WO2021031767A1 - Procédé de planification de ressources, dispositif frontal intelligent, passerelle intelligente et système distribué - Google Patents

Procédé de planification de ressources, dispositif frontal intelligent, passerelle intelligente et système distribué Download PDF

Info

Publication number
WO2021031767A1
WO2021031767A1 PCT/CN2020/103084 CN2020103084W WO2021031767A1 WO 2021031767 A1 WO2021031767 A1 WO 2021031767A1 CN 2020103084 W CN2020103084 W CN 2020103084W WO 2021031767 A1 WO2021031767 A1 WO 2021031767A1
Authority
WO
WIPO (PCT)
Prior art keywords
smart
end device
task
smart front
gateway
Prior art date
Application number
PCT/CN2020/103084
Other languages
English (en)
Chinese (zh)
Inventor
周平
Original Assignee
中兴通讯股份有限公司
Priority date (The priority date 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 date listed.)
Filing date
Publication date
Application filed by 中兴通讯股份有限公司 filed Critical 中兴通讯股份有限公司
Publication of WO2021031767A1 publication Critical patent/WO2021031767A1/fr

Links

Images

Classifications

    • H—ELECTRICITY
    • H04—ELECTRIC COMMUNICATION TECHNIQUE
    • H04L—TRANSMISSION OF DIGITAL INFORMATION, e.g. TELEGRAPHIC COMMUNICATION
    • H04L65/00—Network arrangements, protocols or services for supporting real-time applications in data packet communication
    • H04L65/40—Support for services or applications
    • H—ELECTRICITY
    • H04—ELECTRIC COMMUNICATION TECHNIQUE
    • H04L—TRANSMISSION OF DIGITAL INFORMATION, e.g. TELEGRAPHIC COMMUNICATION
    • H04L67/00—Network arrangements or protocols for supporting network services or applications
    • H04L67/01—Protocols
    • H04L67/10—Protocols in which an application is distributed across nodes in the network
    • H04L67/1001—Protocols in which an application is distributed across nodes in the network for accessing one among a plurality of replicated servers
    • H04L67/1004—Server selection for load balancing
    • H04L67/1012—Server selection for load balancing based on compliance of requirements or conditions with available server resources
    • H—ELECTRICITY
    • H04—ELECTRIC COMMUNICATION TECHNIQUE
    • H04L—TRANSMISSION OF DIGITAL INFORMATION, e.g. TELEGRAPHIC COMMUNICATION
    • H04L67/00—Network arrangements or protocols for supporting network services or applications
    • H04L67/01—Protocols
    • H04L67/10—Protocols in which an application is distributed across nodes in the network
    • H04L67/1001—Protocols in which an application is distributed across nodes in the network for accessing one among a plurality of replicated servers
    • H04L67/1004—Server selection for load balancing
    • H04L67/1008—Server selection for load balancing based on parameters of servers, e.g. available memory or workload
    • H—ELECTRICITY
    • H04—ELECTRIC COMMUNICATION TECHNIQUE
    • H04L—TRANSMISSION OF DIGITAL INFORMATION, e.g. TELEGRAPHIC COMMUNICATION
    • H04L67/00—Network arrangements or protocols for supporting network services or applications
    • H04L67/01—Protocols
    • H04L67/10—Protocols in which an application is distributed across nodes in the network
    • H04L67/1001—Protocols in which an application is distributed across nodes in the network for accessing one among a plurality of replicated servers
    • H04L67/1029—Protocols in which an application is distributed across nodes in the network for accessing one among a plurality of replicated servers using data related to the state of servers by a load balancer
    • H—ELECTRICITY
    • H04—ELECTRIC COMMUNICATION TECHNIQUE
    • H04L—TRANSMISSION OF DIGITAL INFORMATION, e.g. TELEGRAPHIC COMMUNICATION
    • H04L67/00—Network arrangements or protocols for supporting network services or applications
    • H04L67/01—Protocols
    • H04L67/10—Protocols in which an application is distributed across nodes in the network
    • H04L67/1095—Replication or mirroring of data, e.g. scheduling or transport for data synchronisation between network nodes
    • H—ELECTRICITY
    • H04—ELECTRIC COMMUNICATION TECHNIQUE
    • H04L—TRANSMISSION OF DIGITAL INFORMATION, e.g. TELEGRAPHIC COMMUNICATION
    • H04L67/00—Network arrangements or protocols for supporting network services or applications
    • H04L67/01—Protocols
    • H04L67/10—Protocols in which an application is distributed across nodes in the network
    • H04L67/1097—Protocols in which an application is distributed across nodes in the network for distributed storage of data in networks, e.g. transport arrangements for network file system [NFS], storage area networks [SAN] or network attached storage [NAS]
    • H—ELECTRICITY
    • H04—ELECTRIC COMMUNICATION TECHNIQUE
    • H04L—TRANSMISSION OF DIGITAL INFORMATION, e.g. TELEGRAPHIC COMMUNICATION
    • H04L67/00—Network arrangements or protocols for supporting network services or applications
    • H04L67/50—Network services
    • H04L67/60—Scheduling or organising the servicing of application requests, e.g. requests for application data transmissions using the analysis and optimisation of the required network resources
    • H04L67/63—Routing a service request depending on the request content or context

Definitions

  • the embodiment of the present invention relates to the field of security technology, in particular to a resource scheduling method, an intelligent front-end device, an intelligent gateway, and a distributed system.
  • front-end monitoring equipment collected data and transmitted the data to the back-end server or cloud computing platform for intelligent analysis.
  • Intelligent front-end equipment can preprocess video images to remove image redundant information, so that part or all of the video analysis is migrated to front-end computing, reducing the computing, storage and network bandwidth requirements of the cloud center, and improving the response speed of the equipment.
  • the computing and storage capabilities of access devices are different and change over time.
  • the types of tasks undertaken by different access devices are not the same, such as the need for cross-border alarm analysis near the perimeter, face capture at entrances and exits, and license plate recognition on the road.
  • front-end computing Most of the data storage and computing tasks in front-end computing rely on smart front-end equipment. Unlike cloud computing centers that have stable infrastructure protection, many smart front-end devices are exposed to the natural environment for a long time and are easily damaged by natural or man-made damage. In the context of front-end intelligent computing, the reliability of the entire security system and the stability of computing face new problems.
  • the embodiment of the present invention provides a resource scheduling method, which includes: when a first smart front-end device is not capable of performing a task, a smart gateway determines a second smart front-end device capable of performing the task; The smart front-end device sends the task, and the task carries the service address of the second smart front-end device.
  • An embodiment of the present invention provides a resource scheduling method, including: when a first smart front-end device is not capable of performing a computing task, a smart gateway determines a second smart front-end device capable of performing the computing task; The second smart front-end device sends the calculation task.
  • the embodiment of the present invention provides a resource scheduling method, including: a smart front-end device receives a task sent by a smart gateway, and obtains from the smart gateway the service addresses of other smart front-end devices that assist in executing the task; The service address transfers the task to the other intelligent front-end equipment.
  • An embodiment of the present invention provides an intelligent gateway, including: a memory, a processor, and a resource scheduler stored on the memory and capable of running on the processor, wherein the resource scheduler is executed by the processor When implementing the steps of the corresponding resource scheduling method described above.
  • the embodiment of the present invention provides an intelligent front-end device, including: a memory, a processor, and a resource scheduler stored on the memory and capable of running on the processor, wherein the resource scheduler is controlled by the processor.
  • An embodiment of the present invention provides a computer-readable storage medium that stores a resource scheduling program, where the resource scheduling program is executed by a processor to implement the steps of the above-mentioned resource scheduling method.
  • Fig. 1 is a flowchart of a resource scheduling method according to Embodiment 1 of the present invention (applied to an intelligent gateway);
  • Embodiment 2 is a flowchart of a resource scheduling method according to Embodiment 2 of the present invention (applied to an intelligent gateway);
  • Figure 3 is a flow chart of a resource scheduling method according to Embodiment 3 of the present invention (applied to smart front-end equipment);
  • FIG. 4 is a schematic diagram of an intelligent gateway according to Embodiment 4 of the present invention.
  • FIG. 5 is a schematic diagram of an intelligent gateway according to Embodiment 5 of the present invention.
  • FIG. 6 is a schematic diagram of an intelligent front-end device according to Embodiment 6 of the present invention.
  • Figure 7 is a schematic diagram of a distributed system of Example 1.
  • Fig. 8 is a flowchart of a resource scheduling method of Example 2.
  • Fig. 9 is a flowchart of a resource scheduling method of Example 3.
  • Example 10 is a flowchart of a resource scheduling method of Example 4.
  • Fig. 11 is a flowchart of a resource scheduling method of Example 5.
  • Fig. 12 is a flowchart of a resource scheduling method of Example 6.
  • FIG. 13 is a flowchart of a resource scheduling method of Example 7.
  • Figure 14 is a schematic diagram of a smart gateway according to an embodiment of the present invention.
  • Fig. 15 is a schematic diagram of a smart front-end device according to an embodiment of the present invention.
  • an embodiment of the present invention provides a resource scheduling method, including:
  • Step S110 when the first smart front-end device is not capable of performing a task, the smart gateway determines a second smart front-end device capable of performing the task;
  • Step S120 the smart gateway sends the task to the first smart front-end device, where the task carries the service address of the second smart front-end device;
  • the task includes: a calculation task, a storage task, or a data recovery task.
  • the first smart front-end device is not capable of performing tasks, including any of the following:
  • the resources of the first smart front-end device are insufficient to complete the task
  • the smart gateway receives the resource request of the first smart front-end device
  • the data of the first smart front-end device has been backed up or migrated to other smart front-end devices.
  • the smart gateway determines that the first smart front-end device is not capable of performing the task by querying the resource status of the first smart front-end device; or, the smart gateway receives all the tasks.
  • the resource request sent by the first smart front-end device determines that the first smart front-end device is not capable of performing the task.
  • the smart gateway queries the resource status of each smart front-end device in the smart front-end device cluster, searches for a second smart front-end device whose resource status meets the task requirements, and determines the second smart front-end device as capable of performing the task Smart front-end equipment.
  • the resource status includes at least one of the following: computing capacity, storage capacity and bandwidth;
  • the method further includes:
  • the smart gateway receives the calculation task execution result returned by the second smart front-end device, and sends the calculation task execution result to the server;
  • the server includes: a cloud server and/or a local server;
  • the computing task is allocated by the server to the first intelligent front-end device
  • the execution result of the calculation task may be successful execution of the task or failure of the execution of the task, and the calculation result may be carried when the execution of the task is successful;
  • the storage task includes: a backup task or a data migration task;
  • the storage task is to back up the designated data of the smart front-end device A
  • the storage space of the smart front-end device A is insufficient
  • a copy of the designated data of the smart front-end device A is copied, and the copy is stored in other smart front-end devices ( For example, on smart front-end devices B and C), smart front-end devices B and C each store a part of the copy.
  • the storage task is to perform data migration on the designated data of smart front-end device A
  • the storage space of smart front-end device A is insufficient, transfer the designated data of smart front-end device A to other smart front-end devices (such as smart front-end device B and In C)
  • the intelligent front-end devices B and C each store a part of the specified data.
  • the method further includes:
  • the smart gateway receives the storage task execution result returned by the first smart front-end device, and sends the storage task execution result to the server;
  • the server includes: a cloud server and/or a local server;
  • the storage task is allocated by the server to the first smart front-end device
  • the storage task execution result refers to storage success or failure
  • the method further includes:
  • the smart gateway stores the data storage relationship between the first smart front-end device and the second smart front-end device;
  • the number of second smart front-end devices capable of performing storage tasks is one or more;
  • the smart gateway determines whether the data of the first smart front-end device has been backed up or migrated to the second smart front-end device, and if yes, the first smart The front-end device is not capable of performing the data recovery task and the second intelligent front-end device is capable of performing the data recovery task.
  • the method further includes:
  • execution result of the data recovery task refers to the success or failure of data recovery
  • the method further includes:
  • the smart gateway When the smart gateway fails to send a task to the first smart front-end device, it determines the second smart front-end device as a transit device;
  • the smart gateway receives the task execution result of the first smart front-end device returned by the second smart front-end device.
  • an embodiment of the present invention provides a resource scheduling method, including:
  • Step S210 When the first smart front-end device is not capable of performing a computing task, the smart gateway determines a second smart front-end device capable of performing the computing task;
  • Step S220 The smart gateway sends the computing task to the second smart front-end device.
  • the first smart front-end device is not capable of performing computing tasks, including any one of the following:
  • the resources of the first smart front-end device are insufficient to complete the computing task
  • the smart gateway receives the resource request of the first smart front-end device.
  • the smart gateway determines that the first smart front-end device is not capable of executing the computing task by querying the resource status of the first smart front-end device; or, the smart gateway receives a computing resource request sent by the first smart front-end device When determining that the first smart front-end device is not capable of performing the computing task;
  • the smart gateway queries the resource status of each smart front-end device in the smart front-end device cluster, searches for a second smart front-end device whose resource state meets the requirements of the computing task, and determines that the second smart front-end device is capable of executing the Intelligent front-end equipment for computing tasks.
  • the resource status includes at least one of the following: computing capacity, storage capacity and bandwidth;
  • the method further includes:
  • the smart gateway When the smart gateway fails to send a calculation task to the first smart front-end device, it determines the second smart front-end device as a transit device;
  • the smart gateway receives the calculation task execution result of the first smart front-end device returned by the second smart front-end device.
  • an embodiment of the present invention provides a resource scheduling method, including:
  • Step S310 The smart front-end device receives the task sent by the smart gateway, and obtains from the smart gateway the service addresses of other smart front-end devices that assist in executing the task;
  • step S320 the smart front-end device transfers the task to the other smart front-end device according to the service address.
  • the task includes: a calculation task, a storage task, or a data recovery task.
  • the method before the smart front-end device obtains the service addresses of other smart front-end devices that assist in executing the task from the smart gateway, the method further includes:
  • the smart front-end device determines that the device is not capable of performing the task, and sends a resource request to the smart gateway.
  • the smart front-end device determines that the device is not capable of performing computing tasks by querying the resource status of the device;
  • the smart front-end device when the task is a storage task, stores data that needs to be backed up or migrated to the other smart front-end device according to the service address.
  • the method further includes:
  • the smart front-end device returns the storage task execution result to the smart gateway
  • the smart front-end device when the task is a data recovery task, obtains the previously backed-up or migrated data from the other smart front-end device according to the service address.
  • the method further includes:
  • the smart front-end device receives a transfer request, and the transfer request carries the communication address of the smart front-end device that needs the transfer service;
  • the smart front-end equipment establishes a communication connection with the smart front-end equipment that needs transit services;
  • the smart front-end equipment receives tasks from the smart gateway, and forwards the tasks to the smart front-end equipment that needs a transit service;
  • the smart front-end device receives the task execution result from the smart front-end device that needs the transfer service, and forwards the task execution result to the smart gateway.
  • an embodiment of the present invention provides an intelligent gateway, including:
  • the analysis module 401 is configured to determine a second smart front-end device capable of performing the task when the first smart front-end device is not capable of performing the task;
  • the task includes: a calculation task, a storage task, or a data recovery task.
  • the first smart front-end device is not capable of performing tasks, including any of the following:
  • the resources of the first smart front-end device are insufficient to complete the task
  • the smart gateway receives the resource request of the first smart front-end device
  • the data of the first smart front-end device has been backed up or migrated to other smart front-end devices.
  • the analysis module is configured to determine that the first smart front-end device is not capable of performing the task in the following manner: by querying the resource status of the first smart front-end device It is determined that the first smart front-end device is not capable of performing the task; or, when a resource request sent by the first smart front-end device is received, it is determined that the first smart front-end device is not capable of performing the task.
  • the resource status includes at least one of the following: computing capacity, storage capacity and bandwidth;
  • the analysis module is configured to determine the second smart front-end device capable of executing the task in the following manner: query in the smart front-end device cluster The resource status of each smart front-end device is searched for a second smart front-end device whose resource status meets the task requirements, and the second smart front-end device is determined as the smart front-end device capable of executing the task.
  • the smart gateway further includes: a first receiving module 403, configured to receive the calculation task execution result returned by the second smart front-end device, and send the calculation task execution result to the server;
  • the server includes: a cloud server and/or a local server;
  • the computing task is allocated by the server to the first intelligent front-end device
  • the execution result of the calculation task may be successful execution of the task or failure of the execution of the task, and the calculation result may also be carried when the execution of the task is successful;
  • the storage task includes: a backup task or a data migration task;
  • the device further includes: a second receiving module 404, configured to receive the storage task execution result returned by the first smart front-end device, and send the storage task execution result to the server;
  • the server includes: a cloud server and/or a local server;
  • the storage task is allocated by the server to the first smart front-end device
  • the storage task execution result refers to storage success or failure
  • the second receiving module is further configured to store the data storage relationship between the first smart front-end device and the second smart front-end device after receiving the storage task execution result returned by the first smart front-end device ;
  • the number of second smart front-end devices capable of performing storage tasks is one or more;
  • the analysis module is used to determine whether the data of the first smart front-end device has been backed up or migrated to the second smart front-end device, and if yes, the first smart front-end device is determined The smart front-end device is not capable of performing data recovery tasks and the second smart front-end device is capable of performing the data recovery tasks.
  • the device further includes: a third receiving module 405, configured to receive the data recovery task returned by the first smart front-end device after sending the data recovery task to the first smart front-end device The results of the implementation;
  • execution result of the data recovery task refers to the success or failure of data recovery
  • the task sending module is further configured to determine a second smart front-end device as a transfer device when sending a task to the first smart front-end device fails; send a transfer request to the second smart front-end device, and The communication address of the first smart front-end device; receiving the task execution result of the first smart front-end device returned by the second smart front-end device.
  • an embodiment of the present invention provides an intelligent gateway, including:
  • the analysis module 501 is configured to determine a second smart front-end device capable of performing the computing task when the first smart front-end device is not capable of performing the computing task;
  • Task sending module 502 configured to send the computing task to the second smart front-end device
  • the first smart front-end device is not capable of performing computing tasks, including any one of the following:
  • the resources of the first smart front-end device are insufficient to complete the computing task
  • the smart gateway receives the resource request of the first smart front-end device.
  • the analysis module is configured to determine that the first smart front-end device is not capable of performing the computing task by querying the resource status of the first smart front-end device; or, receiving a transmission from the first smart front-end device Determining that the first intelligent front-end device is not capable of executing the computing task when the computing resource is requested;
  • each smart front-end device in the smart front-end device cluster search for a second smart front-end device whose resource status meets the requirements of the computing task, and determine the second smart front-end device as a smart capable of executing the computing task Front-end equipment.
  • the resource status includes at least one of the following: computing capacity, storage capacity and bandwidth;
  • the task sending module is further configured to determine the second smart front-end device as a transfer device when sending a computing task to the first smart front-end device fails; send a transfer request and the transfer request to the second smart front-end device The communication address of the first smart front-end device; receiving the calculation task execution result of the first smart front-end device returned by the second smart front-end device.
  • an embodiment of the present invention provides an intelligent front-end device, including:
  • the task receiving module 601 is configured to receive tasks sent by the smart gateway, and obtain the service addresses of other smart front-end devices that assist in executing the tasks from the smart gateway;
  • the task processing module 602 is configured to transfer the task to the other intelligent front-end equipment according to the service address.
  • the task includes: a calculation task, a storage task, or a data recovery task.
  • the smart front-end device further includes: a request module 603, configured to determine from the smart gateway that the device is not capable of executing the service address of other smart front-end devices that assist in executing the task. Task, send a resource request to the smart gateway.
  • a request module 603 configured to determine from the smart gateway that the device is not capable of executing the service address of other smart front-end devices that assist in executing the task. Task, send a resource request to the smart gateway.
  • the request module is configured to determine that the device is not capable of performing computing tasks by querying the resource status of the device;
  • the task processing module is configured to store data that needs to be backed up or migrated to the other smart front-end device according to the service address.
  • the smart front-end device further includes: a feedback module 604, configured to store data that needs to be backed up or migrated on the other smart front-end device, and then return the storage task execution result to the smart gateway;
  • the task processing module is configured to obtain the previously backed up or migrated data from the other intelligent front-end device according to the service address.
  • the smart front-end device further includes a transfer module 605 for receiving a transfer request, and the transfer request carries the communication address of the smart front-end device that needs the transfer service; and the smart front-end device that needs the transfer service Establish a communication connection; receive tasks from the smart gateway, and forward the tasks to the smart front-end equipment that needs transit services; receive the task execution results from the smart front-end devices that need transit services, and forward the task execution results to the smart Gateway.
  • a transfer module 605 for receiving a transfer request, and the transfer request carries the communication address of the smart front-end device that needs the transfer service
  • the smart front-end device that needs the transfer service Establish a communication connection; receive tasks from the smart gateway, and forward the tasks to the smart front-end equipment that needs transit services; receive the task execution results from the smart front-end devices that need transit services, and forward the task execution results to the smart Gateway.
  • an embodiment of the present invention provides an intelligent gateway, including:
  • the resource scheduling program is executed by the processor 1402 to implement the above-mentioned embodiment 1 The steps of the resource scheduling method described.
  • an embodiment of the present invention provides an intelligent gateway, including:
  • the resource scheduling program is executed by the processor 1402 to implement the above-mentioned embodiment 2 The steps of the resource scheduling method described.
  • an embodiment of the present invention provides an intelligent front-end device, including:
  • the embodiment of the present invention provides a distributed system, including: the above-mentioned intelligent front-end equipment and an intelligent gateway.
  • the embodiment of the present invention provides a computer-readable storage medium, the computer-readable storage medium stores a resource scheduling program, and the resource scheduling program implements the foregoing embodiment 1 or embodiment 2 or Steps of the resource scheduling method described in embodiment 3.
  • this example provides a distributed computing and storage system, including: an intelligent gateway (GateWay) and an intelligent front-end device.
  • the distributed computing and storage system is highly scalable, and realizes a unified external service interface through the intelligent gateway service, which reduces the difficulty of equipment access.
  • the smart gateway is the hub that connects the smart front-end device and the back-end server (cloud server and/or local server), and provides various service functions through API (Application Programming Interface) interfaces.
  • the smart front-end device can call the interface to register
  • the back-end server can call the interface to view the device information of the currently connected smart front-end device
  • the smart front-end device initiates a request for computing resources.
  • the intelligent front-end equipment receives instructions from the back-end server and processes tasks, and can provide computing, storage and forwarding functions through API interfaces.
  • Smart front-end devices can be connected to the smart gateway in a wired or wireless manner, and the smart front-end devices mainly forward messages through the smart gateway, and can also achieve direct communication in a wireless manner.
  • the smart front-end equipment accesses the system through the registration service interface provided by the smart gateway.
  • the smart gateway can view the resource status of the current device (including CPU utilization, storage status, network utilization, etc.) by calling the status query interface provided by the smart front-end device, and it can also obtain services of various capabilities provided by the current device by calling the capability interface Address, the services include computing services, storage services, transit services, etc.
  • the smart front-end device can obtain information of all smart front-end devices in the cluster through the service provided by the smart gateway. The information includes the communication address of the smart front-end device and storage and computing capability information.
  • This example provides a resource scheduling method.
  • the smart front-end equipment When the smart front-end equipment is overloaded and unable to receive new tasks, it can request computing resources from the smart gateway.
  • the smart gateway searches for all smart front-end devices in the cluster and comprehensively considers the computing, storage, and communication capabilities of the equipment to select suitable ones. And then forward the computing service address of the appropriate smart front-end device to the smart front-end device requesting computing resources. Forwarding computing resources through the smart gateway can prevent a certain smart front-end device from being overloaded with tasks.
  • the resource scheduling method of this example may include the following steps:
  • Step S101 The background server delivers tasks to the smart front-end device A through the smart gateway.
  • Step S102 After receiving the task, the smart front-end device A judges whether the current load exceeds the threshold, and if it exceeds the threshold, it initiates a request for computing resources to the smart gateway;
  • Step S103 After receiving the request, the smart gateway searches for all smart front-end devices in the cluster and comprehensively considers the computing, storage, and communication capabilities of the devices to select a suitable smart front-end device B, and then forwards the computing service address of the smart front-end device B To smart front-end equipment A.
  • Step S104 After the smart front-end device A obtains the service address of the smart front-end device B, the task is transferred through the interface provided by the smart front-end device B, and the data required for the calculation task can be sent to the smart front-end device B when needed.
  • Step S105 The smart front-end device B performs calculation after obtaining the task, and then forwards the calculation result to the background server through the smart gateway.
  • This example provides a resource scheduling method.
  • the smart gateway receives the task sent by the back-end server, it can determine whether the current device is capable of computing by obtaining the current resource status of the smart front-end device. If the computing power is insufficient, it searches for all smart front-end devices in the cluster and comprehensively considers the device's Computing, storage and communication capabilities, etc., screen out the appropriate smart front-end equipment, and then send the task to the appropriate smart front-end equipment, and at the same time forward the relevant service address of the original smart front-end equipment to the new smart front-end equipment, the new smart front-end equipment Relevant data can be obtained from the original smart front-end equipment. Forwarding computing resources through the smart gateway can prevent a certain smart front-end device from being overloaded with tasks.
  • the resource scheduling method of this example may include the following steps:
  • Step S101 The background server delivers tasks to the smart front-end device A through the smart gateway.
  • Step S102 The smart gateway first judges whether device A has enough computing resources to perform the task. If the computing power is insufficient, it searches for a suitable smart front-end device B with computing power that meets the requirements; among them, the bandwidth of the device is considered when searching, and the calculation and Storage capacity.
  • Step S103 The smart gateway forwards the calculation task to the smart front-end device B, and sends the related service address of the smart front-end device A to the smart front-end device B.
  • Step S104 The smart front-end device B performs calculations after receiving the task and the related service address of the smart front-end device A.
  • the smart front-end device B obtains relevant data according to the relevant service address of the smart front-end device A;
  • the task sent by the back-end server is to perform image analysis on the video surveillance data of the smart front-end device A. Since each smart front-end device can only obtain the video data in its own monitoring area, the smart front-end device B needs to obtain the video data from the smart front-end device. A get the relevant data, and then calculate.
  • the smart gateway may not send the relevant service address of the smart front-end device A to the smart front-end device B; when the computing task requires When relying on the data in the smart front-end device A, the smart gateway sends the related service address of the smart front-end device A to the smart front-end device B, and the smart front-end device B obtains the related data according to the related service address of the smart front-end device A.
  • Step S105 After the calculation of the smart front-end device B is completed, the calculation result is forwarded to the back-end server through the smart gateway.
  • This example provides a resource scheduling method.
  • the smart gateway When the back-end server issues a backup or data migration instruction to the smart front-end device A, the smart gateway first determines whether the current smart front-end device A has enough storage space to store data. If the space is not enough, it searches for a suitable smart front-end through a certain strategy Devices B and C, and send the searched storage addresses and task instructions of smart front-end devices B and C to smart front-end device A together. When the smart front-end device A receives the instruction, the data to be stored is evenly sliced, and the data is transferred through the received storage addresses of the smart front-end devices B and C in turn. Forwarding storage resource backup requests through the intelligent gateway service can prevent a certain intelligent front-end device from causing data loss due to certain factors, and improve data reliability.
  • the resource scheduling method of this example may include the following steps:
  • Step S101 The background server issues a backup or data migration task to the smart front-end device A through the smart gateway.
  • Step S102 The smart gateway first determines whether the current smart front-end device A has enough storage space to store data, and if the space is not enough, it searches for suitable smart front-end devices (for example, smart front-end devices B and C) through a certain strategy.
  • suitable smart front-end devices for example, smart front-end devices B and C
  • Step S103 The smart gateway forwards the storage service address list (B, C) and storage instructions of the smart front-end device to the smart front-end device A.
  • Step S104 After the smart front-end device A obtains the storage instruction and the storage service address list, the data that needs to be backed up or migrated is evenly transferred to other smart front-end devices.
  • Step S105 The smart front-end device A sends the task execution result to the smart gateway.
  • task execution results include: backup success or backup failure
  • the task execution results include: data migration success or data migration failure;
  • Step S106 the smart gateway stores the data relationship
  • the data relationship stored by the smart gateway is: the data backup address of smart front-end device A is smart front-end device B and smart front-end device C;
  • the data relationship stored by the smart gateway is: the data migration address of smart front-end device A is smart front-end device B and smart front-end device C;
  • Step S107 The smart gateway sends the task execution result to the background server.
  • This example provides a resource scheduling method.
  • the smart front-end device A When the smart front-end device A has insufficient storage space and cannot receive new backup or data migration tasks, it can request storage resources from the smart gateway.
  • the smart gateway searches for suitable smart front-end devices B and C through a certain strategy, and then determines the appropriate
  • the storage service address of the smart front-end device is forwarded to the smart front-end device A that requests storage resources.
  • the smart front-end device A receives the instruction, the data to be stored is evenly sliced, and the data is transferred through the received storage addresses of the smart front-end devices B and C in turn. Forwarding storage resource backup requests through the intelligent gateway service can prevent a certain intelligent front-end device from causing data loss due to certain factors, and improve data reliability.
  • the resource scheduling method of this example may include the following steps:
  • Step S101 The background server issues a backup or data migration task to the smart front-end device A through the smart gateway.
  • Step S102 After receiving the task, the smart front-end device A judges whether there is enough storage space to store data, and if the space is not enough, it initiates a request for storage resources to the smart gateway;
  • Step S103 After receiving the request, the smart gateway searches for suitable smart front-end devices (for example, smart front-end devices B and C) through a certain strategy.
  • suitable smart front-end devices for example, smart front-end devices B and C
  • Step S104 The smart gateway forwards the storage service address list (B, C) and storage instructions of the smart front-end device to the smart front-end device A.
  • Step S105 After the smart front-end device A obtains the instruction and the storage service address list, it evenly transfers the data that needs to be backed up or migrated to other smart front-end devices.
  • Step S106 The smart front-end device A sends the task execution result to the smart gateway.
  • task execution results include: backup success or backup failure
  • the task execution results include: data migration success or data migration failure;
  • Step S107 the smart gateway stores the data relationship
  • the data relationship stored by the smart gateway is: the data backup address of smart front-end device A is smart front-end device B and smart front-end device C;
  • the data relationship stored by the smart gateway is: the data migration address of smart front-end device A is smart front-end device B and smart front-end device C;
  • Step S108 The smart gateway sends the task execution result to the background server.
  • This example provides a resource scheduling method.
  • the smart gateway sends the previously stored service storage address and task instructions to the smart front-end device A together.
  • the smart front-end device A receives the task instruction, it first determines whether the storage address of the backup data is stored locally, and if not, it restores the data through the storage address passed by the gateway. Forwarding the data recovery request through the intelligent gateway service can prevent a certain intelligent front-end device from causing data loss due to certain factors, and improve the reliability of the data.
  • the resource scheduling method of this example may include the following steps:
  • Step S101 The background server issues a data recovery task to the smart front-end device A through the smart gateway.
  • Step S102 The smart gateway forwards the data recovery instruction and the server address list (smart front-end device B, C) for data backup or migration to the smart front-end device A.
  • Step S103 After receiving the instruction, the smart front-end device A first searches whether the server address for data backup or migration is stored locally, and if not, it uses the address list passed by the smart gateway.
  • Step S104 The smart front-end device A restores the data through the address list.
  • smart front-end device A obtains data from smart front-end devices B and C respectively according to the server address of the data backup or migration;
  • Step S105 The smart front-end device A forwards the task execution result to the back-end server through the gateway.
  • the task execution result refers to: data recovery success or data recovery failure.
  • This example provides a resource scheduling method.
  • the smart gateway When the smart gateway loses connection with the smart front-end device, the smart gateway selects the appropriate one through a certain search strategy (considering the distance between other smart front-end devices and the smart front-end device that has lost contact, communication capabilities, and current resource utilization) Smart front-end device B then initiates a transfer request to smart front-end device B, smart front-end device B establishes a connection with smart front-end device A, and all subsequent messages sent by smart front-end device A to the smart gateway are forwarded by smart front-end device B.
  • a smart front-end device loses connection with the smart gateway, data can be transferred through other smart front-end devices in the cluster, thereby improving the reliability and stability of the system.
  • the resource scheduling method of this example may include the following steps:
  • Step S101 The background server issues a task instruction to a certain smart front-end device (smart front-end device A).
  • Step S102 The smart gateway tries to forward the task instruction to the smart front-end device A for multiple times.
  • Step S103 After the smart gateway fails to attempt to communicate with the smart front-end device A, it searches for the best transit device (the smart front-end device B) through a certain search strategy.
  • Step S104 The smart gateway initiates a transfer request to the smart front-end device B, and provides the wireless communication address of the smart front-end device A.
  • Step S105 After receiving the transfer request, the smart front-end device B actively establishes a communication connection with the smart front-end device A, and forwards the instruction to the smart front-end device A.
  • Step S106 The smart front-end device A performs calculations after receiving the instruction, and then returns the calculation result to the smart front-end device B;
  • Step S107 The smart front-end device B feeds back the calculation result to the back-end server through the smart gateway.
  • the smart gateway determines a second smart front-end device capable of performing the task
  • the smart gateway sends the task to the first smart front-end device, and the task carries the service address of the second smart front-end device.
  • the embodiment of the present invention can improve the reliability of the security system and the stability of calculation.
  • the embodiments of the present invention can improve the reliability of the security system and the stability of calculation and storage.
  • Such software may be distributed on a computer-readable medium
  • the computer-readable medium may include a computer storage medium (or non-transitory medium) and a communication medium (or transitory medium).
  • the term computer storage medium includes volatile and non-volatile memory implemented in any method or technology for storing information (such as computer-readable instructions, data structures, program modules, or other data).
  • Computer storage media include but are not limited to RAM, ROM, EEPROM, flash memory or other memory technology, CD-ROM, digital versatile disk (DVD) or other optical disk storage, magnetic cassette, tape, magnetic disk storage or other magnetic storage device, or Any other medium used to store desired information and that can be accessed by a computer.
  • communication media usually contain computer-readable instructions, data structures, program modules, or other data in a modulated data signal such as carrier waves or other transmission mechanisms, and may include any information delivery media .

Landscapes

  • Engineering & Computer Science (AREA)
  • Computer Networks & Wireless Communication (AREA)
  • Signal Processing (AREA)
  • Computer Hardware Design (AREA)
  • General Engineering & Computer Science (AREA)
  • Multimedia (AREA)
  • Data Exchanges In Wide-Area Networks (AREA)

Abstract

L'invention concerne un procédé de planification de ressources, un dispositif frontal intelligent, un passerelle intelligente et un système distribué. Le procédé de planification de ressources comprend les étapes suivantes : lorsqu'un premier dispositif frontal intelligent n'est pas apte à exécuter une tâche, une passerelle intelligente détermine un second dispositif frontal intelligent apte à exécuter la tâche (S110) ; et la passerelle intelligente envoie la tâche au premier dispositif frontal intelligent, la tâche transportant une adresse de service du second dispositif frontal intelligent (S120).
PCT/CN2020/103084 2019-08-22 2020-07-20 Procédé de planification de ressources, dispositif frontal intelligent, passerelle intelligente et système distribué WO2021031767A1 (fr)

Applications Claiming Priority (2)

Application Number Priority Date Filing Date Title
CN201910778773.5A CN112422598A (zh) 2019-08-22 2019-08-22 资源调度方法、智能前端设备、智能网关及分布式系统
CN201910778773.5 2019-08-22

Publications (1)

Publication Number Publication Date
WO2021031767A1 true WO2021031767A1 (fr) 2021-02-25

Family

ID=74660125

Family Applications (1)

Application Number Title Priority Date Filing Date
PCT/CN2020/103084 WO2021031767A1 (fr) 2019-08-22 2020-07-20 Procédé de planification de ressources, dispositif frontal intelligent, passerelle intelligente et système distribué

Country Status (2)

Country Link
CN (1) CN112422598A (fr)
WO (1) WO2021031767A1 (fr)

Cited By (1)

* Cited by examiner, † Cited by third party
Publication number Priority date Publication date Assignee Title
CN113760303A (zh) * 2021-11-10 2021-12-07 杭州安恒信息技术股份有限公司 一种微前端应用资源的处理方法、装置、设备及存储介质

Citations (6)

* Cited by examiner, † Cited by third party
Publication number Priority date Publication date Assignee Title
US20090248835A1 (en) * 2008-03-31 2009-10-01 Subhankar Panda Offloading data transfers between a local and remote network
CN104363300A (zh) * 2014-11-26 2015-02-18 浙江宇视科技有限公司 一种服务器集群中计算任务分布式调度装置
US20170164237A1 (en) * 2015-12-03 2017-06-08 The Trustees Of The Stevens Institute Of Technology System Apparatus And Methods For Cognitive Cloud Offloading In A Multi-Rat Enabled Wireless Device
CN109600419A (zh) * 2018-11-12 2019-04-09 南京信息工程大学 一种移动边缘计算环境下支持车联网应用的计算迁移方法
CN109819037A (zh) * 2019-01-29 2019-05-28 武汉鸿瑞达信息技术有限公司 一种自适应计算与通信的方法和系统
CN109862592A (zh) * 2018-12-06 2019-06-07 北京邮电大学 一种基于多基站协作的移动边缘计算环境下资源管理和调度方法

Family Cites Families (7)

* Cited by examiner, † Cited by third party
Publication number Priority date Publication date Assignee Title
CN1299482C (zh) * 2003-11-13 2007-02-07 上海交通大学 工业设备网络化监控协同终端及终端间协同访问实现方法
CN104158581B (zh) * 2013-05-13 2018-03-02 电信科学技术研究院 一种中继节点的发现方法及装置
CN105182828B (zh) * 2015-09-18 2018-09-07 深圳前海达闼科技有限公司 一种设备请求协助、响应设备协助请求的方法及设备
CN106341860B (zh) * 2016-08-26 2020-01-21 宇龙计算机通信科技(深圳)有限公司 一种中继网络连接方法及相关设备
CN108234537A (zh) * 2016-12-13 2018-06-29 杭州海康威视数字技术股份有限公司 一种数据传输方法、装置及分布式系统
CN106843031A (zh) * 2016-12-15 2017-06-13 北京光年无限科技有限公司 用于智能机器人的协同处理方法及系统
CN109547531B (zh) * 2018-10-19 2021-04-09 华为技术有限公司 数据处理的方法、装置和计算设备

Patent Citations (6)

* Cited by examiner, † Cited by third party
Publication number Priority date Publication date Assignee Title
US20090248835A1 (en) * 2008-03-31 2009-10-01 Subhankar Panda Offloading data transfers between a local and remote network
CN104363300A (zh) * 2014-11-26 2015-02-18 浙江宇视科技有限公司 一种服务器集群中计算任务分布式调度装置
US20170164237A1 (en) * 2015-12-03 2017-06-08 The Trustees Of The Stevens Institute Of Technology System Apparatus And Methods For Cognitive Cloud Offloading In A Multi-Rat Enabled Wireless Device
CN109600419A (zh) * 2018-11-12 2019-04-09 南京信息工程大学 一种移动边缘计算环境下支持车联网应用的计算迁移方法
CN109862592A (zh) * 2018-12-06 2019-06-07 北京邮电大学 一种基于多基站协作的移动边缘计算环境下资源管理和调度方法
CN109819037A (zh) * 2019-01-29 2019-05-28 武汉鸿瑞达信息技术有限公司 一种自适应计算与通信的方法和系统

Cited By (1)

* Cited by examiner, † Cited by third party
Publication number Priority date Publication date Assignee Title
CN113760303A (zh) * 2021-11-10 2021-12-07 杭州安恒信息技术股份有限公司 一种微前端应用资源的处理方法、装置、设备及存储介质

Also Published As

Publication number Publication date
CN112422598A (zh) 2021-02-26

Similar Documents

Publication Publication Date Title
US11159411B2 (en) Distributed testing service
WO2020147331A1 (fr) Procédé et système de surveillance de micro-services
US10983880B2 (en) Role designation in a high availability node
US7756888B2 (en) Method and apparatus for providing heterogeneous resources for client systems
US8484510B2 (en) Enhanced cluster failover management
US8583773B2 (en) Autonomous primary node election within a virtual input/output server cluster
US6138251A (en) Method and system for reliable remote object reference management
WO2022001173A1 (fr) Procédé et dispositif de radiomessagerie coopérative terrestre par satellite pour système de communication par satellite
US10333788B2 (en) System and method for acquiring, processing and updating global information
CN113965560A (zh) 数据传输方法和代理服务器、存储介质及电子装置
CN106991008B (zh) 一种资源锁管理方法、相关设备及系统
US10783045B2 (en) Active-active architecture for distributed ISCSI target in hyper-converged storage
US11922059B2 (en) Method and device for distributed data storage
CN112463290A (zh) 动态调整计算容器的数量的方法、系统、装置和存储介质
US20080115127A1 (en) Apparatus and method for carrying out information processing by virtualization
WO2021031767A1 (fr) Procédé de planification de ressources, dispositif frontal intelligent, passerelle intelligente et système distribué
CN109981779B (zh) 服务提供方法、服务器及计算机存储介质
KR20160068881A (ko) 분산 저장 시스템에서의 캐시 및 비-캐시 사용
CN114416470A (zh) 一种云端监控方法、系统、设备及计算机存储介质
US9547590B2 (en) Managing memory
CN112468310B (zh) 流媒体集群节点管理方法、装置及存储介质
US11153173B1 (en) Dynamically updating compute node location information in a distributed computing environment
WO2023109062A1 (fr) Système et procédé de récupération d'urgence infonuagique, dispositif électronique et support de stockage
CN111382132A (zh) 医学影像数据云存储系统
CN113391759B (zh) 一种通信方法和设备

Legal Events

Date Code Title Description
121 Ep: the epo has been informed by wipo that ep was designated in this application

Ref document number: 20855669

Country of ref document: EP

Kind code of ref document: A1

NENP Non-entry into the national phase

Ref country code: DE

122 Ep: pct application non-entry in european phase

Ref document number: 20855669

Country of ref document: EP

Kind code of ref document: A1

122 Ep: pct application non-entry in european phase

Ref document number: 20855669

Country of ref document: EP

Kind code of ref document: A1