.
The received message load balancing module is used for the management node to acquire the state information of the second working node through the second communication long connection, and configures a load balancing strategy according to the state information of the second working node to acquire the received message context of the second working node connected with the first working node.
And the foreign-domain node message receiving module is used for pulling simulation data from the message consumption queue of the first working node according to the connection of the received message context and the second communication length by the simulation application of the second working node to finish message receiving.
A computer device comprising a memory storing a computer program and a processor which when executing the computer program performs the steps of:
In the distributed joint simulation operation process, a joint simulation resource training network is constructed based on the clusters. The joint simulation resource training network comprises a management console and a cluster, wherein the cluster comprises a management node and a plurality of working nodes.
The working nodes are divided into a first working node and a second working node according to the communication domain, the simulation application of the first working node calls an API interface to establish a first communication long connection with the management node, and the second working node where the message production queue is located is actively searched for from the management node.
The management node obtains the state information of the first working node through the first communication long connection, and configures a load balancing strategy according to the state information of the first working node to obtain a transmission message context of the first working node connected with the second working node.
The simulation application of the first working node sends simulation data to the message production queue of the second working node according to the message sending context and the first communication length connection to complete message sending.
And the simulation application of the second working node calls the API interface to establish a second communication long connection with the management node, and actively searches the first working node of the message consumption queue from the management node.
The management node acquires the state information of the second working node through the second communication long connection, and configures a load balancing strategy according to the state information of the second working node to acquire a receiving message context of the second working node connected with the first working node.
The simulation application of the second working node pulls simulation data from the message consumption queue of the first working node according to the received message context and the connection of the second communication length to finish message receiving.
A computer readable storage medium having stored thereon a computer program which when executed by a processor performs the steps of:
In the distributed joint simulation operation process, a joint simulation resource training network is constructed based on the clusters. The joint simulation resource training network comprises a management console and a cluster, wherein the cluster comprises a management node and a plurality of working nodes.
The working nodes are divided into a first working node and a second working node according to the communication domain, the simulation application of the first working node calls an API interface to establish a first communication long connection with the management node, and the second working node where the message production queue is located is actively searched for from the management node.
The management node obtains the state information of the first working node through the first communication long connection, and configures a load balancing strategy according to the state information of the first working node to obtain a transmission message context of the first working node connected with the second working node.
The simulation application of the first working node sends simulation data to the message production queue of the second working node according to the message sending context and the first communication length connection to complete message sending.
And the simulation application of the second working node calls the API interface to establish a second communication long connection with the management node, and actively searches the first working node of the message consumption queue from the management node.
The management node acquires the state information of the second working node through the second communication long connection, and configures a load balancing strategy according to the state information of the second working node to acquire a receiving message context of the second working node connected with the first working node.
The simulation application of the second working node pulls simulation data from the message consumption queue of the first working node according to the received message context and the connection of the second communication length to finish message receiving.
The cluster-based joint simulation implementation method, the cluster-based joint simulation implementation system, the cluster-based joint simulation implementation equipment and the storage medium are characterized in that a cluster architecture is used, wherein the cluster architecture comprises a management node and a plurality of working nodes and is used for distributed processing of simulation tasks, a long-connection communication mechanism is used for establishing a stable communication channel between different nodes so as to support data transmission and state information transfer, communication and data synchronization between the nodes are ensured, and a simulation process is more accurate and reliable. In addition, message queues are used to transfer messages between nodes, including message production queues and message consumption queues. Furthermore, the management node establishes a load balancing strategy according to the state information of each working node, and in a large-scale simulation environment, the loads of different nodes can be unbalanced, and the load balancing strategy is dynamically adjusted, so that the load of each node can be balanced according to actual conditions, the load balancing problem is solved, tasks and resources are reasonably distributed, and the resource utilization rate is improved. In addition, the joint simulation resource training network supports dynamic expansion of nodes in the cluster, and working nodes can be increased according to requirements, so that simulation requirements of different scales are met. Meanwhile, the realization system corresponding to the method enables the user to obtain greater flexibility, and has good expandability and maintainability, thereby ensuring the continuity of system operation.
Drawings
FIG. 1 is an application scenario diagram of a cluster-based joint simulation implementation method in one embodiment;
FIG. 2 is a flow diagram of a cluster-based joint simulation implementation method in one embodiment;
FIG. 3 is a flow diagram of a management node operating mechanism in one embodiment;
FIG. 4 is a flow diagram of the operating mechanism of a worker node in one embodiment;
FIG. 5 is a block diagram of a cluster-based joint simulation implementation system in one embodiment;
Fig. 6 is an internal structural diagram of a computer device in one embodiment.
Detailed Description
The present application will be described in further detail with reference to the drawings and examples, in order to make the objects, technical solutions and advantages of the present application more apparent. It should be understood that the specific embodiments described herein are for purposes of illustration only and are not intended to limit the scope of the application.
The cluster-based joint simulation implementation method provided by the application can be applied to an application environment shown in fig. 1. In the distributed joint simulation process, a user accesses a management console by using a browser, the management console is remotely connected with a management node of the cluster, an HTTP request is submitted to a Restful interface of the management node, and configuration management and state inquiry are carried out on the cluster. And meanwhile, the cluster feeds the joint simulation control result and the authority back to the management console in real time. The cluster comprises a management node and two regional working nodes, wherein different regions participate in joint simulation deployment of the working nodes, and the management node comprises six modules of RESTful service, safety guarantee, load balancing, node configuration, registration service and state updating; the region A and the region B are respectively provided with a plurality of working nodes and a simulation application module of the current region, and each working node comprises four modules of starting registration, timing reporting, a theme queue and a common queue. After the joint simulation resource training network is started, the working node is started, long connection, registration node and heartbeat maintenance connection are established for the management node, and state information of the node is reported at regular time. The management node collects registration information and state information of simulation applications of the nodes and provides queue load balancing inquiry for the simulation applications in each area.
In one embodiment, as shown in fig. 2, a cluster-based joint simulation implementation method is provided, and an application environment of the method in fig. 1 is taken as an example for explanation, which includes the following steps:
step 202, constructing a joint simulation resource training network based on clusters in the running process of the distributed joint simulation.
The joint simulation resource training network comprises a management console and a cluster, wherein the cluster comprises a management node and a plurality of working nodes.
Step 204, the working nodes are divided into a first working node and a second working node according to the communication domain, the simulation application of the first working node calls an API interface to establish a first communication long connection with the management node, and the second working node where the message production queue is located is actively searched for from the management node.
If the plurality of working nodes are in the same communication domain, the plurality of working nodes are local working nodes in the current communication domain, and the data information transmission between the local working nodes is applicable to the communication connection technology in the prior art; if the plurality of working nodes are in different communication domains, the plurality of working nodes divide a plurality of groups of working node clusters according to the communication domains, each working node cluster comprises a plurality of local working nodes, as shown in fig. 1, a first working node is one local working node in the working node clusters of the region A, a second working node is one local working node in the working node clusters of the region B, and data information between the first working node and the second working node is sent or received as cross-domain communication connection.
In addition, a simulation application is allocated to each communication domain, when the local working node in the communication domain performs cross-domain communication connection, a communication long connection is required to be established with the simulation application in the local domain, and after simulation data of the region A are generated by using the simulation application of the region A, a long connection is established with a management node to perform cross-domain message transmission.
In step 206, the management node obtains the status information of the first working node through the first communication long connection, and configures a load balancing policy according to the status information of the first working node, so as to obtain the context of the sending message of the first working node connected with the second working node.
Specifically, the simulation application of the region A sends an application calling API interface to establish long connection with the management node, registers self information of the simulation application of the region A, and actively searches the management node for the working node where the target queue is located. And the management node returns an available second work node connection context according to the configured load balancing strategy. The simulation application of the region A establishes long connection with the second working node by using the second working node connection context, and sends simulation data of the region A to a queue of the second working node of the region B in the cluster.
In step 208, the simulation application of the first working node sends the simulation data to the message production queue of the second working node to complete message sending according to the message sending context and the first communication long connection.
Step 210, the simulation application of the second working node calls the API interface to establish a second communication length connection with the management node, and actively searches the first working node of the message consumption queue from the management node.
In step 212, the management node obtains the status information of the second working node through the second communication long connection, and configures the load balancing policy according to the status information of the second working node, so as to obtain the context of the received message of the second working node connected with the first working node.
In step 214, the simulation application of the second working node pulls the simulation data from the message consumption queue of the first working node to complete message reception according to the connection between the received message context and the second communication length.
The second working node may also directly pull data from the first working node of zone a through the communication link between zone a and zone B.
In the cluster-based joint simulation implementation method, the cluster architecture comprises a management node and a plurality of working nodes, the management node and the working nodes are used for distributed processing of simulation tasks, a long-connection communication mechanism is used for establishing a stable communication channel between different nodes so as to support data transmission and state information transfer, communication and data synchronization between the nodes are ensured, and a simulation process is more accurate and reliable. In addition, message queues are used to transfer messages between nodes, including message production queues and message consumption queues. Furthermore, the management node establishes a load balancing strategy according to the state information of each working node, and in a large-scale simulation environment, the loads of different nodes can be unbalanced, and the load balancing strategy is dynamically adjusted, so that the load of each node can be balanced according to actual conditions, the load balancing problem is solved, tasks and resources are reasonably distributed, and the resource utilization rate is improved. In addition, the joint simulation resource training network supports dynamic expansion of nodes in the cluster, and working nodes can be increased according to requirements, so that simulation requirements of different scales are met.
In one embodiment, in the running process of distributed joint simulation, a joint simulation resource training network is built by starting a management node in one cluster and a management console outside the cluster based on the cluster.
In one embodiment, a management node includes: a communication subsystem, a service processing subsystem and a storage subsystem. The simulation application of the first working node acts as a simulation unit for the message producer. The simulation application of the second working node acts as a simulation unit for the message consumer. The simulation unit of the message producer directly establishes a load balancing distribution strategy of the message queue in the cluster through the communication subsystem of the management node to realize message transmission.
It is worth noting that the management node is used to manage all server resources of the clustered system as if they were all running on the same server. Cluster objects can be increased and reduced, data can be moved among different servers in the cluster, and the load of the servers can be manually balanced, the servers can be unloaded, and the maintenance is convenient. Meanwhile, the state of the cluster can be monitored from nodes and resources at any position in the network, when a fault server is connected back, the fault server automatically returns to a working state, and the cluster technology automatically balances the load in the cluster without any intervention.
In one embodiment, the management console obtains remote management rights for the management cluster through a RESTful service of the remote management API access communication subsystem.
In one embodiment, the simulation application of the first working node calls an API interface to establish a first communication long connection with the management node, the first working node reports the state information of the first working node and the registration information of the simulation application of the first working node to the management node through the first communication long connection, and the second working node actively searches the message production queue to the management node.
It should be noted that, the cluster system using the cluster technology can be extended to a plurality of service peaks including hundreds of CPUs, and the advantage of the extension capability is obvious. Different topics can be bound to different servers, guaranteeing the sequentiality of messages. Cluster services may also be continually tuned to meet ever-increasing application demands. Additional nodes may also be added when the total load of the cluster exceeds the actual capacity of the cluster.
In one embodiment, the sending application of the simulation application of the first working node periodically queries the management node for load balancing of the message production queue, and updates the working nodes in the cluster distributed by the management node.
In one embodiment, the receiving application of the simulation application of the second working node queries the management node for load balancing of the message consumption queue at regular time, and updates the message consumption queue distributed by the management node and the working nodes in the cluster corresponding to the message consumption queue.
It is worth noting that the cluster service is used to own the entire cluster system resources. When a system in the cluster fails, the disk drives and IP addresses will automatically be transferred from the failed server to the available servers. The cluster software distributes work on the failed node to the remaining nodes. In the switching process, the client of the user automatically processes, and the application is not perceived.
In one embodiment, as shown in fig. 3, the management node provides service registration, service discovery, monitoring of the running states and load conditions of each working node in the cluster, centralized storage of cluster state information, unified management of cluster working node configuration, cluster queue load balancing, and connection security, log and local core process monitoring. The management node can divide a plurality of subsystems, and the subsystem division follows the principle of high cohesion and low coupling, thereby facilitating modularized development.
It is worth noting that the management node is an entry point for cluster access. The management node name guarantees the uniqueness of the name by the service. The working node registers with the management node and reports the state information. The management node gathers the status report of the working node and the simulation application registration information, and performs dynamic cluster queue load balancing distribution. The simulation application access cluster needs to register in the management node, and waits for the management node to return to the load balancing queue and the working node. The management console accesses the RESTful service of the management node using a remote management API to remotely manage the cluster.
In one embodiment, as shown in FIG. 4, the working node monitoring subsystem registers with the management node, reporting status information and pulling runtime configuration. Work node names are guaranteed by the service to be unique in name.
Specifically, in the publish-subscribe mode, the simulation application connection management node acquires available working nodes, the available working nodes are connected to send messages, and the working node communication subsystem uses the thread pool to concurrently process simulation application messages.
Further, the message processing subsystem of the working node processes various types of messages, and the storage subsystem provides for reliable storage and massive stacking of messages. The simulation application subscribes and pulls messages from the topic queue of the working node for consumption. In addition, the topic queue is used for publishing the subscription mode, and at least one time of message sending and message receiving is guaranteed.
It should be noted that a working node may divide up multiple subsystems. The subsystem division follows the principle of high cohesion and low coupling, and is convenient for modularized development.
It should be understood that, although the steps in the flowcharts of fig. 2-4 are shown in order as indicated by the arrows, these steps are not necessarily performed in order as indicated by the arrows. The steps are not strictly limited to the order of execution unless explicitly recited herein, and the steps may be executed in other orders. Moreover, at least some of the steps in fig. 2-4 may include multiple sub-steps or stages that are not necessarily performed at the same time, but may be performed at different times, nor does the order in which the sub-steps or stages are performed necessarily occur in sequence, but may be performed alternately or alternately with at least a portion of the other steps or sub-steps of other steps.
In one embodiment, as shown in FIG. 5, a cluster-based joint simulation implementation system is provided, comprising: the system comprises a joint simulation training network construction module 502, a message production queue node searching module 504, a message sending load balancing module 506, a heterogenous node message sending module 508, a message consumption queue node searching module 510, a message receiving load balancing module 512 and a heterogenous node message receiving module 514, wherein:
the joint simulation training network construction module 502 is configured to construct a joint simulation resource training network based on the cluster in the distributed joint simulation operation process. The joint simulation resource training network comprises a management console and a cluster, wherein the cluster comprises a management node and a plurality of working nodes.
The message production queue node searching module 504 is configured to divide the working node into a first working node and a second working node according to the communication domain, call an API interface by a simulation application of the first working node to establish a first communication long connection with the management node, and actively search the management node for the second working node where the message production queue is located.
The send message load balancing module 506 is configured to obtain, by the management node, status information of the first working node through the first long communication connection, and configure a load balancing policy according to the status information of the first working node, to obtain a send message context in which the first working node is connected to the second working node.
And the foreign node message sending module 508 is used for sending the simulation data to the message production queue of the second working node by the simulation application of the first working node according to the message sending context and the connection of the first communication length to complete message sending.
The message consumption queue node searching module 510 is configured to call the API interface by the simulation application of the second working node to establish a second communication length connection with the management node, and actively search the management node for the first working node of the message consumption queue.
The received message load balancing module 512 is configured to obtain, by the management node, status information of the second working node through the second communication long connection, and configure a load balancing policy according to the status information of the second working node, to obtain a received message context of the second working node connected to the first working node.
The foreign node message receiving module 514 is configured to pull the simulation data from the message consumption queue of the first working node according to the connection between the received message context and the second communication length by the simulation application of the second working node to complete message reception.
For specific limitations on the cluster-based co-simulation implementation system, reference may be made to the above limitation on the cluster-based co-simulation implementation method, which is not described herein. The modules in the cluster-based joint simulation implementation system may be implemented in whole or in part by software, hardware, or a combination thereof. The above modules may be embedded in hardware or may be independent of a processor in the computer device, or may be stored in software in a memory in the computer device, so that the processor may call and execute operations corresponding to the above modules.
In one embodiment, a computer device is provided, which may be a terminal, and the internal structure of which may be as shown in fig. 6. The computer device includes a processor, a memory, a network interface, a display screen, and an input device connected by a system bus. Wherein the processor of the computer device is configured 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 computer programs in the non-volatile storage media. The network interface of the computer device is used for communicating with an external terminal through a network connection. The computer program, when executed by a processor, implements a cluster-based joint simulation implementation method. The display screen of the computer equipment can be a liquid crystal display screen or an electronic ink display screen, and the input device of the computer equipment can be a touch layer covered on the display screen, can also be keys, a track ball or a touch pad arranged on the shell of the computer equipment, and can also be an external keyboard, a touch pad or a mouse and the like.
It will be appreciated by persons skilled in the art that the structures shown in fig. 5-6 are block diagrams of only portions of structures associated with aspects of the application and are not intended to limit the computer device to which aspects of the application may be applied, and that a particular computer device may include more or fewer components than shown, or may combine certain components, or may have a different arrangement of components.
In one embodiment, a computer device is provided comprising a memory storing a computer program and a processor that when executing the computer program performs the steps of:
In the distributed joint simulation operation process, a joint simulation resource training network is constructed based on the clusters. The joint simulation resource training network comprises a management console and a cluster, wherein the cluster comprises a management node and a plurality of working nodes.
The working nodes are divided into a first working node and a second working node according to the communication domain, the simulation application of the first working node calls an API interface to establish a first communication long connection with the management node, and the second working node where the message production queue is located is actively searched for from the management node.
The management node obtains the state information of the first working node through the first communication long connection, and configures a load balancing strategy according to the state information of the first working node to obtain a transmission message context of the first working node connected with the second working node.
The simulation application of the first working node sends simulation data to the message production queue of the second working node according to the message sending context and the first communication length connection to complete message sending.
And the simulation application of the second working node calls the API interface to establish a second communication long connection with the management node, and actively searches the first working node of the message consumption queue from the management node.
The management node acquires the state information of the second working node through the second communication long connection, and configures a load balancing strategy according to the state information of the second working node to acquire a receiving message context of the second working node connected with the first working node.
The simulation application of the second working node pulls simulation data from the message consumption queue of the first working node according to the received message context and the connection of the second communication length to finish message receiving.
In one embodiment, a computer readable storage medium is provided having a computer program stored thereon, which when executed by a processor, performs the steps of:
In the distributed joint simulation operation process, a joint simulation resource training network is constructed based on the clusters. The joint simulation resource training network comprises a management console and a cluster, wherein the cluster comprises a management node and a plurality of working nodes.
The working nodes are divided into a first working node and a second working node according to the communication domain, the simulation application of the first working node calls an API interface to establish a first communication long connection with the management node, and the second working node where the message production queue is located is actively searched for from the management node.
The management node obtains the state information of the first working node through the first communication long connection, and configures a load balancing strategy according to the state information of the first working node to obtain a transmission message context of the first working node connected with the second working node.
The simulation application of the first working node sends simulation data to the message production queue of the second working node according to the message sending context and the first communication length connection to complete message sending.
And the simulation application of the second working node calls the API interface to establish a second communication long connection with the management node, and actively searches the first working node of the message consumption queue from the management node.
The management node acquires the state information of the second working node through the second communication long connection, and configures a load balancing strategy according to the state information of the second working node to acquire a receiving message context of the second working node connected with the first working node.
The simulation application of the second working node pulls simulation data from the message consumption queue of the first working node according to the received message context and the connection of the second communication length to finish message receiving.
Those skilled in the art will appreciate that implementing all or part of the above described methods may be accomplished by way of a computer program stored on a non-transitory computer readable storage medium, which when executed, may comprise the steps of the embodiments of the methods described above. Any reference to memory, storage, database, or other medium used in embodiments provided herein may include non-volatile and/or volatile memory. The nonvolatile memory can include Read Only Memory (ROM), programmable ROM (PROM), electrically Programmable ROM (EPROM), electrically Erasable Programmable ROM (EEPROM), or flash memory. Volatile memory can include Random Access Memory (RAM) or external cache memory. By way of illustration and not limitation, RAM is available in a variety of forms such as Static RAM (SRAM), dynamic RAM (DRAM), synchronous DRAM (SDRAM), double Data Rate SDRAM (DDRSDRAM), enhanced SDRAM (ESDRAM), synchronous link (SYNCHLINK) DRAM (SLDRAM), memory bus (Rambus) direct RAM (RDRAM), direct memory bus dynamic RAM (DRDRAM), and memory bus dynamic RAM (RDRAM), among others.
The technical features of the above embodiments may be arbitrarily combined, and all possible combinations of the technical features in the above embodiments are not described for brevity of description, however, as long as there is no contradiction between the combinations of the technical features, they should be considered as the scope of the description.
The above examples merely represent a few embodiments of the present application, which are described in more detail and are not to be construed as limiting the scope of the application. It should be noted that it will be apparent to those skilled in the art that several variations and modifications can be made without departing from the spirit of the application, which are all within the scope of the application. Accordingly, the scope of the application should be assessed as that of the appended claims.
Claims (10)
1. A cluster-based joint simulation implementation method, the method comprising:
in the distributed joint simulation operation process, constructing a joint simulation resource training network based on clusters; the joint simulation resource training network comprises a management console and the cluster, wherein the cluster comprises a management node and a plurality of working nodes;
The working nodes are divided into a first working node and a second working node according to a communication domain, a simulation application calling API interface of the first working node establishes a first communication long connection with the management node, and actively searches the second working node where a message production queue is located for the management node;
the management node acquires the state information of the first working node through the first communication long connection, and configures a load balancing strategy according to the state information of the first working node to acquire a transmission message context of the first working node connected with the second working node;
the simulation application of the first working node sends simulation data to a message production queue of the second working node according to the message sending context and the first communication long connection to complete message sending;
The simulation application of the second working node calls an API interface to establish a second communication length connection with the management node, and actively searches the first working node of the message consumption queue from the management node;
the management node acquires the state information of the second working node through the second communication long connection, and configures a load balancing strategy according to the state information of the second working node to acquire a receiving message context of the second working node connected with the first working node;
And the simulation application of the second working node pulls simulation data from the message consumption queue of the first working node according to the received message context and the connection of the second communication length to finish message receiving.
2. The method of claim 1, wherein constructing a co-simulation resource training network based on clusters during distributed co-simulation operation comprises:
in the distributed joint simulation operation process, a joint simulation resource training network is built by starting a management node in the cluster and a management console outside the cluster based on the cluster.
3. The method according to claim 1, wherein the management node comprises: a communication subsystem, a service processing subsystem and a storage subsystem;
The simulation application of the first working node serves as a simulation unit of a message producer;
The simulation application of the second working node serves as a simulation unit of a message consumer;
And the simulation unit of the message producer directly establishes a load balancing distribution strategy of the message queue in the cluster through the communication subsystem of the management node to realize message transmission.
4. The method of claim 3, further comprising, during the running of the distributed co-simulation, after the step of constructing the co-simulation resource training network based on the clusters:
and the management console obtains the remote management authority for managing the cluster through the RESTful service of the remote management API accessing the communication subsystem.
5. The method of claim 4, wherein the first working node's emulation application call API interface establishes a first long communication connection with the management node and actively searches the management node for the second working node in which a message production queue is located, comprising:
And the simulation application of the first working node calls an API interface to establish a first communication long connection with the management node, the first working node reports the state information of the first working node and the registration information of the simulation application of the first working node to the management node through the first communication long connection, and actively searches the second working node of the message production queue from the management node.
6. The method of claim 5, further comprising, after the simulation application of the first working node sends a simulation data complete message to the message production queue of the second working node according to the send message context with the first communication long connection:
And the sending application of the simulation application of the first working node queries the management node for the load balancing of the message production queue at regular time, and updates the working nodes in the cluster distributed by the management node.
7. The method of claim 1, further comprising, after the simulation application of the second working node completes message receipt by pulling simulation data from the message consumption queue of the first working node in accordance with the received message context and the second communication length connection:
And the receiving application of the simulation application of the second working node queries the management node for the load balancing of the message consumption queue at regular time, and updates the message consumption queue distributed by the management node and the working nodes in the cluster corresponding to the message consumption queue.
8. A cluster-based joint simulation implementation system, the system comprising:
The joint simulation training network construction module is used for constructing a joint simulation resource training network based on the clusters in the distributed joint simulation operation process; the joint simulation resource training network comprises a management console and the cluster, wherein the cluster comprises a management node and a plurality of working nodes;
the message production queue node searching module is used for dividing the working node into a first working node and a second working node according to a communication domain, enabling a simulation application of the first working node to call an API interface to establish a first communication long connection with the management node, and actively searching the second working node where the message production queue is located from the management node;
the message sending load balancing module is used for the management node to acquire the state information of the first working node through the first communication long connection, and configures a load balancing strategy according to the state information of the first working node to acquire a message sending context of the first working node connected with the second working node;
The foreign-domain node message sending module is used for the simulation application of the first working node to send simulation data to the message production queue of the second working node according to the message sending context and the first communication length connection so as to complete message sending;
The message consumption queue node searching module is used for calling an API interface by the simulation application of the second working node to establish second communication long connection with the management node and actively searching the first working node of the message consumption queue for the management node;
The received message load balancing module is used for the management node to acquire the state information of the second working node through the second communication long connection, and configures a load balancing strategy according to the state information of the second working node to acquire a received message context of the second working node connected with the first working node;
And the foreign-domain node message receiving module is used for the simulation application of the second working node to pull simulation data from the message consumption queue of the first working node according to the received message context and the connection of the second communication length so as to complete message receiving.
9. A computer device comprising a memory and a processor, the memory storing a computer program, characterized in that the processor implements the steps of the method of any of claims 1 to 7 when the computer program is executed.
10. A computer readable storage medium, on which a computer program is stored, characterized in that the computer program, when being executed by a processor, implements the steps of the method of any of claims 1 to 7.
Priority Applications (1)
| Application Number | Priority Date | Filing Date | Title |
|---|---|---|---|
| CN202410327528.3A CN117938863B (en) | 2024-03-21 | 2024-03-21 | Cluster-based joint simulation implementation method, system, equipment and storage medium |
Applications Claiming Priority (1)
| Application Number | Priority Date | Filing Date | Title |
|---|---|---|---|
| CN202410327528.3A CN117938863B (en) | 2024-03-21 | 2024-03-21 | Cluster-based joint simulation implementation method, system, equipment and storage medium |
Publications (2)
| Publication Number | Publication Date |
|---|---|
| CN117938863A true CN117938863A (en) | 2024-04-26 |
| CN117938863B CN117938863B (en) | 2024-05-24 |
Family
ID=90754232
Family Applications (1)
| Application Number | Title | Priority Date | Filing Date |
|---|---|---|---|
| CN202410327528.3A Active CN117938863B (en) | 2024-03-21 | 2024-03-21 | Cluster-based joint simulation implementation method, system, equipment and storage medium |
Country Status (1)
| Country | Link |
|---|---|
| CN (1) | CN117938863B (en) |
Citations (5)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| US20070230458A1 (en) * | 2004-08-23 | 2007-10-04 | Nec Corporation | Communication Network, Communication Apparatus, Communication Control Method and Communication Control Program |
| CN101436959A (en) * | 2008-12-18 | 2009-05-20 | 中国人民解放军国防科学技术大学 | Method for distributing and scheduling parallel artificial tasks based on background management and control architecture |
| US8670747B1 (en) * | 2012-04-19 | 2014-03-11 | The Boeing Company | Mobile network connectivity |
| US20200145344A1 (en) * | 2018-11-01 | 2020-05-07 | International Business Machines Corporation | Operating a message queue cluster having multiple nodes |
| CN113746683A (en) * | 2021-09-15 | 2021-12-03 | 北京航空航天大学 | Interconnection, intercommunication and interoperation simulation method under cross-domain environment |
-
2024
- 2024-03-21 CN CN202410327528.3A patent/CN117938863B/en active Active
Patent Citations (5)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| US20070230458A1 (en) * | 2004-08-23 | 2007-10-04 | Nec Corporation | Communication Network, Communication Apparatus, Communication Control Method and Communication Control Program |
| CN101436959A (en) * | 2008-12-18 | 2009-05-20 | 中国人民解放军国防科学技术大学 | Method for distributing and scheduling parallel artificial tasks based on background management and control architecture |
| US8670747B1 (en) * | 2012-04-19 | 2014-03-11 | The Boeing Company | Mobile network connectivity |
| US20200145344A1 (en) * | 2018-11-01 | 2020-05-07 | International Business Machines Corporation | Operating a message queue cluster having multiple nodes |
| CN113746683A (en) * | 2021-09-15 | 2021-12-03 | 北京航空航天大学 | Interconnection, intercommunication and interoperation simulation method under cross-domain environment |
Non-Patent Citations (2)
| Title |
|---|
| 蔡霖腾;徐琪;梁广;: "推拉技术在卫星地面运控系统软件中的实现", 电信快报, no. 05, 10 May 2020 (2020-05-10), pages 24 - 33 * |
| 魏明江等: "《数字配电网边缘计算模拟实验平台》", 《中国电力》, no. 3, 27 December 2023 (2023-12-27), pages 12 - 19 * |
Also Published As
| Publication number | Publication date |
|---|---|
| CN117938863B (en) | 2024-05-24 |
Similar Documents
| Publication | Publication Date | Title |
|---|---|---|
| US8112659B2 (en) | Reducing recovery time for business organizations in case of disasters | |
| CN106663033B (en) | System and method for supporting a wraparound domain and proxy model and updating service information for cross-domain messaging in a transactional middleware machine environment | |
| JP2015537307A (en) | Component-oriented hybrid cloud operating system architecture and communication method thereof | |
| CN103533063A (en) | Method and device capable of realizing dynamic expansion of WEB (World Wide Web) application resource | |
| US5872929A (en) | Method and system for managing terminals in a network computing system using terminal information including session status | |
| CN112118315A (en) | Data processing system, method, device, electronic equipment and storage medium | |
| CN113422842B (en) | Distributed power utilization information data acquisition system considering network load | |
| CN108427619B (en) | Log management method and device, computing equipment and storage medium | |
| US20100332532A1 (en) | Distributed directory environment using clustered ldap servers | |
| Han et al. | EdgeTuner: Fast scheduling algorithm tuning for dynamic edge-cloud workloads and resources | |
| US20240118935A1 (en) | Pod deployment method and apparatus | |
| CN114666335B (en) | Distributed system load balancing device based on data distribution service DDS | |
| CN117938863B (en) | Cluster-based joint simulation implementation method, system, equipment and storage medium | |
| CN115225645B (en) | Service updating method, device, system and storage medium | |
| CN116089079A (en) | Big data-based computer resource allocation management system and method | |
| Hamerski et al. | Publish-subscribe programming for a NoC-based multiprocessor system-on-chip | |
| Nick et al. | Overview of IBM system/390 parallel sysplex-a commercial parallel processing system | |
| JP5100011B2 (en) | Network resource management apparatus, network resource management system, and network resource management method | |
| Sun et al. | PROXZONE: one cloud computing system for support paas in energy power applications | |
| CN111698454B (en) | Inter-domain resource pushing method and device for dynamically selecting optimal path | |
| US20230283663A1 (en) | Randomization of heartbeat communications among multiple partition groups | |
| CN117749893A (en) | Calling method, device, computer and storage medium for service among service clusters | |
| Bayyapu et al. | Load scheduling in a cloud based massive video-storage environment | |
| Zhang et al. | Towards a scalable and energy-efficient resource manager for coupling cluster computing with distributed embedded computing | |
| CN117336353A (en) | Service discovery method, device, electronic equipment and storage medium |
Legal Events
| Date | Code | Title | Description |
|---|---|---|---|
| PB01 | Publication | ||
| PB01 | Publication | ||
| SE01 | Entry into force of request for substantive examination | ||
| SE01 | Entry into force of request for substantive examination | ||
| GR01 | Patent grant | ||
| GR01 | Patent grant |