WO2023184917A1 - Computing power information processing method and system and computing power gateway - Google Patents

Computing power information processing method and system and computing power gateway Download PDF

Info

Publication number
WO2023184917A1
WO2023184917A1 PCT/CN2022/123292 CN2022123292W WO2023184917A1 WO 2023184917 A1 WO2023184917 A1 WO 2023184917A1 CN 2022123292 W CN2022123292 W CN 2022123292W WO 2023184917 A1 WO2023184917 A1 WO 2023184917A1
Authority
WO
WIPO (PCT)
Prior art keywords
computing power
gateway
information
computing
resource node
Prior art date
Application number
PCT/CN2022/123292
Other languages
French (fr)
Chinese (zh)
Inventor
解云鹏
雷波
赵倩颖
唐静
李云鹤
周舸帆
Original Assignee
中国电信股份有限公司
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 中国电信股份有限公司 filed Critical 中国电信股份有限公司
Publication of WO2023184917A1 publication Critical patent/WO2023184917A1/en

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
    • H04L67/01Protocols
    • H04L67/10Protocols in which an application is distributed across nodes in the network

Definitions

  • This application is based on the application with CN application number 202210325008.
  • Figure 2 is a schematic flowchart of a method for processing computing power information according to other embodiments of the present disclosure.
  • computing resource nodes are managed by a cloud management platform that is independent of the computing network.
  • the computing power network obtains the computing power information of computing resource nodes, it needs to establish a connection with the cloud management platform first, and then obtain the computing power information through the cloud management platform. This results in the computing power network not being able to obtain computing power information in a timely manner.
  • the first computing power gateway obtains the first computing power information.
  • Figure 3 is a schematic structural diagram of a computing power gateway according to some embodiments of the present disclosure.
  • the computing power gateway 300 includes an acquisition module 310 and a sending module 320.
  • the computing power gateway 300 may serve as the first computing power gateway.
  • Figure 4 is a schematic structural diagram of a computing power gateway according to other embodiments of the present disclosure.
  • the computing power network management and control platform 510 is configured to obtain the first transmission delay between the first computing power gateway 521 and the second computing power gateway 522, and determine the second transmission delay based on the first transmission delay. .
  • embodiments of the present disclosure may be provided as methods, systems, or computer program products. Accordingly, the present disclosure may take the form of an entirely hardware embodiment, an entirely software embodiment, or an embodiment that combines software and hardware aspects. Furthermore, the present disclosure may take the form of a computer program product embodied on one or more computer-usable non-transitory storage media (including, but not limited to, disk memory, CD-ROM, optical storage, etc.) having computer-usable program code embodied therein. .

Landscapes

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

Abstract

The present disclosure relates to the technical field of computing power networks, and provides a computing power information processing method and system and a computing power gateway. The method comprises: a first computing power gateway acquires first computing power information of a first computing power resource node, the first computing power information comprising an identifier of the first computing power resource node and a computing power resource of the first computing power resource node; and the first computing power gateway sends second computing power information to at least one of a computing power network management and control platform and a second computing power gateway, the second computing power information comprising the first computing power information and an identifier of the first computing power gateway.

Description

算力信息的处理方法、处理系统及算力网关Computing power information processing method, processing system and computing power gateway
相关申请的交叉引用Cross-references to related applications
本申请是以CN申请号为202210325008.X,申请日为2022年3月30日的申请为基础,并主张其优先权,该CN申请的公开内容在此作为整体引入本申请中。This application is based on the application with CN application number 202210325008.
技术领域Technical field
本公开涉及算力网络技术领域,尤其是一种算力信息的处理方法、处理系统及算力网关。The present disclosure relates to the field of computing power network technology, and in particular, to a computing power information processing method, a processing system and a computing power gateway.
背景技术Background technique
算力网络是一种根据业务需求,在云、网、边之间按需分配和灵活调度计算资源、存储资源以及网络资源的新型信息基础设施。The computing power network is a new type of information infrastructure that allocates and flexibly schedules computing resources, storage resources, and network resources among clouds, networks, and edges based on business needs.
算力网络的建设需要扩展网络能力,不仅要能够分发网络信息,而且要能够分发算力资源节点的算力信息,从而实现基于网络信息和算力信息的算力资源的优化分配。The construction of a computing power network requires the expansion of network capabilities, not only to be able to distribute network information, but also to be able to distribute computing power information of computing resource nodes, thereby achieving optimal allocation of computing power resources based on network information and computing power information.
发明内容Contents of the invention
根据本公开实施例的一方面,提供一种算力信息的处理方法,包括:第一算力网关获取第一算力资源节点的第一算力信息,所述第一算力信息包括所述第一算力资源节点的标识与所述第一算力资源节点具有的算力资源;以及所述第一算力网关发送第二算力信息到算力网络管控平台和第二算力网关中的至少一个,所述第二算力信息包括所述第一算力信息和所述第一算力网关的标识。According to an aspect of an embodiment of the present disclosure, a method for processing computing power information is provided, including: a first computing power gateway obtains first computing power information of a first computing power resource node, where the first computing power information includes the The identification of the first computing power resource node and the computing power resource possessed by the first computing power resource node; and the first computing power gateway sends the second computing power information to the computing power network management and control platform and the second computing power gateway At least one of, the second computing power information includes the first computing power information and the identification of the first computing power gateway.
在一些实施例中,所述第一算力网关接收所述第二算力网关发送的第三算力信息,所述第三算力信息包括第四算力信息和所述第二算力网关的标识,所述第四算力信息包括第二算力资源节点的标识与所述第二算力资源节点具有的算力资源。In some embodiments, the first computing power gateway receives the third computing power information sent by the second computing power gateway, and the third computing power information includes fourth computing power information and the second computing power gateway The fourth computing power information includes the identification of the second computing power resource node and the computing power resources possessed by the second computing power resource node.
在一些实施例中,所述第一算力网关是所述算力网络管控平台管控的任意一个算力网关,所述第二算力网关是所述算力网络管控平台管控的除所述第一算力网关外的任意一个算力网关。In some embodiments, the first computing power gateway is any computing power gateway controlled by the computing power network management and control platform, and the second computing power gateway is any computing power gateway controlled by the computing power network management and control platform except the third computing power gateway. Any computing power gateway other than one computing power gateway.
在一些实施例中,所述第一算力网关发送网络信息到所述算力网络管控平台,所述网络信息包括所述第一算力网关与所述第二算力网关之间的第一传输时延。In some embodiments, the first computing power gateway sends network information to the computing power network management and control platform, and the network information includes the first computing power gateway between the first computing power gateway and the second computing power gateway. Transmission delay.
在一些实施例中,所述第一算力网关接收来自所述第二算力网关的响应消息;以及基于所述响应消息,确定所述第一传输时延。In some embodiments, the first computing power gateway receives a response message from the second computing power gateway; and based on the response message, determines the first transmission delay.
在一些实施例中,所述第一算力网关保存所述第一算力信息。In some embodiments, the first computing power gateway saves the first computing power information.
在一些实施例中,所述第一算力网关响应于所述算力网络管控平台发送的算力资源分配请求,发送所述算力资源分配请求到所述第一算力资源节点,以使得所述第一算力资源节点基于所述算力资源分配请求分配算力资源;所述第一算力网关接收所述第一算力资源节点发送的算力资源分配结果,所述算力资源分配结果表示算力资源分配是否成功;所述第一算力网关在所述算力资源分配结果表示算力资源分配成功的情况下,基于所述算力资源分配结果对所述第一算力信息进行更新;以及所述第一算力网关发送算力资源分配响应到所述算力网络管控平台,所述算力资源分配响应表示所述第一算力信息是否更新成功。In some embodiments, the first computing power gateway responds to the computing power resource allocation request sent by the computing power network management and control platform, and sends the computing power resource allocation request to the first computing power resource node, so that The first computing power resource node allocates computing power resources based on the computing power resource allocation request; the first computing power gateway receives the computing power resource allocation result sent by the first computing power resource node, and the computing power resource The allocation result indicates whether the computing power resource allocation is successful; when the computing power resource allocation result indicates that the computing power resource allocation is successful, the first computing power gateway assigns the first computing power to the first computing power gateway based on the computing power resource allocation result. The information is updated; and the first computing power gateway sends a computing power resource allocation response to the computing power network management and control platform, where the computing power resource allocation response indicates whether the first computing power information is updated successfully.
在一些实施例中,所述第一算力网关接收所述第一算力资源节点发送的第一状态信息,所述第一状态信息表示所述第一算力资源节点是否能够被所述第一算力网关管理;其中,在所述第一算力资源节点能够被所述第一算力网关管理的情况下,所述第一算力网关获取所述第一算力信息。In some embodiments, the first computing power gateway receives first status information sent by the first computing power resource node, and the first status information indicates whether the first computing power resource node can be used by the first computing power resource node. A computing power gateway management; wherein, when the first computing power resource node can be managed by the first computing power gateway, the first computing power gateway obtains the first computing power information.
在一些实施例中,所述算力资源包括中央处理器资源、图形处理器资源、现场可编程门阵列资源和内存资源中的至少一种。In some embodiments, the computing resources include at least one of central processing unit resources, graphics processor resources, field programmable gate array resources, and memory resources.
在一些实施例中,所述第一算力资源节点和所述算力网络管控平台中的每一个与所述第一算力网关通过HTTPS RESTful接口相连。In some embodiments, each of the first computing power resource node and the computing power network management and control platform is connected to the first computing power gateway through an HTTPS RESTful interface.
在一些实施例中,所述第一算力网关基于BGP协议或IGP协议发送所述第二算力信息到所述第二算力网关。In some embodiments, the first computing power gateway sends the second computing power information to the second computing power gateway based on the BGP protocol or the IGP protocol.
根据本公开的另一方面,提供一种算力网关,作为第一算力网关,包括:获取模块,被配置为获取第一算力资源节点的第一算力信息,所述第一算力信息包括所述第一算力资源节点的标识与所述第一算力资源节点具有的算力资源;以及发送模块,被配置为发送第二算力信息到算力网络管控平台和第二算力网关中的至少一个,所述第二算力信息包括所述第一算力信息和所述第一算力网关的标识。According to another aspect of the present disclosure, a computing power gateway is provided. As a first computing power gateway, it includes: an acquisition module configured to obtain first computing power information of a first computing power resource node, the first computing power The information includes the identification of the first computing power resource node and the computing power resource possessed by the first computing power resource node; and a sending module configured to send the second computing power information to the computing power network management and control platform and the second computing power resource node. At least one of the computing power gateways, the second computing power information includes the first computing power information and the identification of the first computing power gateway.
根据本公开的又一方面,提供一种算力网关,包括:存储器;以及耦接至所述存储器的处理器,所述处理器被配置为基于存储在所述存储器的指令执行上述任意一个实施例所述的方法。According to yet another aspect of the present disclosure, a computing power gateway is provided, including: a memory; and a processor coupled to the memory, the processor being configured to execute any one of the above implementations based on instructions stored in the memory. method described in the example.
根据本公开的还一方面,提供一种算力信息的处理系统,包括:第一算力网关, 例如是上述任意一个实施例所述的算力网关;以及所述算力网络管控平台,被配置为接收并显示所述第二算力信息,以使得用户基于所述第二算力信息选择算力资源节点。According to another aspect of the present disclosure, a computing power information processing system is provided, including: a first computing power gateway, such as the computing power gateway described in any of the above embodiments; and the computing power network management and control platform, which is Configured to receive and display the second computing power information, so that the user selects a computing power resource node based on the second computing power information.
根据本公开的还一方面,提供一种算力信息的处理系统,其中,所述算力网络管控平台还被配置为根据所述第一传输时延确定所述算力网络管控平台与所述第一算力资源节点之间的第二传输时延,以便用户根据所述第二传输时延和所述第一算力信息确定是否选择从所述第一算力资源节点申请分配资源。According to yet another aspect of the present disclosure, a system for processing computing power information is provided, wherein the computing power network management and control platform is further configured to determine the relationship between the computing power network management and control platform and the computing power information based on the first transmission delay. The second transmission delay between the first computing resource nodes allows the user to determine whether to apply for resource allocation from the first computing resource node based on the second transmission delay and the first computing power information.
根据本公开实施例的还一方面,提供一种计算机可读存储介质,包括计算机程序指令,其中,所述计算机程序指令被处理器执行时实现上述任意一个实施例所述的方法。According to another aspect of the embodiments of the present disclosure, a computer-readable storage medium is provided, including computer program instructions, wherein when the computer program instructions are executed by a processor, the method described in any of the above embodiments is implemented.
根据本公开实施例的还一方面,提供一种计算机程序产品,包括计算机程序,其中,所述计算机程序被处理器执行时实现上述任意一个实施例所述的方法。According to another aspect of the embodiments of the present disclosure, a computer program product is provided, including a computer program, wherein when the computer program is executed by a processor, the method described in any of the above embodiments is implemented.
本公开实施例中,通过第一算力网关获取算力资源节点的算力信息,再将算力信息进行分发,使得算力网络能够及时地获取算力信息。In this disclosed embodiment, the computing power information of the computing power resource node is obtained through the first computing power gateway, and then the computing power information is distributed, so that the computing power network can obtain the computing power information in a timely manner.
下面通过附图和实施例,对本公开的技术方案做进一步的详细描述。The technical solution of the present disclosure will be described in further detail below through the accompanying drawings and examples.
附图说明Description of drawings
为了更清楚地说明本公开实施例或现有技术中的技术方案,下面将对实施例或现有技术描述中所需要使用的附图作简单地介绍,显而易见地,下面描述中的附图仅仅是本公开的一些实施例,对于本领域普通技术人员来讲,在不付出创造性劳动的前提下,还可以根据这些附图获得其他的附图。In order to explain the embodiments of the present disclosure or the technical solutions in the prior art more clearly, the drawings needed to be used in the description of the embodiments or the prior art will be briefly introduced below. Obviously, the drawings in the following description are only These are some embodiments of the present disclosure. For those of ordinary skill in the art, other drawings can be obtained based on these drawings without exerting creative efforts.
图1是根据本公开一些实施例的算力信息的处理方法的流程示意图。Figure 1 is a schematic flowchart of a method for processing computing power information according to some embodiments of the present disclosure.
图2是根据本公开另一些实施例的算力信息的处理方法的流程示意图。Figure 2 is a schematic flowchart of a method for processing computing power information according to other embodiments of the present disclosure.
图3是根据本公开一些实施例的算力网关的结构示意图。Figure 3 is a schematic structural diagram of a computing power gateway according to some embodiments of the present disclosure.
图4是根据本公开另一些实施例的算力网关的结构示意图。Figure 4 is a schematic structural diagram of a computing power gateway according to other embodiments of the present disclosure.
图5是根据本公开一些实施例的算力信息的处理系统的结构示意图。Figure 5 is a schematic structural diagram of a computing power information processing system according to some embodiments of the present disclosure.
具体实施方式Detailed ways
下面将结合本公开实施例中的附图,对本公开实施例中的技术方案进行清楚、完整地描述,显然,所描述的实施例仅仅是本公开一部分实施例,而不是全部的实施例。基于本公开中的实施例,本领域普通技术人员在没有作出创造性劳动的前提下所获得 的所有其他实施例,都属于本公开保护的范围。The technical solutions in the embodiments of the present disclosure will be clearly and completely described below with reference to the accompanying drawings in the embodiments of the present disclosure. Obviously, the described embodiments are only some of the embodiments of the present disclosure, rather than all of the embodiments. Based on the embodiments in the present disclosure, all other embodiments obtained by those of ordinary skill in the art without making creative efforts fall within the scope of protection of the present disclosure.
除非另外具体说明,否则在这些实施例中阐述的部件和步骤的相对布置、数字表达式和数值不限制本公开的范围。The relative arrangement of components and steps, numerical expressions, and numerical values set forth in these examples do not limit the scope of the disclosure unless otherwise specifically stated.
同时,应当明白,为了便于描述,附图中所示出的各个部分的尺寸并不是按照实际的比例关系绘制的。At the same time, it should be understood that, for convenience of description, the dimensions of various parts shown in the drawings are not drawn according to actual proportional relationships.
对于相关领域普通技术人员已知的技术、方法和设备可能不作详细讨论,但在适当情况下,所述技术、方法和设备应当被视为授权说明书的一部分。Techniques, methods and devices known to those of ordinary skill in the relevant art may not be discussed in detail, but where appropriate, such techniques, methods and devices should be considered part of the authorized specification.
在这里示出和讨论的所有示例中,任何具体值应被解释为仅仅是示例性的,而不是作为限制。因此,示例性实施例的其它示例可以具有不同的值。In all examples shown and discussed herein, any specific values are to be construed as illustrative only and not as limiting. Accordingly, other examples of the exemplary embodiments may have different values.
应注意到:相似的标号和字母在下面的附图中表示类似项,因此,一旦某一项在一个附图中被定义,则在随后的附图中不需要对其进行进一步讨论。It should be noted that similar reference numerals and letters refer to similar items in the following figures, so that once an item is defined in one figure, it does not need further discussion in subsequent figures.
发明人注意到,相关技术中,算力资源节点由独立于算力网络的云管平台管理。算力网络在获取算力资源节点的算力信息时,需要先与云管平台建立连接,再经由云管平台获取算力信息,这导致算力网络对于算力信息的获取不够及时。The inventor noted that in related technologies, computing resource nodes are managed by a cloud management platform that is independent of the computing network. When the computing power network obtains the computing power information of computing resource nodes, it needs to establish a connection with the cloud management platform first, and then obtain the computing power information through the cloud management platform. This results in the computing power network not being able to obtain computing power information in a timely manner.
图1是根据本公开一些实施例的算力信息的处理方法的流程示意图。Figure 1 is a schematic flowchart of a method for processing computing power information according to some embodiments of the present disclosure.
在步骤102,第一算力网关获取第一算力资源节点的第一算力信息。这里,第一算力信息包括第一算力资源节点的标识与第一算力资源节点具有的算力资源。In step 102, the first computing power gateway obtains the first computing power information of the first computing power resource node. Here, the first computing power information includes the identification of the first computing power resource node and the computing power resources possessed by the first computing power resource node.
在一些实施例中,算力资源包括中央处理器资源、图形处理器资源、现场可编程门阵列资源和内存资源中的至少一种。第一算力资源节点例如有中心云算力节点、边缘云算力节点和端算力节点等。In some embodiments, the computing resources include at least one of central processing unit resources, graphics processor resources, field programmable gate array resources, and memory resources. The first computing power resource node includes, for example, a central cloud computing power node, an edge cloud computing power node, and a terminal computing power node.
后文将结合一些实施例进一步介绍第一算力网关如何获取第一算力资源节点的第一算力信息。How the first computing power gateway obtains the first computing power information of the first computing power resource node will be further described below with reference to some embodiments.
在步骤104,第一算力网关发送第二算力信息到算力网络管控平台和第二算力网关中的至少一个。这里,第二算力信息包括第一算力信息和第一算力网关的标识。In step 104, the first computing power gateway sends the second computing power information to at least one of the computing power network management and control platform and the second computing power gateway. Here, the second computing power information includes the first computing power information and the identification of the first computing power gateway.
例如,第一算力网关发送第二算力信息到算力网络管控平台,以使得算力网络管控平台能够获取算力信息,便于实现算力资源的集中式管控,为后续的算力资源交易提供基础保障。For example, the first computing power gateway sends the second computing power information to the computing power network management and control platform, so that the computing power network management and control platform can obtain the computing power information, which facilitates centralized management and control of computing power resources and facilitates subsequent transactions of computing power resources. Provide basic protection.
又例如,第一算力网关发送第二算力信息到第二算力网关,以使得第二算力网关能够获取算力信息,便于实现算力资源的分布式管控。For another example, the first computing power gateway sends the second computing power information to the second computing power gateway, so that the second computing power gateway can obtain the computing power information to facilitate distributed management and control of computing power resources.
再例如,第一算力网关发送第二算力信息到算力网络管控平台和第二算力网关, 以便将算力资源的集中式管控与分布式管控相结合。For another example, the first computing power gateway sends the second computing power information to the computing power network management and control platform and the second computing power gateway, so as to combine centralized management and control of computing power resources with distributed management and control.
在一些实施例中,第二算力网关与第一算力网关位于相同的自治域内。在另一些实施例中,第二算力网关与第一算力网关位于不同的自治域内。In some embodiments, the second computing power gateway and the first computing power gateway are located in the same autonomous domain. In other embodiments, the second computing power gateway and the first computing power gateway are located in different autonomous domains.
后文将结合一些实施例进一步介绍第一算力网关如何发送第二算力信息到算力网络管控平台和第二算力网关中的至少一个。How the first computing power gateway sends the second computing power information to at least one of the computing power network management and control platform and the second computing power gateway will be further described below with reference to some embodiments.
上述实施例中,通过第一算力网关获取算力资源节点的算力信息,再将算力信息进行分发,使得算力网络能够及时地获取算力信息。In the above embodiment, the computing power information of the computing power resource node is obtained through the first computing power gateway, and then the computing power information is distributed, so that the computing power network can obtain the computing power information in a timely manner.
在一些实施例中,第一算力网关是算力网络管控平台管控的任意一个算力网关,换言之,任意一个算力网关都能够获取该算力网关下的算力资源节点的算力信息。In some embodiments, the first computing power gateway is any computing power gateway controlled by the computing power network management and control platform. In other words, any computing power gateway can obtain the computing power information of the computing power resource nodes under the computing power gateway.
在一些实施例中,第二算力网关是算力网络管控平台管控的除第一算力网关外的任意一个算力网关。换言之,除第一算力网关外的任意一个算力网关均可以获取到第一算力网关的第一算力信息。In some embodiments, the second computing power gateway is any computing power gateway controlled by the computing power network management and control platform except the first computing power gateway. In other words, any computing power gateway other than the first computing power gateway can obtain the first computing power information of the first computing power gateway.
上述实施例中,每个算力网关既能够获取到该算力网关下的算力资源节点的算力信息,也能够获取到其他算力网关下的算力资源节点的算力信息,便于利用算力网关实现算力资源的分布式管控。In the above embodiment, each computing power gateway can not only obtain the computing power information of the computing power resource nodes under the computing power gateway, but also obtain the computing power information of the computing power resource nodes under other computing power gateways, which facilitates utilization. The computing power gateway realizes distributed management and control of computing power resources.
下面结合一些实施例介绍第一算力网关如何获取算力信息。The following describes how the first computing power gateway obtains computing power information with reference to some embodiments.
首先介绍第一算力网关如何获取第一算力信息。First, we will introduce how the first computing power gateway obtains the first computing power information.
在一些实施例中,第一算力网关接收第一算力资源节点发送的第一状态信息,第一状态信息表示第一算力资源节点是否能够被第一算力网关管理。进一步地,在第一算力资源节点能够被第一算力网关管理的情况下,第一算力网关获取第一算力信息。In some embodiments, the first computing power gateway receives first status information sent by the first computing power resource node, and the first status information indicates whether the first computing power resource node can be managed by the first computing power gateway. Further, when the first computing power resource node can be managed by the first computing power gateway, the first computing power gateway obtains the first computing power information.
例如,在新增的第一算力资源节点上线时,第一状态信息可以表示第一算力资源节点能够被第一算力网关管理以及该第一算力资源节点是新增节点。相应地,第一算力网关接收到第一状态信息后,就向新增的第一算力资源节点获取第一算力信息。For example, when a newly added first computing power resource node comes online, the first status information may indicate that the first computing power resource node can be managed by the first computing power gateway and that the first computing power resource node is a new node. Correspondingly, after receiving the first status information, the first computing power gateway obtains the first computing power information from the newly added first computing power resource node.
上述实施例中,响应于第一状态信息获取第一算力信息,使得第一算力网关能够及时获取第一算力信息。In the above embodiment, the first computing power information is obtained in response to the first status information, so that the first computing power gateway can obtain the first computing power information in time.
在一些实施例中,第一算力资源节点除了发送第一状态信息,还发送接口统一资源标识符(URI)信息到第一算力网关,以使得第一算力网关能够基于接口URI信息与第一算力资源节点通信。例如,第一算力资源节点首次发送第一状态信息到第一算力网关时,可以一并发送接口URI信息。In some embodiments, in addition to sending the first status information, the first computing power resource node also sends interface uniform resource identifier (URI) information to the first computing power gateway, so that the first computing power gateway can communicate with the first computing power gateway based on the interface URI information. The first computing resource node communicates. For example, when the first computing power resource node sends the first status information to the first computing power gateway for the first time, it may also send the interface URI information.
在一些实施例中,第一算力资源节点和算力网络管控平台中的每一个与第一算力 网关通过HTTPS RESTful接口相连。In some embodiments, each of the first computing power resource node and the computing power network management and control platform is connected to the first computing power gateway through an HTTPS RESTful interface.
下面结合一些实施例介绍第一算力网关如何基于HTTPS RESTful接口获取第一算力信息。The following describes how the first computing power gateway obtains the first computing power information based on the HTTPS RESTful interface in conjunction with some embodiments.
表1是根据本公开一些实施例的第一算力信息获取请求的HTTPS RESTful接口报文格式。表2是根据本公开一些实施例的第一算力信息获取请求的参数。表3是根据本公开一些实施例的第一算力信息获取响应的参数。Table 1 is the HTTPS RESTful interface message format of the first computing power information acquisition request according to some embodiments of the present disclosure. Table 2 is the parameters of the first computing power information acquisition request according to some embodiments of the present disclosure. Table 3 is the parameters of the first computing power information acquisition response according to some embodiments of the present disclosure.
表1Table 1
接口URIInterface URI /api/v1/kids/{kid}/nodes/{name}/api/v1/kids/{kid}/nodes/{name}
请求方式Request method HTTPS POSTHTTPS POST
数据交互格式Data interaction format application/jsonapplication/json
表2Table 2
数据项data item 类型type 数据项描述Data item description 是否必须Is it necessary
codecode IntegerInteger 请求码Request code yes
作为一些实现方式,第一算力网关基于表1和表2生成第一算力信息获取请求。例如,第一算力信息获取请求可以包括请求码“001”,请求码“001”表示获取第一算力资源节点的全部算力信息。又例如,第一算力信息获取请求可以包括请求码“002”,请求码“002”表示获取第一算力资源节点的特定类型的算力信息,例如是获取中央处理器资源的算力信息。As some implementations, the first computing power gateway generates a first computing power information acquisition request based on Table 1 and Table 2. For example, the first computing power information acquisition request may include a request code “001”, and the request code “001” indicates obtaining all computing power information of the first computing power resource node. For another example, the first computing power information acquisition request may include a request code “002”. The request code “002” indicates obtaining a specific type of computing power information of the first computing power resource node, such as obtaining computing power information of a central processor resource. .
表3table 3
数据项data item 类型type 数据项描述Data item description 是否必须Is it necessary
codecode IntegerInteger 响应码response code yes
msgmsg StringString 响应信息response message yes
datadata JsonJson 返回数据Return data yes
作为一些实现方式,第一算力资源节点接收到第一算力信息获取请求后,按照表1和表3生成第一算力信息获取响应。例如,在第一算力资源节点能够成功响应的情况下,第一算力信息获取响应包括响应码“200”、表示第一算力资源节点成功响应的响应信息以及表示第一算力信息的相关数据。又例如,在第一算力资源节点不能够成功响应的情况下,第一算力信息获取响应包括响应码“201”、表示第一算力资源节点响应失败原因的响应信息以及相关数据。As some implementation methods, after receiving the first computing power information acquisition request, the first computing power resource node generates a first computing power information acquisition response according to Table 1 and Table 3. For example, in the case where the first computing power resource node can respond successfully, the first computing power information acquisition response includes the response code “200”, response information indicating that the first computing power resource node successfully responded, and response information indicating the first computing power information. related data. For another example, when the first computing power resource node fails to respond successfully, the first computing power information acquisition response includes a response code “201”, response information indicating the reason for the failure of the first computing power resource node to respond, and related data.
上述实施例中,通过统一的HTTPS RESTful接口获取算力信息,在接收到涉及中央处理器资源、图形处理器资源、现场可编程门阵列资源和内存资源等算力形态不同的异构算力资源的算力信息时,能够屏蔽异构算力资源特征,统一算力信息的格式,便于后续进行处理。In the above embodiment, computing power information is obtained through a unified HTTPS RESTful interface, and heterogeneous computing power resources involving different computing power forms such as central processing unit resources, graphics processor resources, field programmable gate array resources, and memory resources are received. When computing power information, it can shield the characteristics of heterogeneous computing power resources and unify the format of computing power information to facilitate subsequent processing.
后文将结合一些其他实施例对本公开的另一些HTTPS RESTful接口报文格式及参数进行介绍。The following article will introduce some other HTTPS RESTful interface message formats and parameters of the present disclosure in conjunction with some other embodiments.
接下来介绍第一算力网关如何获取第三算力信息。Next, we will introduce how the first computing power gateway obtains the third computing power information.
在一些实施例中,第一算力网关接收第二算力网关发送的第三算力信息。这里,第三算力信息包括第四算力信息和第二算力网关的标识,第四算力信息包括第二算力资源节点的标识与第二算力资源节点具有的算力资源。In some embodiments, the first computing power gateway receives the third computing power information sent by the second computing power gateway. Here, the third computing power information includes fourth computing power information and the identification of the second computing power gateway, and the fourth computing power information includes the identification of the second computing power resource node and the computing power resources possessed by the second computing power resource node.
在一些实施例中,第二算力网关可以直接与算力网络管控平台连接。在另一些实施例中,第二算力网关可以通过第一算力网关与算力网络管控平台连接。In some embodiments, the second computing power gateway can be directly connected to the computing power network management and control platform. In other embodiments, the second computing power gateway may be connected to the computing power network management and control platform through the first computing power gateway.
在一些实施例中,第一算力网关保存第一算力信息。作为一些实现方式,第一算力网关具有本地数据库,用于保存第一算力信息。进一步地,本地数据库还可以保存第三算力信息。In some embodiments, the first computing power gateway stores the first computing power information. As some implementation methods, the first computing power gateway has a local database for saving the first computing power information. Furthermore, the local database can also store third computing power information.
上述实施例中,通过对算力信息进行保存,有利于实现算力信息的分布式存储,还有利于后续实现算力资源的分布式管控。In the above embodiment, by saving the computing power information, it is beneficial to achieve distributed storage of computing power information, and is also beneficial to the subsequent distributed management and control of computing power resources.
下面介绍第一算力网关如何发送第二算力信息到算力网络管控平台和第二算力网关中的至少一个。The following describes how the first computing power gateway sends the second computing power information to at least one of the computing power network management and control platform and the second computing power gateway.
首先介绍如何发送第二算力信息到第二算力网关。First, we will introduce how to send the second computing power information to the second computing power gateway.
在一些实施例中,第一算力网关基于边界网关协议(BGP)或内部网关协议(IGP)发送第二算力信息到第二算力网关。In some embodiments, the first computing power gateway sends the second computing power information to the second computing power gateway based on Border Gateway Protocol (BGP) or Interior Gateway Protocol (IGP).
接下来介绍如何发送第二算力信息到算力网络管控平台。Next, we will introduce how to send the second computing power information to the computing power network management and control platform.
在一些实施例中,第一算力网关发送第二状态信息到算力网络管控平台,第二状态信息表示第一算力网关是否能够被算力网络管控平台管理。In some embodiments, the first computing power gateway sends second status information to the computing power network management and control platform, and the second status information indicates whether the first computing power gateway can be managed by the computing power network management and control platform.
在一些实施例中,第一算力网关除了发送第二状态信息,还发送IP地址到算力网络管控平台,以使得算力网络管控平台能够基于IP地址与第一算力网关通信。例如,第一算力网关首次发送第二状态信息到算力网络管控平台时,可以一并发送IP地址。In some embodiments, in addition to sending the second status information, the first computing power gateway also sends an IP address to the computing power network management and control platform, so that the computing power network management and control platform can communicate with the first computing power gateway based on the IP address. For example, when the first computing power gateway sends the second status information to the computing power network management and control platform for the first time, it can also send the IP address.
进一步地,在第二状态信息表示第一算力网关能够被算力网络管控平台管理的情 况下,算力网络管控平台响应于第二状态信息,发送算力信息获取请求。Further, when the second status information indicates that the first computing power gateway can be managed by the computing power network management and control platform, the computing power network management and control platform responds to the second status information and sends a computing power information acquisition request.
相应地,第一算力网关响应于算力信息获取请求,发送算力信息获取响应到算力网络管控平台,算力信息获取响应中可以包括第二算力信息。Correspondingly, in response to the computing power information acquisition request, the first computing power gateway sends a computing power information acquisition response to the computing power network management and control platform, and the computing power information acquisition response may include the second computing power information.
上述实施例中,第一算力网关将第二算力信息发送到算力网络管控平台,有利于实现算力资源的集中式管控,也为后续算力资源的交易与分配提供了基础。In the above embodiment, the first computing power gateway sends the second computing power information to the computing power network management and control platform, which is conducive to realizing centralized management and control of computing power resources, and also provides a basis for subsequent transactions and allocation of computing power resources.
在一些实施例中,算力网络管控平台还具有平台数据库,能够保存第二算力信息。进一步地,平台数据库也能够保存第三算力信息,例如是在第二算力网关将第三算力信息发送到算力网络管控平台的情况下。In some embodiments, the computing power network management and control platform also has a platform database that can store the second computing power information. Furthermore, the platform database can also store the third computing power information, for example, when the second computing power gateway sends the third computing power information to the computing power network management and control platform.
在一些实施例中,第一算力网关还可以发送网络信息到算力网络管控平台。网络信息包括第一算力网关与第二算力网关之间的第一传输时延。进一步地,算力网络管控平台的平台数据库也能够保存网络信息。In some embodiments, the first computing power gateway can also send network information to the computing power network management and control platform. The network information includes the first transmission delay between the first computing power gateway and the second computing power gateway. Furthermore, the platform database of the computing power network management and control platform can also save network information.
作为一些实现方式,网络信息还包括带宽信息。例如,带宽信息包括第一算力网关与第二算力网关之间的带宽。As some implementations, network information also includes bandwidth information. For example, the bandwidth information includes the bandwidth between the first computing power gateway and the second computing power gateway.
下面介绍第一传输时延的几种确定方法。Several methods for determining the first transmission delay are introduced below.
在一些实施例中,第一算力网关接收来自第二算力网关的响应消息,基于响应消息确定第一传输时延。In some embodiments, the first computing power gateway receives a response message from the second computing power gateway, and determines the first transmission delay based on the response message.
例如,第一算力网关发送第二算力信息到第二算力网关后,第二网关发送响应消息,第二算力网关的响应消息包括表示发送响应消息时刻的时间戳,第一算力网关接收到响应消息后,基于表示发送响应消息时刻的时间戳和接收到响应消息的当前时间确定第一传输时延。For example, after the first computing power gateway sends the second computing power information to the second computing power gateway, the second computing power gateway sends a response message. The response message of the second computing power gateway includes a timestamp indicating the time when the response message is sent. The first computing power gateway After receiving the response message, the gateway determines the first transmission delay based on the timestamp indicating the time when the response message is sent and the current time when the response message is received.
又例如,第一算力网关发送PING指令到第二算力网关,第二算力网关响应于PING指令发送携带第一传输时延的响应消息,由此,第一算力网关确定第一传输时延。For another example, the first computing power gateway sends a PING instruction to the second computing power gateway, and the second computing power gateway sends a response message carrying the first transmission delay in response to the PING instruction. Thus, the first computing power gateway determines the first transmission time. time delay.
再例如,第一算力网关发送给第二算力网关的第二算力信息包括表示第一算力网关发送时刻的时间戳,第二算力网关基于表示第一算力网关发送时刻的时间戳和接收到第二算力信息的当前时间确定第一传输时延,发送响应消息给第一算力网关,响应消息中包括第一传输时延。For another example, the second computing power information sent by the first computing power gateway to the second computing power gateway includes a timestamp indicating the sending time of the first computing power gateway, and the second computing power gateway is based on the time indicating the sending time of the first computing power gateway. stamp and the current time when the second computing power information is received to determine the first transmission delay, and send a response message to the first computing power gateway, where the response message includes the first transmission delay.
上述实施例中,第一算力网关获取网关之间的第一传输时延,并将传输时延发送给算力网络管控平台,有利于后续基于第一传输时延确定从算力网络管控平台到算力资源节点之间的传输时延,便于用户选择合适的算力资源节点。In the above embodiment, the first computing power gateway obtains the first transmission delay between the gateways and sends the transmission delay to the computing power network management and control platform, which is beneficial to subsequent determination of the slave computing power network management and control platform based on the first transmission delay. The transmission delay to the computing resource node facilitates users to choose the appropriate computing resource node.
图2是根据本公开另一些实施例的算力信息的处理方法的流程示意图。表4是根据本公开一些实施例的算力资源分配请求的HTTPS RESTful接口报文格式。表5是根据本公开一些实施例的算力资源分配请求的参数。表6是根据本公开一些实施例的算力资源分配结果的参数。表7是根据本公开一些实施例的算力资源分配响应的参数。Figure 2 is a schematic flowchart of a method for processing computing power information according to other embodiments of the present disclosure. Table 4 is the HTTPS RESTful interface message format of the computing resource allocation request according to some embodiments of the present disclosure. Table 5 shows parameters of a computing resource allocation request according to some embodiments of the present disclosure. Table 6 is the parameters of the computing resource allocation results according to some embodiments of the present disclosure. Table 7 is the parameters of the computing resource allocation response according to some embodiments of the present disclosure.
表4Table 4
接口URIInterface URI /api/v1/kids/{kid}/nodes/{name}/api/v1/kids/{kid}/nodes/{name}
请求方式Request method HTTPS POSTHTTPS POST
数据交互格式Data interaction format application/jsonapplication/json
表5table 5
数据项data item 类型type 数据项描述Data item description 是否必须Is it necessary
codecode IntegerInteger 请求码Request code yes
datadata JsonJson 配置数据Configuration Data yes
在步骤202,第一算力网关响应于算力网络管控平台发送的算力资源分配请求,发送算力资源分配请求到第一算力资源节点,以使得第一算力资源节点基于算力资源分配请求分配算力资源。In step 202, the first computing power gateway responds to the computing power resource allocation request sent by the computing power network management and control platform, and sends the computing power resource allocation request to the first computing power resource node, so that the first computing power resource node is based on the computing power resource. Allocation requests allocate computing resources.
作为一些实现方式,第一算力网关根据表4和表5发送算力资源分配请求。例如,算力分配资源请求包括请求码“101”和配置数据,配置数据表示请求分配的算力资源的种类与大小。As some implementations, the first computing power gateway sends a computing power resource allocation request according to Table 4 and Table 5. For example, a computing power allocation resource request includes a request code "101" and configuration data. The configuration data indicates the type and size of the computing power resources requested to be allocated.
在步骤204,接收第一算力资源节点发送的算力资源分配结果。这里,算力资源分配结果表示算力资源分配是否成功。In step 204, receive the computing resource allocation result sent by the first computing resource node. Here, the computing power resource allocation result indicates whether the computing power resource allocation is successful.
表6Table 6
数据项data item 类型type 数据项描述Data item description 是否必须Is it necessary
codecode IntegerInteger 响应码response code yes
msgmsg StringString 响应信息response message yes
作为一些实现方式,第一算力资源节点按照表4和表6发送算力资源分配结果。例如,在算力资源分配成功的情况下,算力资源分配结果包括响应码“200”和表示算力资源分配成功的响应信息。又例如,在算力资源分配失败的情况下,算力资源分配结果包括响应码“201”和表示算力资源分配失败原因的响应信息。As some implementation methods, the first computing resource node sends the computing resource allocation results according to Table 4 and Table 6. For example, when the computing resource allocation is successful, the computing resource allocation result includes a response code “200” and response information indicating that the computing resource allocation is successful. For another example, when the computing resource allocation fails, the computing resource allocation result includes a response code “201” and response information indicating the reason for the computing resource allocation failure.
在步骤206,在算力资源分配结果表示算力资源分配成功的情况下,基于算力资 源分配结果对第一算力信息进行更新。In step 206, if the computing power resource allocation result indicates that the computing power resource allocation is successful, the first computing power information is updated based on the computing power resource allocation result.
在一些实施例中,在算力资源分配结果表示算力资源分配失败的情况下,第一算力网关不对第一算力信息进行更新。In some embodiments, when the computing power resource allocation result indicates that computing power resource allocation fails, the first computing power gateway does not update the first computing power information.
在步骤208,发送算力资源分配响应到算力网络管控平台。这里,算力资源分配响应表示第一算力信息是否更新成功。In step 208, a computing power resource allocation response is sent to the computing power network management and control platform. Here, the computing power resource allocation response indicates whether the first computing power information is updated successfully.
表7Table 7
数据项data item 类型type 数据项描述Data item description 是否必须Is it necessary
codecode IntegerInteger 响应码response code yes
msgmsg StringString 响应信息response message yes
作为一些实现方式,第一算力网关按照表4和表7生成算力资源分配响应。As some implementation methods, the first computing power gateway generates a computing power resource allocation response according to Table 4 and Table 7.
例如,在第一算力网关对第一算力信息更新成功的情况下,算力资源分配响应包括响应码“300”和表示第一算力信息更新成功的响应信息。进一步地,算力网络平台基于算力资源分配响应更新第一信息。For example, when the first computing power gateway successfully updates the first computing power information, the computing power resource allocation response includes a response code “300” and response information indicating that the first computing power information is successfully updated. Further, the computing power network platform updates the first information based on the computing power resource allocation response.
又例如,在第一算力网关对第一算力信息更新失败的情况下,算力资源分配响应包括响应码“301”和表示第一算力信息更新失败的响应信息。第一算力网关对第一算力信息更新失败例如发生在第一算力网关出现设备故障、网络故障或断电的情况下。进一步地,算力网络管控平台可以根据预设策略基于表示第一信息更新失败的算力资源分配响应做出相应的决策。For another example, in the case where the first computing power gateway fails to update the first computing power information, the computing power resource allocation response includes a response code “301” and response information indicating that the update of the first computing power information fails. The failure of the first computing power gateway to update the first computing power information may occur, for example, when an equipment failure, network failure, or power outage occurs in the first computing power gateway. Further, the computing power network management and control platform can make corresponding decisions based on the computing power resource allocation response indicating the failure of the first information update according to the preset policy.
作为一些实现方式,算力网络管控平台可以基于算力资源分配响应对第二算力信息进行更新。As some implementation methods, the computing power network management and control platform can update the second computing power information based on the computing power resource allocation response.
例如,在算力资源分配响应表示第一算力信息更新成功的情况下,算力网络管控平台可以基于算力资源分配请求和算力资源分配响应对第二算力信息进行更新。For example, when the computing power resource allocation response indicates that the first computing power information is successfully updated, the computing power network management and control platform can update the second computing power information based on the computing power resource allocation request and the computing power resource allocation response.
又例如,在算力资源分配响应表示第一算力信息更新成功的情况下,第一算力网关发送更新后的第二算力信息到算力网络管控平台,以使得算力网络管控平台对第二算力信息进行更新。For another example, when the computing power resource allocation response indicates that the first computing power information is successfully updated, the first computing power gateway sends the updated second computing power information to the computing power network management and control platform, so that the computing power network management and control platform can The second computing power information is updated.
上述实施例中,通过第一算力网关实现算力资源的分配和算力信息的更新,既有利于实现算力资源的交易,充分发挥算力网络的价值,又有利于及时获取算力资源的变化情况,以便及时同步算力信息。In the above embodiment, the allocation of computing power resources and the updating of computing power information are realized through the first computing power gateway, which is not only conducive to the transaction of computing power resources, giving full play to the value of the computing power network, but also conducive to timely acquisition of computing power resources. changes in order to synchronize computing power information in a timely manner.
本说明书中各个实施例均采用递进的方式描述,每个实施例重点说明的都是与其它实施例的不同之处,各个实施例之间相同或相似的部分相互参见即可。对于算力网 关实施例而言,由于其与方法实施例基本对应,所以描述的比较简单,相关之处参见方法实施例的部分说明即可。Each embodiment in this specification is described in a progressive manner, and each embodiment focuses on its differences from other embodiments. The same or similar parts between the various embodiments can be referred to each other. For the computing power gateway embodiment, since it basically corresponds to the method embodiment, the description is relatively simple. For relevant information, please refer to the partial description of the method embodiment.
图3是根据本公开一些实施例的算力网关的结构示意图。Figure 3 is a schematic structural diagram of a computing power gateway according to some embodiments of the present disclosure.
如图3所示,算力网关300包括获取模块310和发送模块320。算力网关300可以作为第一算力网关。As shown in Figure 3, the computing power gateway 300 includes an acquisition module 310 and a sending module 320. The computing power gateway 300 may serve as the first computing power gateway.
获取模块310被配置为获取第一算力资源节点的第一算力信息。例如,第一算力信息包括第一算力资源节点的标识与第一算力资源节点具有的算力资源。The acquisition module 310 is configured to acquire the first computing power information of the first computing power resource node. For example, the first computing power information includes the identification of the first computing power resource node and the computing power resources possessed by the first computing power resource node.
发送模块320被配置为发送第二算力信息到算力网络管控平台和第二算力网关中的至少一个。例如,第二算力信息包括第一算力信息和第一算力网关的标识。The sending module 320 is configured to send the second computing power information to at least one of the computing power network management and control platform and the second computing power gateway. For example, the second computing power information includes the first computing power information and the identification of the first computing power gateway.
图4是根据本公开另一些实施例的算力网关的结构示意图。Figure 4 is a schematic structural diagram of a computing power gateway according to other embodiments of the present disclosure.
如图4所示,算力网关400包括存储器401以及耦接至该存储器401的处理器402,处理器402被配置为基于存储在存储器401中的指令,执行前述任意一个实施例的方法。As shown in Figure 4, the computing power gateway 400 includes a memory 401 and a processor 402 coupled to the memory 401. The processor 402 is configured to execute the method of any of the foregoing embodiments based on instructions stored in the memory 401.
存储器401例如可以包括系统存储器、固定非易失性存储介质等。系统存储器例如可以存储有操作系统、应用程序、引导装载程序(Boot Loader)以及其他程序等。The memory 401 may include, for example, system memory, fixed non-volatile storage media, and the like. System memory may store, for example, operating systems, application programs, boot loaders, and other programs.
算力网关400还可以包括输入输出接口403、网络接口404、存储接口405等。这些接口403、404、405之间、以及存储器401与处理器402之间例如可以通过总线506连接。输入输出接口403为显示器、鼠标、键盘、触摸屏等输入输出设备提供连接接口。网络接口404为各种联网设备提供连接接口。存储接口405为SD卡、U盘等外置存储设备提供连接接口。The computing power gateway 400 may also include an input and output interface 403, a network interface 404, a storage interface 405, etc. These interfaces 403, 404, and 405, and the memory 401 and the processor 402 may be connected through a bus 506, for example. The input and output interface 403 provides a connection interface for input and output devices such as a monitor, mouse, keyboard, and touch screen. Network interface 404 provides a connection interface for various networked devices. The storage interface 405 provides a connection interface for external storage devices such as SD cards and USB disks.
图5是根据本公开一些实施例的算力信息的处理系统的结构示意图。Figure 5 is a schematic structural diagram of a computing power information processing system according to some embodiments of the present disclosure.
如图5所示,算力信息的处理系统500包括算力网络管控平台510和第一算力网关521。As shown in Figure 5, the computing power information processing system 500 includes a computing power network management and control platform 510 and a first computing power gateway 521.
第一算力网关521例如是算力网关300或算力网关400。The first computing power gateway 521 is, for example, the computing power gateway 300 or the computing power gateway 400 .
算力网络管控平台510被配置为接收并显示第二算力信息,以使得用户能够基于第二算力信息选择算力资源节点。The computing power network management and control platform 510 is configured to receive and display the second computing power information, so that the user can select the computing power resource node based on the second computing power information.
在一些实施例中,算力信息的处理系统500还包括第二算力网关522、第一算力资源节点531和第二算力资源节点532。In some embodiments, the computing power information processing system 500 also includes a second computing power gateway 522, a first computing power resource node 531, and a second computing power resource node 532.
第二算力网关522例如是算力网关300或算力网关400。The second computing power gateway 522 is, for example, the computing power gateway 300 or the computing power gateway 400 .
第一算力资源节点531的数量可以是一个或多个。The number of first computing resource nodes 531 may be one or more.
第二算力资源节点532的数量也可以是一个或多个。The number of second computing resource nodes 532 may also be one or more.
在一些实施例中,算力网络管控平台510还被配置为确定算力网络管控平台510与第一算力资源节点531之间的第二传输时延,以便用户根据第二传输时延和第一算力信息确定是否选择从第一算力资源节点531申请分配资源。In some embodiments, the computing power network management and control platform 510 is also configured to determine the second transmission delay between the computing power network management and control platform 510 and the first computing power resource node 531, so that the user can determine the second transmission delay according to the second transmission delay and the first computing power resource node 531. A computing power information determines whether to apply for allocation of resources from the first computing power resource node 531.
作为一些实现方式,算力网络管控平台510能够同时显示算力资源节点的算力信息以及到该算力资源节点的第二传输时延,以便用户结合自己的需求选择合适的算力资源节点。As some implementation methods, the computing power network management and control platform 510 can simultaneously display the computing power information of the computing power resource node and the second transmission delay to the computing power resource node, so that users can select the appropriate computing power resource node based on their own needs.
作为一些实现方式,算力网络管控平台510被配置为获取第一算力网关521与第二算力网关522之间的第一传输时延,并根据第一传输时延确定第二传输时延。As some implementations, the computing power network management and control platform 510 is configured to obtain the first transmission delay between the first computing power gateway 521 and the second computing power gateway 522, and determine the second transmission delay based on the first transmission delay. .
例如,算力网络管控平台510可以获取第二算力网关522发送的网络信息,该网络信息中可以携带第一算力网关521与第二算力网关522之间的第一传输时延。在第一算力网关521与算力网络管控平台510之间无法直接通信,但第一算力网关521与第二算力网关522之间、第二算力网关522与算力网络管控平台510之间均可以直接通信的情况下,算力网络管控平台510可以根据第一算力网关521与第二算力网关522之间的第一传输时延、第一算力网关521与第一算力资源节点531之间的传输时延、以及算力网络管控平台510与第二算力网关522之间的传输时延计算得到算力网络管控平台510与第一算力资源节点531之间的第二传输时延。For example, the computing power network management and control platform 510 can obtain the network information sent by the second computing power gateway 522, and the network information can carry the first transmission delay between the first computing power gateway 521 and the second computing power gateway 522. There is no direct communication between the first computing power gateway 521 and the computing power network management and control platform 510, but there is no direct communication between the first computing power gateway 521 and the second computing power gateway 522, and between the second computing power gateway 522 and the computing power network management and control platform 510. In the case where they can directly communicate with each other, the computing power network management and control platform 510 can calculate the first transmission delay between the first computing power gateway 521 and the second computing power gateway 522, the first computing power gateway 521 and the first computing power gateway 522. The transmission delay between the computing power resource nodes 531 and the transmission delay between the computing power network management and control platform 510 and the second computing power gateway 522 are calculated to obtain the transmission delay between the computing power network management and control platform 510 and the first computing power resource node 531. Second transmission delay.
在一些实施例中,算力网络管控平台510还具有交易功能,在用户选择算力资源节点后或者在向用户提供算力资源后,算力网络管控平台510可以进行交易结算。In some embodiments, the computing power network management and control platform 510 also has a transaction function. After the user selects a computing power resource node or after providing computing power resources to the user, the computing power network management and control platform 510 can perform transaction settlement.
本公开实施例还提供了一种计算机可读存储介质,包括计算机程序指令,该计算机程序指令被处理器执行时实现上述任意一个实施例的方法。Embodiments of the present disclosure also provide a computer-readable storage medium, including computer program instructions. When the computer program instructions are executed by a processor, the method of any of the above embodiments is implemented.
本公开实施例还提供了一种计算机程序产品,包括计算机程序,其中,所述计算机程序被处理器执行时实现上述任意一项所述的方法。An embodiment of the present disclosure also provides a computer program product, including a computer program, wherein when the computer program is executed by a processor, any one of the above methods is implemented.
至此,已经详细描述了本公开的各实施例。为了避免遮蔽本公开的构思,没有描述本领域所公知的一些细节。本领域技术人员根据上面的描述,完全可以明白如何实施这里公开的技术方案。Up to this point, various embodiments of the present disclosure have been described in detail. To avoid obscuring the concepts of the present disclosure, some details that are well known in the art have not been described. Based on the above description, those skilled in the art can completely understand how to implement the technical solution disclosed here.
本领域内的技术人员应当明白,本公开的实施例可提供为方法、系统、或计算机程序产品。因此,本公开可采用完全硬件实施例、完全软件实施例、或结合软件和硬件方面的实施例的形式。而且,本公开可采用在一个或多个其中包含有计算机可用程序代码的计算机可用非瞬时性存储介质(包括但不限于磁盘存储器、CD-ROM、光学 存储器等)上实施的计算机程序产品的形式。Those skilled in the art will appreciate that embodiments of the present disclosure may be provided as methods, systems, or computer program products. Accordingly, the present disclosure may take the form of an entirely hardware embodiment, an entirely software embodiment, or an embodiment that combines software and hardware aspects. Furthermore, the present disclosure may take the form of a computer program product embodied on one or more computer-usable non-transitory storage media (including, but not limited to, disk memory, CD-ROM, optical storage, etc.) having computer-usable program code embodied therein. .
本公开是参照根据本公开实施例的方法、设备(系统)、和计算机程序产品的流程图和/或方框图来描述的。应理解,可由计算机程序指令实现流程图中一个流程或多个流程和/或方框图中一个方框或多个方框中指定的功能。可提供这些计算机程序指令到通用计算机、专用计算机、嵌入式处理机或其他可编程数据处理设备的处理器以产生一个机器,使得通过计算机或其他可编程数据处理设备的处理器执行的指令产生用于实现在流程图一个流程或多个流程和/或方框图一个方框或多个方框中指定的功能的装置。The disclosure is described with reference to flowchart illustrations and/or block diagrams of methods, apparatus (systems), and computer program products according to embodiments of the disclosure. It will be understood that the functions specified in one or more processes in the flowchart illustrations and/or in one block or blocks in the block diagrams can be implemented by computer program instructions. These computer program instructions may be provided to a processor of a general purpose computer, special purpose computer, embedded processor, or other programmable data processing device to produce a machine, such that the instructions executed by the processor of the computer or other programmable data processing device produce a use A device for realizing the functions specified in one process or multiple processes of the flowchart and/or one block or multiple blocks of the block diagram.
这些计算机程序指令也可存储在能引导计算机或其他可编程数据处理设备以特定方式工作的计算机可读存储器中,使得存储在该计算机可读存储器中的指令产生包括指令装置的制造品,该指令装置实现在流程图一个流程或多个流程和/或方框图一个方框或多个方框中指定的功能。These computer program instructions may also be stored in a computer-readable memory that causes a computer or other programmable data processing apparatus to operate in a particular manner, such that the instructions stored in the computer-readable memory produce an article of manufacture including the instruction means, the instructions The device implements the functions specified in a process or processes of the flowchart and/or a block or blocks of the block diagram.
这些计算机程序指令也可装载到计算机或其他可编程数据处理设备上,使得在计算机或其他可编程设备上执行一系列操作步骤以产生计算机实现的处理,从而在计算机或其他可编程设备上执行的指令提供用于实现在流程图一个流程或多个流程和/或方框图一个方框或多个方框中指定的功能的步骤。These computer program instructions may also be loaded onto a computer or other programmable data processing device, causing a series of operating steps to be performed on the computer or other programmable device to produce computer-implemented processing, thereby executing on the computer or other programmable device. Instructions provide steps for implementing the functions specified in a process or processes of a flowchart diagram and/or a block or blocks of a block diagram.
虽然已经通过示例对本公开的一些特定实施例进行了详细说明,但是本领域的技术人员应该理解,以上示例仅是为了进行说明,而不是为了限制本公开的范围。本领域的技术人员应该理解,可在不脱离本公开的范围和精神的情况下,对以上实施例进行修改或者对部分技术特征进行等同替换。本公开的范围由所附权利要求来限定。Although some specific embodiments of the present disclosure have been described in detail through examples, those skilled in the art will understand that the above examples are for illustration only and are not intended to limit the scope of the disclosure. Those skilled in the art should understand that the above embodiments can be modified or some technical features can be equivalently replaced without departing from the scope and spirit of the present disclosure. The scope of the disclosure is defined by the appended claims.

Claims (18)

  1. 一种算力信息的处理方法,包括:A method for processing computing power information, including:
    第一算力网关获取第一算力资源节点的第一算力信息,所述第一算力信息包括所述第一算力资源节点的标识与所述第一算力资源节点具有的算力资源;以及The first computing power gateway obtains the first computing power information of the first computing power resource node. The first computing power information includes the identification of the first computing power resource node and the computing power of the first computing power resource node. resources; and
    所述第一算力网关发送第二算力信息到算力网络管控平台和第二算力网关中的至少一个,所述第二算力信息包括所述第一算力信息和所述第一算力网关的标识。The first computing power gateway sends second computing power information to at least one of the computing power network management and control platform and the second computing power gateway. The second computing power information includes the first computing power information and the first computing power gateway. The identity of the computing power gateway.
  2. 根据权利要求1所述的方法,还包括:The method of claim 1, further comprising:
    所述第一算力网关接收所述第二算力网关发送的第三算力信息,所述第三算力信息包括第四算力信息和所述第二算力网关的标识,所述第四算力信息包括第二算力资源节点的标识与所述第二算力资源节点具有的算力资源。The first computing power gateway receives the third computing power information sent by the second computing power gateway. The third computing power information includes fourth computing power information and the identification of the second computing power gateway. The third computing power gateway The four computing power information includes the identification of the second computing power resource node and the computing power resources possessed by the second computing power resource node.
  3. 根据权利要求1或2所述的方法,其中,The method according to claim 1 or 2, wherein,
    所述第一算力网关是所述算力网络管控平台管控的任意一个算力网关,所述第二算力网关是所述算力网络管控平台管控的除所述第一算力网关外的任意一个算力网关。The first computing power gateway is any computing power gateway controlled by the computing power network management and control platform, and the second computing power gateway is other than the first computing power gateway controlled by the computing power network management and control platform. Any computing power gateway.
  4. 根据权利要求1-3中任一项所述的方法,其中,所述第一算力网关至少发送所述第二算力信息到所述算力网络管控平台,所述方法还包括:The method according to any one of claims 1-3, wherein the first computing power gateway sends at least the second computing power information to the computing power network management and control platform, and the method further includes:
    所述第一算力网关发送网络信息到所述算力网络管控平台,所述网络信息包括所述第一算力网关与所述第二算力网关之间的第一传输时延。The first computing power gateway sends network information to the computing power network management and control platform, where the network information includes a first transmission delay between the first computing power gateway and the second computing power gateway.
  5. 根据权利要求4所述的方法,还包括:The method of claim 4, further comprising:
    所述第一算力网关接收来自所述第二算力网关的响应消息;以及The first computing power gateway receives a response message from the second computing power gateway; and
    基于所述响应消息,确定所述第一传输时延。Based on the response message, the first transmission delay is determined.
  6. 根据权利要求1-5中任一项所述的方法,还包括:The method according to any one of claims 1-5, further comprising:
    所述第一算力网关保存所述第一算力信息。The first computing power gateway stores the first computing power information.
  7. 根据权利要求6所述的方法,还包括:The method of claim 6, further comprising:
    所述第一算力网关响应于所述算力网络管控平台发送的算力资源分配请求,发送所述算力资源分配请求到所述第一算力资源节点,以使得所述第一算力资源节点基于所述算力资源分配请求分配算力资源;The first computing power gateway responds to the computing power resource allocation request sent by the computing power network management and control platform, and sends the computing power resource allocation request to the first computing power resource node, so that the first computing power resource allocation request is sent to the first computing power resource node. The resource node allocates computing power resources based on the computing power resource allocation request;
    所述第一算力网关接收所述第一算力资源节点发送的算力资源分配结果,所述算力资源分配结果表示算力资源分配是否成功;The first computing power gateway receives the computing power resource allocation result sent by the first computing power resource node, and the computing power resource allocation result indicates whether the computing power resource allocation is successful;
    所述第一算力网关在所述算力资源分配结果表示算力资源分配成功的情况下,基于所述算力资源分配结果对所述第一算力信息进行更新;以及The first computing power gateway updates the first computing power information based on the computing power resource allocation result when the computing power resource allocation result indicates that the computing power resource allocation is successful; and
    所述第一算力网关发送算力资源分配响应到所述算力网络管控平台,所述算力资源分配响应表示所述第一算力信息是否更新成功。The first computing power gateway sends a computing power resource allocation response to the computing power network management and control platform, and the computing power resource allocation response indicates whether the first computing power information is updated successfully.
  8. 根据权利要求1-7中任一项所述的方法,还包括:The method according to any one of claims 1-7, further comprising:
    所述第一算力网关接收所述第一算力资源节点发送的第一状态信息,所述第一状态信息表示所述第一算力资源节点是否能够被所述第一算力网关管理;The first computing power gateway receives the first status information sent by the first computing power resource node, and the first status information indicates whether the first computing power resource node can be managed by the first computing power gateway;
    其中,在所述第一算力资源节点能够被所述第一算力网关管理的情况下,所述第一算力网关获取所述第一算力信息。Wherein, when the first computing power resource node can be managed by the first computing power gateway, the first computing power gateway obtains the first computing power information.
  9. 根据权利要求1-8中任一项所述的方法,其中,The method according to any one of claims 1-8, wherein,
    所述算力资源包括中央处理器资源、图形处理器资源、现场可编程门阵列资源和内存资源中的至少一种。The computing resources include at least one of central processing unit resources, graphics processor resources, field programmable gate array resources and memory resources.
  10. 根据权利要求1-9中任一项所述的方法,其中,The method according to any one of claims 1-9, wherein,
    所述第一算力资源节点和所述算力网络管控平台中的每一个与所述第一算力网关通过HTTPS RESTful接口相连。Each of the first computing power resource node and the computing power network management and control platform is connected to the first computing power gateway through an HTTPS RESTful interface.
  11. 根据权利要求1-10中任一项所述的方法,其中,The method according to any one of claims 1-10, wherein,
    所述第一算力网关基于边界网关协议或内部网关协议发送所述第二算力信息到所述第二算力网关。The first computing power gateway sends the second computing power information to the second computing power gateway based on a border gateway protocol or an interior gateway protocol.
  12. 一种算力网关,作为第一算力网关,包括:A computing power gateway, as the first computing power gateway, includes:
    获取模块,被配置为获取第一算力资源节点的第一算力信息,所述第一算力信息包括所述第一算力资源节点的标识与所述第一算力资源节点具有的算力资源;以及The acquisition module is configured to obtain the first computing power information of the first computing power resource node, where the first computing power information includes the identification of the first computing power resource node and the computing power of the first computing power resource node. human resources; and
    发送模块,被配置为发送第二算力信息到算力网络管控平台和第二算力网关中的至少一个,所述第二算力信息包括所述第一算力信息和所述第一算力网关的标识。A sending module configured to send second computing power information to at least one of the computing power network management and control platform and the second computing power gateway, where the second computing power information includes the first computing power information and the first computing power gateway. The identity of the power gateway.
  13. 一种算力网关,包括:A computing power gateway, including:
    存储器;以及memory; and
    耦接至所述存储器的处理器,被配置为基于存储在所述存储器中的指令,执行权利要求1-11任意一项所述的方法。A processor coupled to the memory is configured to perform the method of any one of claims 1-11 based on instructions stored in the memory.
  14. 一种算力信息的处理系统,包括:A computing power information processing system, including:
    第一算力网关,为如权利要求12或13所述的算力网关;以及The first computing power gateway is the computing power gateway as claimed in claim 12 or 13; and
    所述算力网络管控平台,被配置为接收并显示所述第二算力信息,以使得用户基于所述第二算力信息选择算力资源节点。The computing power network management and control platform is configured to receive and display the second computing power information, so that the user selects a computing power resource node based on the second computing power information.
  15. 根据权利要求14所述的处理系统,其中,The processing system of claim 14, wherein
    所述算力网络管控平台还被配置为确定所述算力网络管控平台与所述第一算力资源节点之间的第二传输时延,以便用户根据所述第二传输时延和所述第一算力信息确定是否选择从所述第一算力资源节点申请分配资源。The computing power network management and control platform is also configured to determine a second transmission delay between the computing power network management and control platform and the first computing power resource node, so that the user can determine the second transmission delay according to the second transmission delay and the first computing power resource node. The first computing power information determines whether to apply for allocation of resources from the first computing power resource node.
  16. 根据权利要求15所述的处理系统,其中,The processing system of claim 15, wherein:
    所述算力网络管控平台被配置为获取第一算力网关与第二算力网关之间的第一传输时延,并根据所述第一传输时延确定所述第二传输时延。The computing power network management and control platform is configured to obtain the first transmission delay between the first computing power gateway and the second computing power gateway, and determine the second transmission delay based on the first transmission delay.
  17. 一种计算机可读存储介质,包括计算机程序指令,其中,所述计算机程序指令被处理器执行时实现权利要求1-11任意一项所述的方法。A computer-readable storage medium includes computer program instructions, wherein when the computer program instructions are executed by a processor, the method of any one of claims 1-11 is implemented.
  18. 一种计算机程序产品,包括计算机程序,其中,所述计算机程序被处理器执行时实现权利要求1-11任意一项所述的方法。A computer program product includes a computer program, wherein when the computer program is executed by a processor, the method of any one of claims 1-11 is implemented.
PCT/CN2022/123292 2022-03-30 2022-09-30 Computing power information processing method and system and computing power gateway WO2023184917A1 (en)

Applications Claiming Priority (2)

Application Number Priority Date Filing Date Title
CN202210325008.XA CN114760304A (en) 2022-03-30 2022-03-30 Computing power information processing method and system and computing power gateway
CN202210325008.X 2022-03-30

Publications (1)

Publication Number Publication Date
WO2023184917A1 true WO2023184917A1 (en) 2023-10-05

Family

ID=82329609

Family Applications (1)

Application Number Title Priority Date Filing Date
PCT/CN2022/123292 WO2023184917A1 (en) 2022-03-30 2022-09-30 Computing power information processing method and system and computing power gateway

Country Status (2)

Country Link
CN (1) CN114760304A (en)
WO (1) WO2023184917A1 (en)

Families Citing this family (1)

* Cited by examiner, † Cited by third party
Publication number Priority date Publication date Assignee Title
CN114760304A (en) * 2022-03-30 2022-07-15 中国电信股份有限公司 Computing power information processing method and system and computing power gateway

Citations (6)

* Cited by examiner, † Cited by third party
Publication number Priority date Publication date Assignee Title
CN113709048A (en) * 2020-05-21 2021-11-26 中国移动通信有限公司研究院 Routing information sending and receiving method, network element and node equipment
CN113840317A (en) * 2020-06-08 2021-12-24 中国移动通信有限公司研究院 Calculation capacity reporting method, calculation capacity obtaining method, calculation capacity network element and calculation capacity sensing control network element
WO2022016466A1 (en) * 2020-07-23 2022-01-27 北京小米移动软件有限公司 Resource request information processing method and apparatus, and communication device and storage medium
CN114095577A (en) * 2020-07-31 2022-02-25 中国移动通信有限公司研究院 Resource request method and device, calculation network element node and calculation application equipment
CN114157667A (en) * 2021-10-28 2022-03-08 山东浪潮科学研究院有限公司 Computing power network service system and method facing gateway equipment
CN114760304A (en) * 2022-03-30 2022-07-15 中国电信股份有限公司 Computing power information processing method and system and computing power gateway

Family Cites Families (4)

* Cited by examiner, † Cited by third party
Publication number Priority date Publication date Assignee Title
CN109936472A (en) * 2017-12-18 2019-06-25 上海无线通信研究中心 The node computing capability calculated towards mist describes method, exchange method and its equipment
US11075999B2 (en) * 2018-08-28 2021-07-27 Citrix Systems, Inc. Accessing resources in a remote access or cloud-based network environment
CN111800282B (en) * 2019-04-08 2023-03-28 阿里巴巴集团控股有限公司 Network system, instance management and control method, device and storage medium
CN114221959A (en) * 2021-12-14 2022-03-22 中国电信股份有限公司 Service sharing method, device and system

Patent Citations (6)

* Cited by examiner, † Cited by third party
Publication number Priority date Publication date Assignee Title
CN113709048A (en) * 2020-05-21 2021-11-26 中国移动通信有限公司研究院 Routing information sending and receiving method, network element and node equipment
CN113840317A (en) * 2020-06-08 2021-12-24 中国移动通信有限公司研究院 Calculation capacity reporting method, calculation capacity obtaining method, calculation capacity network element and calculation capacity sensing control network element
WO2022016466A1 (en) * 2020-07-23 2022-01-27 北京小米移动软件有限公司 Resource request information processing method and apparatus, and communication device and storage medium
CN114095577A (en) * 2020-07-31 2022-02-25 中国移动通信有限公司研究院 Resource request method and device, calculation network element node and calculation application equipment
CN114157667A (en) * 2021-10-28 2022-03-08 山东浪潮科学研究院有限公司 Computing power network service system and method facing gateway equipment
CN114760304A (en) * 2022-03-30 2022-07-15 中国电信股份有限公司 Computing power information processing method and system and computing power gateway

Also Published As

Publication number Publication date
CN114760304A (en) 2022-07-15

Similar Documents

Publication Publication Date Title
US11704144B2 (en) Creating virtual machine groups based on request
US10079837B2 (en) Distributed topology enabler for identity manager
US10701139B2 (en) Life cycle management method and apparatus
WO2020177533A1 (en) Electronic invoice identifier allocation method, and electronic ticket generating method, device and system
US10700947B2 (en) Life cycle management method and device for network service
CN108536519B (en) Method for automatically building Kubernetes main node and terminal equipment
US9999030B2 (en) Resource provisioning method
CN111385114B (en) VNF service instantiation method and device
US10153941B2 (en) Distributed operational control in computing systems
WO2018149221A1 (en) Device management method and network management system
US8412810B1 (en) Provisioning and managing a cluster deployed on a cloud
JP2022137138A (en) multi-cluster ingress
WO2018006676A1 (en) Acceleration resource processing method and apparatus and network function virtualization system
EP3905588A1 (en) Cloud platform deployment method and apparatus, server and storage medium
WO2019057055A1 (en) Task processing method and apparatus, electronic device, and storage medium
CN109416646B (en) Optimization method for container allocation and processing equipment
WO2023184917A1 (en) Computing power information processing method and system and computing power gateway
WO2021169264A1 (en) Automatic scheduling method and apparatus for database access layer middleware
US9106676B1 (en) Grid-based server messaging infrastructure
WO2018188607A1 (en) Stream processing method and device
WO2023197666A1 (en) Service scheduling method, system, vtep, storage medium, and computer program product
CN114615268B (en) Service network, monitoring node, container node and equipment based on Kubernetes cluster
CN112910796B (en) Traffic management method, apparatus, device, storage medium, and program product
WO2022028092A1 (en) Vnf instantiation method and apparatus
US11537440B2 (en) Infrastructure adaptive consistency level mechanism

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: 22934735

Country of ref document: EP

Kind code of ref document: A1