[go: up one dir, main page]
More Web Proxy on the site http://driver.im/

WO2023274293A1 - 算力通告的发送方法、装置及算力网元节点 - Google Patents

算力通告的发送方法、装置及算力网元节点 Download PDF

Info

Publication number
WO2023274293A1
WO2023274293A1 PCT/CN2022/102298 CN2022102298W WO2023274293A1 WO 2023274293 A1 WO2023274293 A1 WO 2023274293A1 CN 2022102298 W CN2022102298 W CN 2022102298W WO 2023274293 A1 WO2023274293 A1 WO 2023274293A1
Authority
WO
WIPO (PCT)
Prior art keywords
computing power
node
target
network element
sending
Prior art date
Application number
PCT/CN2022/102298
Other languages
English (en)
French (fr)
Inventor
姚惠娟
付月霞
孙滔
陆璐
Original Assignee
中国移动通信有限公司研究院
中国移动通信集团有限公司
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 中国移动通信有限公司研究院, 中国移动通信集团有限公司 filed Critical 中国移动通信有限公司研究院
Priority to JP2023580883A priority Critical patent/JP7695417B2/ja
Priority to EP22832105.5A priority patent/EP4366279A4/en
Priority to US18/575,866 priority patent/US20250106305A1/en
Publication of WO2023274293A1 publication Critical patent/WO2023274293A1/zh

Links

Images

Classifications

    • HELECTRICITY
    • H04ELECTRIC COMMUNICATION TECHNIQUE
    • H04LTRANSMISSION OF DIGITAL INFORMATION, e.g. TELEGRAPHIC COMMUNICATION
    • H04L67/00Network arrangements or protocols for supporting network services or applications
    • H04L67/50Network services
    • H04L67/51Discovery or management thereof, e.g. service location protocol [SLP] or web services
    • HELECTRICITY
    • H04ELECTRIC COMMUNICATION TECHNIQUE
    • H04LTRANSMISSION OF DIGITAL INFORMATION, e.g. TELEGRAPHIC COMMUNICATION
    • H04L67/00Network arrangements or protocols for supporting network services or applications
    • H04L67/50Network services
    • H04L67/60Scheduling or organising the servicing of application requests, e.g. requests for application data transmissions using the analysis and optimisation of the required network resources
    • H04L67/63Routing a service request depending on the request content or context
    • HELECTRICITY
    • H04ELECTRIC COMMUNICATION TECHNIQUE
    • H04LTRANSMISSION OF DIGITAL INFORMATION, e.g. TELEGRAPHIC COMMUNICATION
    • H04L45/00Routing or path finding of packets in data switching networks
    • H04L45/02Topology update or discovery
    • H04L45/04Interdomain routing, e.g. hierarchical routing
    • HELECTRICITY
    • H04ELECTRIC COMMUNICATION TECHNIQUE
    • H04LTRANSMISSION OF DIGITAL INFORMATION, e.g. TELEGRAPHIC COMMUNICATION
    • H04L41/00Arrangements for maintenance, administration or management of data switching networks, e.g. of packet switching networks
    • H04L41/50Network service management, e.g. ensuring proper service fulfilment according to agreements
    • H04L41/5058Service discovery by the service manager

Definitions

  • the present disclosure relates to the field of data communication networks, in particular to a method and device for sending a computing power announcement, and a computing power network element node.
  • the computing resources in the network are integrated into every corner of the network, so that each network node can become a provider of resources, and the user's request can be satisfied by calling the nearest node resource, which is no longer limited to a specific node, avoiding the connection and waste of network scheduling resources.
  • the purpose of the disclosed technical solution is to provide a computing power notification sending method, device and computing power network element node, which are used to solve the problem of large notification overhead in the network system of computing power processing in related technologies.
  • the present disclosure provides a method for sending a computing power announcement, which is applied to a first computing power network element node, wherein the method includes:
  • the computing power notification information includes at least one of the following:
  • the second field information used to record the computing power resource status of the target computing power node
  • the third field information used to record the computing power service status of the target computing power node.
  • the sending method wherein the method further includes:
  • the computing power announcement information is sent.
  • the transmission strategy includes:
  • the sending of the computing power notification information is an active release
  • the sending of the computing power notification information is sending the computing power notification information based on the obtained computing power service request.
  • the target service is a hotspot service
  • the target service is a non-hotspot service
  • the sending method wherein the target service is a hotspot service, and sending the computing power announcement information according to the transmission strategy includes:
  • the target notification domain includes a target geographic location range and/or a target service deployment area.
  • sending the computing power notification information includes:
  • BGP Border Gateway Protocol
  • the first field information, the second field information and the third field information are respectively one field information in the extended border gateway protocol BGP message.
  • An embodiment of the present disclosure also provides a method for sending a computing power announcement, which is applied to a second computing power network element node, wherein the method includes:
  • the computing power notification information includes at least one of the following:
  • the second field information used to record the computing power resource status of the target computing power node
  • the third field information used to record the computing power service status of the target computing power node.
  • the sending method wherein receiving the computing power announcement information of the target computing power node sent by the first computing power network element node, includes:
  • the sending method wherein receiving the computing power announcement information of the target computing power node sent by the first computing power network element node, includes:
  • the second computing power network element node is in the target notification domain of the first computing power network element node
  • the target notification domain includes a target geographic location range and/or a target service deployment area.
  • the sending method, wherein receiving the computing power notification information includes:
  • the first field information, the second field information and the third field information are respectively one field information in the extended BGP message.
  • An embodiment of the present disclosure also provides a computing power network element node, wherein the computing power network element node is a first computing power network element node, and includes a transceiver, wherein the transceiver is used for:
  • the computing power notification information includes at least one of the following:
  • the second field information used to record the computing power resource status of the target computing power node
  • the third field information used to record the computing power service status of the target computing power node.
  • An embodiment of the present disclosure also provides a computing power network element node, wherein the computing power network element node is a second computing power network element node, and includes a transceiver, wherein the transceiver is used for:
  • the computing power notification information includes at least one of the following:
  • the second field information used to record the computing power resource status of the target computing power node
  • the third field information used to record the computing power service status of the target computing power node.
  • An embodiment of the present disclosure also provides a device for sending a computing power announcement, which is applied to a first computing power network element node, wherein the device includes:
  • a sending module configured to send the computing power announcement information of the target computing power node to the second computing power network element node
  • the computing power notification information includes at least one of the following:
  • the second field information used to record the computing power resource status of the target computing power node
  • the third field information used to record the computing power service status of the target computing power node.
  • An embodiment of the present disclosure also provides a device for sending a computing power announcement, which is applied to a second computing power network element node, wherein the device includes:
  • the receiving module is configured to receive the computing power announcement information of the target computing power node sent by the first computing power network element node;
  • the computing power notification information includes at least one of the following:
  • the second field information used to record the computing power resource status of the target computing power node
  • the third field information used to record the computing power service status of the target computing power node.
  • An embodiment of the present disclosure also provides a computing power network element node, including: a processor, a memory, and a program stored in the memory and operable on the processor, and the program is implemented when executed by the processor.
  • the sending method of the computing power announcement as described in any one of the above.
  • An embodiment of the present disclosure also provides a readable storage medium, wherein a program is stored on the readable storage medium, and when the program is executed by a processor, the method for sending a computing power announcement as described in any one of the above items is implemented. step.
  • the method for sending the computing power announcement in the embodiment of the present disclosure classifies the computing power notification information according to the content of the computing power notification and the frequency to be sent, and selects different computing power notifications for different types of computing power notification information Protocols and notification strategies to reduce unnecessary signaling overhead and improve the transmission efficiency of computing power notifications.
  • FIG. 1 is a schematic structural diagram of an implementation of a computing power notification sending method applied to a computing power processing network system according to an embodiment of the present disclosure
  • FIG. 2 is a schematic flowchart of a method for sending a computing power announcement according to one embodiment of the present disclosure
  • Fig. 3 is a schematic diagram of an extended BGP message used to send computing power announcement information in an embodiment of the present disclosure
  • FIG. 4 is a schematic diagram illustrating transmission of hotspot services
  • FIG. 5 is a schematic diagram illustrating transmission of non-hotspot services
  • FIG. 6 is a schematic flowchart of a method for sending a computing power announcement according to another embodiment of the present disclosure
  • FIG. 7 is a schematic structural diagram of a computing power network element node described in one of the implementation manners of the embodiments of the present disclosure.
  • FIG. 8 is a schematic structural diagram of a computing power network element node described in another implementation manner of an embodiment of the present disclosure.
  • Fig. 9 is a schematic structural diagram of a sending device for a computing power notification according to one implementation mode of the embodiments of the present disclosure.
  • Fig. 10 is a schematic structural diagram of a computing power notification sending device according to another embodiment of the present disclosure.
  • the method for sending the notification of computing power described in the embodiments of the present disclosure is applied to the network system of computing power processing, and may also be called a computing power-aware network, a computing power network, a computing-network-integrated network, or a new type of computing-network-integrated network.
  • the computing power processing network system may include:
  • the network system can also include The structure of computing network management layer, computing power application layer, computing power routing layer, computing power resource layer and network resource layer; or, it can also include computing power service layer, computing power platform layer, computing power resource layer, computing power routing
  • the structure of the layer and the network resource layer is not limited to the implementation structure shown in FIG. 1 .
  • a computing power network element node refers to a network device with computing power in this article.
  • the computing power network element nodes may further include computing power routing nodes and computing power nodes (computing power nodes are sometimes also called computing nodes).
  • the computing power routing node can be located in the computing power routing layer of the computing power processing network system, and is a network device that transmits notifications of computing power resource information in the computing power processing network system.
  • Computing power nodes located in the computing power resource layer and/or network resource layer, refer to devices with computing power, which are used to provide computing power resources, which are equivalent to devices that process computing tasks in a computing power processing network system, such as data center Server equipment, all-in-one machines, etc.
  • the computing power node in the embodiment of the present disclosure may also be a computing power network element device, and the computing power network element device is a network transmission device at the network resource layer, such as a router. Power resources, providing computing power services.
  • the computing power notification information is transmitted between the computing power routing layer and the computing power resource layer, and all computing power information (including computing power resource information and computing power service information, etc.) is notified together. It is impossible to realize self-adaptive selection of different protocols and methods for notification in the network, resulting in a large amount of notification overhead in the network.
  • the embodiment of the present disclosure provides a method for sending a computing power notification. According to the content of the computing power notification Classify the computing power notification information and the frequency that needs to be sent. For different types of computing power notification information, choose different computing power notification protocols and notification strategies to reduce unnecessary signaling overhead and improve computing power notifications. transmission efficiency.
  • the embodiment of the present disclosure provides a method for sending a computing power announcement, which is applied to a first computing power network element node, as shown in FIG. 2 , the method includes:
  • the computing power notification information includes at least one of the following:
  • the second field information used to record the computing power resource status of the target computing power node
  • the third field information used to record the computing power service status of the target computing power node.
  • the first computing power network element node and the second computing power network element node may be one of computing power routing nodes and computing power nodes respectively, and optionally, the first The computing power network element node and the second computing power network element node may be any computing power routing node or computing power node in computing power business transmission.
  • the target computing power node is one of the computing power nodes in the process of computing power business transmission, and the computing power notification information of the target computing power node is among multiple computing power network element nodes in the computing power processing network system
  • the first computing power network element node and the second computing power network element node are two transmission nodes in the computing power service transmission process.
  • the method for sending the computing power announcement described in the specific embodiments of the present disclosure divides the computing power notification information into a variety of different types.
  • it may include:
  • computing power notification information including computing power service capability information is used to generate computing power topology and computing power service topology, and optionally, used in the registration process of computing power nodes, such as for computing power resources and computing power services Notify the status of the initial deployment of the computing power service;
  • the computing power service capability information may include the computing power enabling information of the computing power node and/or the initial deployment information of the computing power service;
  • Computing power notification information including computing power resource status is used for notification in the basic resource service request mode, and the notification protocol and notification strategy specifically used for computing power resource status notification can be adjusted adaptively.
  • the status of computing power resources includes central processing unit (Central Processing Unit, CPU)/graphics processing unit (Graphics Processing Unit, GPU), computing power deployment form and computing power deployment at least one of location etc.;
  • Computing power notification information including computing power service status is used for notification in the computing power service mode, and the notification protocol and notification strategy specifically used for computing power service status notification can be adjusted adaptively.
  • the computing power service status includes at least one of service identification (service ID), number of service connections, and service duration.
  • the computing power announcement information sent may include at least one of the following:
  • the second field information used to record the computing power resource status of the target computing power node
  • the third field information used to record the computing power service status of the target computing power node.
  • sending the computing power announcement information includes:
  • BGP Border Gateway Protocol
  • the first field information, the second field information and the third field information are respectively one field information in the extended BGP message.
  • the computing power notification information is carried through network protocol extensions, such as sending computing power notification information based on the computing power notification protocol extended by BGP/Interior Gateway Protocol (IGP).
  • network protocol extensions such as sending computing power notification information based on the computing power notification protocol extended by BGP/Interior Gateway Protocol (IGP).
  • the extended field in the message is used to carry computing power service capability information, which is used for notification of the initial deployment status of computing power resources and computing power services. That is, in the embodiment of the present disclosure, the first field information used to record the computing power service capability information of the target computing power node may be one of the field information in the extended BGP message.
  • the generation of computing power service topology includes two steps.
  • the first step is to generate service topology information.
  • the service topology information includes service identification information and service deployment location information; Notification deployment service identification information, such as service ID information, can be notified through Border Gateway Protocol Link State (BGP Link-State, BGP-LS), Dynamic Host Configuration Protocol (Dynamic Host Configuration Protocol, DHCP); optionally, BGP-LS can be extended to carry computing power service capability information: to identify the computing power service deployment information of each computing power node, computing power service information (such as service ID information) can be added to the node attribute (node attribute) field, and between nodes Notifications are made in advance, and the computing power service topology is first established.
  • Figure 3 shows the BGP node flag (node flag) field diagram, and the "Rsvd" field can be used to identify the computing power service capability information of the computing power node.
  • the method for sending the computing power notification described in the embodiments of the present disclosure may optionally design a customized computing power information update protocol according to the specific requirements for computing power information update. Notice that, optionally, the computing power resource status and computing power service status can be carried in a BGP update (update) extension field.
  • corresponding sending protocols can be set respectively according to the specific requirements of different message content of the sent computing power notification information, including update frequency, notification strategy, etc., that is, through different The field information of the field information sends the computing power announcement information of different message content.
  • the method for sending a computing power announcement described in the embodiment of the present disclosure optionally, the method further includes:
  • the computing power announcement information is sent.
  • an adaptive transmission strategy is provided according to the service status of the target service to be transmitted and/or the specific notification content of the computing power notification information.
  • the delivery strategy includes:
  • the sending of the computing power notification information is an active release
  • the sending of the computing power notification information is sending the computing power notification information based on the obtained computing power service request.
  • the target service is a hotspot service
  • the target service is a non-hotspot service
  • the target services to be transmitted can be divided into hotspot services and non-hotspot services, and different notification strategies are adopted for different types of divided services.
  • the computing power network element node located at the first hop node when the target service is transmitted classifies the transmitted target service as a hotspot service or a non-hotspot service.
  • the target service is a hotspot service
  • sending the computing power notification information includes:
  • the target notification domain includes a target geographic location range and/or a target service deployment area.
  • the computing power network element node which can be a computing power node or a computing power routing node
  • the computing power notification information does not make a network-wide computing power notification, but It is through the announcement within the scope of local announcement in the hotspot area.
  • the computing power service provider 10 actively sends computing power notification information to each computing power network element node 20 (such as a routing node), and the computing power notification information is distributed among multiple computing power network element nodes. Transfer between 20.
  • the division method of the target notification domain (that is, the notification range): the adjacent domain can be identified as a notification domain according to the geographical location, and the status information of the service is notified within this range (that is, the status information based on the geographic location as the dimension).
  • transmission strategy to send computing power notification information to computing power network element nodes within the target geographical location
  • another implementation method can divide the area with the same service deployment into the same notification domain according to the service dimension, and adopt this
  • the computing power notification information is sent to the computing power network element nodes in the target service deployment area.
  • the notification relationship between the notification domains can be determined according to the existing autonomous system (Autonomous System, AS) domain division in the Internet Protocol (Internet Protocol, IP) protocol .
  • AS Autonomous System
  • IP Internet Protocol
  • the sending of the computing power notification information is based on the obtained computing power service request, and the computing power notification information is sent. That is to say, specifically, the passive computing request is used to send computing power notification information, and the computing power notification information is not broadcast on the entire network to reduce the signaling overhead of computing power notification.
  • the computing power service message terminal 30 (such as a terminal) needs to send a computing power service request first, and the first computing power network element node 21 of the computing power routing (that is, is the first hop node), after receiving the computing power service request, continue to send the computing power service request to one or more computing power network element nodes that deploy corresponding services and computing power, and the computing power service provider 10
  • the computing power service requests feedback of computing power notification information, and optionally, the fed back computing power notification information may include computing power resource status and/or computing power service status.
  • the computing power notification information is classified according to the content of the computing power notification and the frequency to be sent, and for different types of computing power notification information, different computing power notification protocols and notifications are selected.
  • strategy to avoid unnecessary signaling overhead and provide fast route convergence optionally, according to the perceived multi-dimensional resource status, through the resource collaborative scheduling of the computing network, the business can be scheduled to the best destination node through the best path. While ensuring the best user experience, it improves the resource rate of the operator's network.
  • Another embodiment of the present disclosure also provides a method for sending a computing power announcement, which is applied to a second computing power network element node, as shown in FIG. 6 , the method includes:
  • the computing power notification information includes at least one of the following:
  • the second field information used to record the computing power resource status of the target computing power node
  • the third field information used to record the computing power service status of the target computing power node.
  • the first computing power network element node and the second computing power network element node may be one of computing power routing nodes and computing power nodes respectively, and optionally, the first computing power network element node and the second computing power network element node may be any computing power routing node or computing power node in computing power business transmission.
  • the target computing power node is one of the computing power nodes in the process of computing power business transmission, and the computing power notification information of the target computing power node is among multiple computing power network element nodes in the computing power processing network system
  • the first computing power network element node and the second computing power network element node are two transmission nodes in the computing power service transmission process.
  • the method for sending the computing power announcement in the embodiment of the present disclosure classifies the computing power notification information according to the content of the computing power notification and the frequency to be sent, and selects different computing power notifications for different types of computing power notification information Protocols and notification strategies to reduce unnecessary signaling overhead and improve the transmission efficiency of computing power notifications.
  • the sending method wherein receiving the computing power announcement information of the target computing power node sent by the first computing power network element node, includes:
  • the sending method wherein receiving the computing power announcement information of the target computing power node sent by the first computing power network element node, includes:
  • the second computing power network element node is in the target notification domain of the first computing power network element node
  • the target notification domain includes a target geographic location range and/or a target service deployment area.
  • the sending method, wherein receiving the computing power notification information includes:
  • the first field information, the second field information and the third field information are respectively one field information in the extended BGP message.
  • An embodiment of the present disclosure also provides a computing power network element node, wherein the computing power network element node is a first computing power network element node, as shown in FIG. 7 , the first computing power network element node 700 includes a transceiver 710 and processor 720, wherein the transceiver 710 is configured to:
  • the computing power notification information includes at least one of the following:
  • the second field information used to record the computing power resource status of the target computing power node
  • the third field information used to record the computing power service status of the target computing power node.
  • the processor 720 is used to:
  • the computing power announcement information is sent.
  • the computing power network element node wherein the transmission strategy includes:
  • the sending of the computing power notification information is an active release
  • the sending of the computing power notification information is sending the computing power notification information based on the obtained computing power service request.
  • the processor 720 determines that the sending of the computing power announcement information is an active release
  • the processor 720 determines that the sending of the computing power notification information is based on the obtained computing power service request, and sends the computing power notification information.
  • the computing power network element node wherein the target service is a hotspot service
  • the processor 720 sends the computing power notification information according to the transmission strategy, including:
  • the target notification domain includes a target geographic location range and/or a target service deployment area.
  • the computing power network element node, wherein the transceiver 710 sends the computing power notification information includes:
  • the first field information, the second field information and the third field information are respectively one field information in the extended BGP message.
  • Another embodiment of the present disclosure also provides a computing power network element node, wherein the computing power network element node is a second computing power network element node.
  • the second computing power network element node 800 includes a transceiver machine 810, wherein the transceiver 810 is used for:
  • the computing power notification information includes at least one of the following:
  • the second field information used to record the computing power resource status of the target computing power node
  • the third field information used to record the computing power service status of the target computing power node.
  • the computing power network element node wherein the transceiver 810 receives the computing power announcement information of the target computing power node sent by the first computing power network element node, includes:
  • the computing power network element node wherein the transceiver 810 receives the computing power announcement information of the target computing power node sent by the first computing power network element node, includes:
  • the computing power network element node wherein the second computing power network element node is in the target notification domain of the first computing power network element node;
  • the target notification domain includes a target geographic location range and/or a target service deployment area.
  • the computing power network element node, wherein the transceiver 810 receives the computing power notification information includes:
  • the first field information, the second field information and the third field information are respectively one field information in the extended BGP message.
  • An embodiment of the present disclosure also provides a device for sending a computing power announcement, which is applied to a first computing power network element node. As shown in FIG. 9 , the device includes:
  • a sending module 910 configured to send the computing power notification information of the target computing power node to the second computing power network element node
  • the computing power notification information includes at least one of the following:
  • the second field information used to record the computing power resource status of the target computing power node
  • the third field information used to record the computing power service status of the target computing power node.
  • the sending device wherein the device further includes a processing module 920, and the processing module 920 is configured to:
  • the computing power announcement information is sent.
  • the transmission strategy includes:
  • the sending of the computing power notification information is an active release
  • the sending of the computing power notification information is sending the computing power notification information based on the obtained computing power service request.
  • the sending device when the target service is a hotspot service, it is determined that the sending of the computing power notification information is an active release;
  • the target service is a non-hotspot service
  • the sending device wherein the target service is a hotspot service
  • the processing module 920 sends the computing power notification information according to the transmission strategy, including:
  • the target notification domain includes a target geographic location range and/or a target service deployment area.
  • the sending device wherein the sending module 910 sends the computing power notification information includes:
  • the first field information, the second field information and the third field information are respectively one field information in the extended BGP message.
  • Another embodiment of the present disclosure also provides a device for sending a computing power announcement, which is applied to a second computing power network element node. As shown in FIG. 10 , the device includes:
  • the receiving module 1010 is configured to receive the computing power announcement information of the target computing power node sent by the first computing power network element node;
  • the computing power notification information includes at least one of the following:
  • the second field information used to record the computing power resource status of the target computing power node
  • the third field information used to record the computing power service status of the target computing power node.
  • the sending device wherein the receiving module 1010 receives the computing power announcement information of the target computing power node sent by the first computing power network element node, includes:
  • the sending device wherein the receiving module 1010 receives the computing power announcement information of the target computing power node sent by the first computing power network element node, includes:
  • the second computing power network element node is in the target announcement domain of the first computing power network element node
  • the target notification domain includes a target geographic location range and/or a target service deployment area.
  • the sending device, wherein the receiving module 1010 receives the computing power notification information includes:
  • the first field information, the second field information and the third field information are respectively one field information in the extended BGP message.
  • An embodiment of the present disclosure also provides a computing power network element node, which includes: a processor, a memory, and a program stored on the memory and operable on the processor, and the program is executed by the processor Realize the sending method of the computing power announcement as described in any one of the above.
  • the computer-readable storage medium is applied to the above-mentioned terminal, and when applied to the terminal, the execution steps in the method for reporting a smoke alarm are as described in detail above, and will not be repeated here.
  • the disclosed methods and devices can be implemented in other ways.
  • the device embodiments described above are only illustrative.
  • the division of the units is only a logical function division. In actual implementation, there may be other division methods.
  • multiple units or components can be combined or May be integrated into another system, or some features may be ignored, or not implemented.
  • the mutual coupling or direct coupling or communication connection shown or discussed may be through some interfaces, and the indirect coupling or communication connection of devices or units may be in electrical, mechanical or other forms.
  • each functional unit in each embodiment of the present disclosure may be integrated into one processing unit, each unit may be physically included separately, or two or more units may be integrated into one unit.
  • the above-mentioned integrated units can be implemented in the form of hardware, or in the form of hardware plus software functional units.
  • the above-mentioned integrated units implemented in the form of software functional units may be stored in a computer-readable storage medium.
  • the above-mentioned software functional units are stored in a storage medium, and include several instructions to enable a computer device (which may be a personal computer, server, or network device, etc.) to execute some steps of the sending and receiving methods described in various embodiments of the present disclosure.
  • the aforementioned storage media include: U disk, mobile hard disk, read-only memory (Read-Only Memory, ROM), random access memory (Random Access Memory, RAM), magnetic disk or optical disc and other media that can store program codes. .

Landscapes

  • Engineering & Computer Science (AREA)
  • Computer Networks & Wireless Communication (AREA)
  • Signal Processing (AREA)
  • Data Exchanges In Wide-Area Networks (AREA)
  • Multi Processors (AREA)
  • Management, Administration, Business Operations System, And Electronic Commerce (AREA)
  • Mobile Radio Communication Systems (AREA)

Abstract

本公开提供一种算力通告的发送方法、装置及算力网元节点。所述方法包括:向第二算力网元节点发送目标算力节点的算力通告信息;其中,所述算力通告信息包括以下中的至少之一:用于记录所述目标算力节点的算力服务能力信息的第一字段信息;用于记录所述目标算力节点的算力资源状态的第二字段信息;用于记录所述目标算力节点的算力服务状态的第三字段信息。

Description

算力通告的发送方法、装置及算力网元节点
相关申请的交叉引用
本公开主张在2021年7月2日在中国提交的中国专利申请号No.202110750298.8的优先权,其全部内容通过引用包含于此。
技术领域
本公开涉及数据通信网络领域,尤其是指一种算力通告的发送方法、装置及算力网元节点。
背景技术
从云计算、边缘计算的发展大趋势下,未来社会中会在靠近用户的不同距离遍布许多不同规模的算力,通过全球网络为用户提供各类个性化的服务。从百亿量级的智能终端,到全球十亿量级的家庭网关,再到每个城市中未来边缘计算带来的数千个具备计算能力的边缘云,以及每个国家数十个大型的云数据中心(Data Center,DC),形成海量的泛在算力从各处接入互联网,形成计算和网络深度融合的发展趋势。
网络中的计算资源融入到网络的各个角落,使每一个网络节点都可以成为资源的提供者,用户的请求可以通过调用最近的节点资源来满足,不再局限于某一特定节点,避免造成连接和网络调度资源的浪费。
目前,基于算力处理的网络系统中,无法自适应选择不同的协议和方式在网络中通告信息,从而造成网络中的大量通告开销。
发明内容
本公开技术方案的目的在于提供一种算力通告的发送方法、装置及算力网元节点,用于解决相关技术算力处理的网络系统中,通告开销较大的问题。
本公开提供一种算力通告的发送方法,应用于第一算力网元节点,其中,所述方法包括:
向第二算力网元节点发送目标算力节点的算力通告信息;
其中,所述算力通告信息包括以下中的至少之一:
用于记录所述目标算力节点的算力服务能力信息的第一字段信息;
用于记录所述目标算力节点的算力资源状态的第二字段信息;
用于记录所述目标算力节点的算力服务状态的第三字段信息。
可选地,所述的发送方法,其中,所述方法还包括:
根据待传输的目标业务和/或算力通告信息,确定所述算力通告信息的传输策略;
根据所述传输策略,发送所述算力通告信息。
可选地,所述的发送方法,其中,所述传输策略包括:
所述算力通告信息的发送为主动发布;或者
所述算力通告信息的发送为基于所获得的算力服务请求,发送所述算力通告信息。
可选地,所述的发送方法,其中,所述目标业务为热点服务时,确定所述算力通告信息的发送为主动发布;
所述目标业务为非热点服务时,确定所述算力通告信息的发送为基于所获得的算力服务请求,发送所述算力通告信息。
可选地,所述的发送方法,其中,所述目标业务为热点服务,根据所述传输策略,发送所述算力通告信息,包括:
向处于目标通告域内的所述第二算力网元节点发送所述算力通告信息;
其中,所述目标通告域包括目标地理位置范围和/或目标服务部署区域。
可选地,所述的发送方法,其中,发送所述算力通告信息,包括:
通过扩展边界网关协议(Border Gateway Protocol,BGP)消息发送所述算力通告信息;
其中,所述第一字段信息、所述第二字段信息和所述第三字段信息分别为扩展边界网关协议BGP消息中的其中一字段信息。
本公开实施例还提供一种算力通告的发送方法,应用于第二算力网元节点,其中,所述方法包括:
接收第一算力网元节点发送的目标算力节点的算力通告信息;
其中,所述算力通告信息包括以下中的至少之一:
用于记录所述目标算力节点的算力服务能力信息的第一字段信息;
用于记录所述目标算力节点的算力资源状态的第二字段信息;
用于记录所述目标算力节点的算力服务状态的第三字段信息。
可选地,所述的发送方法,其中,接收第一算力网元节点发送的目标算力节点的算力通告信息,包括:
接收所述第一算力网元节点主动发送的所述算力通告信息。
可选地,所述的发送方法,其中,接收第一算力网元节点发送的目标算力节点的算力通告信息,包括:
在接收用户端发送的第一算力服务请求后,向第一算力网元节点发送第二算力服务请求;
接收所述第一算力网元节点响应所述第二算力服务请求发送的所述算力通告信息。
可选地,所述的发送方法,其中,所述第二算力网元节点处于所述第一算力网元节点的目标通告域内;
其中,所述目标通告域包括目标地理位置范围和/或目标服务部署区域。
可选地,所述的发送方法,其中,接收所述算力通告信息,包括:
通过扩展边界网关协议BGP消息接收所述算力通告信息;
其中,所述第一字段信息、所述第二字段信息和所述第三字段信息分别为扩展BGP消息中的其中一字段信息。
本公开实施例还提供一种算力网元节点,其中所述算力网元节点为第一算力网元节点,包括收发机,其中,所述收发机用于:
向第二算力网元节点发送目标算力节点的算力通告信息;
其中,所述算力通告信息包括以下中的至少之一:
用于记录所述目标算力节点的算力服务能力信息的第一字段信息;
用于记录所述目标算力节点的算力资源状态的第二字段信息;
用于记录所述目标算力节点的算力服务状态的第三字段信息。
本公开实施例还提供一种算力网元节点,其中所述算力网元节点为第二算力网元节点,包括收发机,其中,所述收发机用于:
接收第一算力网元节点发送的目标算力节点的算力通告信息;
其中,所述算力通告信息包括以下中的至少之一:
用于记录所述目标算力节点的算力服务能力信息的第一字段信息;
用于记录所述目标算力节点的算力资源状态的第二字段信息;
用于记录所述目标算力节点的算力服务状态的第三字段信息。
本公开实施例还提供一种算力通告的发送装置,应用于第一算力网元节点,其中,所述装置包括:
发送模块,用于向第二算力网元节点发送目标算力节点的算力通告信息;
其中,所述算力通告信息包括以下中的至少之一:
用于记录所述目标算力节点的算力服务能力信息的第一字段信息;
用于记录所述目标算力节点的算力资源状态的第二字段信息;
用于记录所述目标算力节点的算力服务状态的第三字段信息。
本公开实施例还提供一种算力通告的发送装置,应用于第二算力网元节点,其中,所述装置包括:
接收模块,用于接收第一算力网元节点发送的目标算力节点的算力通告信息;
其中,所述算力通告信息包括以下中的至少之一:
用于记录所述目标算力节点的算力服务能力信息的第一字段信息;
用于记录所述目标算力节点的算力资源状态的第二字段信息;
用于记录所述目标算力节点的算力服务状态的第三字段信息。
本公开实施例还提供一种算力网元节点,包括:处理器、存储器及存储在所述存储器上并可在所述处理器上运行的程序,所述程序被所述处理器执行时实现如上任一项所述的算力通告的发送方法。
本公开实施例还提供一种可读存储介质,其中,所述可读存储介质上存储有程序,所述程序被处理器执行时实现如上任一项所述的算力通告的发送方法中的步骤。
本公开上述技术方案中的至少一个具有以下有益效果:
本公开实施例所述算力通告的发送方法,根据算力通告的内容和所需要发送的频率等,对算力通告信息进行分类,对于不同类型的算力通告信息,选择不同的算力通告协议和通告策略,以降低不必要的信令开销,提高算力 通告发送的传输效率。
附图说明
图1为本公开实施例所述算力通告的发送方法应用于算力处理的网络系统的其中一实施方式的结构示意图;
图2为本公开其中一实施例所述算力通告的发送方法的流程示意图;
图3为本公开实施例中用于发送算力通告信息的扩展BGP消息的示意图;
图4为说明用于热点服务传输的示意图;
图5为说明用于非热点服务传输的示意图;
图6为本公开另一实施例所述算力通告的发送方法的流程示意图;
图7为本公开实施例其中一实施方式所述算力网元节点的结构示意图;
图8为本公开实施例另一实施方式所述算力网元节点的结构示意图;
图9为本公开实施例其中一实施方式所述算力通告的发送装置的结构示意图;
图10为本公开实施例另一实施方式所述算力通告的发送装置的结构示意图。
具体实施方式
下面将参照附图更详细地描述本公开的示例性实施例。虽然附图中显示了本公开的示例性实施例,然而应当理解,可以以各种形式实现本公开而不应被这里阐述的实施例所限制。相反,提供这些实施例是为了能够更透彻地理解本公开,并且能够将本公开的范围完整的传达给本领域的技术人员。
本申请的说明书和权利要求书中的术语“第一”、“第二”等是用于区别类似的对象,而不必用于描述特定的顺序或先后次序。应该理解这样使用的数据在适当情况下可以互换,以便这里描述的本申请的实施例例如能够以除了在这里图示或描述的那些以外的顺序实施。此外,术语“包括”和“具有”以及他们的任何变形,意图在于覆盖不排他的包含,例如,包含了一系列步骤或单元的过程、方法、系统、产品或设备不必限于清楚地列出的那些步骤或单元,而是可包括没有清楚地列出的或对于这些过程、方法、产品或设备 固有的其它步骤或单元。说明书以及权利要求中“和/或”表示所连接对象的至少其中之一。
以下描述提供示例而并非限定权利要求中阐述的范围、适用性或者配置。可以对所讨论的要素的功能和布置作出改变而不会脱离本公开的精神和范围。各种示例可恰适地省略、替代、或添加各种规程或组件。例如,可以按不同于所描述的次序来执行所描述的方法,并且可以添加、省去、或组合各种步骤。另外,参照某些示例所描述的特征可在其他示例中被组合。
为帮助更好的理解本公开实施例的相关方案,下面对本公开实施例所述算力通告的发送方法所应用的系统,以及所涉及的相关概念进行说明。
本公开实施例所述算力通告的发送方法,应用于算力处理的网络系统,也可以称为算力感知网络、算力网络、算网一体网络或者计算网络融合的新型网络等名称。其中一实施方式,如图1所示,所述算力处理的网络系统可以包括:
算力路由层;
算力资源层;
网络资源层;
算网管理层;以及
算力服务层。
所述网络系统除可以为包括上述的算力路由层、算力资源层、网络资源层、算网管理层及算力服务层的结构之外,另一实施方式,该网络系统也可以为包括算网管理层、算力应用层、算力路由层、算力资源层和网络资源层的结构;或者,也可以为包括算力服务层、算力平台层、算力资源层、算力路由层和网络资源层的结构,具体并不以图1所示实施结构为限。
需要说明的是,本公开实施例中,算力网元节点,在本文中是指具有算力的网络设备。算力网元节点进一步的可包括算力路由节点和算力节点(算力节点有时候也被称为计算节点)。其中,算力路由节点,可以位于算力处理的网络系统的算力路由层,是一种将算力资源信息在算力处理的网络系统中的通告传输的网络设备。
算力节点,位于算力资源层和/或网络资源层,是指具备计算能力的设备, 用于提供算力资源,相当于算力处理的网络系统中处理计算任务的设备,例如数据中心的服务器设备、一体机等。另外,本公开实施例的算力节点还可以是算力网元设备,所述算力网元设备为网络资源层的网络传输设备,如路由器等,同时该算力网元设备还可以提供算力资源,提供算力服务。
通常技术的算力处理的网络系统中,算力路由层与算力资源层之间传输算力通告信息,其中全部的算力信息(包括算力资源信息和算力服务信息等)一起通告,无法实现自适应选择不同的协议和方式在网络中通告,从而造成网络中的大量通告开销,为解决该技术问题,本公开实施例提供一种算力通告的发送方法,根据算力通告的内容和所需要发送的频率等,对算力通告信息进行分类,对于不同类型的算力通告信息,选择不同的算力通告协议和通告策略,以降低不必要的信令开销,提高算力通告发送的传输效率。
可选地,其中一实施方式,本公开实施例提供一种算力通告的发送方法,应用于第一算力网元节点,如图2所示,所述方法包括:
S210,向第二算力网元节点发送目标算力节点的算力通告信息;
其中,所述算力通告信息包括以下中的至少之一:
用于记录所述目标算力节点的算力服务能力信息的第一字段信息;
用于记录所述目标算力节点的算力资源状态的第二字段信息;
用于记录所述目标算力节点的算力服务状态的第三字段信息。
需要说明的是,本公开实施例中,第一算力网元节点和第二算力网元节点可以分别为算力路由节点和算力节点中的其中之一,且可选地,第一算力网元节点和第二算力网元节点可以分别为算力业务传输中的任一算力路由节点或算力节点。
可选地,目标算力节点为算力业务传输过程中的其中一算力节点,该目标算力节点的算力通告信息在算力处理的网络系统中的多个算力网元节点之间传输,第一算力网元节点和第二算力网元节点为算力业务传输过程中的其中两个传输节点。
本公开具体实施例所述算力通告的发送方法,将算力通告信息划分为多种不同类型,可选地,可以包括:
算力服务能力信息;
算力资源状态;
算力服务状态。
其中,包括算力服务能力信息的算力通告信息,用于生成算力拓扑以及算力服务拓扑,可选地,用于算力节点的注册流程,如用于对算力资源和算力服务的初始化部署的状况进行通告;可选地,该算力服务能力信息可以包括算力节点的算力使能信息和/或算力服务初始化部署信息;
包括算力资源状态的算力通告信息,用于基础资源服务请求模式下的通告,其中具体用于算力资源状态通告的通告协议和通告策略可自适性调整。本公开实施例中,其中一实施方式,可选地,算力资源状态包括中央处理器(Central Processing Unit,CPU)/图形处理器(Graphics Processing Unit,GPU)、算力部署形态和算力部署位置等的至少之一;
包括算力服务状态的算力通告信息,用于算力服务模式下的通告,其中具体用于算力服务状态通告的通告协议和通告策略可自适性调整。本公开实施例中,其中一实施方式,可选地,算力服务状态包括服务标识(service ID)、服务连接数和服务持续时间等中的至少之一。
采用本公开实施例所述算力通告的发送方法,通过将算力通告信息划分为多种不同的类型,根据不同算力通告信息分别发送的通告协议和通告策略,分别发送相应的算力通告信息,使得所发送的算力通告信息可以包括以下中的至少之一:
用于记录所述目标算力节点的算力服务能力信息的第一字段信息;
用于记录所述目标算力节点的算力资源状态的第二字段信息;
用于记录所述目标算力节点的算力服务状态的第三字段信息。
可选地,在步骤S210,发送所述算力通告信息,包括:
通过扩展边界网关协议(Border Gateway Protocol,BGP)消息发送所述算力通告信息;
其中,所述第一字段信息、所述第二字段信息和所述第三字段信息分别为扩展BGP消息中的其中一字段信息。
采用本公开实施例所述算力通告的发送方法,针对能够将算力通告信息划分为多种不同类型分别进行通告的方式,可以设计多种算力信息通告协议, 不同的算力通告信息依据不同的算力信息通告协议发送,也即算力通告信息中用于发送不同的算力通告内容的字段信息不同。
本公开实施例中,可选地,通过网络协议扩展携带算力通告信息,如基于BGP/内部网关协议(Interior Gateway Protocol,IGP)扩展的算力通告协议发送算力通告信息。
其中一实施方式,可选地,通过扩展BGP消息中,利用消息中的扩展字段携带算力服务能力信息,用于算力资源和算力服务的初始化部署的状况进行通告。也即,本公开实施例中,用于记录所述目标算力节点的算力服务能力信息的第一字段信息,可以为扩展BGP消息中的其中一字段信息。
需要说明的是,算力服务拓扑的生成包括两步,第一步是生成服务拓扑信息,可选地,该服务拓扑信息包括服务标识信息、服务部署的位置信息;可选的,算力节点通告部署服务标识信息,如service ID信息等,可以通过边界网关协议链路状态(BGP Link-State,BGP-LS)、动态主机配置协议(Dynamic Host Configuration Protocol,DHCP)进行通告;可选地,可以通过扩展BGP-LS携带算力服务能力信息:识别各算力节点的算力服务部署信息,可以在节点属性(node attribute)字段增加算力服务信息(如service ID信息),并在节点之间通告,先行建立算力服务拓扑。如图3所示为BGP节点标志(node flag)字段图,通过“Rsvd”字段可以用来标识算力节点的算力服务能力信息。
本公开实施例所述算力通告的发送方法,可选地,根据算力信息更新的特定需求,设计定制化的算力信息更新协议,举例说明,根据算力资源状态和算力服务状态进行通告,可选地,该算力资源状态和算力服务状态可以采用BGP更新(update)扩展字段来携带。
需要说明的是,本公开实施例所述发送方法,可以根据所发送的算力通告信息的不同消息内容的特定需求,包括更新频率、通告策略等,分别设置对应的发送协议,也即通过不同的字段信息发送不同消息内容的算力通告信息。
本公开实施例所述算力通告的发送方法,可选地,所述方法还包括:
根据待传输的目标业务和/或算力通告信息,确定所述算力通告信息的传输策略;
根据所述传输策略,发送所述算力通告信息。
采用本公开实施例所述发送方法,根据待传输的目标业务的业务状态和/或算力通告信息的具体通告内容,提供自适应的传输策略。
所述传输策略包括:
所述算力通告信息的发送为主动发布;或者
所述算力通告信息的发送为基于所获得的算力服务请求,发送所述算力通告信息。
可选地,本公开实施例所述发送方法,所述目标业务为热点服务时,确定所述算力通告信息的发送为主动发布;
所述目标业务为非热点服务时,确定所述算力通告信息的发送为基于所获得的算力服务请求,发送所述算力通告信息。
采用该实施方式,可选地,算力处理的网络系统中,可以将所需要传输的目标业务划分为热点服务和非热点服务,对所划分的不同类型的业务采用不同的通告策略。可选地,位于目标业务传输时的第一跳节点的算力网元节点,将所传输的目标业务划分为热点服务或非热点服务。
可选地,对热点服务,确定所述算力通告信息的发送为主动发布。
其中一实施方式,所述目标业务为热点服务,根据所述传输策略,发送所述算力通告信息,包括:
向处于目标通告域内的所述第二算力网元节点发送所述算力通告信息;
其中,所述目标通告域包括目标地理位置范围和/或目标服务部署区域。
具体地,对于目标业务为热点服务,需要算力网元节点(可以为算力节点或者算力路由节点)主动发布算力通告信息,同时该算力通告信息不做全网算力通告,而是通过热点区域内进行局部通告范围内的通告。如图4所示,采用该实施方式,算力服务提供者10主动向各算力网元节点20(如为路由节点)发送算力通告信息,算力通告信息在多个算力网元节点20之间传输。
其中一实施方式,目标通告域(也即通告范围)的划分方法:可以按照地理位置,标识相邻域为一个通告域,在这个范围内通告服务的状态信息(也即依据地理位置为维度的传输策略,向处于目标地理位置范围内的算力网元节点发送算力通告信息);另一实施方式,可以依据服务为维度,将有同一服 务部署的区域划分为同一个通告域,采用该实施方式,对于所传输的目标业务,根据所确定的依据服务为维度的传输策略,向处于目标服务部署区域内的算力网元节点发送算力通告信息。
其中,依据地理位置为维度时,可选的,可以根据网际互连协议(Internet Protocol,IP)协议中已有的自治系统(Autonomous System,AS)域划分,确定各通告域之间的通告关系。
采用本公开实施例所述发送方法,可选地,对于非热点服务,确定所述算力通告信息的发送为基于所获得的算力服务请求,发送所述算力通告信息。也即,具体地,采用被动计算请求发送算力通告信息,算力通告信息不做全网广播,以降低算力通告的信令开销。
具体地,如图5所示,采用该实施方式,首先需要算力服务消息端30(如为终端)先发送算力服务请求,算力路由的第一个算力网元节点21(也即为第一跳节点),收到算力服务请求后,继续向一个或者多个部署相应服务和算力的算力网元节点发该算力服务请求,算力服务提供者10根据所接收的该算力服务请求反馈算力通告信息,可选地,所反馈的算力通告信息可以包括算力资源状态和/或算力服务状态。
采用本公开实施例所述发送方法,根据算力通告的内容和所需要发送的频率等,对算力通告信息进行分类,对于不同类型的算力通告信息,选择不同的算力通告协议和通告策略,以避免不必要的信令开销,并提供路由的快速收敛;可选地,根据感知多维资源状态,通过算网的资源协同调度,实现业务通过最佳路径调度到最佳目的节点,在保证用户最佳体验的同时,提高运营商网络的资源利率。
本公开另一实施例还提供一种算力通告的发送方法,应用于第二算力网元节点,如图6所示,所述方法包括:
S610,接收第一算力网元节点发送的目标算力节点的算力通告信息;
其中,所述算力通告信息包括以下中的至少之一:
用于记录所述目标算力节点的算力服务能力信息的第一字段信息;
用于记录所述目标算力节点的算力资源状态的第二字段信息;
用于记录所述目标算力节点的算力服务状态的第三字段信息。
本公开实施例中,第一算力网元节点和第二算力网元节点可以分别为算力路由节点和算力节点中的其中之一,且可选地,第一算力网元节点和第二算力网元节点可以分别为算力业务传输中的任一算力路由节点或算力节点。
可选地,目标算力节点为算力业务传输过程中的其中一算力节点,该目标算力节点的算力通告信息在算力处理的网络系统中的多个算力网元节点之间传输,第一算力网元节点和第二算力网元节点为算力业务传输过程中的其中两个传输节点。
本公开实施例所述算力通告的发送方法,根据算力通告的内容和所需要发送的频率等,对算力通告信息进行分类,对于不同类型的算力通告信息,选择不同的算力通告协议和通告策略,以降低不必要的信令开销,提高算力通告发送的传输效率。
可选地,所述的发送方法,其中,接收第一算力网元节点发送的目标算力节点的算力通告信息,包括:
接收所述第一算力网元节点主动发送的所述算力通告信息。
可选地,所述的发送方法,其中,接收第一算力网元节点发送的目标算力节点的算力通告信息,包括:
在接收用户端发送的第一算力服务请求后,向第一算力网元节点发送第二算力服务请求;
接收所述第一算力网元节点响应所述第二算力服务请求发送的所述算力通告信息。
可选地,所述的发送方法,其中,所述第二算力网元节点处于所述第一算力网元节点的目标通告域内;
其中,所述目标通告域包括目标地理位置范围和/或目标服务部署区域。
可选地,所述的发送方法,其中,接收所述算力通告信息,包括:
通过扩展BGP消息接收所述算力通告信息;
其中,所述第一字段信息、所述第二字段信息和所述第三字段信息分别为扩展BGP消息中的其中一字段信息。
本公开实施例还提供一种算力网元节点,其中所述算力网元节点为第一算力网元节点,如图7所示,该第一算力网元节点700包括收发机710和处 理器720,其中,所述收发机710用于:
向第二算力网元节点发送目标算力节点的算力通告信息;
其中,所述算力通告信息包括以下中的至少之一:
用于记录所述目标算力节点的算力服务能力信息的第一字段信息;
用于记录所述目标算力节点的算力资源状态的第二字段信息;
用于记录所述目标算力节点的算力服务状态的第三字段信息。
可选地,所述的算力网元节点,其中,处理器720用于:
根据待传输的目标业务和/或算力通告信息,确定所述算力通告信息的传输策略;
根据所述传输策略,发送所述算力通告信息。
可选地,所述的算力网元节点,其中,所述传输策略包括:
所述算力通告信息的发送为主动发布;或者
所述算力通告信息的发送为基于所获得的算力服务请求,发送所述算力通告信息。
可选地,所述的算力网元节点,其中,所述目标业务为热点服务时,处理器720确定所述算力通告信息的发送为主动发布;
所述目标业务为非热点服务时,处理器720确定所述算力通告信息的发送为基于所获得的算力服务请求,发送所述算力通告信息。
可选地,所述的算力网元节点,其中,所述目标业务为热点服务,处理器720根据所述传输策略,发送所述算力通告信息,包括:
向处于目标通告域内的所述第二算力网元节点发送所述算力通告信息;
其中,所述目标通告域包括目标地理位置范围和/或目标服务部署区域。
可选地,所述的算力网元节点,其中,所述收发机710发送所述算力通告信息,包括:
通过扩展BGP消息发送所述算力通告信息;
其中,所述第一字段信息、所述第二字段信息和所述第三字段信息分别为扩展BGP消息中的其中一字段信息。
本公开另一实施例还提供一种算力网元节点,其中所述算力网元节点为第二算力网元节点,如图8所示,该第二算力网元节点800包括收发机810, 其中,所述收发机810用于:
接收第一算力网元节点发送的目标算力节点的算力通告信息;
其中,所述算力通告信息包括以下中的至少之一:
用于记录所述目标算力节点的算力服务能力信息的第一字段信息;
用于记录所述目标算力节点的算力资源状态的第二字段信息;
用于记录所述目标算力节点的算力服务状态的第三字段信息。
可选地,所述的算力网元节点,其中,所述收发机810接收第一算力网元节点发送的目标算力节点的算力通告信息,包括:
接收所述第一算力网元节点主动发送的所述算力通告信息。
可选地,所述的算力网元节点,其中,所述收发机810接收第一算力网元节点发送的目标算力节点的算力通告信息,包括:
在接收用户端发送的第一算力服务请求后,向第一算力网元节点发送第二算力服务请求;
接收所述第一算力网元节点响应所述第二算力服务请求发送的所述算力通告信息。
可选地,所述的算力网元节点,其中,所述第二算力网元节点处于所述第一算力网元节点的目标通告域内;
其中,所述目标通告域包括目标地理位置范围和/或目标服务部署区域。
可选地,所述的算力网元节点,其中,所述收发机810接收所述算力通告信息,包括:
通过扩展BGP消息接收所述算力通告信息;
其中,所述第一字段信息、所述第二字段信息和所述第三字段信息分别为扩展BGP消息中的其中一字段信息。
本公开实施例还提供一种算力通告的发送装置,应用于第一算力网元节点,如图9所示,所述装置包括:
发送模块910,用于向第二算力网元节点发送目标算力节点的算力通告信息;
其中,所述算力通告信息包括以下中的至少之一:
用于记录所述目标算力节点的算力服务能力信息的第一字段信息;
用于记录所述目标算力节点的算力资源状态的第二字段信息;
用于记录所述目标算力节点的算力服务状态的第三字段信息。
可选地,所述的发送装置,其中,所述装置还包括处理模块920,该处理模块920用于:
根据待传输的目标业务和/或算力通告信息,确定所述算力通告信息的传输策略;
根据所述传输策略,发送所述算力通告信息。
可选地,所述的发送装置,其中,所述传输策略包括:
所述算力通告信息的发送为主动发布;或者
所述算力通告信息的发送为基于所获得的算力服务请求,发送所述算力通告信息。
可选地,所述的发送装置,其中,所述目标业务为热点服务时,确定所述算力通告信息的发送为主动发布;
所述目标业务为非热点服务时,确定所述算力通告信息的发送为基于所获得的算力服务请求,发送所述算力通告信息。
可选地,所述的发送装置,其中,所述目标业务为热点服务,处理模块920根据所述传输策略,发送所述算力通告信息,包括:
向处于目标通告域内的所述第二算力网元节点发送所述算力通告信息;
其中,所述目标通告域包括目标地理位置范围和/或目标服务部署区域。
可选地,所述的发送装置,其中,发送模块910发送所述算力通告信息,包括:
通过扩展BGP消息发送所述算力通告信息;
其中,所述第一字段信息、所述第二字段信息和所述第三字段信息分别为扩展BGP消息中的其中一字段信息。
本公开另一实施例还提供一种算力通告的发送装置,应用于第二算力网元节点,如图10所示,所述装置包括:
接收模块1010,用于接收第一算力网元节点发送的目标算力节点的算力通告信息;
其中,所述算力通告信息包括以下中的至少之一:
用于记录所述目标算力节点的算力服务能力信息的第一字段信息;
用于记录所述目标算力节点的算力资源状态的第二字段信息;
用于记录所述目标算力节点的算力服务状态的第三字段信息。
可选地,所述的发送装置,其中,接收模块1010接收第一算力网元节点发送的目标算力节点的算力通告信息,包括:
接收所述第一算力网元节点主动发送的所述算力通告信息。
可选地,所述的发送装置,其中,接收模块1010接收第一算力网元节点发送的目标算力节点的算力通告信息,包括:
在接收用户端发送的第一算力服务请求后,向第一算力网元节点发送第二算力服务请求;
接收所述第一算力网元节点响应所述第二算力服务请求发送的所述算力通告信息。
可选地,所述的发送装置,其中,所述第二算力网元节点处于所述第一算力网元节点的目标通告域内;
其中,所述目标通告域包括目标地理位置范围和/或目标服务部署区域。
可选地,所述的发送装置,其中,接收模块1010接收所述算力通告信息,包括:
通过扩展BGP消息接收所述算力通告信息;
其中,所述第一字段信息、所述第二字段信息和所述第三字段信息分别为扩展BGP消息中的其中一字段信息。
本公开实施例还提供一种算力网元节点,其中,包括:处理器、存储器及存储在所述存储器上并可在所述处理器上运行的程序,所述程序被所述处理器执行时实现如上任一项所述的算力通告的发送方法。
另外,本公开具体实施例还提供一种可读存储介质,其上存储有程序,其中,该程序被处理器执行时实现如上中任一项所述算力通告的发送方法中的步骤。
具体地,该计算机可读存储介质应用于上述的终端,在应用于终端时,对应烟感告警上报的方法中的执行步骤如上的详细描述,在此不再赘述。
在本申请所提供的几个实施例中,应该理解到,所揭露方法和装置,可 以通过其它的方式实现。例如,以上所描述的装置实施例仅仅是示意性的,例如,所述单元的划分,仅仅为一种逻辑功能划分,实际实现时可以有另外的划分方式,例如多个单元或组件可以结合或者可以集成到另一个系统,或一些特征可以忽略,或不执行。另一点,所显示或讨论的相互之间的耦合或直接耦合或通信连接可以是通过一些接口,装置或单元的间接耦合或通信连接,可以是电性,机械或其它的形式。
另外,在本公开各个实施例中的各功能单元可以集成在一个处理单元中,也可以是各个单元单独物理包括,也可以两个或两个以上单元集成在一个单元中。上述集成的单元既可以采用硬件的形式实现,也可以采用硬件加软件功能单元的形式实现。
上述以软件功能单元的形式实现的集成的单元,可以存储在一个计算机可读取存储介质中。上述软件功能单元存储在一个存储介质中,包括若干指令用使得一台计算机设备(可以是个人计算机,服务器,或者网络设备等)执行本公开各个实施例所述收发方法的部分步骤。而前述的存储介质包括:U盘、移动硬盘、只读存储器(Read-Only Memory,ROM)、随机存取存储器(Random Access Memory,RAM)、磁碟或者光盘等各种可以存储程序代码的介质。
以上所述的是本公开的优选实施方式,应当指出对于本技术领域的普通人员来说,在不脱离本公开所述原理前提下,还可以作出若干改进和润饰,这些改进和润饰也应视为本公开的保护范围。

Claims (17)

  1. 一种算力通告的发送方法,应用于第一算力网元节点,其中,所述方法包括:
    向第二算力网元节点发送目标算力节点的算力通告信息;
    其中,所述算力通告信息包括以下中的至少之一:
    用于记录所述目标算力节点的算力服务能力信息的第一字段信息;
    用于记录所述目标算力节点的算力资源状态的第二字段信息;
    用于记录所述目标算力节点的算力服务状态的第三字段信息。
  2. 根据权利要求1所述的发送方法,其中,所述方法还包括:
    根据待传输的目标业务和/或算力通告信息,确定所述算力通告信息的传输策略;
    根据所述传输策略,发送所述算力通告信息。
  3. 根据权利要求2所述的发送方法,其中,所述传输策略包括:
    所述算力通告信息的发送为主动发布;或者
    所述算力通告信息的发送为基于所获得的算力服务请求,发送所述算力通告信息。
  4. 根据权利要求3所述的发送方法,其中,所述目标业务为热点服务时,确定所述算力通告信息的发送为主动发布;
    所述目标业务为非热点服务时,确定所述算力通告信息的发送为基于所获得的算力服务请求,发送所述算力通告信息。
  5. 根据权利要求4所述的发送方法,其中,所述目标业务为热点服务,根据所述传输策略,发送所述算力通告信息,包括:
    向处于目标通告域内的所述第二算力网元节点发送所述算力通告信息;
    其中,所述目标通告域包括目标地理位置范围和/或目标服务部署区域。
  6. 根据权利要求1所述的发送方法,其中,发送所述算力通告信息,包括:
    通过扩展边界网关协议BGP消息发送所述算力通告信息;
    其中,所述第一字段信息、所述第二字段信息和所述第三字段信息分别 为扩展边界网关协议BGP消息中的其中一字段信息。
  7. 一种算力通告的发送方法,应用于第二算力网元节点,其中,所述方法包括:
    接收第一算力网元节点发送的目标算力节点的算力通告信息;
    其中,所述算力通告信息包括以下中的至少之一:
    用于记录所述目标算力节点的算力服务能力信息的第一字段信息;
    用于记录所述目标算力节点的算力资源状态的第二字段信息;
    用于记录所述目标算力节点的算力服务状态的第三字段信息。
  8. 根据权利要求7所述的发送方法,其中,接收第一算力网元节点发送的目标算力节点的算力通告信息,包括:
    接收所述第一算力网元节点主动发送的所述算力通告信息。
  9. 根据权利要求7所述的发送方法,其中,接收第一算力网元节点发送的目标算力节点的算力通告信息,包括:
    在接收用户端发送的第一算力服务请求后,向第一算力网元节点发送第二算力服务请求;
    接收所述第一算力网元节点响应所述第二算力服务请求发送的所述算力通告信息。
  10. 根据权利要求8所述的发送方法,其中,所述第二算力网元节点处于所述第一算力网元节点的目标通告域内;
    其中,所述目标通告域包括目标地理位置范围和/或目标服务部署区域。
  11. 根据权利要求7所述的发送方法,其中,接收所述算力通告信息,包括:
    通过扩展边界网关协议BGP消息接收所述算力通告信息;
    其中,所述第一字段信息、所述第二字段信息和所述第三字段信息分别为扩展BGP消息中的其中一字段信息。
  12. 一种算力网元节点,所述算力网元节点为第一算力网元节点,包括收发机,其中,所述收发机用于:
    向第二算力网元节点发送目标算力节点的算力通告信息;
    其中,所述算力通告信息包括以下中的至少之一:
    用于记录所述目标算力节点的算力服务能力信息的第一字段信息;
    用于记录所述目标算力节点的算力资源状态的第二字段信息;
    用于记录所述目标算力节点的算力服务状态的第三字段信息。
  13. 一种算力网元节点,所述算力网元节点为第二算力网元节点,包括收发机,其中,所述收发机用于:
    接收第一算力网元节点发送的目标算力节点的算力通告信息;
    其中,所述算力通告信息包括以下中的至少之一:
    用于记录所述目标算力节点的算力服务能力信息的第一字段信息;
    用于记录所述目标算力节点的算力资源状态的第二字段信息;
    用于记录所述目标算力节点的算力服务状态的第三字段信息。
  14. 一种算力通告的发送装置,应用于第一算力网元节点,其中,所述装置包括:
    发送模块,用于向第二算力网元节点发送目标算力节点的算力通告信息;
    其中,所述算力通告信息包括以下中的至少之一:
    用于记录所述目标算力节点的算力服务能力信息的第一字段信息;
    用于记录所述目标算力节点的算力资源状态的第二字段信息;
    用于记录所述目标算力节点的算力服务状态的第三字段信息。
  15. 一种算力通告的发送装置,应用于第二算力网元节点,其中,所述装置包括:
    接收模块,用于接收第一算力网元节点发送的目标算力节点的算力通告信息;
    其中,所述算力通告信息包括以下中的至少之一:
    用于记录所述目标算力节点的算力服务能力信息的第一字段信息;
    用于记录所述目标算力节点的算力资源状态的第二字段信息;
    用于记录所述目标算力节点的算力服务状态的第三字段信息。
  16. 一种算力网元节点,包括:处理器、存储器及存储在所述存储器上并可在所述处理器上运行的程序,其中,所述程序被所述处理器执行时实现如权利要求1至6中任一项所述的算力通告的发送方法,或者实现如权利要求7至11中任一项所述的算力通告的发送方法。
  17. 一种可读存储介质,其中,所述可读存储介质上存储有程序,所述程序被处理器执行时实现如权利要求1至6中任一项所述的算力通告的发送方法中的步骤,或者实现如权利要求7至11中任一项所述的算力通告的发送方法中的步骤。
PCT/CN2022/102298 2021-07-02 2022-06-29 算力通告的发送方法、装置及算力网元节点 WO2023274293A1 (zh)

Priority Applications (3)

Application Number Priority Date Filing Date Title
JP2023580883A JP7695417B2 (ja) 2021-07-02 2022-06-29 演算能力通知の送信方法、装置及び演算能力ネットワークエレメントノード
EP22832105.5A EP4366279A4 (en) 2021-07-02 2022-06-29 METHOD AND APPARATUS FOR SENDING COMPUTING POWER ADVERTISEMENT, AND COMPUTING POWER NETWORK ELEMENT NODE
US18/575,866 US20250106305A1 (en) 2021-07-02 2022-06-29 Method for transmission of computing power announcement, and computing power network element node

Applications Claiming Priority (2)

Application Number Priority Date Filing Date Title
CN202110750298.8 2021-07-02
CN202110750298.8A CN115567530A (zh) 2021-07-02 2021-07-02 算力通告的发送方法、装置及算力网元节点

Publications (1)

Publication Number Publication Date
WO2023274293A1 true WO2023274293A1 (zh) 2023-01-05

Family

ID=84691440

Family Applications (1)

Application Number Title Priority Date Filing Date
PCT/CN2022/102298 WO2023274293A1 (zh) 2021-07-02 2022-06-29 算力通告的发送方法、装置及算力网元节点

Country Status (5)

Country Link
US (1) US20250106305A1 (zh)
EP (1) EP4366279A4 (zh)
JP (1) JP7695417B2 (zh)
CN (1) CN115567530A (zh)
WO (1) WO2023274293A1 (zh)

Cited By (2)

* Cited by examiner, † Cited by third party
Publication number Priority date Publication date Assignee Title
CN116684418A (zh) * 2023-08-03 2023-09-01 北京神州泰岳软件股份有限公司 基于算力服务网关的算力编排调度方法、算力网络及装置
CN116743878A (zh) * 2023-08-14 2023-09-12 新华三技术有限公司 算力注册方法、装置、计算机设备及存储介质

Families Citing this family (1)

* Cited by examiner, † Cited by third party
Publication number Priority date Publication date Assignee Title
CN119946147A (zh) * 2023-11-01 2025-05-06 中兴通讯股份有限公司 服务路由通告和确定方法、算力路由网关以及存储介质

Citations (3)

* Cited by examiner, † Cited by third party
Publication number Priority date Publication date Assignee Title
CN110782343A (zh) * 2018-07-30 2020-02-11 中移(苏州)软件技术有限公司 分布式网络中基于区块链的算力流通方法及系统
CN111510383A (zh) * 2019-01-31 2020-08-07 华为技术有限公司 一种路由计算方法以及相关设备
CN112751826A (zh) * 2020-12-07 2021-05-04 中兴通讯股份有限公司 算力应用流量转发方法及装置

Family Cites Families (22)

* Cited by examiner, † Cited by third party
Publication number Priority date Publication date Assignee Title
US8495244B2 (en) * 2005-06-29 2013-07-23 Jumpstart Wireless Corporation System and method for dynamic automatic communication path selection, distributed device synchronization and task delegation
CN103581239B (zh) * 2012-07-27 2019-01-22 中兴通讯股份有限公司 一种设备和服务的发现方法、装置
WO2014032291A1 (en) * 2012-08-31 2014-03-06 Telefonaktiebolaget L M Ericsson(Publ) Methods and devices for switching between peer-to-peer and multimedia broadcast multicast service
WO2015171075A1 (en) * 2014-05-06 2015-11-12 Mediatek Singapore Pte. Ltd. Method for discovering services
US9699085B2 (en) * 2014-11-13 2017-07-04 Cisco Technology, Inc. Periodic advertisements of host capabilities in virtual cloud computing infrastructure
CN106162565B (zh) * 2015-04-09 2021-06-01 北京三星通信技术研究有限公司 传输组通信业务数据的方法、系统及装置
US20160352842A1 (en) * 2015-05-27 2016-12-01 Qualcomm Incorporated Proxy advertisements in a neighbor aware network
US20160352782A1 (en) * 2015-05-27 2016-12-01 Qualcomm Incorporated Proxy advertisements in a neighbor aware network
US10025636B2 (en) * 2016-04-15 2018-07-17 Google Llc Modular electronic devices with contextual task management and performance
CN109417682B (zh) * 2016-07-05 2021-01-29 华为技术有限公司 业务处理的方法、设备和系统
US11277338B2 (en) * 2016-09-26 2022-03-15 Juniper Networks, Inc. Distributing service function chain data and service function instance data in a network
US10574445B2 (en) * 2016-12-21 2020-02-25 Intel IP Corporation Range constrained device configuration
CN109936472A (zh) * 2017-12-18 2019-06-25 上海无线通信研究中心 面向雾计算的节点计算能力描述方法、交互方法及其设备
US20190320407A1 (en) * 2018-04-12 2019-10-17 Qualcomm Incorporated Range-based provision of network services
CN112491716B (zh) * 2019-09-12 2023-07-18 华为技术有限公司 算力路由方法及装置
CN110851529B (zh) * 2019-11-01 2024-05-28 腾讯科技(深圳)有限公司 算力调度方法及相关设备
US20210235255A1 (en) * 2020-01-29 2021-07-29 Qualcomm Incorporated Neighborhood awareness networking (nan) extension to 6 ghz operation
CN114513450A (zh) * 2020-10-26 2022-05-17 华为技术有限公司 计算路由信息发送方法、装置、设备及存储介质
CN112465359B (zh) * 2020-12-01 2024-03-15 中国联合网络通信集团有限公司 算力调用方法和装置
US11516311B2 (en) * 2021-01-22 2022-11-29 Avago Technologies International Sales Pte. Limited Distributed machine-learning resource sharing and request routing
CN115226073A (zh) * 2021-04-15 2022-10-21 华为技术有限公司 报文转发方法、装置及系统、计算机可读存储介质
CN115225722A (zh) * 2021-04-20 2022-10-21 中兴通讯股份有限公司 算力资源的通告方法及装置、存储介质、电子装置

Patent Citations (3)

* Cited by examiner, † Cited by third party
Publication number Priority date Publication date Assignee Title
CN110782343A (zh) * 2018-07-30 2020-02-11 中移(苏州)软件技术有限公司 分布式网络中基于区块链的算力流通方法及系统
CN111510383A (zh) * 2019-01-31 2020-08-07 华为技术有限公司 一种路由计算方法以及相关设备
CN112751826A (zh) * 2020-12-07 2021-05-04 中兴通讯股份有限公司 算力应用流量转发方法及装置

Non-Patent Citations (1)

* Cited by examiner, † Cited by third party
Title
See also references of EP4366279A4 *

Cited By (4)

* Cited by examiner, † Cited by third party
Publication number Priority date Publication date Assignee Title
CN116684418A (zh) * 2023-08-03 2023-09-01 北京神州泰岳软件股份有限公司 基于算力服务网关的算力编排调度方法、算力网络及装置
CN116684418B (zh) * 2023-08-03 2023-11-10 北京神州泰岳软件股份有限公司 基于算力服务网关的算力编排调度方法、算力网络及装置
CN116743878A (zh) * 2023-08-14 2023-09-12 新华三技术有限公司 算力注册方法、装置、计算机设备及存储介质
CN116743878B (zh) * 2023-08-14 2023-10-27 新华三技术有限公司 算力注册方法、装置、计算机设备及存储介质

Also Published As

Publication number Publication date
JP2024526270A (ja) 2024-07-17
US20250106305A1 (en) 2025-03-27
EP4366279A4 (en) 2025-06-25
CN115567530A (zh) 2023-01-03
EP4366279A1 (en) 2024-05-08
JP7695417B2 (ja) 2025-06-18

Similar Documents

Publication Publication Date Title
US11693716B2 (en) Independent datastore in a network routing environment
WO2022028418A1 (zh) 算力处理的网络系统、业务处理方法及设备
CN109842906B (zh) 一种通信的方法、装置及系统
WO2023274293A1 (zh) 算力通告的发送方法、装置及算力网元节点
US10581932B2 (en) Network-based dynamic data management
US8719427B2 (en) Efficiency for network group communication
EP2932657B1 (en) Information centric networking based service centric networking
JP6302050B2 (ja) 改善された発見のためのシステムおよび方法
CN113709048A (zh) 一种路由信息的发送、接收方法、网元及节点设备
WO2022184094A1 (zh) 算力处理的网络系统、业务处理方法及算力网元节点
CN107404512B (zh) 资源订阅方法、资源订阅装置和资源订阅系統
US20210297896A1 (en) Wireless communication system
WO2023169374A1 (zh) 一种路由方法及系统、节点
WO2023155669A1 (zh) 用户平面功能的选择方法及设备
JP7684394B2 (ja) バックアップネットワーク機能を提供するためのネットワークノードおよびネットワークノードにおける方法
US11265931B2 (en) Method and device for establishing connection
Noh et al. SPIZ: an effective service discovery protocol for mobile ad hoc networks
CN102647334A (zh) 一种数据路由方法和装置
CN115550234B (zh) 一种信息通告方法、控制器及存储介质
WO2018077313A1 (zh) 连接能力的通告方法及装置
CN108123871A (zh) 等价多路径ecmp处理方法及装置
JP2004201201A (ja) Wap端末及び通信方法並びに通信プログラム
CN114374649A (zh) 混合路由方法、装置和网络设备
CN106817261A (zh) 一种用于ndn网络的路由信息更新方法、装置及系统
CN113068223A (zh) 基于切片信息的本地分流方法、装置、设备及存储介质

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: 22832105

Country of ref document: EP

Kind code of ref document: A1

ENP Entry into the national phase

Ref document number: 2023580883

Country of ref document: JP

Kind code of ref document: A

WWE Wipo information: entry into national phase

Ref document number: 2022832105

Country of ref document: EP

NENP Non-entry into the national phase

Ref country code: DE

ENP Entry into the national phase

Ref document number: 2022832105

Country of ref document: EP

Effective date: 20240202

WWP Wipo information: published in national office

Ref document number: 18575866

Country of ref document: US