Computing resource allocation method, management device, server and storage medium

Abstract

The disclosure provides a computing power resource allocation method, a management device, a server and a storage medium, wherein the method comprises the following steps: a computing power network controller performs computing power resource matching based on a computing power resource acquisition request, so as to select a computing power resource server in a computing power network; the computing power network controller determines a computing power resource access path of a terminal APP accessing the computing power resource server, sends path information of the computing power resource access path, address information of the terminal and the computing power resource server to a network equipment head node of the computing power resource access path, and sends the address information of the computing power resource server to the terminal APP. The method, device, server and storage medium provided by the disclosure can meet the transmission delay and bandwidth requirement of the user to the computing power resource, and guarantee the service performance of the computing power resource.

Description

TECHNICAL FIELD

[0001] The present application relates to the technical field of communication, in particular to a computing power resource allocation method, a management device, a server and a storage medium. BACKGROUND

[0002] With the wide application of big data and artificial intelligence (AI), the demand for computing power resources of users is increasing day by day, and suppliers can provide computing power resources of different brands, different functional characteristics and different prices to provide users with rich choices of computing power resources. Because a large number of computing power resource applications have high requirements for transmission quality (such as delay and bandwidth requirements), in order to guarantee the service performance of computing power resources, the transmission line needs to provide delay and bandwidth guarantee. At present, there is no technical solution that can provide computing power resources that meet high-quality transmission services. SUMMARY

[0003] Therefore, one of the technical problems to be solved by the present application is to provide a computing power resource allocation method, a management device, a server and a storage medium.

[0004] According to a first aspect of the present application, a computing power resource allocation method is provided, comprising: a computing power network controller receiving a computing power resource acquisition request sent by a terminal APP; the computing power network controller performing computing power resource matching based on the computing power resource acquisition request, so as to select a computing power resource server in a computing power network; the computing power network controller determines a computing power resource access path of the terminal APP accessing the computing power resource server, and sends path information of the computing power resource access path and address information of the terminal and the computing power resource server to a network device head node of the computing power resource access path; wherein the network device head node generates a transmission tunnel based on the path information, so as to transmit a service flow corresponding to the terminal APP through the transmission tunnel after the terminal APP accesses; and the computing power network controller sends the address information of the computing power resource server to the terminal APP.

[0005] Optionally, the computing power network controller receives computing power resource information reported by the computing power resource server; wherein the computing power resource information includes: computing power resource ID, location information, available computing power resource and storage capacity information.

[0006] Optionally, the computing power resource server reports the computing power resource information at a regular time, or reports the computing power resource information when the computing power resource server determines that the change value of the available computing power resource of itself exceeds a threshold value.

[0007] Optionally, the information carried by the computing resource acquisition request includes: a user location, a required computing capacity, a required storage amount, a transmission delay requirement, and a bandwidth requirement; the computing resource matching based on the computing resource acquisition request includes: selecting candidate computing resource servers in the computing network based on the required computing capacity and the required storage amount; determining transmission delay and transmission bandwidth between the user location and the candidate computing resource servers; and selecting a computing resource server from the candidate computing resource servers according to a screening condition, wherein the screening condition includes: the transmission delay is less than the transmission delay requirement and the transmission bandwidth is greater than the bandwidth requirement.

[0008] Optionally, the computing resource access path of the terminal APP accessing the computing resource server is determined by the computing network controller based on a shortest path transmission delay rule, wherein a sum of transmission delays between adjacent network devices in the computing resource access path is less than the transmission delay requirement, and transmission bandwidths between adjacent network devices are all greater than the bandwidth requirement.

[0009] Optionally, the path information includes: SID List information of each network device in the computing resource access path; and the path information of the computing resource access path, the address information of the terminal and the computing resource server are sent to a head node of the network device in the computing resource access path, including: sending the SID List information and the IP addresses of the terminal and the computing resource server to the head node of the network device.

[0010] Optionally, the head node of the network device configures an access control list for a service flow based on the IP addresses of the terminal and the computing resource server, encapsulates a packet header carrying the SID List information, and guides a matched service flow into a SID List tunnel for transmission.

[0011] According to a second aspect of the present disclosure, a computing power resource management apparatus is provided, which is arranged in a computing power network controller and comprises: a computing power request receiving module configured to receive a computing power resource acquisition request sent by a terminal APP; a computing power resource matching module configured to perform computing power resource matching based on the computing power resource acquisition request, so as to select a computing power resource server in a computing power network; an access path determining module configured to determine a computing power resource access path of the terminal APP accessing the computing power resource server, and send path information of the computing power resource access path and address information of the terminal and the computing power resource server to a network device head node of the computing power resource access path; wherein the network device head node generates a transmission tunnel based on the path information, so as to transmit a service flow corresponding to the terminal APP through the transmission tunnel after the terminal APP accesses; and a resource address sending module configured to send the address information of the computing power resource server to the terminal APP.

[0012] Optionally, the computing power resource matching module is configured to receive computing power resource information reported by the computing power resource server; wherein the computing power resource information comprises a computing power resource ID, location information, available computing power resource and storage capacity information.

[0013] Optionally, the computing power resource server reports the computing power resource information at a regular time, or reports the computing power resource information when the computing power resource server determines that a change value of available computing power resource thereof exceeds a threshold value.

[0014] Optionally, the computing power resource acquisition request carries information including a user location, required computing capacity, required storage quantity, transmission delay requirement and bandwidth requirement; the computing power resource matching module is configured to select a candidate computing power resource server in the computing power network based on the required computing capacity and the required storage quantity; determine transmission delay and transmission bandwidth between the user location and the candidate computing power resource server; and select a computing power resource server from the candidate computing power resource according to a screening condition; wherein the screening condition comprises that the transmission delay is less than the transmission delay requirement and the transmission bandwidth is greater than the bandwidth requirement.

[0015] Optionally, the access path determining module is configured to determine a computing power resource access path of the terminal APP accessing the computing power resource server based on a shortest path transmission delay rule; wherein a sum of transmission delays between adjacent network devices in the computing power resource access path is less than the transmission delay requirement, and transmission bandwidths between adjacent network devices are all greater than the bandwidth requirement.

[0016] Optionally, the path information comprises SID List information of each network device in the computing resource access path; the access path determination module is configured to send the SID List information, the IP address of the terminal and the computing resource server to the network device head node.

[0017] Optionally, the network device head node configures an access control list for a service flow based on the IP address of the terminal and the computing resource server, encapsulates a message header carrying the SID List information, and uses the message header to guide a matched service flow into a SID List tunnel for transmission.

[0018] According to a third aspect of the present disclosure, a computing resource management apparatus is provided, comprising a memory and a processor coupled to the memory, the processor being configured to execute the method described above based on instructions stored in the memory.

[0019] According to a fourth aspect of the present disclosure, a computing resource network controller is provided, comprising the computing resource management apparatus described above.

[0020] According to a fifth aspect of the present disclosure, a computer readable storage medium is provided, the computer readable storage medium storing computer instructions, the instructions being executed by a processor to perform the method described above.

[0021] The computing resource allocation method, management apparatus, server and storage medium of the present disclosure dynamically select computing resources with transmission quality guarantee for users through a computing resource network controller, meet the transmission delay and bandwidth requirements of users to computing resources, and guarantee the service performance of computing resources. BRIEF DESCRIPTION OF DRAWINGS

[0022] In order to more clearly illustrate the technical solutions in the embodiments of the present disclosure or the prior art, a brief introduction will be given below to the drawings needed to be used in the embodiments or prior art description. Obviously, the drawings in the following description are only some embodiments of the present disclosure, and other drawings can be obtained by those skilled in the art without creative labor under the premise of the drawings.

[0023] Figure 1 Flowchart of one embodiment of the computing resource allocation method according to the present disclosure;

[0024] Figure 2 Schematic diagram of a computing resource network; Figure 3 Functional architecture diagram of a computing resource network;

[0025] Figure 4 Flowchart of another embodiment of the computing resource allocation method according to the present disclosure;

[0026] Figure 5 A schematic diagram of performing computing resource allocation according to one embodiment of the computing resource allocation method according to the present disclosure;

[0027] Figure 6 A module schematic diagram of one embodiment of the computing resource management apparatus according to the present disclosure;

[0028] Figure 7 A module schematic diagram of another embodiment of the computing resource management apparatus according to the present disclosure. DETAILED DESCRIPTION

[0029] The present disclosure will be described more fully hereinafter with reference to the accompanying drawings, in which example embodiments of the present disclosure are described. The technical solutions in the embodiments of the present disclosure will be described clearly and completely with reference to the accompanying drawings of the embodiments of the present disclosure. Obviously, the described embodiments are only part of the embodiments of the present disclosure, rather than all the embodiments of the present disclosure. Based on the embodiments in the present disclosure, all other embodiments obtained by those skilled in the art without creative work fall within the scope of protection of the present disclosure.

[0030] Figure 1 A flow schematic diagram of one embodiment of the computing resource allocation method according to the present disclosure is shown as follows: Figure 1

[0031] Step 101, the computing network controller receives a computing resource acquisition request sent by a terminal APP.

[0032] In one embodiment, the terminal APP can be a plurality of APPs installed on the terminal, such as e-commerce APPs, computing APPs, etc. The terminal can be a mobile phone, a tablet computer, etc. The computing resource can be a computing resource server, etc. The computing resource provided by the computing resource server includes CPU, memory, storage space, etc.

[0033] Step 102, the computing network controller performs computing resource matching based on the computing resource acquisition request, so as to select a computing resource server in the computing network.

[0034] Step 103, the computing network controller determines a computing resource access path of the terminal APP accessing the computing resource server, and sends path information of the computing resource access path, address information of the terminal and the computing resource server to a network device head node of the computing resource access path.

[0035] In one embodiment, the network devices constituting the computing resource access path include switches, routers, etc. The network device head node generates a transmission tunnel based on the path information, so as to transmit a service flow corresponding to the terminal APP through the transmission tunnel after the terminal APP accesses. ​

[0036] Step 104, the computing power network controller sends the address information of the computing power resource server to the terminal APP.

[0037] The computing power resource allocation method in the above embodiment dynamically selects computing power resources with transmission quality guarantee for users by the computing power network controller, meeting the user's demand for high-quality transmission service computing power resources.

[0038] In one embodiment, the computing power network controller receives the computing power resource information reported by the computing power resource server, which includes computing power resource ID, location information, available computing power resources, and storage capacity information, etc. The computing power resource reports the computing power resource information regularly, or when the computing power resource determines that the computing power resource change value exceeds the change value threshold, it reports the computing power resource information.

[0039] As shown in Figure 2 The computing power network is composed of computing power resource servers, network devices, various mobile and fixed terminals distributed everywhere, with different brands, different functions and capabilities, and different computing power. Since the utilization of computing power resources of the computing power resource server is a dynamic change process, it needs to be reported to the computing power network controller (with a computing power resource management module) in real time according to the strategy (the strategy can be regular reporting or change reporting).

[0040] As shown in Figure 3 The computing power network function architecture includes computing power network resource layer, computing power network control layer, and computing power network service layer. The computing power network resource layer mainly includes computing resources, storage resources, and network resources, etc. The computing power network control layer is responsible for computing power resource information collection, network topology data collection, network traffic data collection, link transmission delay data collection, and transmission delay and bandwidth calculation. The computing power network service layer is responsible for various computing power network application services, including user self-service APP, available computing power resource information (such as computing power resource provider brand, price, CPU computing power, storage, functional characteristics, etc.), optimization of the transmission line of the obtained computing power resources, etc.

[0041] In one embodiment, the information carried by the computing power resource acquisition request includes user location, required computing power, required storage quantity, transmission delay requirement, bandwidth requirement, etc. The computing power network controller selects candidate computing power resource servers in the computing power network based on the required computing power and the required storage quantity, determines the transmission delay and transmission bandwidth between the user location and the candidate computing power resource servers, and selects the computing power resource server from the candidate computing power resources according to the screening conditions, which include transmission delay less than transmission delay requirement and transmission bandwidth greater than bandwidth requirement, etc.

[0042] The computing power network controller can generate computing power resource access paths corresponding to computing power resources using various methods. For example, the computing power network controller selects target computing power resources based on the shortest path transmission delay rule to generate computing power resource access paths. The total transmission delay between adjacent network devices in the computing power resource access path is less than the transmission delay requirement, and the transmission bandwidth between adjacent network devices is greater than the bandwidth requirement.

[0043] Terminal information includes terminal IP addresses, and path information includes SID List information for each network device in the computing resource access path. The computing network controller sends the SID List information, the IP addresses of the terminals and computing resource servers to the network device head nodes. The network device head nodes configure access control lists for the service flows based on the IP addresses of the terminals and computing resource servers, encapsulating a header carrying the SID List information to guide the matching service flows into the SID List tunnel for transmission. Various existing methods can be used to establish SID List tunnels and transmit service flows.

[0044] In one embodiment, a user self-service APP software installed on a user's mobile phone or computer communicates with the computing power network controller through a standard RESTful interface, submitting the user's request information for ordering computing power resources on the APP. Based on the user's request information, the computing power network controller calculates one or more transmission paths that meet the required quantity of computing power resources and have guaranteed latency and bandwidth, and distributes these paths to the head node accessed by the user in the form of a SID List. Simultaneously, it returns the IP addresses of available computing power resource servers to the APP.

[0045] The network device header node configures ACLs for service flows based on the user's source IP address and the destination computing resource (computing resource server) IP address, encapsulates a packet header carrying the SID List, and imports the matching service flows into the SID List tunnel. Users submit computing resource subscription requests (computing resource acquisition requests) on the APP, carrying information including user location (IP address), transmission latency, bandwidth, computing power, and storage.

[0046] The computing power network controller collects topology data from network devices and maintains the network-wide topology information, collects network-wide traffic data and maintains the Traffic Engineering Database (TEDB), and collects transmission latency data for all network links. Based on the computing resource utilization reported by the computing resource servers across the network, the computing power network controller collects and reports dynamically changing available computing resources in real time (including the IP addresses of computing resource servers, available CPUs, storage, etc.).

[0047] Figure 4 This is a flowchart illustrating an embodiment of the computing resource allocation method according to the present disclosure, as follows: Figure 4 As shown:

[0048] Step 401: Collect and maintain network topology information, collect network traffic data, and collect network link transmission latency data.

[0049] Step 402: Report dynamically changing available resource information according to the policy, including computing resource service providers, location (IP address), computing power (CPU), storage, etc.

[0050] Step 403: Submit the request information for ordering computing resources, including user location (IP address), transmission latency, bandwidth, computing power, storage and other requirements.

[0051] Step 404: Based on the user location (IP address) and the obtained computing resource location (IP address) in the computing resource request information obtained from the user APP, calculate the transmission latency from the user terminal to all available computing resource servers, and calculate the transmission bandwidth based on the network traffic data.

[0052] Step 405: Based on the user's request for ordered computing resources, calculate one or more transmission paths that meet the requirements for the number of computing resources and have guaranteed latency and bandwidth, and send them to the head node accessed by the user in the form of a SID List along with the user's IP address and the selected computing resource IP address.

[0053] Step 406: Return the IP address of the available computing power resource server to the APP.

[0054] Step 407: The head node configures ACLs for the service flow based on the user source IP address and the destination computing resource IP address, encapsulates a packet header carrying the SID List, and imports the matched service flow into the SID List tunnel.

[0055] The computing power network controller calculates the transmission latency and guaranteed bandwidth from the user terminal to all available computing power resource servers based on information such as the user's IP address, transmission latency, and bandwidth obtained from the user's computing power resource request information and the IP addresses of available computing power resource servers obtained from the computing power network controller. This satisfies the user's transmission latency and bandwidth requirements to computing power resources and ensures the performance of computing power resource services.

[0056] In one embodiment, such as Figure 5 As shown, the computing power network contains multiple computing resource servers. These servers report their available computing resources to the computing power network controller in real time according to a policy (regular reporting or change reporting). This information includes the computing resource provider ID, location (IP address), available computing power, and storage. The computing power network controller obtains computing resource request information from the user's self-service app, including the user's location (IP address), required computing power and storage, and requirements for transmission latency and bandwidth.

[0057] For example, a user's computing power requirements are 5 cores, 1GB of storage, a transmission latency of less than 20ms, and a bandwidth of no less than 50Mbps. The computing power network controller matches computing resources according to the user's needs, determining that only the available resources of computing resource server 3 can meet the user's computing power requirements. Based on the acquired global network topology information, the user's IP address, and the IP address of computing resource server 3, the computing power network controller determines the user's access network device 1, and computing resource server 3 connects to network device 6.

[0058] The computing network controller also collects transmission latency data for every link in the entire network and obtains the available bandwidth information for each link from the acquired total network traffic data (TEDB). Based on the shortest transmission latency algorithm, the computing network controller determines that the shortest transmission latency from network device 1 to network device 6 is 15ms. The transmission latency of link L1 from network device 1 to network device 2 is 3ms, the transmission latency of link L2 from network device 2 to network device 3 is 4ms, the transmission latency of link L4 from network device 3 to network device 5 is 5ms, and the transmission latency of link L6 from network device 5 to network device 6 is 3ms. Based on the total network TEDB data, the computing network controller determines that the available bandwidth of each link in the path meets the user's transmission bandwidth requirement of no less than 50Mbps.

[0059] exist Figure 5 In this example, another path from network device 1 to network device 6 is: network device 1 - network device 2 - network device 4 - network device 6. Although it involves fewer hops, the cumulative transmission latency of the transmission links L1, L3, and L5 is 17ms, which is not the shortest path. The computing power network controller returns the IP address of computing power resource server 3, which meets the user's computing power resource requirements, to the user's self-service APP.

[0060] Based on the Segment ID List (SID List) information obtained from the shortest path algorithm, the computing power network controller sends this SID List, along with the user's IP address and the computing resource server's IP address, to the head node network device 1 where the user accesses the network. The head node configures an Access Control List (ACL) for the service flow based on the user's source IP address and the destination computing resource IP address, encapsulates a packet header carrying the SID List, and imports the matching service flow into the SID List tunnel. The IP packets sent by the user to the destination computing resource server will then be delivered to the destination computing resource server for processing along the SID List tunnel.

[0061] In one embodiment, such as Figure 6As shown, this disclosure provides a computing power resource management device 60, which is installed in a computing power network controller. The computing power resource management device 60 includes: a computing power request receiving module 61, a computing power resource matching module 62, an access path determination module 63, and a resource address sending module 64.

[0062] The computing power request receiving module 61 receives a computing power resource acquisition request sent by the terminal APP. The computing power resource matching module 62 performs computing power resource matching based on the computing power resource acquisition request to select a computing power resource server in the computing power network. The access path determination module 63 determines the computing power resource access path for the terminal APP to access the computing power resource server, and sends the path information of the computing power resource access path, the address information of the terminal and the computing power resource server to the network device head node of the computing power resource access path. The network device head node generates a transmission tunnel based on the path information, which is used to transmit the service flow corresponding to the terminal APP through the transmission tunnel after the terminal APP accesses the network. The resource address sending module 64 sends the address information of the computing power resource server to the terminal APP.

[0063] In one embodiment, the computing resource matching module 62 receives computing resource information reported by the computing resource server. This computing resource information includes computing resource ID, location information, available computing resources, and storage capacity information. The computing resource server reports the computing resource information periodically, or when it determines that the change in its available computing resources exceeds a threshold, it reports the computing resource information.

[0064] In one embodiment, the information carried in the computing resource acquisition request includes the user's location, required computing power, required storage quantity, transmission latency requirements, and bandwidth requirements. The computing resource matching module 62 selects candidate computing resource servers from the computing network based on the required computing power and required storage quantity. The computing resource matching module 62 determines the transmission latency and transmission bandwidth between the user's location and the candidate computing resource servers, and selects a computing resource server from the candidate computing resources according to screening criteria, including a transmission latency less than the transmission latency requirement and a transmission bandwidth greater than the bandwidth requirement.

[0065] In one embodiment, the access path determination module 63 determines the computing resource access path for the terminal APP to access the computing resource server based on the shortest path transmission delay rule. The total transmission delay between adjacent network devices in the computing resource access path is less than the transmission delay requirement, and the transmission bandwidth between adjacent network devices is greater than the bandwidth requirement. The path information includes the SID List information of each network device in the computing resource access path, and the access path determination module 63 sends the SID List information, the IP addresses of the terminal and the computing resource server to the network device head node.

[0066] In one embodiment, such asFigure 7 As shown, this disclosure provides a computing resource management device, including a memory 71, a processor 72, a communication interface 73, and a bus 74. The memory 71 is used to store instructions, and the processor 72 is coupled to the memory 71. The processor 72 is configured to execute the above-described computing resource allocation method based on the instructions stored in the memory 71.

[0067] The memory 71 can be high-speed RAM, non-volatile memory, or a memory array. The memory 71 may also be divided into blocks, and these blocks can be combined into virtual volumes according to certain rules. The processor 72 can be a central processing unit (CPU), an application-specific integrated circuit (ASIC), or one or more integrated circuits configured to implement the computing resource allocation method of this disclosure.

[0068] In one embodiment, this disclosure provides a computing network controller, including the computing resource management device as described in any of the above embodiments.

[0069] In one embodiment, this disclosure provides a computer-readable storage medium storing computer instructions that, when executed by a processor, implement the method as described in any of the above embodiments.

[0070] The computing power resource allocation method, management device, server, and storage medium in the above embodiments dynamically select computing power resources with transmission quality assurance for users through the computing power network controller, meet the transmission latency and bandwidth requirements of users to computing power resources, and ensure the service performance of computing power resources; by selecting transmission paths with latency and bandwidth assurance for users, user services can reach the destination computing power resources through the SR-TE tunnel, thereby improving the service performance of computing power resources.

[0071] The methods and systems of this disclosure may be implemented in many ways. For example, they may be implemented by software, hardware, firmware, or any combination of software, hardware, and firmware. The above-described order of steps for the methods is for illustrative purposes only, and the steps of the methods of this disclosure are not limited to the order specifically described above unless otherwise specifically stated. Furthermore, in some embodiments, this disclosure may also be implemented as a program recorded on a recording medium, the program including machine-readable instructions for implementing the methods according to this disclosure. Thus, this disclosure also covers recording media storing programs for performing the methods according to this disclosure.

[0072] The description in this disclosure is provided for illustrative and descriptive purposes only and is not intended to be exhaustive or to limit the disclosure to its forms. Many modifications and variations will be apparent to those skilled in the art. The embodiments were chosen and described in order to better illustrate the principles and practical application of this disclosure and to enable those skilled in the art to understand this disclosure and to design various embodiments with various modifications suitable for a particular purpose.

Claims

1. A method for allocating computing resources, comprising: The computing power network controller receives computing power resource acquisition requests sent by the terminal APP; The computing power network controller performs computing power resource matching based on the computing power resource acquisition request, in order to select a computing power resource server in the computing power network; The computing power network controller determines the computing power resource access path of the terminal APP to access the computing power resource server, and sends the path information of the computing power resource access path, the address information of the terminal and the computing power resource server to the network device head node of the computing power resource access path; The network device head node generates a transmission tunnel based on the path information, which is used to transmit the service flow corresponding to the terminal APP through the transmission tunnel after the terminal APP is accessed. The computing power network controller sends the address information of the computing power resource server to the terminal APP; The information carried in the computing resource acquisition request includes: user location, required computing power, required storage quantity, transmission latency requirements, and bandwidth requirements; the computing network controller performs computing resource matching based on the computing resource acquisition request to select computing resource servers in the computing network, including: The computing power network controller selects candidate computing power resource servers from the computing power network based on the required computing power and required storage quantity; the computing power network controller determines the transmission latency and transmission bandwidth between the user location and the candidate computing power resource servers; the computing power network controller selects computing power resource servers from the candidate computing power resources according to the screening criteria; the screening criteria include: the transmission latency is less than the transmission latency requirement and the transmission bandwidth is greater than the bandwidth requirement.

2. The method of claim 1, further comprising: The computing power network controller receives computing power resource information reported by the computing power resource server; wherein, the computing power resource information includes: computing power resource ID, location information, available computing power resources, and storage capacity information.

3. The method of claim 2, further comprising: The computing resource server periodically reports the computing resource information, or reports the computing resource information when the computing resource server determines that the change value of its available computing resources exceeds the threshold.

4. The method as described in claim 1, wherein the computing power network controller determines the computing power resource access path for the terminal APP to access the computing power resource server, including: The computing power network controller determines the computing power resource access path for the terminal APP to access the computing power resource server based on the shortest path transmission delay rule; Wherein, the total transmission delay between adjacent network devices in the computing resource access path is less than the transmission delay requirement, and the transmission bandwidth between adjacent network devices is greater than the bandwidth requirement.

5. The method according to any one of claims 1 to 4, wherein, The path information includes: SID List information of each network device in the computing resource access path; sending the path information of the computing resource access path, the address information of the terminal and the computing resource server to the network device head node of the computing resource access path includes: The SID List information, the IP addresses of the terminal and the computing resource server are sent to the network device head node.

6. The method of claim 5, further comprising: The network device head node configures an access control list for the service flow based on the IP addresses of the terminal and the computing resource server, and encapsulates a packet header carrying the SID List information to import the matching service flow into the SID List tunnel for transmission.

7. A computing resource management device, installed in a computing network controller, comprising: The computing power request receiving module is used to receive computing power resource acquisition requests sent by the terminal APP; The computing power resource matching module is used to match computing power resources based on the computing power resource acquisition request, so as to select computing power resource servers in the computing power network; The access path determination module is used to determine the computing resource access path of the terminal APP to access the computing resource server, and send the path information of the computing resource access path, the address information of the terminal and the computing resource server to the network device head node of the computing resource access path; wherein, the network device head node generates a transmission tunnel based on the path information, so as to transmit the service flow corresponding to the terminal APP through the transmission tunnel after the terminal APP accesses the network. The resource address sending module is used to send the address information of the computing power resource server to the terminal APP; The information carried in the computing power resource acquisition request includes: user location, required computing power, required storage quantity, transmission latency requirements, and bandwidth requirements; The computing power resource matching module is used to select candidate computing power resource servers in the computing power network based on the required computing power and required storage quantity; determine the transmission latency and transmission bandwidth between the user location and the candidate computing power resource servers; and select computing power resource servers from the candidate computing power resources according to the screening conditions, which include: the transmission latency is less than the transmission latency requirement and the transmission bandwidth is greater than the bandwidth requirement.

8. The apparatus of claim 7, wherein, The computing resource matching module is used to receive computing resource information reported by the computing resource server; wherein, the computing resource information includes: computing resource ID, location information, available computing resources, and storage capacity information.

9. The apparatus of claim 8, wherein, The computing resource server periodically reports the computing resource information, or reports the computing resource information when the computing resource server determines that the change value of its available computing resources exceeds the threshold.

10. The apparatus of claim 7, wherein, The access path determination module is used to determine the computing resource access path for the terminal APP to access the computing resource server based on the shortest path transmission delay rule; wherein, the total transmission delay between adjacent network devices in the computing resource access path is less than the transmission delay requirement, and the transmission bandwidth between adjacent network devices is greater than the bandwidth requirement.

11. The apparatus according to any one of claims 7 to 10, wherein, The path information includes: SID List information of each network device in the computing resource access path; The access path determination module is used to send the SID List information, the IP address of the terminal and the computing resource server to the network device head node.

12. The apparatus of claim 11, wherein, The network device head node configures an access control list for the service flow based on the IP addresses of the terminal and the computing resource server, and encapsulates a packet header carrying the SID List information to import the matching service flow into the SID List tunnel for transmission.

13. A computing resource management device, comprising: Memory; And a processor coupled to the memory, the processor being configured to perform the method as described in any one of claims 1 to 6 based on instructions stored in the memory.

14. A computing network controller, comprising: The computing resource management device as described in any one of claims 7 to 13.

15. A computer-readable storage medium storing computer instructions that are executed by a processor according to any one of claims 1 to 6.

Images