CN108459900B - Anti-radiation reinforcement collaborative design-simulation system and method based on cloud - Google Patents
Anti-radiation reinforcement collaborative design-simulation system and method based on cloud Download PDFInfo
- Publication number
- CN108459900B CN108459900B CN201810051265.2A CN201810051265A CN108459900B CN 108459900 B CN108459900 B CN 108459900B CN 201810051265 A CN201810051265 A CN 201810051265A CN 108459900 B CN108459900 B CN 108459900B
- Authority
- CN
- China
- Prior art keywords
- message
- subtask
- module
- simulation
- task
- 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.)
- Active
Links
Images
Classifications
-
- G—PHYSICS
- G06—COMPUTING; CALCULATING OR COUNTING
- G06F—ELECTRIC DIGITAL DATA PROCESSING
- G06F9/00—Arrangements for program control, e.g. control units
- G06F9/06—Arrangements for program control, e.g. control units using stored programs, i.e. using an internal store of processing equipment to receive or retain programs
- G06F9/44—Arrangements for executing specific programs
- G06F9/455—Emulation; Interpretation; Software simulation, e.g. virtualisation or emulation of application or operating system execution engines
- G06F9/45533—Hypervisors; Virtual machine monitors
- G06F9/45558—Hypervisor-specific management and integration aspects
-
- G—PHYSICS
- G06—COMPUTING; CALCULATING OR COUNTING
- G06F—ELECTRIC DIGITAL DATA PROCESSING
- G06F16/00—Information retrieval; Database structures therefor; File system structures therefor
- G06F16/20—Information retrieval; Database structures therefor; File system structures therefor of structured data, e.g. relational data
- G06F16/25—Integrating or interfacing systems involving database management systems
-
- G—PHYSICS
- G06—COMPUTING; CALCULATING OR COUNTING
- G06F—ELECTRIC DIGITAL DATA PROCESSING
- G06F9/00—Arrangements for program control, e.g. control units
- G06F9/06—Arrangements for program control, e.g. control units using stored programs, i.e. using an internal store of processing equipment to receive or retain programs
- G06F9/46—Multiprogramming arrangements
- G06F9/48—Program initiating; Program switching, e.g. by interrupt
- G06F9/4806—Task transfer initiation or dispatching
- G06F9/4843—Task transfer initiation or dispatching by program, e.g. task dispatcher, supervisor, operating system
Abstract
The invention discloses a cloud-based anti-radiation reinforcement collaborative design-simulation system, which is used for solving the problems of difficult collaborative work and low simulation efficiency in the field of anti-radiation reinforcement, and the implementation method comprises the following steps: the front-end system acquires an anti-radiation reinforcement collaborative design-simulation task; the task decomposition module decomposes and sends the anti-radiation reinforcement collaborative design-simulation task; ) The task flow control module performs flow control on a plurality of subtasks and sends the subtasks; the task scheduling module performs task scheduling on the first subtask and sends the first subtask; the resource scheduling module schedules resources for the first subtask; the storage forwarding module acquires a model file and parameters required by a first subtask; the storage and forwarding module stores the execution result of the first subtask executed by the resource of the first subtask on the basic platform into the platform unified database module; the flow control module judges whether all the subtasks in the execution sequence table are executed completely; and the front-end system displays the design-simulation result.
Description
Technical Field
The invention belongs to the technical field of computers, and relates to a distributed collaborative design-simulation system and a distributed collaborative design-simulation method for the field of radiation hardening resistance, which can be used for radiation hardening resistance design and risk estimation of electronic systems, instruments and the like in a radiation environment.
Background
Radiation-resistant reinforcement is carried out on electronic systems, instruments and the like, radiation effect simulation needs to be carried out on designed mechanical devices and circuit systems in the design stage, problems possibly occurring in the actual radiation environment are predicted, and therefore guidance and correction are carried out on the design process, and the radiation-resistant performance of the mechanical devices and the circuit systems is evaluated.
With the deepening of the design and simulation technology in the field of radiation hardening resistance, the performance requirements of radiation hardening resistance design and simulation software on a simulation system are increasing day by day, and the introduction of the cloud computing technology into the field of radiation hardening resistance is imperative. At present, cloud-based simulation systems have been proposed in other fields, which can greatly improve design, simulation efficiency and system resource utilization rate, for example, patent application with application publication number CN106789339A entitled "a distributed cloud simulation method and system based on lightweight virtualization architecture" discloses a distributed cloud simulation system based on lightweight virtualization architecture, and an overall framework of the distributed cloud simulation system includes a cloud simulation central control platform and a plurality of server cluster simulation container modules. The emulation resource virtualization based on the lightweight virtualization uses the container, but since the container shares some public libraries, the emulation resource package based on the container image may expose some private information, and the container supports limited types of operating systems, such as the Windows operating system is not supported at present. Another common cloud simulation system is implemented by using a scheme based on a SaaS (platform as a service) technology, and virtual machines are used in simulation resource virtualization, but the virtual machine-based resource encapsulation is large in size, low in simulation resource replication and sharing efficiency, limited in reusability, and more difficult to implement rapid deployment among multiple centers. Therefore, the existing implementation scheme of the cloud simulation system has the problem that the design simulation tool software compatibility and the simulation resource utilization rate are difficult to improve at the same time.
The design-simulation in the field of radiation-resistant reinforcement relates to multiple disciplines of mechanics, physics, thermal, mechanics, electromagnetism and the like, different design/simulation software of the multiple disciplines, such as AutoCAD, OrCAD, ProE, MCNP, Ansys, SystemVision and the like, is needed in the design-simulation process, the software can be used for designing and modeling a mechanical structure and a circuit system, and can be used for simulating the radiation-resistant effect of a device or a circuit according to different factors (such as radiation dose, single event effect and the like), and a complete radiation-resistant reinforcement design-simulation process needs to be completed by the cooperation of the multiple software of the different disciplines. To actually improve the design-simulation efficiency of the anti-radiation reinforcement, it is necessary to completely realize the cooperative work of the anti-radiation reinforcement design-simulation software. At present, no effective automatic and cooperative design-simulation system and method exist in the field of anti-radiation reinforcement in China. The main reason is that there are several problems to be solved: 1. the subjects and the used models of various design software/simulation software are different, the required input data and the generated output data are also different, the data conversion between different software needs to be realized in the whole collaborative design and simulation process so that the output of one software can be used for the input of the other software, and the automatic conversion tool is lacked among partial software related to the radiation-resistant reinforcement field at present, and manual conversion is also needed. 2. To perform the cooperation of the radiation-hardening resistant design and the simulation, a plurality of tool software are required to cooperate, and the tool software is required to be executed in sequence strictly according to the general flow of the radiation-hardening resistant design simulation, and a tool for performing strict flow control on the execution of the tool software involved in the radiation-hardening resistance is lacking at present. 3. The quantity of a plurality of databases for storing relevant parameters of the radiation-resistant reinforced design-simulation, model files and simulation results is large, the types of the databases are greatly different, and the integration is difficult. However, the existing collaborative simulation systems in other fields cannot provide technologies for solving the three problems.
Disclosure of Invention
The invention aims to overcome the defects of the prior art, provides a cloud-based anti-radiation reinforcement collaborative design-simulation system and method, and aims to improve the efficiency of anti-radiation reinforcement simulation.
In order to achieve the purpose, the invention adopts the technical scheme that:
the utility model provides a radiation-resistant reinforcement collaborative design-simulation system based on cloud, includes that basic platform system, design-simulation braced system, front end system and platform unify database module, wherein:
the basic platform system is used for providing a cloud-based operating environment for the design-simulation supporting system, the front-end system and the platform unified database module;
the design-simulation support system is used for decomposing an anti-radiation reinforcement design-simulation task, controlling an anti-radiation reinforcement design-simulation flow, scheduling resources required by the anti-radiation reinforcement design-simulation, and performing format conversion on data generated in the anti-radiation reinforcement design-simulation process so as to assist the cooperation of the anti-radiation reinforcement design-simulation;
the front-end system is used for acquiring the input of anti-radiation reinforcement design-simulation parameters and model files, displaying the state and result of design-simulation, and providing a virtual machine and container management interface and a user management interface;
the platform unified database module is used for storing model files and parameters required by the anti-radiation reinforcement design-simulation and results of the anti-radiation reinforcement design-simulation output, and providing a unified data access and management interface for the basic platform system, the design-simulation support system and the front-end system.
The above-mentioned radiation-resistant reinforcement collaborative design-simulation system based on cloud, the basic platform system includes basic cloud resources, a virtual machine cluster based on cloud and a container cluster based on cloud, wherein:
the basic cloud resources are used for providing operating environments needed by the cloud-based virtual machine cluster and the cloud-based container cluster.
The cloud-based virtual machine cluster comprises a plurality of virtual machines with different operating environments and is used for providing an operating environment with high privacy requirement and harsh system environment requirement;
the cloud-based container cluster is composed of a plurality of lightweight simulation containers and used for providing a lightweight operation environment without special requirements.
The above-mentioned radiation-hardening resistant collaborative design-simulation system based on cloud, the design-simulation support system includes a message-based middleware system and a design-simulation auxiliary module group, wherein:
the message-based middleware system adopts a bus/component architecture to realize communication and data transmission among various design-simulation nodes and various modules of a design-simulation auxiliary module group, and comprises a message server, a message bus and component middleware; the message server is used for receiving the registration of the component middleware, analyzing and marking the received message sent by the component middleware and sending the message to a message bus;
the message bus is used for issuing the messages marked and processed by the message server to each component middleware; the component middleware is a component responsible for receiving and sending messages on each module of the design-simulation auxiliary module group, is used for receiving messages sent by a message bus and matched with a routing key of the component middleware, and sends the messages to the affiliated functional module for processing;
the design-simulation auxiliary module group comprises a data conversion module, a resource scheduling module, a task decomposition module, a task scheduling module, a resource monitoring module, a task flow control module, a model storing and forwarding module and a log module; the data conversion module is used for completing the conversion of the output result of one piece of anti-radiation reinforcement design-simulation software to the input format of the other piece of anti-radiation reinforcement design-simulation software; the resource scheduling module is used for providing virtual machine or container resources required by the scheduling of the design-simulation task and a design-simulation environment; the task decomposition module is used for decomposing the design-simulation task into a plurality of subtasks which can be executed by single design-simulation software or a design-simulation auxiliary module; the task scheduling module comprises a task scheduling queue and is used for scheduling a plurality of design-simulation tasks; the resource monitoring module is used for monitoring the use condition of resources; the task flow control module is used for controlling the execution sequence of the subtasks; the model storing and forwarding module is used for storing a result of design-simulation completion to a database and forwarding and executing required model files and parameters; and the log module is used for recording logs generated by executing tasks each time.
In the above radiation hardening cooperative design-simulation system based on cloud, the unified database module of the platform includes a database middleware and a plurality of heterogeneous databases, wherein:
the database middleware is used for providing a uniform interface for accessing and managing a plurality of heterogeneous databases;
the heterogeneous databases comprise a component radiation effect library, an electronic model library, a radiation source library, a material library and a result library, and are used for storing parameters and model files required by the anti-radiation reinforcement design-simulation and the result output by the anti-radiation reinforcement design-simulation.
A radiation-resistant reinforcement collaborative design-simulation method based on cloud is realized by a design-simulation support system, a front-end system and a platform unified database module which are operated on a cloud environment provided by a basic platform system, and comprises the following steps:
(1) the front-end system acquires an anti-radiation reinforcement collaborative design-simulation task:
the front-end system acquires parameters, privacy requirements and model files required by the anti-radiation reinforcement design-simulation input by a user to obtain an anti-radiation reinforcement collaborative design-simulation task;
(2) the task decomposition module decomposes and sends the anti-radiation reinforcement collaborative design-simulation task:
(2a) the task decomposition module decomposes the anti-radiation reinforcement collaborative design-simulation task according to categories to obtain a plurality of subtasks of three types of design, simulation and model conversion, and sends a decomposition result to the message server in a message form through the component middleware of the decomposition module;
(2b) the message server analyzes the message containing the decomposition result, marks a routing key of the task flow control module on the analyzed message, and sends the marked message to the design-simulation auxiliary module group through the message bus;
(3) the task flow control module performs flow control on a plurality of subtasks and sends the following steps:
(3a) the component middleware of the task flow control module judges whether the message is the message sent to the task flow control module by checking the routing key of the received message, if so, the message is analyzed to obtain a plurality of subtasks, otherwise, the message is discarded;
(3b) the task flow control module performs flow control on the multiple subtasks according to the sequence of the radiation-resistant reinforced design-simulation to obtain an execution sequence table of the multiple subtasks, and sends a first subtask in the execution sequence table to the message server in a message form through the component middleware of the task flow control module;
(3c) the message server analyzes the message containing the first subtask, marks a routing key of the task scheduling module on the analyzed message, and sends the marked message to the design-simulation auxiliary module group through a message bus;
(4) the task scheduling module performs task scheduling on the first subtask and sends the first subtask:
(4a) the component middleware of the task scheduling module judges whether the message is the message sent to the task scheduling module or not by checking the routing key of the received message, if so, the message is analyzed to obtain a first subtask, otherwise, the message is discarded;
(4b) the task scheduling module adds a first subtask into a scheduling queue, sets the first subtask to be schedulable when resources required by the execution of the first subtask are free, and sends the first subtask set to be schedulable to a message server in a message form through component middleware of the task scheduling module;
(4c) the message server analyzes the message containing the first subtask set to be in a schedulable state, marks a routing key of the resource scheduling module on the analyzed message, and sends the marked message to the design-simulation auxiliary module group through the message bus;
(5) the resource scheduling module schedules resources for the first subtask:
(5a) the component middleware of the resource scheduling module judges whether the message is the message sent to the resource scheduling module or not by checking the routing key of the received message, if so, the message is analyzed to obtain a first subtask, otherwise, the message is discarded;
(5b) the resource scheduling module is a first subtask with a requirement on privacy or operating system sensitivity, the resources are scheduled from the cloud-based virtual machine cluster, the resources are scheduled from the cloud-based container cluster for a schedulable subtask without a requirement on privacy or operating system sensitivity, and when the first subtask is a design type subtask, the GPU resources are scheduled for the first subtask through the GPU acceleration module to obtain the resources of the first subtask;
(6) the storage and forwarding module acquires a model file and parameters required by the first subtask:
the storage forwarding module initiates a request to the platform unified database module, and takes the response of the platform unified database module to the request as parameters and model files required by the first subtask;
(7) the storage and forwarding module stores the execution result of the first subtask executed by the resource of the first subtask on the basic platform into the platform unified database module;
(8) the task flow control module judges whether all the subtasks in the execution sequence table are executed completely:
the task flow control module removes the first executed subtask from the execution sequence table, and judges whether the execution sequence table is empty, if yes, step (11) is executed, otherwise, step (9) is executed;
(9) the task flow control module performs flow control on other subtasks in the execution sequence table after the first subtask is removed, and sends the flow control result:
the task flow control module performs flow control on other subtasks in the execution sequence table after removing the first subtask to obtain a new execution sequence table, and the component middleware of the task flow control module sends the first subtask in the new execution sequence table to the message server in a message form;
(10) the message server analyzes and marks the message containing the first subtask and then sends the message:
the message server analyzes the message containing the first subtask, marks the routing key of the task scheduling module on the analyzed message, sends the marked message to the design-simulation auxiliary module group through the message bus, and executes the step (4);
(11) the front-end system displays the design-simulation results obtained from the platform unified database module.
Compared with the prior art, the invention has the following advantages:
1) the task flow control module can control the software in the field of anti-radiation reinforcement to sequentially execute tasks on the cloud-based virtual machine or container according to the anti-radiation reinforcement design-simulation flow strictly, complete the cooperative work of all the software of anti-radiation reinforcement design-simulation, and effectively improve the efficiency of anti-radiation reinforcement design simulation.
2) The GPU acceleration module accelerates the design task, and further improves the speed of anti-radiation reinforcement design-simulation.
3) The resource scheduling module can automatically schedule resources for the anti-radiation reinforcement design-simulation task according to task categories and privacy requirements, the resources comprise two resources, namely a cloud-based virtual machine and a container, the problems that simulation tool software is incompatible and the utilization rate of simulation resources is low in the conventional cloud simulation system are solved, and the utilization rate of the simulation resources is improved while the system compatibility with the simulation tool software is ensured.
4) The platform unified database module provides a unified interface for a plurality of heterogeneous databases, simplifies the development difficulty of a data access part, improves the efficiency of program development, covers a plurality of types of databases, and facilitates the integration of the databases.
Drawings
FIG. 1 is a schematic diagram of the overall architecture of the collaborative design-simulation system according to the present invention;
FIG. 2 is a diagram of a message-based intermediate system architecture of the present invention;
FIG. 3 is a block diagram of the unified database of the present invention;
fig. 4 is a flowchart of the implementation of the collaborative design-simulation method according to the present invention.
Detailed Description
The invention is described in further detail below with reference to the figures and specific examples.
Referring to fig. 1, a cloud-based anti-radiation reinforcement collaborative design-simulation system includes a base platform system, a design-simulation support system, a front-end system, and a platform unified database module, wherein:
the basic platform system is used for providing a cloud-based operating environment for the design-simulation supporting system, the front-end system and the platform unified database module and comprises basic cloud resources, a cloud-based virtual machine cluster and a cloud-based container cluster. Wherein:
the basic cloud resources are used for providing operating environments needed by the cloud-based virtual machine cluster and the cloud-based container cluster.
The cloud-based virtual machine cluster comprises a plurality of virtual machines with different operating environments and is used for providing an operating environment with high privacy requirement and harsh system environment requirement;
the cloud-based container cluster consists of a plurality of lightweight simulation containers and is used for providing a lightweight operation environment without special requirements;
the design-simulation support system comprises a message-based middleware system and a design-simulation auxiliary module group, wherein:
referring to fig. 2, the message-based middleware system, using a "bus/component" architecture, implements communication and data transmission between each design-simulation node and each module of the design-simulation auxiliary module group, including a message server, a message bus and component middleware;
the message server is used for receiving the registration of the component middleware, analyzing and marking the received message sent by the component middleware and sending the message to a message bus;
the message bus is used for issuing the messages marked and processed by the message server to each component middleware;
the component middleware is a component responsible for receiving and sending messages on each module of the design-simulation auxiliary module group, is used for receiving messages sent by a message bus and matched with a routing key of the component middleware, and sends the messages to the affiliated functional module for processing;
the message server and the message bus implement a bus part in a "bus/component" architecture, and the component middleware and the modules to which it belongs implement a component part in the "bus/component" architecture. The delivery of messages takes a "publish-subscribe" mode. Registration of the component middleware on the message server results in a unique routing key that serves as an identifier of the message subscription. When a message is sent to the message server, the message server can carry out simple analysis on the message, know the type of the message, mark the message with a routing key of a module capable of processing the message, the message bus is only responsible for sending the marked message, each component middleware can receive the message, judge whether the routing key marked by the message is consistent with the message bus, receive the message if the routing key marked by the message is consistent with the message bus, and not receive the message if the routing key marked by the message bus is inconsistent with the message bus.
The design-simulation auxiliary module group comprises a data conversion module, a resource scheduling module, a task decomposition module, a task scheduling module, a resource monitoring module, a task flow control module, a model storing and forwarding module and a log module. Wherein:
the data conversion module is used for completing the conversion of an output result of one design-simulation software to an input format of another design-simulation software, and comprises an MCNP (model-aided design language) auxiliary modeling module and a netlist file analysis module based on an IGES (information system integration standard), wherein the MCNP auxiliary modeling module based on the IGES is used for converting a three-dimensional CAD (computer-aided design) model output by a PRO/E (PRO/electronic engineering) tool into a model file based on an IGES protocol, and rapidly generating an MCNP input file to replace parameters required by manual input of the MCNP; the netlist file analysis module is used for analyzing and converting a netlist file output by the orCAD tool to generate input required by the SystemVison simulation tool.
The resource scheduling module is used for providing virtual machine or container resources required by the execution of the design-simulation task and a design-simulation environment, scheduling an idle container or virtual machine from the container cluster or the virtual machine cluster according to the requirements of the subtask simulation environment (such as the requirements of tool software for executing the subtask on an operating system) and the privacy requirements of a user, and selecting whether to schedule virtual GPU resources for the subtask according to whether the subtask is a simulation design type subtask;
the task decomposition module is used for decomposing the design-simulation task into subtasks which can be executed by single design-simulation software or a design-simulation auxiliary module, and sending the decomposed result to the task flow control module;
the task scheduling module comprises a task scheduling queue and is used for scheduling a plurality of design-simulation tasks. And the task scheduling module is used for scheduling the design-simulation task selection task according to the state of the resources required by the tasks in the scheduling queue.
The resource monitoring module is used for monitoring the use condition of resources, such as the use condition of virtual machine resources in a virtual machine cluster and the use condition of container resources in a container cluster and the use condition of GPU resources;
the task flow control module is used for controlling the execution sequence of the subtasks;
the model storing and forwarding module is used for storing a result of design-simulation completion to a database and forwarding the result to a next module needing the result;
and the log module is used for recording logs generated by executing the tasks each time so as to analyze the execution condition of the tasks by the user.
The front-end system is used for acquiring the input of anti-radiation reinforcement design-simulation parameters and model files, displaying the state and result of design-simulation, and providing a virtual machine and container management interface and a user management interface;
the platform unified database module is used for storing model files and parameters required by the anti-radiation reinforcement design-simulation and results of the anti-radiation reinforcement design-simulation output, and providing a unified data access and management interface for the basic platform system, the design-simulation support system and the front-end system.
The platform unified database module described with reference to fig. 4 includes a database middleware and a plurality of heterogeneous databases, wherein:
the database middleware is used for providing a uniform interface for accessing and managing a plurality of heterogeneous databases. The database middleware is realized according to a three-layer architecture, and the upper layer is a query processing layer and provides: SQL analysis function-unified processing application submitted request, SQL interception function-interception of analyzed abnormal and wrong statements, SQL routing function-selection of appropriate database according to request; the middle layer is mainly responsible for SQL/result pushing function of the request/result transmission layer; the lower layer is a mixed storage layer, which is a database connection pool realized based on JDBC technology, contains a driver capable of various types of databases and is responsible for connecting a plurality of heterogeneous databases.
The heterogeneous databases comprise a component radiation effect library, an electronic model library, a radiation source library, a material library and a result library, and are used for storing parameters and model files required by the anti-radiation reinforcement design-simulation and the result output by the anti-radiation reinforcement design-simulation.
Referring to fig. 4, a cloud-based anti-radiation reinforcement collaborative design-simulation method implemented by a design-simulation support system, a front-end system and a platform unified database module operating on a cloud environment provided by a base platform system includes the following steps:
(1) the front-end system acquires an anti-radiation reinforcement collaborative design-simulation task:
the front-end system acquires parameters, privacy requirements and model files required by the anti-radiation reinforcement design-simulation input by a user to obtain an anti-radiation reinforcement collaborative design-simulation task;
(2) the task decomposition module decomposes and sends the anti-radiation reinforcement collaborative design-simulation task:
(2a) the task decomposition module decomposes the anti-radiation reinforcement collaborative design-simulation task according to categories to obtain a plurality of subtasks of three types of design, simulation and model conversion, and sends a decomposition result to the message server in a message form through the component middleware of the decomposition module;
(2b) the message server analyzes the message containing the decomposition result, marks a routing key of the task flow control module on the analyzed message, and sends the marked message to the design-simulation auxiliary module group through the message bus;
(3) the task flow control module performs flow control on a plurality of subtasks and sends the following steps:
(3a) the component middleware of the task flow control module judges whether the message is the message sent to the task flow control module by checking the routing key of the received message, if so, the message is analyzed to obtain a plurality of subtasks, otherwise, the message is discarded;
(3b) and the task flow control module performs flow control on the plurality of subtasks according to the sequence of the radiation-resistant reinforced design-simulation to obtain an execution sequence list of the plurality of subtasks, and sends the first subtask in the execution sequence list to the message server in a message form through the component middleware of task flow control.
(3c) The message server analyzes the message containing the first subtask, marks a routing key of the task scheduling module on the analyzed message, and sends the marked message to the design-simulation auxiliary module group through a message bus;
(4) the task scheduling module performs task scheduling on the first subtask and sends the first subtask:
(4a) the component middleware of the task scheduling module judges whether the message is the message sent to the task scheduling module or not by checking the routing key of the received message, if so, the message is analyzed to obtain a first subtask, otherwise, the message is discarded;
(4b) the task scheduling module adds a first subtask into a scheduling queue, sets the first subtask to be schedulable when resources required by the execution of the first subtask are free, and sends the first subtask set to be schedulable to a message server in a message form through component middleware of the task scheduling module;
(4c) the message server analyzes the message containing the first subtask set to be in a schedulable state, marks a routing key of the resource scheduling module on the analyzed message, and sends the marked message to the design-simulation auxiliary module group through the message bus;
(5) the resource scheduling module schedules and executes the required resources for the scheduled subtasks:
(5a) the component middleware of the resource scheduling module judges whether the message is the message sent to the resource scheduling module or not by checking the routing key of the received message, if so, the message is analyzed to obtain a first subtask, otherwise, the message is discarded;
(5b) the resource scheduling module is a first subtask with a requirement on privacy or operating system sensitivity, the resources are scheduled from the cloud-based virtual machine cluster, the resources are scheduled from the cloud-based container cluster for a schedulable subtask without a requirement on privacy or operating system sensitivity, and when the schedulable subtask is a design type subtask, the GPU resources are scheduled for the schedulable subtask through the GPU acceleration module to obtain resources for executing the first subtask;
(6) the storage and forwarding module acquires a model file and parameters required by the first subtask:
the storage forwarding module initiates a request to the platform unified database module, and takes the response of the platform unified database module to the request as parameters and model files required by the first subtask;
(7) the resource executing the first subtask executes the first subtask on the basic platform and stores the execution result through the storage and forwarding module:
the resource executing the first subtask executes the first subtask on the basic platform, and after the execution is finished, the execution result is stored in the platform unified database module through the storage and forwarding module;
(8) the task flow control module judges whether all the subtasks in the execution sequence table are executed completely:
the task flow control module removes the executed subtasks from the execution sequence table, judges whether the execution sequence table is empty, if the execution sequence table is empty, executes the step (10), and if the execution sequence table is not empty, executes the step (9);
(9) the task flow control module performs flow control on a plurality of subtasks in the sequence table and sends the following steps:
(9a) sending the first subtask in the execution sequence table to a message server in a message form through a component middleware controlled by a task flow;
(9b) the message server analyzes the message containing the first subtask, marks a routing key of the task scheduling module on the analyzed message, and sends the marked message to the design-simulation auxiliary module group through a message bus;
(9c) executing the step (4) to the step (8);
(10) and the design-simulation task management module of the front-end system displays the design-simulation result obtained from the platform unified database module.
Claims (1)
1. A radiation-resistant reinforcement collaborative design-simulation method based on cloud is characterized in that the method is realized by a design-simulation support system, a front-end system and a platform unified database module which are operated on a cloud environment provided by a basic platform system, and comprises the following steps:
(1) the front-end system acquires an anti-radiation reinforcement collaborative design-simulation task:
the front-end system acquires parameters, privacy requirements and model files required by the anti-radiation reinforcement design-simulation input by a user to obtain an anti-radiation reinforcement collaborative design-simulation task;
(2) the task decomposition module decomposes and sends the anti-radiation reinforcement collaborative design-simulation task:
(2a) the task decomposition module decomposes the anti-radiation reinforcement collaborative design-simulation task according to categories to obtain a plurality of subtasks of three types of design, simulation and model conversion, and sends a decomposition result to the message server in a message form through the component middleware of the decomposition module;
(2b) the message server analyzes the message containing the decomposition result, marks a routing key of the task flow control module on the analyzed message, and sends the marked message to the design-simulation auxiliary module group through the message bus;
(3) the task flow control module performs flow control on a plurality of subtasks and sends the following steps:
(3a) the component middleware of the task flow control module judges whether the message is the message sent to the task flow control module by checking the routing key of the received message, if so, the message is analyzed to obtain a plurality of subtasks, otherwise, the message is discarded;
(3b) the task flow control module performs flow control on the multiple subtasks according to the sequence of the radiation-resistant reinforced design-simulation to obtain an execution sequence table of the multiple subtasks, and sends a first subtask in the execution sequence table to the message server in a message form through the component middleware of the task flow control module;
(3c) the message server analyzes the message containing the first subtask, marks a routing key of the task scheduling module on the analyzed message, and sends the marked message to the design-simulation auxiliary module group through a message bus;
(4) the task scheduling module performs task scheduling on the first subtask and sends the first subtask:
(4a) the component middleware of the task scheduling module judges whether the message is the message sent to the task scheduling module or not by checking the routing key of the received message, if so, the message is analyzed to obtain a first subtask, otherwise, the message is discarded;
(4b) the task scheduling module adds a first subtask into a scheduling queue, sets the first subtask to be schedulable when resources required by the execution of the first subtask are free, and sends the first subtask set to be schedulable to a message server in a message form through component middleware of the task scheduling module;
(4c) the message server analyzes the message containing the first subtask set to be in a schedulable state, marks a routing key of the resource scheduling module on the analyzed message, and sends the marked message to the design-simulation auxiliary module group through the message bus;
(5) the resource scheduling module schedules resources for the first subtask:
(5a) the component middleware of the resource scheduling module judges whether the message is the message sent to the resource scheduling module or not by checking the routing key of the received message, if so, the message is analyzed to obtain a first subtask, otherwise, the message is discarded;
(5b) the resource scheduling module is a first subtask with a requirement on privacy or operating system sensitivity, the resources are scheduled from the cloud-based virtual machine cluster, the resources are scheduled from the cloud-based container cluster for a schedulable subtask without a requirement on privacy or operating system sensitivity, and when the first subtask is a design type subtask, the GPU resources are scheduled for the first subtask through the GPU acceleration module to obtain the resources of the first subtask;
(6) the storage and forwarding module acquires a model file and parameters required by the first subtask:
the storage forwarding module initiates a request to the platform unified database module, and takes the response of the platform unified database module to the request as parameters and model files required by the first subtask;
(7) the storage and forwarding module stores the execution result of the first subtask executed by the resource of the first subtask on the basic platform into the platform unified database module;
(8) the task flow control module judges whether all the subtasks in the execution sequence table are executed completely:
the task flow control module removes the first executed subtask from the execution sequence table, and judges whether the execution sequence table is empty, if yes, step (11) is executed, otherwise, step (9) is executed;
(9) the task flow control module performs flow control on other subtasks in the execution sequence table after the first subtask is removed, and sends the flow control result:
the task flow control module performs flow control on other subtasks in the execution sequence table after removing the first subtask to obtain a new execution sequence table, and the component middleware of the task flow control module sends the first subtask in the new execution sequence table to the message server in a message form;
(10) the message server analyzes and marks the message containing the first subtask and then sends the message:
the message server analyzes the message containing the first subtask, marks the routing key of the task scheduling module on the analyzed message, sends the marked message to the design-simulation auxiliary module group through the message bus, and executes the step (4);
(11) the front-end system displays the design-simulation results obtained from the platform unified database module.
Priority Applications (1)
| Application Number | Priority Date | Filing Date | Title |
|---|---|---|---|
| CN201810051265.2A CN108459900B (en) | 2018-01-19 | 2018-01-19 | Anti-radiation reinforcement collaborative design-simulation system and method based on cloud |
Applications Claiming Priority (1)
| Application Number | Priority Date | Filing Date | Title |
|---|---|---|---|
| CN201810051265.2A CN108459900B (en) | 2018-01-19 | 2018-01-19 | Anti-radiation reinforcement collaborative design-simulation system and method based on cloud |
Publications (2)
| Publication Number | Publication Date |
|---|---|
| CN108459900A CN108459900A (en) | 2018-08-28 |
| CN108459900B true CN108459900B (en) | 2021-06-01 |
Family
ID=63221401
Family Applications (1)
| Application Number | Title | Priority Date | Filing Date |
|---|---|---|---|
| CN201810051265.2A Active CN108459900B (en) | 2018-01-19 | 2018-01-19 | Anti-radiation reinforcement collaborative design-simulation system and method based on cloud |
Country Status (1)
| Country | Link |
|---|---|
| CN (1) | CN108459900B (en) |
Families Citing this family (3)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN109583027B (en) * | 2018-10-31 | 2023-09-26 | 中车工业研究院有限公司 | Simulation system and method based on remote collaboration |
| CN112084015B (en) * | 2020-08-28 | 2023-08-15 | 西藏宁算科技集团有限公司 | Cloud computing-based simulation cloud platform building system and method |
| CN112966426A (en) * | 2021-03-17 | 2021-06-15 | 西安电子科技大学 | Space radiation effect simulation method based on visual editor in Web platform |
Family Cites Families (5)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| US8621613B1 (en) * | 2009-05-26 | 2013-12-31 | Amazon Technologies, Inc. | Detecting malware in content items |
| US10580105B2 (en) * | 2015-05-29 | 2020-03-03 | Intel Corporation | Container access to graphics processing unit resources |
| CN105677446B (en) * | 2016-01-28 | 2019-05-28 | 中国电子科技集团公司第十研究所 | The visual modeling method of Distributed Simulation Platform |
| CN106533772A (en) * | 2016-11-24 | 2017-03-22 | 北京动力机械研究所 | Cloud simulation service method |
| CN106789339B (en) * | 2017-01-19 | 2020-08-25 | 北京仿真中心 | Distributed cloud simulation method and system based on lightweight virtualization framework |
-
2018
- 2018-01-19 CN CN201810051265.2A patent/CN108459900B/en active Active
Non-Patent Citations (2)
| Title |
|---|
| "天河一号"工业设计仿真云平台中间件研究;邓子云等;《中国机械工程》;20150320;第26卷(第6期);第766-772页 * |
| SENDIM for Incremental Development of Cloud Networks: Simulation,Emulation and Deployment Integration Middleware;Pradeeban Kathiravelu等;《2016 IEEE International Conference on Cloud Engineering (IC2E)》;20160602;第143-146页 * |
Also Published As
| Publication number | Publication date |
|---|---|
| CN108459900A (en) | 2018-08-28 |
Similar Documents
| Publication | Publication Date | Title |
|---|---|---|
| Baldassari et al. | PROTOB: An object oriented methodology for developing discrete event dynamic systems | |
| CN108459900B (en) | Anti-radiation reinforcement collaborative design-simulation system and method based on cloud | |
| CN111324610A (en) | Data synchronization method and device | |
| CN102521024B (en) | Job scheduling method based on bioinformation cloud platform | |
| CN111176645A (en) | Power grid big data application-oriented data integration management system and implementation method thereof | |
| CN107632845B (en) | Integrated knowledge cloud service method and system for multi-axis milling of runner blade | |
| CN112115611B (en) | Collaborative simulation management system | |
| CN107239675A (en) | Biological information analysis system based on cloud platform | |
| WO2024012221A1 (en) | Method for creating virtual service shared pool on basis of formatted data stream file base template | |
| CN103810272A (en) | Data processing method and system | |
| Wolf et al. | Automatic performance analysis of MPI applications based on event traces | |
| CN113010598A (en) | Dynamic self-adaptive distributed cooperative workflow system for remote sensing big data processing | |
| CN100588197C (en) | Gridding emulation method and its emulator | |
| CN115495221A (en) | Data processing system and method | |
| CN113934832A (en) | Interactive processing method, device, equipment, medium and program product based on session | |
| CN112016256B (en) | Integrated circuit development platform, method, storage medium and equipment | |
| Mueller et al. | Automatic generation of simulation models for semiconductor manufacturing | |
| Baldassari et al. | PROTOB a hierarchical object-oriented CASE tool for distributed systems | |
| Bianchi et al. | An ASM-based model for grid job management | |
| CN115857918A (en) | Data processing method and device, electronic equipment and storage medium | |
| US11915035B1 (en) | Task state updating method and apparatus, device, and medium | |
| CN115237547A (en) | Unified container cluster hosting system and method for non-intrusive HPC computing cluster | |
| CN112000669B (en) | Environment monitoring data processing method and device, storage medium and terminal | |
| Gonzalez et al. | A simulation-based controller for distributed discrete-event systems with application to flexible manufacturing | |
| CN103543986B (en) | The implementation method and device of the calculating task of CFX |
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 |