Idle computing power scheduling system and method based on computing power gateway

Abstract

The invention relates to an idle computing power scheduling system and method based on a computing power gateway. The system comprises a computing power gateway, an access gateway, a plurality of relay gateways and a computing power brain, the computing power gateway is deployed in a resource pool, the access gateway is deployed in a user terminal, and the computing power brain is respectively connected with the computing power gateway, the access gateway and the relay gateway; the computing power gateway communicates with the relay gateway through a virtual wide area network formed by a plurality of relay gateways; the access gateway sends a computing power resource request to a computing power brain; the computing power gateway receives and manages idle computing power resources of the resource pool where the computing power gateway is located; the computing power brain obtains computing power resource information uploaded by the computing power gateway; under the condition that a computing power resource request is received, idle computing power resources are scheduled, and computing power identifiers are distributed to computing power resource information; and returning the computing power resource information after allocation of the computing power identifier to the access gateway to enable the user terminal to initiate a network request, the network request being used for driving the access gateway to distribute traffic based on the computing power identifier, and the network request carrying the computing power identifier.

Description

Technical Field

[0001] The present application relates to the field of computing power network technology, and in particular to a system and method for scheduling idle computing power based on a computing power gateway. Background Art

[0002] Institutions such as university laboratories, research institutes, and corporate R&D laboratories usually purchase physical servers, switches, and other computing equipment to build their own clusters. Due to various reasons such as business changes, the resource utilization rate of the cluster resource pool is relatively low, resulting in idle computing resources. How to realize the utilization of idle computing resources is an important issue that needs to be solved in the computing network field. Summary of the invention

[0003] Based on this, it is necessary to provide an idle computing power scheduling system and method based on a computing power gateway to address the above technical problems.

[0004] In a first aspect, the present application provides an idle computing power scheduling system based on a computing power gateway, the system comprising: a computing power gateway, an access gateway, multiple relay gateways and a computing power brain;

[0005] Among them, the computing power gateway is deployed in the resource pool, the access gateway is deployed in the user terminal, and the computing power brain is connected to the computing power gateway, access gateway and relay gateway respectively;

[0006] The computing power gateway and the relay gateway communicate through a virtual wide area network composed of multiple relay gateways;

[0007] The access gateway is used to: send computing resource requests to the computing brain;

[0008] The computing power gateway is used to: manage the idle computing power resources in the resource pool to determine the computing power resource information of the resource pool;

[0009] The computing brain is used for:

[0010] Obtain computing resource information uploaded by the computing gateway;

[0011] When receiving a computing resource request, dispatch idle computing resources and assign computing power identifiers to computing resource information;

[0012] The computing power resource information after the computing power identifier is allocated is returned to the access gateway so that the user terminal can initiate a network request. The network request is used to drive the access gateway to distribute traffic based on the computing power identifier. The network request carries the computing power identifier.

[0013] In one of the embodiments, the computing power brain is used to send computing power instructions to the computing power gateway and send network instructions to the computing power gateway, relay gateway and access gateway when receiving a computing power resource request. The computing power instructions and network instructions both include a computing power identifier.

[0014] In one of the embodiments, both the access gateway and the relay gateway are used to distribute traffic to the relay gateway based on the computing power identifier, and the computing power gateway is used to forward traffic to the physical server in the resource pool based on the computing power identifier.

[0015] In one of the embodiments, the relay gateway is used to distribute traffic to the computing power gateway according to the computing power identifier, and the computing power gateway is used to forward the traffic to the physical server in the resource pool according to the computing power identifier.

[0016] In one embodiment, the computing power brain is used to establish a global view of the computing power resource information and network information of the resource pool.

[0017] In one of the embodiments, the computing power gateway is used to manage physical servers in the resource pool based on an out-of-band management protocol.

[0018] In one embodiment, the out-of-band management protocol is the IPMI protocol.

[0019] In one embodiment, the computing power gateway is used to configure the internal network of the resource pool based on the switch management protocol.

[0020] In one embodiment, the switch management protocol is the SNMP protocol.

[0021] In a second aspect, a method for scheduling idle computing power based on a computing power gateway is provided, which is applied to the above-mentioned idle computing power scheduling system based on a computing power gateway, and the method includes:

[0022] Send computing resource requests to the computing brain based on the access gateway;

[0023] Based on the idle computing resources in the resource pool where the computing power gateway is located, the computing power resource information of the resource pool is determined;

[0024] Obtain computing power resource information uploaded by the computing power gateway based on the computing power brain, and dispatch idle computing power resources and assign computing power identifiers to computing power resource information when receiving computing power resource requests;

[0025] The computing power brain returns the computing power resource information after the computing power identifier is allocated to the access gateway, so that the user terminal initiates a network request. The network request is used to drive the access gateway to distribute traffic based on the computing power identifier. The network request carries the computing power identifier.

[0026] The above idle computing power scheduling system and method based on computing power gateway. By deploying access gateways on user terminals and building a virtual wide area network between resource pools based on relay gateways, a computing power network channel is established for user terminals to access idle computing power resources. The computing power gateway deployed based on the resource pool manages various idle computing power resources, accesses the computing power network, calls idle computing power resources based on the computing power brain, and distributes network traffic and accesses computing power resources through unified allocation of computing power identifiers, thereby achieving effective scheduling of idle computing power resources and improving computing power resource utilization. BRIEF DESCRIPTION OF THE DRAWINGS

[0027] In order to more clearly illustrate the technical solutions in the embodiments of the present application or related technologies, the drawings required for use in the embodiments of the present application or related technical descriptions will be briefly introduced below. Obviously, the drawings described below are only some embodiments of the present application. For ordinary technicians in this field, other related drawings can be obtained based on these drawings without paying creative work.

[0028] Figure 1 It is a structural diagram of an idle computing power scheduling system based on a computing power gateway in one embodiment;

[0029] Figure 2 It is a sequence diagram of an idle computing power scheduling system based on a computing power gateway in one embodiment;

[0030] Figure 3 The figure is a flow chart of a resource pool accessing a computing power network through a computing power gateway in one embodiment. DETAILED DESCRIPTION

[0031] In order to make the purpose, technical solution and advantages of the present application more clearly understood, the present application is further described in detail below in conjunction with the accompanying drawings and embodiments. It should be understood that the specific embodiments described herein are only used to explain the present application and are not used to limit the present application.

[0032] In an exemplary embodiment, Figure 1 As shown, a system for scheduling idle computing power based on a computing power gateway is provided, which includes: a computing power gateway, an access gateway, multiple relay gateways and a computing power brain.

[0033] The computing power gateway is deployed in the resource pool, and the access gateway is deployed in the user terminal. The user terminal can be a computer device or a personal computer in the computer room.

[0034] The computing brain is connected to the computing gateway, access gateway, and relay gateway respectively. The computing gateway and relay gateway communicate through a virtual WAN composed of multiple relay gateways. The access gateway accesses the virtual WAN and cooperates with the computing gateway and relay gateway to establish a secure network channel to the computing resources. The virtual WAN can be a wide area network such as SD-WAN, CDN, and acceleration network. As the core gateway and edge gateway of the virtual WAN, the relay gateway accepts the network rules issued by the computing brain and implements routing forwarding.

[0035] Among them, the access gateway is used to send computing power resource requests to the computing power brain. The computing power gateway is used to manage the idle computing power resources in the resource pool to determine the computing power resource information of the resource pool. The computing power gateway can support lightweight computing power management and network gateway functions to connect various idle computing power resources to the computing power network. The computing power gateway supports the use of computing power identification to address and access computing power resources.

[0036] The computing power brain is used to manage computing power information and network information management, such as Figure 2 As shown, it can manage network policies and wide area network views, as well as computing resources and computing identifiers, and is responsible for the unified scheduling of computing resources and networks.

[0037] like Figure 2 As shown, the computing power brain obtains the computing power resource information uploaded by the computing power gateway, and when receiving a computing power resource request, it dispatches idle computing power resources and allocates computing power identifiers to the computing power resource information. The computing power brain returns the computing power resource information after the computing power identifier is allocated to the access gateway, so that the service program of the user terminal can initiate a network request to the access gateway when receiving the computing power resource information after the computing power identifier is allocated. The network request is used to drive the access gateway to distribute traffic based on the computing power identifier, and the network request carries the computing power identifier. The unified scheduling of computing power resources and networks based on the same computing power identifier is realized.

[0038] Specifically, the idle computing power scheduling system based on the computing power gateway provided in the embodiment of the present application establishes a computing power network channel for user terminals to access idle computing power resources by deploying an access gateway on the user terminal and building a virtual wide area network between resource pools based on the relay gateway. The computing power gateway deployed based on the resource pool manages various idle computing power resources, accesses the computing power network, calls idle computing power resources based on the computing power brain, and distributes network traffic and accesses computing power resources by uniformly allocating computing power identifiers, thereby realizing effective scheduling of idle computing power resources and improving the utilization rate of computing power resources.

[0039] In one embodiment, when the computing power gateway and the relay gateway communicate within the virtual wide area network built between the computing power resource pools, they can communicate based on preset secure communication mechanisms, such as identity authentication, multi-user network isolation, communication encryption and other mechanisms.

[0040] In one of the embodiments, both the access gateway and the relay gateway are used to distribute traffic to the relay gateway based on the computing power identifier, and the computing power gateway is used to forward traffic to the physical server in the resource pool based on the computing power identifier.

[0041] Both the access gateway and the relay gateway distribute traffic to the relay gateway based on the computing power identifier, ensuring that the traffic can be accurately located to the area or node with the required computing power. The computing power gateway then forwards the traffic to the appropriate physical server in the resource pool based on the computing power identifier, ensuring the reasonable allocation and utilization of computing power resources. This precise matching method avoids the waste and idleness of computing power resources and improves the overall utilization of computing power resources.

[0042] In one of the embodiments, the relay gateway is used to distribute traffic to the computing power gateway according to the computing power identifier, and the computing power gateway is used to forward the traffic to the physical server in the resource pool according to the computing power identifier.

[0043] The relay gateway distributes traffic to the corresponding computing power gateway according to the computing power identifier, ensuring that the traffic can be accurately directed to the area or node that can provide the required computing power as required. The computing power gateway determines the location of the target physical server by analyzing the computing power identifier in the traffic, and forwards the traffic to the server, ensuring that the network traffic can directly reach the physical server that can provide the required computing power, thereby meeting business needs.

[0044] In one embodiment, the computing power brain is used to establish a global view of the computing power resource information and network information of the resource pool.

[0045] Network information covers the connection relationship, bandwidth, latency and other network performance parameters between all nodes in the computing network. This information is of great significance for optimizing data transmission paths, reducing network congestion, and improving data transmission efficiency. This global view enables the computing brain to make more accurate and efficient scheduling decisions.

[0046] Optionally, the computing power brain can update the computing power resource information and network information in the resource pool regularly or in real time to ensure the accuracy and timeliness of the global view. This can be achieved by establishing a stable communication connection with each node in the resource pool and collecting their status reports in real time.

[0047] Optionally, the computing brain can dynamically adjust the allocation of idle computing resources and the configuration of the network according to business needs and resource conditions to maximize resource utilization and optimize network performance.

[0048] Optionally, the computing brain can also provide early warning and rapid recovery of potential faults in the computing network. For example, once an abnormality is detected in a node or link, the corresponding fault recovery mechanism is immediately triggered to ensure network stability and business continuity.

[0049] In one embodiment, the computing power gateway is used to manage the physical servers in the resource pool based on an out-of-band management protocol. The out-of-band management protocol may be an IPMI protocol, which senses the number, power status, hardware information, etc. of the physical servers.

[0050] The computing power gateway manages the physical servers in the resource pool through the out-of-band management protocol, that is, it includes them in the management scope. This means that the computing power gateway can monitor, configure, control and optimize the performance and status of these servers. For example, server perception, installation of operating systems, startup, shutdown, restart and other operations are achieved through the out-of-band management protocol. Specifically, the computing power gateway can regularly scan the physical servers in the resource pool to obtain their configuration, status, performance and other information to understand the current status of the server for subsequent management and optimization. The computing power gateway can also install the operating system by uploading the operating system image to the server and then configuring the startup parameters to start the system from the image. The computing power gateway can also remotely start or shut down the server, or automatically restart it when the server fails.

[0051] The computing power gateway manages physical servers based on the out-of-band management protocol, which can respond to server failures and performance issues more quickly, thereby improving management efficiency. The encryption and authentication functions provided by the out-of-band management protocol can ensure the security and integrity of communications.

[0052] In one embodiment, the out-of-band management protocol is an IPMI (Intelligent Platform Management Interface) protocol.

[0053] Among them, the core of the IPMI protocol is the Baseboard Management Controller (BMC), which can be integrated on the server's motherboard and can run independently of the server's processor, BIOS or operating system. The computing power gateway monitors the hardware status of the edge network and data center server based on the IPMI protocol, and can adjust the computing power resource allocation strategy according to actual needs to optimize the utilization efficiency of computing power resources.

[0054] Optionally, you can add the physical server's IPMI information, including the IP address, user name, and password, to the management interface of the computing power gateway to manage the physical server (include it in the management scope).

[0055] In one embodiment, the computing power gateway is used to configure the internal network of the resource pool based on the switch management protocol.

[0056] Specifically, the computing power gateway identifies all switches and interfaces of each switch in the internal network of the resource pool, which can be achieved by scanning the network, collecting device information, and establishing a device list. Then the computing power gateway selects the switch management protocol (such as SNMP, SSH, Telnet, etc.) that is suitable for the application scenario, and configures it according to network requirements and security policies to support the computing power gateway to communicate and remotely control the switch (for example, the communication and control process may include verifying the IP address, port number, user name and password of the switch management interface). The computing power gateway configures the virtual local area network (VLAN) and subnet through the switch management protocol according to the needs of the resource pool to isolate different network traffic and improve the security and performance of the network. The computing power gateway can also configure the routing table on the switch to ensure unimpeded communication between the internal networks of the resource pool. At the same time, set the access control list (ACL) to limit unnecessary network traffic and potential security threats. The computing power gateway continuously monitors the status of the switch and network performance through the switch management protocol. When a fault occurs, the problem can be quickly located and repaired.

[0057] The idle computing power scheduling system based on computing power gateway provided in the embodiment of the present application configures the internal network of the resource pool through the switch management protocol to achieve network isolation between multi-user computing power resources. And through the automated and centralized management method, the configuration efficiency of the internal network of the resource pool is significantly improved, and the speed of network deployment is accelerated.

[0058] In one embodiment, the switch management protocol is the SNMP protocol.

[0059] SNMP (Simple Network Management Protocol) is a set of network management protocols defined by the Internet Engineering Task Force (IETF). The SNMP protocol allows effective communication and information exchange between the computing power gateway and the switch, thereby realizing functions such as remote monitoring, configuration and diagnosis of network devices to achieve switch configuration. The SNMP protocol supports multiple security mechanisms, such as authentication, encryption, and access control, which the computing power gateway can use to protect network resources from unauthorized access and attacks.

[0060] In order to better illustrate the implementation process provided by the embodiment of the present application, Figure 2 The following is an example for explanation:

[0061] Users can apply for computing power resources through the access gateway based on business programs (for example, browsers, shell tools, etc.) in the computer room or user terminals such as user PCs. The access gateway sends the computing power request to the computing network brain; the access gateway may include a computing power acquisition gateway and a network access gateway.

[0062] The computing network brain dispatches computing resources, assigns computing power identifiers to computing resources, issues computing power instructions to computing power gateways, and issues network instructions to computing power gateways, relay gateways, and access gateways. Computing power instructions may include information such as resource specifications, resource quantities, and computing power identifiers, and network instructions may include information such as user identity identifiers, computing power identifiers, and computing power gateways.

[0063] The computing power gateway installs the operating system and starts up the physical server through the out-of-band management protocol, and configures internal networks such as VLANs through the switch management protocol.

[0064] The access gateway returns the computing power resource information of the allocated computing power identifier to the business program, so the computing power resource information includes the computing power identifier, and the computing power resource information may also include resource specifications, etc.

[0065] The service program of the user terminal sends a network request to the access gateway, which may carry a computing power identifier in the address or header of the network request. The access gateway may include a computing power acquisition gateway and a network access gateway.

[0066] The access gateway and relay gateway distribute network traffic to the corresponding computing power gateway based on the computing power identifier.

[0067] The computing power gateway forwards network traffic to the corresponding computing power resources, such as physical servers, based on the computing power identifier.

[0068] In one of the embodiments, the computing power brain is used to send computing power instructions to the computing power gateway and send network instructions to the computing power gateway, relay gateway and access gateway when receiving a computing power resource request. The computing power instructions and network instructions both include a computing power identifier.

[0069] Specifically, the computing brain selects and dispatches idle computing resources based on business needs, the distribution and characteristics of computing resources, and other factors, and assigns computing power identifiers to computing power resources. The computing power identifier is an identification system in the computing power network that is used to uniquely identify computing power resources. By assigning computing power identifiers to computing power resources, it is convenient to identify, query, and manage computing power resources.

[0070] The computing power brain sends computing power instructions to the computing power gateway, and implements the access and forwarding of idle computing power resources based on the computing power gateway. By sending computing power instructions to the computing power gateway, the computing power gateway is instructed on how to access, forward, and process computing power resources based on the computing power identifier. The computing power brain issues network instructions to the computing power gateway, relay gateway, and access gateway to ensure that the network is correctly connected and communicated based on a unified computing power identifier.

[0071] The scheduling system provided by the embodiment of the present application can improve the utilization rate of computing power resources and avoid waste and idleness of resources. The introduction of computing power identification makes the management of idle computing power resources more standardized and standardized, which helps to enhance the reliability and stability of the computing power network. At the same time, through the collaborative work of computing power gateways, relay gateways and access gateways, the correct connection and communication of the network can be ensured, further improving the reliability of the network.

[0072] In one embodiment, the process of implementing the resource pool accessing the computing power network through the computing power gateway can be as follows: Figure 3 As shown:

[0073] The computing power gateway perceives and manages physical servers through out-of-band management protocols.

[0074] The computing power gateway perceives the internal network topology through the switch management protocol, and the switch management protocol can be the SNMP protocol.

[0075] The computing power gateway reports the computing power resource information and network information of the resource pool to the computing network brain. The computing power resource information may include the number of physical servers, CPU architecture, CPU type, number of CPU cores, memory capacity, GPU architecture, GPU memory capacity, etc. The network information may include the internal network type, network bandwidth, etc.

[0076] The computing network brain establishes a global view of computing power information and network information.

[0077] The idle computing power scheduling system based on the computing power gateway provided in the embodiment of the present application deploys lightweight computing power gateways in various resource pools, manages various idle computing power resources in a standardized manner, connects to the computing power network, and aggregates them into a rich pool of available computing power resources. Users can obtain computing power resources on demand.

[0078] The computing power gateway also builds a virtual wide area network between computing power resource pools, provides a secure network channel for accessing computing power resources, and supports addressing and access using a unified computing power identifier.

[0079] In one embodiment, a method for scheduling idle computing power based on a computing power gateway is also provided, which is applied to the above-mentioned idle computing power scheduling system based on a computing power gateway, and the method includes:

[0080] Send computing resource requests to the computing brain based on the access gateway;

[0081] Based on the idle computing resources in the resource pool where the computing power gateway is located, the computing power resource information of the resource pool is determined;

[0082] Obtain computing power resource information uploaded by the computing power gateway based on the computing power brain, and dispatch idle computing power resources and assign computing power identifiers to computing power resource information when receiving computing power resource requests;

[0083] The computing power brain returns the computing power resource information after the computing power identifier is allocated to the access gateway, so that the user terminal initiates a network request. The network request is used to drive the access gateway to distribute traffic based on the computing power identifier. The network request carries the computing power identifier.

[0084] The implementation process of the method provided in the embodiments of the present application can refer to the description in the above embodiments and will not be repeated here.

[0085] It should be understood that, although the various steps in the flowcharts involved in the above-mentioned embodiments are displayed in sequence according to the indication of the arrows, these steps are not necessarily executed in sequence according to the order indicated by the arrows. Unless there is a clear explanation in this article, the execution of these steps does not have a strict order restriction, and these steps can be executed in other orders. Moreover, at least a part of the steps in the flowcharts involved in the above-mentioned embodiments can include multiple steps or multiple stages, and these steps or stages are not necessarily executed at the same time, but can be executed at different times, and the execution order of these steps or stages is not necessarily to be carried out in sequence, but can be executed in turn or alternately with other steps or at least a part of the steps or stages in other steps.

[0086] A person of ordinary skill in the art can understand that all or part of the processes in the above-mentioned embodiment method can be completed by instructing the relevant hardware through a computer program, and the computer program can be stored in a non-volatile computer-readable storage medium. When the computer program is executed, it can include the processes of the embodiments of the above-mentioned methods. Among them, any reference to the memory, database or other medium used in the embodiments provided in the present application can include at least one of non-volatile memory and volatile memory. Non-volatile memory can include read-only memory (ROM), magnetic tape, floppy disk, flash memory, optical memory, high-density embedded non-volatile memory, resistive random access memory (ReRAM), magnetic random access memory (MRAM), ferroelectric random access memory (FRAM), phase change memory (PCM), graphene memory, etc. Volatile memory can include random access memory (RAM) or external cache memory, etc. As an illustration and not limitation, RAM can be in various forms, such as static random access memory (SRAM) or dynamic random access memory (DRAM). The database involved in each embodiment provided in this application may include at least one of a relational database and a non-relational database. Non-relational databases may include distributed databases based on blockchains, etc., but are not limited to this. The processor involved in each embodiment provided in this application may be a general-purpose processor, a central processing unit, a graphics processor, a digital signal processor, a programmable logic device, a data processing logic device based on quantum computing, an artificial intelligence (AI) processor, etc., but are not limited to this.

[0087] The technical features of the above embodiments may be combined arbitrarily. To make the description concise, not all possible combinations of the technical features in the above embodiments are described. However, as long as there is no contradiction in the combination of these technical features, they should be considered to be within the scope of this application.

[0088] The above-described embodiments only express several implementation methods of the present application, and the descriptions thereof are relatively specific and detailed, but they cannot be construed as limiting the scope of the present application. It should be noted that, for a person of ordinary skill in the art, several modifications and improvements can be made without departing from the concept of the present application, and these all belong to the protection scope of the present application. Therefore, the protection scope of the present application shall be subject to the attached claims.

Claims

1. A system for scheduling idle computing power based on computing power gateway, characterized in that: The system includes: a computing power gateway, an access gateway, multiple relay gateways and a computing power brain; The computing power gateway is deployed in a resource pool, the access gateway is deployed in a user terminal, and the computing power brain is connected to the computing power gateway, the access gateway and the relay gateway respectively; The computing power gateway and the relay gateway communicate with each other through a virtual wide area network formed by the multiple relay gateways; The access gateway is used to: send a computing resource request to the computing brain; The computing power gateway is used to: manage the idle computing power resources in the resource pool to determine the computing power resource information of the resource pool; The computing brain is used for: Obtain computing power resource information uploaded by the computing power gateway; When receiving the computing power resource request, scheduling the idle computing power resources and allocating the computing power identifier to the computing power resource information; The computing power resource information after the computing power identifier is allocated is returned to the access gateway so that the user terminal initiates a network request, and the network request is used to drive the access gateway to distribute traffic based on the computing power identifier, and the network request carries the computing power identifier.

2. The system according to claim 1, characterized in that The computing power brain is used to send computing power instructions to the computing power gateway and send network instructions to the computing power gateway, the relay gateway and the access gateway when receiving the computing power resource request. The computing power instructions and the network instructions both include the computing power identifier.

3. The system according to claim 2, characterized in that The access gateway and the relay gateway are both used to distribute traffic to the relay gateway according to the computing power identifier, and the computing power gateway is used to forward traffic to the physical server of the resource pool according to the computing power identifier.

4. The system according to claim 1, characterized in that The relay gateway is used to distribute traffic to the computing power gateway according to the computing power identifier, and the computing power gateway is used to forward traffic to the physical server of the resource pool according to the computing power identifier.

5. The system according to claim 1, characterized in that The computing power brain is used to establish a global view of the computing power resource information and network information of the resource pool.

6. The idle computing power scheduling system based on computing power gateway according to claim 1 is characterized in that: The computing power gateway is used to manage the physical servers in the resource pool based on the out-of-band management protocol.

7. The idle computing power scheduling system based on computing power gateway according to claim 6 is characterized in that: The out-of-band management protocol is the IPMI protocol.

8. The idle computing power scheduling system based on computing power gateway according to any one of claims 1 to 7, characterized in that: The computing power gateway is used to configure the internal network of the resource pool based on the switch management protocol.

9. The idle computing power scheduling system based on computing power gateway according to claim 8 is characterized in that: The switch management protocol is the SNMP protocol.

10. A method for scheduling idle computing power based on a computing power gateway, characterized in that: Applied to the idle computing power scheduling system based on the computing power gateway as described in any one of claims 1 to 9, the method comprises: Sending a computing power resource request to the computing power brain based on the access gateway; Based on the idle computing power resources of the resource pool where the computing power gateway is managed, the computing power resource information of the resource pool is determined; Based on the computing power brain, the computing power resource information uploaded by the computing power gateway is obtained, and upon receiving the computing power resource request, the idle computing power resources are scheduled and the computing power identifier is allocated to the computing power resource information; Based on the computing power brain, the computing power resource information after the computing power identifier is allocated is returned to the access gateway, so that the user terminal initiates a network request. The network request is used to drive the access gateway to distribute traffic based on the computing power identifier, and the network request carries the computing power identifier.

Images