CN115604768A - Electromagnetic perception task dynamic migration method, system and terminal based on resource state - Google Patents
Electromagnetic perception task dynamic migration method, system and terminal based on resource state Download PDFInfo
- Publication number
- CN115604768A CN115604768A CN202211514490.8A CN202211514490A CN115604768A CN 115604768 A CN115604768 A CN 115604768A CN 202211514490 A CN202211514490 A CN 202211514490A CN 115604768 A CN115604768 A CN 115604768A
- Authority
- CN
- China
- Prior art keywords
- task
- resource
- resources
- electromagnetic
- equipment
- 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
Images
Classifications
-
- H—ELECTRICITY
- H04—ELECTRIC COMMUNICATION TECHNIQUE
- H04W—WIRELESS COMMUNICATION NETWORKS
- H04W28/00—Network traffic management; Network resource management
- H04W28/16—Central resource management; Negotiation of resources or communication parameters, e.g. negotiating bandwidth or QoS [Quality of Service]
-
- 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
- G06F9/4881—Scheduling strategies for dispatcher, e.g. round robin, multi-level priority queues
-
- 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
- G06F9/50—Allocation of resources, e.g. of the central processing unit [CPU]
- G06F9/5005—Allocation of resources, e.g. of the central processing unit [CPU] to service a request
- G06F9/5027—Allocation of resources, e.g. of the central processing unit [CPU] to service a request the resource being a machine, e.g. CPUs, Servers, Terminals
- G06F9/5038—Allocation of resources, e.g. of the central processing unit [CPU] to service a request the resource being a machine, e.g. CPUs, Servers, Terminals considering the execution order of a plurality of tasks, e.g. taking priority or time dependency constraints into consideration
-
- H—ELECTRICITY
- H04—ELECTRIC COMMUNICATION TECHNIQUE
- H04W—WIRELESS COMMUNICATION NETWORKS
- H04W24/00—Supervisory, monitoring or testing arrangements
- H04W24/02—Arrangements for optimising operational condition
-
- Y—GENERAL TAGGING OF NEW TECHNOLOGICAL DEVELOPMENTS; GENERAL TAGGING OF CROSS-SECTIONAL TECHNOLOGIES SPANNING OVER SEVERAL SECTIONS OF THE IPC; TECHNICAL SUBJECTS COVERED BY FORMER USPC CROSS-REFERENCE ART COLLECTIONS [XRACs] AND DIGESTS
- Y02—TECHNOLOGIES OR APPLICATIONS FOR MITIGATION OR ADAPTATION AGAINST CLIMATE CHANGE
- Y02D—CLIMATE CHANGE MITIGATION TECHNOLOGIES IN INFORMATION AND COMMUNICATION TECHNOLOGIES [ICT], I.E. INFORMATION AND COMMUNICATION TECHNOLOGIES AIMING AT THE REDUCTION OF THEIR OWN ENERGY USE
- Y02D10/00—Energy efficient computing, e.g. low power processors, power management or thermal management
Landscapes
- Engineering & Computer Science (AREA)
- Software Systems (AREA)
- Theoretical Computer Science (AREA)
- Computer Networks & Wireless Communication (AREA)
- Signal Processing (AREA)
- Physics & Mathematics (AREA)
- General Engineering & Computer Science (AREA)
- General Physics & Mathematics (AREA)
- Quality & Reliability (AREA)
- Debugging And Monitoring (AREA)
Abstract
The invention discloses a method, a system and a terminal for dynamically migrating an electromagnetic sensing task based on a resource state, belonging to the field of radio monitoring application and comprising the following steps: based on all electromagnetic perception task information of the current whole network and load information of all edge computing nodes, computing a dynamic migration strategy of the electromagnetic perception task according to the optimal principle of resource utilization rate, and distributing corresponding equipment resources and service resources for the electromagnetic perception task; and dynamically allocating the electromagnetic perception tasks to corresponding edge computing nodes for execution according to the dynamic migration strategy. According to the invention, an intelligent scheduling distribution algorithm with optimal monitoring effect, optimal equipment utilization rate and the like is adopted in the resource distribution management, so that the monitoring efficiency and the equipment utilization rate of the system are improved, the intelligent and automatic level of the system is improved, the use efficiency of various resources of the whole system is greatly improved, the elastic expansion of the whole system can be conveniently realized through calculating dynamic migration, and the health of the system is improved.
Description
Technical Field
The invention relates to the field of radio monitoring application, in particular to a method, a system and a terminal for dynamically migrating an electromagnetic sensing task based on a resource state.
Background
With the acceleration of the penetration of a new generation of radio communication technology represented by 5G communication, WIFI communication, satellite communication and the like into the fields of urban economic construction, social development and the like, the urban electromagnetic environment is increasingly complex, various radio interference events occur occasionally, and the task of effectively managing the air radio wave order is more and more complex and fussy by monitoring the air electromagnetic environment in real time by a radio management department. In recent years, radio management departments in provinces and cities of the whole country actively promote the construction of radio monitoring integrated platforms, atomic service transformation is carried out on various monitoring devices in the existing monitoring network according to technical specifications of ultrashort wave monitoring and management integrated platforms, atomic services are registered to the radio monitoring integrated platforms for unified management and scheduling control, and the management of air radio wave order is powerfully supported.
At present, the radio monitoring integrated platform established in each province and city preliminarily realizes the unified access and scheduling management of the whole network monitoring equipment, but the radio monitoring integrated platform is mainly deployed in a centralized manner, and the pressure of all monitoring task scheduling, equipment data access and data processing is concentrated on a central platform, so that a service bottleneck is easily formed; and if a single point of failure occurs in the central platform, the whole radio monitoring application system is not available. In addition, the existing system cannot reasonably distribute resources according to the type and the state of the electromagnetic sensing task, so that the use efficiency of equipment resources and service resources is reduced, and the elastic expansion of the system is not facilitated.
Disclosure of Invention
The invention aims to solve the problem that a radio monitoring integrated platform in the prior art cannot reasonably distribute resources according to the type and the state of an electromagnetic sensing task, and provides a method, a system and a terminal for dynamically migrating the electromagnetic sensing task based on the resource state.
The purpose of the invention is realized by the following technical scheme:
in a first aspect, a method for dynamically migrating an electromagnetic sensing task based on a resource state is provided, which includes the following steps:
deploying a distributed service bus on all edge computing nodes;
after all equipment resources and service resources are virtualized, uniformly registering the equipment resources and the service resources on the distributed service bus;
acquiring resource state information accessed by each edge computing node, and computing load information of each edge computing node according to the resource state information;
based on all electromagnetic sensing task information of the current whole network and load information of all edge computing nodes, computing a dynamic migration strategy of the electromagnetic sensing task according to the resource utilization rate optimization principle, and distributing corresponding equipment resources and service resources to the electromagnetic sensing task;
and dynamically allocating the electromagnetic perception tasks to corresponding edge computing nodes for execution according to the dynamic migration strategy.
In one example, the virtualization of the device resource comprises:
performing interface abstraction and normalization processing on the monitoring equipment, and mapping the monitoring equipment into virtual equipment;
establishing a corresponding virtual device object through instantiation of the virtual device object;
and carrying out full-network synchronization on the instantiated virtual equipment instance description information to form a global virtual equipment object resource pool.
In one example, the virtualization of the service resources comprises:
and performing atomization service encapsulation on the service function executed by the monitoring equipment according to the minimum granularity, and binding the service function with the virtual equipment object.
In one example, the resource status information includes device resource status information, network resource status information, dynamic ring status information, and service interface status information.
In one example, the calculating load information of each edge computing node according to the resource state information includes:
the distributed service bus deployed on each edge computing node integrates the state information of various resources collected by the node to form state summary information of virtual equipment resources and virtual service resources of the node.
In one example, the calculating the dynamic migration policy of the electromagnetic perception task according to the resource utilization optimization principle includes:
acquiring electromagnetic perception task information;
performing matching calculation of a space domain, a frequency domain, a time domain and a capacity domain according to the task type, the task parameters and the task priority of the electromagnetic perception task;
preliminarily screening out a virtual equipment resource and virtual service resource candidate list meeting task execution requirements;
and finally determining the resources allocated to the electromagnetic perception task according to the optimal monitoring effect or the optimal equipment utilization efficiency.
In one example, the scenario that triggers the calculation of the live migration policy includes:
when the electromagnetic sensing task with higher task priority in the distributed system obtains the relevant resources allocated to the current electromagnetic sensing task, recalculating the dynamic migration strategy for the current electromagnetic sensing task;
when the resources allocated to the current electromagnetic perception task are in failure, recalculating a dynamic migration strategy for the current electromagnetic perception task;
when the current load of the edge computing node executing the electromagnetic perception task is overlarge, the dynamic migration strategy is calculated for the current electromagnetic perception task again, and part of subtasks are selected to be migrated to the edge computing node with the smaller load to be continuously executed.
In one example, dynamically allocating electromagnetic perception tasks to corresponding edge computing nodes for execution according to the dynamic migration policy includes:
and issuing a control right acquisition instruction to the allocated equipment resource to acquire the control right of the equipment resource and the corresponding service resource.
In a second aspect, a resource state-based electromagnetic awareness task live migration system is provided, the system comprising:
the resource virtualization module is used for deploying a distributed service bus on all edge computing nodes, virtualizing all equipment resources and service resources and then uniformly registering the equipment resources and the service resources on the distributed service bus;
the resource state information acquisition module is used for acquiring resource state information accessed by each edge computing node and calculating load information of each edge computing node according to the resource state information;
the dynamic migration strategy calculation module is used for calculating a dynamic migration strategy of the electromagnetic perception task according to the optimal principle of the resource utilization rate and distributing corresponding equipment resources and service resources for the dynamic migration strategy based on all the electromagnetic perception task information of the current whole network and the load information of all the edge calculation nodes;
and the task execution module is used for dynamically allocating the electromagnetic perception task to the corresponding edge computing node for execution according to the dynamic migration strategy.
In a third aspect, a terminal is provided, which includes a memory and a processor, where the memory stores computer instructions executable on the processor, and the processor executes any one of the computer dynamic migration methods when executing the computer instructions.
It should be further noted that, the technical features corresponding to the above options can be combined with each other or replaced to form a new technical solution without conflict.
Compared with the prior art, the invention has the beneficial effects that:
(1) The invention can realize the virtualization management of the resources of the whole system by uniformly registering all the equipment resources and the service resources on the distributed service bus after virtualization, can realize that the radio upper layer application software can directly access the service resources of the whole system after accessing from any node, effectively avoids the problem that the system is unavailable due to the single-point fault of a centralized platform, and greatly improves the availability and the usability of the whole radio monitoring management application system. Meanwhile, a dynamic migration strategy of the electromagnetic sensing task is calculated according to the principle of optimal resource utilization rate, corresponding equipment resources and service resources are distributed to the electromagnetic sensing task, monitoring efficiency and equipment utilization rate are improved, and the intelligent and automatic level of the system is improved in a certain program.
(2) The invention carries out resource virtualization on the edge computing node equipment and the data processing service and the statistical analysis service running on the edge computing node equipment, forms a virtualized resource pool with wider range and more complete capability, and is more favorable for the arrangement and resource scheduling of the electromagnetic sensing task.
(3) According to the invention, the matching calculation of the airspace, the frequency domain, the time domain and the capacity domain is carried out according to the task type, the task parameter and the task priority of the electromagnetic perception task, the resources finally allocated to the electromagnetic perception task are determined according to the optimal monitoring effect or the optimal equipment utilization efficiency selection, the optimal equipment resources are screened out to execute the corresponding perception task, and the use efficiency of the whole network monitoring resources is greatly improved.
(4) In the process of executing the electromagnetic sensing task, the dynamic planning of resource allocation can be carried out by combining the execution condition of the whole system sensing task and the dynamic change condition of the whole system resource, so that the use efficiency of various resources of the whole system is greatly improved; meanwhile, elastic expansion of the whole system can be conveniently realized by calculating dynamic migration, and the robustness of the system is improved.
Drawings
Fig. 1 is a flowchart illustrating a resource state-based electromagnetic sensing task live migration method according to an embodiment of the present invention.
Detailed Description
The technical solutions of the present invention will be described clearly and completely with reference to the accompanying drawings, and it should be understood that the described embodiments are some, but not all embodiments of the present invention. All other embodiments, which can be derived by a person skilled in the art from the embodiments given herein without making any creative effort, shall fall within the protection scope of the present invention.
In addition, the technical features involved in the different embodiments of the present invention described below may be combined with each other as long as they do not conflict with each other.
The invention is mainly based on all the calculation processing task information (including the tasks to be executed and the tasks being executed) of the current whole network and the current load information of all the calculation processing nodes, carries out the dynamic planning of the calculation tasks and the dynamic scheduling of the calculation processing service resources according to the principle of optimal resource utilization rate, and dynamically allocates the calculation processing tasks to the corresponding nodes for execution, thereby realizing the dynamic migration of the calculation processing.
Referring to fig. 1, in an exemplary embodiment, a resource state-based electromagnetic perception task live migration method is provided, which includes the following contents:
deploying a distributed service bus on all edge computing nodes;
after all equipment resources and service resources are virtualized, uniformly registering the equipment resources and the service resources on the distributed service bus;
acquiring resource state information accessed by each edge computing node, and computing load information of each edge computing node according to the resource state information;
based on all electromagnetic perception task information of the current whole network and load information of all edge computing nodes, computing a dynamic migration strategy of the electromagnetic perception task according to the optimal principle of resource utilization rate, and distributing corresponding equipment resources and service resources for the electromagnetic perception task;
and dynamically allocating the electromagnetic perception tasks to corresponding edge computing nodes for execution according to the dynamic migration strategy.
Specifically, after all the device resources and the service resources are virtualized, the device resources and the service resources are uniformly registered on the distributed service bus, so that the virtualized management of the resources of the whole system is realized, the upper-layer application software of the radio can be accessed from any node to directly access the service resources of the whole system, the problem that the system is unavailable due to single-point faults of a centralized platform is effectively solved, and the availability and the usability of the whole radio monitoring management application system are greatly improved. Meanwhile, a dynamic migration strategy of the electromagnetic sensing task is calculated according to the principle of optimal resource utilization rate, corresponding equipment resources and service resources are distributed to the electromagnetic sensing task, monitoring efficiency and equipment utilization rate are improved, and the intelligent and automatic level of the system is improved in a certain program.
Further, the virtualization of the device resource includes:
performing interface abstraction and normalization processing on the monitoring equipment, and mapping the monitoring equipment into virtual equipment;
establishing a corresponding virtual equipment object through instantiation of the virtual equipment object;
and carrying out full network synchronization on the instantiated virtual equipment instance description information to form a global virtual equipment object resource pool.
In one example, the virtualization of the service resources comprises:
and performing atomization service encapsulation on the service function executed by the physical equipment according to the minimum granularity, and binding the service function with the virtual equipment object. Specifically, virtualization of service resources is to perform atomic service encapsulation on business functions such as monitoring device control, data processing, statistical analysis and the like executed on a monitoring device or an edge computing node according to minimum granularity on the basis of virtualization of device resources, bind the business functions with a virtualized device object, uniformly register service resource information to a distributed service bus, and perform global synchronization of all service registration information of the whole system by using a data synchronization mechanism of the distributed service bus to form a virtual service resource pool for the whole system to access.
Furthermore, the resource state information is collected by taking the edge computing node as a unit, and the state information of the resource accessed by the node is collected, wherein the resource state information comprises equipment resource state information, network resource state information, dynamic ring state information and service interface state information.
Wherein, equipment resource state information acquisition includes monitoring facilities state collection and edge calculation node state collection, monitoring facilities state collection mainly through with monitoring facilities last operation equipment control software interface, the information acquisition includes: the working state (working and idle) of the equipment, the fault state (normal and fault), the currently executed monitoring task (idle state is empty) and the like; the edge computing node state acquisition mainly acquires software and hardware running state information of the edge computing node through a system information acquisition interface provided by an operating system (Windows or Linux), and the main information comprises information such as CPU utilization rate, memory utilization rate, current running process number \ thread number, residual disk capacity, current disk IO read-write quantity, current network flow and the like.
The network resource state information collection is through the interface of standard SNMP protocol, with the router, switch interface in the system, the information collection includes: the connection state of the port, the size of data traffic, routing reachable information, etc.
The dynamic loop state information acquisition is realized by interfacing with control software of the environment monitoring equipment and acquiring the on-off state and voltage/current information of a power supply port of the equipment.
The service interface state information acquisition is to interface with atomic service software to acquire the available state of the service interface and the occupied state of the service.
And further, carrying out resource state information synthesis according to the acquired resource state information, wherein the resource state information synthesis comprises resource state information synthesis of each distributed node and resource state information synthesis of the whole system. Wherein, the calculating the load information of each edge computing node according to the resource state information comprises:
the distributed service bus deployed on each edge computing node integrates the state information of various resources collected by the node to form state summary information of virtual equipment resources and virtual service resources of the node. The virtual equipment resource summarization is to associate and integrate the collected equipment state information, the network state information and the dynamic ring state information to obtain virtual equipment resource summarization information. The summary information is divided into two types of virtual resource summary information of the monitoring equipment and virtual resource summary information of the edge computing node. The virtual monitoring equipment resource summary information mainly comprises: the device comprises a working state, a fault state, currently executed monitoring task information, device power supply state information and device network flow information. The virtual resource summary information of the edge computing node mainly comprises: the device comprises a device working state, a fault state, current load information (including CPU utilization rate, memory utilization rate, current running process number \ thread number, residual disk capacity, current disk IO read-write quantity and the like), device power supply state information and device network flow information.
The virtual service resource aggregation is to aggregate the acquired available state of the service interface and the service occupation state according to the binding relationship between the virtual service resources and the virtual equipment resources on the basis of the virtual equipment resource aggregation information, calculate and judge whether the equipment resources carrying service operation can meet the QOS index requirement of service operation, and finally determine the availability of the service resources. The summary information of the virtual service resources comprises service available state, service occupation state, virtual equipment resources depended by service execution and current QOS index value of the service.
The system-wide resource state information synthesis comprises the following steps: and carrying out data synchronization on the virtual equipment resource state information and the virtual service resource state information obtained by comprehensively analyzing each node through a distributed message middleware by using a distributed service bus deployed by each edge computing node, so as to realize comprehensive sharing of the whole system resource state information. On the basis, network state information and routing information reported by each node are combined to form a real-time network topology of the whole system, and reachability and routing information among the nodes is obtained, so that decision support can be provided for subsequent resource scheduling and distribution.
The system also performs resource virtualization on edge computing node equipment, and data processing services and statistical analysis services running on the edge computing node equipment, so that a virtualized resource pool with wider range and more complete capability is formed, and the arrangement and resource scheduling of electromagnetic sensing tasks are facilitated.
Further, the calculating the dynamic migration strategy of the electromagnetic perception task according to the resource utilization optimization principle includes:
acquiring electromagnetic perception task information;
performing matching calculation on a space domain, a frequency domain, a time domain and a capability domain according to the task type, the task parameters and the task priority of the electromagnetic perception task;
preliminarily screening out a virtual equipment resource and virtual service resource candidate list meeting task execution requirements;
and finally determining the resources allocated to the electromagnetic perception task according to the optimal monitoring effect or the optimal equipment utilization efficiency.
Specifically, taking a certain node as an example, the electromagnetic sensing task is received first, the electromagnetic sensing task information issued by a superior node or a cooperative node is received, and the task type and the task parameter are obtained. The task types mainly comprise: the method comprises an electromagnetic environment acquisition task, a cooperative positioning task, an abnormal alarm task, a signal interference task and the like. The task parameters mainly comprise: monitoring frequency range parameters, monitoring geographic area parameters, monitoring task execution time period parameters, and energy service requirement parameters (such as frequency range scanning, signal identification, signal direction finding and the like).
Then, performing resource screening, performing matching calculation on an airspace, a frequency domain, a time domain and a capacity domain according to the type of the received electromagnetic sensing task, the task parameter and the task priority, preliminarily screening out virtual equipment resources and a virtual service resource candidate list which meet task execution requirements, and then determining final allocated resources according to optimal monitoring effect or optimal equipment utilization efficiency selection on the basis, wherein the specific steps are as follows:
s1, primary screening of monitoring equipment resources:
s11, spatial domain screening: firstly, inquiring all monitoring equipment resource candidate lists deployed in a task specified monitoring space area range;
s12, frequency domain screening: on the basis of spatial domain analysis, candidate monitoring equipment resources meeting the monitoring capability requirement of the perception task are further screened out according to the frequency range related to the executed perception task. The method can support monitoring equipment resource combination, namely, a single monitoring equipment resource cannot cover the frequency range of a monitoring task, but the frequency range of the monitoring task can be met by combining a plurality of pieces of equipment;
s13, screening of the capacity domain: on the basis of spatial domain screening and frequency domain screening, further screening equipment resources capable of providing corresponding atomic service resources according to the capability requirements of the monitoring tasks;
s14, time domain screening: on the basis of the screening, according to the execution time period requirement of the task and in combination with the priority of the task, the candidate equipment resources are further screened, and the equipment resources capable of meeting the task execution time requirement are obtained.
S2, secondary screening of monitoring equipment resources: and screening the candidate equipment resources again by adopting the screening with the optimal monitoring effect or the screening with the optimal use efficiency of the monitoring equipment, and determining the equipment resources allocated to the perception task.
S21, optimal screening of monitoring effect: traversing a candidate monitoring equipment resource (or monitoring equipment combined resource) list obtained by preliminary screening, carrying out weighted scoring according to technical indexes such as the coverage area, the scanning speed, the direction finding precision and the like of the monitoring equipment, and finally carrying out sequencing comparison to screen out the monitoring equipment resource with the optimal monitoring effect;
s22, optimal screening of the utilization rate of the monitoring equipment: traversing the candidate monitoring equipment resource (or monitoring equipment combined resource) list obtained by preliminary screening, calculating the utilization rate of the candidate monitoring equipment resource in different allocation schemes according to the information of the current executed task of the monitoring equipment, the list of the tasks to be executed and the like and by combining the requirement of the task execution time period, and determining the sensing equipment resource allocated to the sensing task and the time period for executing the task on the basis of the principle that the equipment utilization rate obtained by all the candidate monitoring equipment comprehensively is optimal.
S3, screening of computing node equipment resources: and screening the computing node equipment resources executed by the electromagnetic sensing task on the basis of completing the resource policy and allocation of the monitoring equipment. The method comprises the following specific steps:
s31, screening a capability domain: according to the functional requirements of the electromagnetic perception task, task priority information and the available state of service provided by each node, screening computing node equipment (or computing node equipment combination) meeting the functional service requirements of task computing processing and statistical analysis to obtain primary candidate computing equipment resources capable of meeting the computing processing capacity requirements of the perception task;
s32, calculating a service QOS index: according to the QOS index requirements of the electromagnetic perception task on the calculation processing service and the statistical analysis service, traversing the candidate calculation equipment resource (or calculation equipment combined resource) list obtained by preliminary screening, calculating to obtain the current QOS index of the service provided by each calculation equipment resource, and further screening out the calculation node equipment resources capable of meeting the QOS index requirements of the service;
s33, optimal screening of service quality: on the basis of the computing equipment resource screening, the computing equipment resources are respectively subjected to service QOS index sequencing according to different service types, and the computing node equipment resource with the highest service QOS index in each type of service is screened out to be used as an execution node of the service. The method adopts an intelligent scheduling and distributing algorithm with optimal monitoring effect, optimal equipment utilization rate and the like in the resource distributing management, improves the monitoring efficiency and the equipment utilization rate of the system, and improves the intelligent and automatic level of the system on a certain program.
Further, the situation of triggering the calculation of the dynamic migration policy includes:
when an electromagnetic sensing task with higher task priority in the distributed system obtains related resources allocated to the current electromagnetic sensing task, recalculating a dynamic migration strategy for the current electromagnetic sensing task, wherein the original equipment or service resources occupied by the task are occupied by other tasks with higher priority; and the task obtains new equipment or service resources through resource scheduling, and the dynamic migration of the virtual resources is carried out.
When the resources allocated to the current electromagnetic sensing task are in failure, the current electromagnetic sensing task cannot be continuously executed, a task scheduling program needs to start to reselect equipment resources and service resources, recalculate a dynamic migration strategy for the current electromagnetic sensing task, and select the resources meeting the requirements to continuously execute the task;
when the current load of the edge computing node executing the electromagnetic perception task is overlarge, the dynamic migration strategy is calculated for the current electromagnetic perception task again, and part of subtasks are selected to be migrated to the edge computing node with the smaller load to be continuously executed.
Further, according to the dynamic migration policy, dynamically allocating the electromagnetic sensing task to a corresponding edge computing node for execution, including:
and issuing a control right acquisition instruction to the allocated equipment resource to acquire the control right of the equipment resource and the corresponding service resource. Specifically, after the resources are selected, the control right of the resources is acquired, and a control right acquisition instruction is issued to the allocated device resources to acquire the control right of the device resources and the corresponding service resources. If the equipment resource is idle resource, the electromagnetic sensing task directly obtains the control right of the equipment resource and the corresponding service resource; if the equipment resource is currently executing other tasks, because the task priority is compared during resource screening, the electromagnetic sensing task directly robs the control right of the equipment resource and the corresponding service resource, and simultaneously triggers the calculation dynamic migration process of the robed resource task.
And finally, the electromagnetic perception task script and the distributed perception resource list are issued to a task script execution engine, the task script execution engine interprets the task script and calls corresponding service resources to execute the task according to the task script flow. Specifically, different task execution scripts are defined in advance according to the types of different electromagnetic perception tasks, perception service resources of corresponding edge computing nodes are distributed for the different task execution scripts, the execution scripts of the electromagnetic perception tasks are flexibly defined, a current task execution script matched with the current electromagnetic perception task is automatically found from a task script template library, and automatic matching is achieved; and then, issuing the current task execution script to a script execution engine of a corresponding edge computing node, and automatically executing the current task execution script by the script execution engine to realize a corresponding service function. The method adopts the script arrangement mode, only the corresponding script file needs to be stored and updated after the process modification and adjustment is carried out, and in the script execution process, the operations of suspension, continuation, termination and the like of the task can be controlled through the script execution engine, so that the task process arrangement is more flexible and convenient.
The script execution engine adopts a C + + and Python mixed programming mode, and a Python execution engine and related functional components are embedded in a C + + host program. The functions of perception task decomposition, resource scheduling and the like which need dynamic change are realized by Python. The engine unifies the script entry function ScriptMain (), from which any workflow initiation is executed. The engine framework capable of executing the Python script is developed through C + +, the Python script is used for realizing specific execution logic and partial data processing functions of the perception task, and therefore flexible customization of the workflow of the perception task is achieved. The specific implementation mode of the Python script workflow engine is as follows: a Python virtual machine is embedded in a C + + host program, and a Python secondary development kit is integrated. After the C + + host program initializes the Python virtual machine, the Python script can be called. Multi-language development involves two parts: processing complex data with high performance requirements by C + + and exporting an interface for Python calling; and the part with low requirements on flexibility and performance is realized by Python, and the embedded Python virtual machine is called by a C + + host program to execute a Python task script to complete the operation of the whole workflow.
The script execution engine automatically executing the current task execution script comprises:
importing a script module by using PyImport _ ImportModule;
obtaining module specific method information using PyObject _ GetAttrString;
converting input parameters by using Py _ VaBuildValue;
calling a specific method using PyObject _ CallObject;
the return result of the PyArg _ Parse conversion method was used.
Further, when resources such as calculation, storage, IO and the like of the task execution node reach a set threshold value in the task execution process, new execution node resources are obtained through resource scheduling, and the task is automatically switched to the new execution node to run.
Further, the execution of the computational live migration for the interrupted electromagnetic sensing task is as follows:
(1) Electromagnetically aware task interruption: and the task scheduler informs the task script engine to interrupt the execution of the electromagnetic sensing task and records the context information (including the line number, the variable value and the like of the currently executed electromagnetic sensing task) of the currently executed electromagnetic sensing task.
(2) Analyzing the requirement of task resources: and analyzing the reason that the currently executed electromagnetic sensing task is interrupted and the related resource requirements to form an electromagnetic sensing task resource requirement list reporting task scheduling program.
(3) Scheduling and allocating: the task scheduling program issues an electromagnetic perception task resource demand list to the resource scheduling and distributing program, starts resource distribution and obtains the control right of the distributed resources, and the specific distribution step refers to resource scheduling and distributing step 4.
(4) And (3) task recovery: the task scheduler issues a task recovery execution notification message to the task script engine, and the task script engine recovers the field information of the interrupted task.
(5) And (3) task execution: and the task script engine continues to execute the electromagnetic sensing task from the interrupted position in the task script, and schedules the reallocated equipment resources to execute corresponding control and calculation services, thereby realizing the dynamic migration of calculation in the task execution process.
In the process of executing the electromagnetic sensing task, the dynamic planning of resource allocation can be carried out by combining the execution condition of the whole system sensing task and the dynamic change condition of the whole system resource, so that the use efficiency of various resources of the whole system is greatly improved; meanwhile, elastic expansion of the whole system can be conveniently realized by calculating dynamic migration, and the robustness of the system is improved.
In another exemplary embodiment, a resource state-based electromagnetic perception task live migration system is provided, the system comprising:
the resource virtualization module is used for deploying a distributed service bus on all edge computing nodes, virtualizing all equipment resources and service resources and then uniformly registering the equipment resources and the service resources on the distributed service bus;
the resource state information acquisition module is used for acquiring resource state information accessed by each edge computing node and calculating load information of each edge computing node according to the resource state information;
the dynamic migration strategy calculation module is used for calculating a dynamic migration strategy of the electromagnetic sensing task according to the resource utilization rate optimal principle based on all electromagnetic sensing task information of the current whole network and load information of all edge calculation nodes, and distributing corresponding equipment resources and service resources to the dynamic migration strategy;
and the task execution module is used for dynamically allocating the electromagnetic perception task to the corresponding edge computing node for execution according to the dynamic migration strategy.
In another exemplary embodiment, a terminal is provided, which includes a memory and a processor, the memory having stored thereon computer instructions executable on the processor, the processor executing any of the computer dynamic migration methods when executing the computer instructions.
The processor may be a single or multi-core central processing unit or a specific integrated circuit, or one or more integrated circuits configured to implement the present invention.
Embodiments of the subject matter and the functional operations described in this specification can be implemented in: tangibly embodied computer software or firmware, computer hardware including the structures disclosed in this specification and their structural equivalents, or a combination of one or more of them. Embodiments of the subject matter described in this specification can be implemented as one or more computer programs, i.e., one or more modules of computer program instructions, encoded on a tangible, non-transitory program carrier for execution by, or to control the operation of, data processing apparatus. Alternatively or additionally, the program instructions may be encoded on an artificially generated propagated signal, e.g., a machine-generated electrical, optical, or electromagnetic signal, that is generated to encode and transmit information to suitable receiver apparatus for execution by the data processing apparatus.
The processes and logic flows described in this specification can be performed by one or more programmable computers executing one or more computer programs to perform corresponding functions by operating on input data and generating output. The processes and logic flows can also be performed by, and apparatus can also be implemented as, special purpose logic circuitry, e.g., an FPGA (field programmable gate array) or an ASIC (application-specific integrated circuit).
Processors suitable for the execution of a computer program include, by way of example, both general and/or special purpose microprocessors, or any other type of central processing unit. Generally, a central processing unit will receive instructions and data from a read-only memory and/or a random access memory. The basic components of a computer include a central processing unit for implementing or executing instructions and one or more memory devices for storing instructions and data. Generally, a computer will also include, or be operatively coupled to receive data from or transfer data to, or both, one or more mass storage devices for storing data, e.g., magnetic, magneto-optical disks, or optical disks. However, a computer does not necessarily have such a device. Moreover, a computer may be embedded in another device, e.g., a mobile telephone, a Personal Digital Assistant (PDA), a mobile audio or video player, a game console, a Global Positioning System (GPS) receiver, or a portable storage device such as a Universal Serial Bus (USB) flash drive, to name a few.
While this specification contains many specific implementation details, these should not be construed as limitations on the scope of any invention or of what may be claimed, but rather as descriptions of features specific to particular embodiments of particular inventions. Certain features that are described in this specification in the context of separate embodiments can also be implemented in combination in a single embodiment. In other instances, features described in connection with one embodiment may be implemented as discrete components or in any suitable subcombination. Moreover, although features may be described above as acting in certain combinations and even initially claimed as such, one or more features from a claimed combination can in some cases be excised from the combination, and the claimed combination may be directed to a subcombination or variation of a subcombination.
Similarly, while operations are depicted in the drawings in a particular order, this should not be understood as requiring that such operations be performed in the particular order shown or in sequential order, or that all illustrated operations be performed, to achieve desirable results. In some cases, multitasking and parallel processing may be advantageous. Moreover, the separation of various system modules and components in the embodiments described above should not be understood as requiring such separation in all embodiments, and it should be understood that the described program components and systems can generally be integrated together in a single software product or packaged into multiple software products.
The above detailed description is for the purpose of describing the invention in detail, and it should not be construed that the detailed description is limited to the description, and it will be apparent to those skilled in the art that various modifications and substitutions can be made without departing from the spirit of the invention.
Claims (10)
1. The electromagnetic perception task dynamic migration method based on the resource state is characterized by comprising the following steps:
deploying a distributed service bus on all edge computing nodes;
after all equipment resources and service resources are virtualized, uniformly registering the equipment resources and the service resources on the distributed service bus;
acquiring resource state information accessed by each edge computing node, and computing load information of each edge computing node according to the resource state information;
based on all electromagnetic sensing task information of the current whole network and load information of all edge computing nodes, computing a dynamic migration strategy of the electromagnetic sensing task according to the resource utilization rate optimization principle, and distributing corresponding equipment resources and service resources to the electromagnetic sensing task;
and dynamically allocating the electromagnetic perception tasks to corresponding edge computing nodes for execution according to the dynamic migration strategy.
2. The resource state-based electromagnetic perception task live migration method according to claim 1, wherein virtualization of the device resource includes:
performing interface abstraction and normalization processing on the monitoring equipment, and mapping the monitoring equipment into virtual equipment;
establishing a corresponding virtual equipment object through instantiation of the virtual equipment object;
and carrying out full-network synchronization on the instantiated virtual equipment instance description information to form a global virtual equipment object resource pool.
3. The resource state-based electromagnetic perception task live migration method according to claim 2, wherein the virtualization of the service resource includes:
and performing atomization service encapsulation on the service function executed by the monitoring equipment according to the minimum granularity, and binding the service function with the virtual equipment object.
4. The resource state-based electromagnetic perception task dynamic migration method of claim 1, wherein the resource state information includes device resource state information, network resource state information, dynamic ring state information, and service interface state information.
5. The method for dynamically migrating electromagnetic perception tasks based on resource states according to claim 4, wherein the calculating load information of each edge computing node according to the resource state information includes:
the distributed service bus deployed on each edge computing node integrates the state information of various resources collected by the node to form state summary information of virtual equipment resources and virtual service resources of the node.
6. The electromagnetic perception task dynamic migration method based on the resource state as claimed in claim 1, wherein the calculating of the dynamic migration strategy of the electromagnetic perception task according to the resource utilization optimization principle includes:
acquiring electromagnetic perception task information;
performing matching calculation of a space domain, a frequency domain, a time domain and a capacity domain according to the task type, the task parameters and the task priority of the electromagnetic perception task;
preliminarily screening out a virtual equipment resource and virtual service resource candidate list meeting task execution requirements;
and finally determining the resources allocated to the electromagnetic sensing task according to the optimal monitoring effect or the optimal equipment utilization efficiency.
7. The resource state-based electromagnetic perception task live migration method according to claim 1, wherein the situation of triggering the calculation of the live migration policy includes:
when the electromagnetic sensing task with higher task priority in the distributed system obtains the relevant resources allocated to the current electromagnetic sensing task, recalculating the dynamic migration strategy for the current electromagnetic sensing task;
when the resources allocated to the current electromagnetic perception task are in failure, recalculating a dynamic migration strategy for the current electromagnetic perception task;
when the current load of the edge computing node executing the electromagnetic perception task is overlarge, the dynamic migration strategy is calculated for the current electromagnetic perception task again, and part of subtasks are selected to be migrated to the edge computing node with the smaller load to be continuously executed.
8. The electromagnetic perception task dynamic migration method based on the resource state according to claim 1, wherein dynamically allocating electromagnetic perception tasks to corresponding edge computing nodes for execution according to the dynamic migration policy comprises:
and issuing a control right acquisition instruction to the allocated equipment resource to acquire the control right of the equipment resource and the corresponding service resource.
9. The electromagnetic perception task dynamic migration system based on the resource state is characterized by comprising the following components:
the resource virtualization module is used for deploying a distributed service bus on all edge computing nodes, virtualizing all equipment resources and service resources and then uniformly registering the equipment resources and the service resources on the distributed service bus;
the resource state information acquisition module is used for acquiring resource state information accessed by each edge computing node and calculating load information of each edge computing node according to the resource state information;
the dynamic migration strategy calculation module is used for calculating a dynamic migration strategy of the electromagnetic perception task according to the optimal principle of the resource utilization rate and distributing corresponding equipment resources and service resources for the dynamic migration strategy based on all the electromagnetic perception task information of the current whole network and the load information of all the edge calculation nodes;
and the task execution module is used for dynamically allocating the electromagnetic perception task to the corresponding edge computing node for execution according to the dynamic migration strategy.
10. A terminal comprising a memory and a processor, wherein the memory stores computer instructions executable on the processor, and the processor executes the computer instructions to perform the method for dynamically migrating the electromagnetic sensing task based on the resource status according to any one of claims 1 to 8.
Priority Applications (1)
Application Number | Priority Date | Filing Date | Title |
---|---|---|---|
CN202211514490.8A CN115604768B (en) | 2022-11-30 | 2022-11-30 | Electromagnetic perception task dynamic migration method, system and terminal based on resource state |
Applications Claiming Priority (1)
Application Number | Priority Date | Filing Date | Title |
---|---|---|---|
CN202211514490.8A CN115604768B (en) | 2022-11-30 | 2022-11-30 | Electromagnetic perception task dynamic migration method, system and terminal based on resource state |
Publications (2)
Publication Number | Publication Date |
---|---|
CN115604768A true CN115604768A (en) | 2023-01-13 |
CN115604768B CN115604768B (en) | 2023-03-07 |
Family
ID=84851848
Family Applications (1)
Application Number | Title | Priority Date | Filing Date |
---|---|---|---|
CN202211514490.8A Active CN115604768B (en) | 2022-11-30 | 2022-11-30 | Electromagnetic perception task dynamic migration method, system and terminal based on resource state |
Country Status (1)
Country | Link |
---|---|
CN (1) | CN115604768B (en) |
Cited By (2)
Publication number | Priority date | Publication date | Assignee | Title |
---|---|---|---|---|
CN117255126A (en) * | 2023-08-16 | 2023-12-19 | 广东工业大学 | Data-intensive task edge service combination method based on multi-objective reinforcement learning |
CN117579626B (en) * | 2023-11-17 | 2024-06-04 | 深圳白鹿云数据科技有限公司 | Optimization method and system based on distributed realization of edge calculation |
Citations (7)
Publication number | Priority date | Publication date | Assignee | Title |
---|---|---|---|---|
CN103167522A (en) * | 2011-12-19 | 2013-06-19 | 电信科学技术研究院 | Method for performing spectrum sensing and equipment |
JPWO2015002174A1 (en) * | 2013-07-02 | 2017-02-23 | ニッコーシ株式会社 | Electromagnetic sensing device and electromagnetic sensing method |
CN106507370A (en) * | 2016-11-25 | 2017-03-15 | 重庆邮电大学 | The method of active frequency spectrum perception switching |
CN106936892A (en) * | 2017-01-09 | 2017-07-07 | 北京邮电大学 | A kind of self-organizing cloud multi-to-multi computation migration method and system |
US20210022182A1 (en) * | 2019-10-04 | 2021-01-21 | Intel Corporation | Detection of listen before talk failure during radio link monitoring |
CN113076177A (en) * | 2021-04-12 | 2021-07-06 | 河北大学 | Dynamic migration method of virtual machine in edge computing environment |
CN114861705A (en) * | 2022-03-31 | 2022-08-05 | 哈尔滨工程大学 | Electromagnetic target intelligent perception identification method based on multi-feature heterogeneous fusion |
-
2022
- 2022-11-30 CN CN202211514490.8A patent/CN115604768B/en active Active
Patent Citations (7)
Publication number | Priority date | Publication date | Assignee | Title |
---|---|---|---|---|
CN103167522A (en) * | 2011-12-19 | 2013-06-19 | 电信科学技术研究院 | Method for performing spectrum sensing and equipment |
JPWO2015002174A1 (en) * | 2013-07-02 | 2017-02-23 | ニッコーシ株式会社 | Electromagnetic sensing device and electromagnetic sensing method |
CN106507370A (en) * | 2016-11-25 | 2017-03-15 | 重庆邮电大学 | The method of active frequency spectrum perception switching |
CN106936892A (en) * | 2017-01-09 | 2017-07-07 | 北京邮电大学 | A kind of self-organizing cloud multi-to-multi computation migration method and system |
US20210022182A1 (en) * | 2019-10-04 | 2021-01-21 | Intel Corporation | Detection of listen before talk failure during radio link monitoring |
CN113076177A (en) * | 2021-04-12 | 2021-07-06 | 河北大学 | Dynamic migration method of virtual machine in edge computing environment |
CN114861705A (en) * | 2022-03-31 | 2022-08-05 | 哈尔滨工程大学 | Electromagnetic target intelligent perception identification method based on multi-feature heterogeneous fusion |
Non-Patent Citations (3)
Title |
---|
HE GUANGDONG 等: "Design and implementation of auto-monitoring system for wireless network", 《2011 IEEE 3RD INTERNATIONAL CONFERENCE ON COMMUNICATION SOFTWARE AND NETWORKS》 * |
SHANGGUANG WANG 等: "A Survey on Service Migration in Mobile Edge Computing", 《IEEE ACCESS》 * |
袁夕华: "无线电监测中电磁环境参数预测研究", 《中国设备工程》 * |
Cited By (2)
Publication number | Priority date | Publication date | Assignee | Title |
---|---|---|---|---|
CN117255126A (en) * | 2023-08-16 | 2023-12-19 | 广东工业大学 | Data-intensive task edge service combination method based on multi-objective reinforcement learning |
CN117579626B (en) * | 2023-11-17 | 2024-06-04 | 深圳白鹿云数据科技有限公司 | Optimization method and system based on distributed realization of edge calculation |
Also Published As
Publication number | Publication date |
---|---|
CN115604768B (en) | 2023-03-07 |
Similar Documents
Publication | Publication Date | Title |
---|---|---|
US10481935B2 (en) | Management system, overall management node, and management method for managing virtualization resources in a mobile communication network | |
US10481953B2 (en) | Management system, virtual communication-function management node, and management method for managing virtualization resources in a mobile communication network | |
CN115550367B (en) | Radio monitoring method and system based on distributed task management and resource scheduling | |
US20190230004A1 (en) | Network slice management method and management unit | |
CN115604768B (en) | Electromagnetic perception task dynamic migration method, system and terminal based on resource state | |
CN108370341B (en) | Resource allocation method, virtual network function manager and network element management system | |
US20160191345A1 (en) | System and method for service embedding and resource orchestration | |
CN110311798B (en) | Method and device for managing virtual resources | |
Nastic et al. | Polaris scheduler: Edge sensitive and slo aware workload scheduling in cloud-edge-iot clusters | |
CN108132827B (en) | Network slice resource mapping method, related equipment and system | |
US20240354149A1 (en) | Rightsizing virtual machine deployments in a cloud computing environment | |
CN110795202B (en) | Resource allocation method and device of virtualized cluster resource management system | |
CN112202829A (en) | Social robot scheduling system and scheduling method based on micro-service | |
CN112583615A (en) | VNF instantiation method, NFVO, VIM, VNFM and system | |
CN108900435B (en) | Service deployment method, device and computer storage medium | |
CN113992688A (en) | Distribution unit cloud deployment method, device, storage medium and system | |
Pusztai et al. | Polaris scheduler: SLO-and topology-aware microservices scheduling at the edge | |
CN109587024B (en) | Resource processing method and related device | |
US20230367654A1 (en) | Automatic node fungibility between compute and infrastructure nodes in edge zones | |
US10986036B1 (en) | Method and apparatus for orchestrating resources in multi-access edge computing (MEC) network | |
US12113719B2 (en) | Method for allocating resources of a network infrastructure | |
CN117608760A (en) | Cloud application hybrid deployment method applied to Kubernetes | |
CN118034900A (en) | Calculation power scheduling method, system, device, equipment and medium of heterogeneous chip | |
KR20130031582A (en) | System and method for providing u-city service | |
CN113098705B (en) | Authorization method and device for life cycle management of network service |
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 |