Methods, equipment, and storage media for operating a computing power network based on a computing power message bus

Abstract

The application provides a computing power network operation method and device based on a computing power message bus and a storage medium. The computing power network comprises an entry node, an exit node and a computing power message bus. The method comprises the following steps: in response to a computing power resource registration request, obtaining service information of the computing power resource based on the exit node and allocating a service identifier to the computing power resource; obtaining the service identifier and the corresponding service information of the computing power resource meeting a preset rule from the computing power message bus based on the entry node and writing the service identifier and the corresponding service information into a computing power resource registration table of the entry node; in response to a computing power task request, obtaining the computing power task based on the entry node, performing resource scheduling on the computing power task, and determining the exit node corresponding to the computing power task; and sending the computing power task to the network address corresponding to the computing power resource based on the exit node, so that the computing power resource executes the computing power task. The method of the application achieves the technical effect of reducing the construction cost and complexity of the computing power network.

Description

Technical Field

[0001] This application relates to the Internet field, and in particular to a computing network operation method, device and storage medium based on a computing power message bus. Background Technology

[0002] With the development of Internet technology, the amount of information data is constantly increasing, and the demand for computing on information data is also increasing. There are massive computing needs in the fields of artificial intelligence, Internet of Things, and Industrial Internet. Computing networks built to meet these computing needs have become an important direction for development.

[0003] In the implementation of existing enterprise computing networks, it is often necessary to connect the distributed computing resource nodes within the enterprise, dynamically and in real time perceive the status of computing and network resources, and coordinate the allocation and scheduling of computing tasks based on the status information of computing and network resources, thereby realizing a network that covers all nodes within the enterprise where computing resources are perceptible, allocable, and schedulable.

[0004] In existing technologies, enterprise computing networks are highly sensitive to complexity and cost, resulting in low compatibility between enterprise computing networks and existing computing network technologies. Furthermore, enterprises possess a wide variety of computing resources with complex types, making it impossible to connect all of them using a unified network technology. The non-fixed network addresses of enterprise computing resources lead to high complexity in locating and routing them. Additionally, enterprise computing resources are distributed across different operating systems, requiring network construction to traverse these systems, further increasing the complexity of enterprise computing network construction. Therefore, existing computing network technologies suffer from both high construction costs and high complexity. Summary of the Invention

[0005] This application provides a computing power network operation method, device, and storage medium based on a computing power message bus, in order to solve the technical problems of high cost and high complexity in the construction of computing power networks in the prior art.

[0006] Firstly, this application provides a method for operating a computing power network based on a computing power message bus. The computing power network includes: an entry node, an exit node, and a computing power message bus, comprising:

[0007] In response to the computing resource registration request, the service information of the computing resources is obtained based on the exit node and a service identifier is allocated to the computing resources;

[0008] Based on the entry node, the service identifier and corresponding service information of the computing resources that conform to the preset rules are obtained from the computing power message bus and written into the computing power resource registry of the entry node.

[0009] In response to a computing power task request, the computing power task is obtained based on the entry node, and resource scheduling is performed on the computing power task to determine the corresponding exit node.

[0010] The computing power task is sent to the network address corresponding to the computing power resource based on the exit node, so that the computing power resource can execute the computing power task.

[0011] Optionally, the computing power network also includes a computing resource scheduling module, the method of which includes:

[0012] The status information of computing resources is obtained based on the exit node and the preset time interval, and the status information is sent to the computing message bus.

[0013] Status information is obtained based on the entry node and the computing power message bus, and the computing power resource registry of the entry node is updated based on the status information;

[0014] The computing resource scheduling module evaluates the performance of the corresponding computing resources based on the status information, determines the evaluation results, and allocates the corresponding computing resources to the computing tasks based on the evaluation results.

[0015] Optionally, the computing power tasks are obtained based on the entry node, and resource scheduling is performed on the computing power tasks to determine the exit node corresponding to the computing power tasks, including:

[0016] Obtain computing power tasks based on the entry node and send the computing power tasks to the computing power resource scheduling queue;

[0017] Obtain the evaluation results of the computing power resources of the entry node, determine the computing power resources corresponding to the computing power tasks based on the evaluation results and scheduling algorithms, and update the service identifier of the computing power resources to the computing power resource scheduling list.

[0018] Based on the computing power resource scheduling list, the computing power tasks are sent to the computing power message queue of the exit node corresponding to the service identifier;

[0019] The computing resource scheduling queue includes: computing task description information, computing task identifier, and corresponding computing resource service identifier;

[0020] The computing power message queue includes: computing power task description information, computing power task identifier, and the service identifier of the corresponding computing power resource.

[0021] Optionally, the evaluation results of the computing power resources of the entry node are obtained, and the computing power resources corresponding to the computing power task are determined based on the evaluation results and the scheduling algorithm, including:

[0022] The evaluation results of computing resources in the computing resource registry are determined based on the entry node.

[0023] Based on the evaluation results, computing resources that meet the computing task requirements are selected from the computing resource registry of the entry node, and the service identifier of the computing resources is determined.

[0024] Optionally, sending computing tasks to the network address corresponding to the computing resources based on the exit node, so that the computing resources can execute the computing tasks, includes:

[0025] Subscribe to computing power tasks based on the exit node, and determine and resolve the network address of the computing power resource based on the service identifier of the computing power resource corresponding to the computing power task.

[0026] The computing task is sent to the network address corresponding to the computing resource, and the computing task is executed based on the computing resource.

[0027] Optionally, the computing power network further includes: a storage node, which, before obtaining a computing power task based on the entry node in response to a computing power task request, also includes:

[0028] Based on the exit node, the service identifier and service information of the computing power resources are sent to the storage node;

[0029] Based on storage nodes, service identifiers and service information are published to the computing resource bus;

[0030] The entry node subscribes to computing resource information from the storage node and obtains computing resource information based on the computing resource bus.

[0031] Optionally, the entry node obtains the service identifier of the computing resources that conform to preset rules and the corresponding service information of the computing resources from the computing power message bus, and writes them into the computing power resource registry of the entry node, including:

[0032] The subscription scope of the entry node is determined based on the entry node;

[0033] Based on the subscription scope, determine whether the computing resources in the computing power message bus are within the subscription scope. If so, subscribe to the computing resources based on the entry node and write the service identifier and service information of the computing resources into the computing resources registry of the entry node.

[0034] Secondly, this application provides a computing network operation device based on a computing power message bus. The computing power network includes: an entry node, an exit node, and a computing power message bus, comprising:

[0035] The first acquisition module is used to respond to the computing resource registration request, acquire the service information of the computing resource based on the exit node, and allocate service identifiers to the computing resource.

[0036] The first processing module is used to obtain the service identifier and corresponding service information of computing resources that conform to preset rules from the computing power message bus based on the entry node, and write them into the computing power resource registry of the entry node.

[0037] The second acquisition module is used to respond to computing power task requests, acquire computing power tasks based on entry nodes, perform resource scheduling on computing power tasks, and send the computing power tasks corresponding to the resource scheduling to the corresponding exit nodes.

[0038] The second processing module is used to send computing power tasks to the network address corresponding to the computing power resources based on the exit node, so as to enable and execute the computing power tasks based on the computing power resources.

[0039] Optionally, the device is also used for:

[0040] The status information of computing resources is obtained based on the exit node and the preset time interval, and the status information is sent to the computing message bus.

[0041] Status information is obtained based on the entry node and the computing power message bus, and the computing power resource registry of the entry node is updated based on the status information;

[0042] The computing resource scheduling module evaluates the performance of the corresponding computing resources based on the status information, determines the evaluation results, and allocates the corresponding computing resources to the computing tasks based on the evaluation results.

[0043] Optionally, the device is also used for:

[0044] Obtain computing power tasks based on the entry node and send the computing power tasks to the computing power resource scheduling queue;

[0045] Obtain the evaluation results of the computing power resources of the entry node, determine the computing power resources corresponding to the computing power tasks based on the evaluation results and scheduling algorithms, and update the service identifier of the computing power resources to the computing power resource scheduling list.

[0046] Based on the computing power resource scheduling list, the computing power tasks are sent to the computing power message queue of the exit node corresponding to the service identifier;

[0047] The computing resource scheduling queue includes: computing task description information, computing task identifier, and corresponding computing resource service identifier;

[0048] The computing power message queue includes: computing power task description information, computing power task identifier, and the service identifier of the corresponding computing power resource.

[0049] Optionally, the device is also used for:

[0050] The evaluation results of computing resources in the computing resource registry are determined based on the entry node.

[0051] Based on the evaluation results, computing resources that meet the computing task requirements are selected from the computing resource registry of the entry node, and the service identifier of the computing resources is determined.

[0052] Optionally, the device is also used for:

[0053] Subscribe to computing power tasks based on the exit node, and determine and resolve the network address of the computing power resource based on the service identifier of the computing power resource corresponding to the computing power task.

[0054] The computing task is sent to the network address corresponding to the computing resource, and the computing task is executed based on the computing resource.

[0055] Optionally, the device is also used for:

[0056] Based on the exit node, the service identifier and service information of the computing power resources are sent to the storage node;

[0057] Based on storage nodes, service identifiers and service information are published to the computing resource bus;

[0058] The entry node subscribes to computing resource information from the storage node and obtains computing resource information based on the computing resource bus.

[0059] Optionally, the device is also used for:

[0060] The subscription scope of the entry node is determined based on the entry node;

[0061] Based on the subscription scope, determine whether the computing resources in the computing power message bus are within the subscription scope. If so, subscribe to the computing resources based on the entry node and write the service identifier and service information of the computing resources into the computing resources registry of the entry node.

[0062] A third aspect of this application provides a computing network operation device based on a computing power message bus, comprising:

[0063] Processor and memory;

[0064] The memory stores the instructions that the computer executes;

[0065] The processor executes computer execution instructions stored in memory, causing the electronic device to execute any of the computing network operation methods based on the computing power message bus in the first aspect.

[0066] Fourthly, this application provides a computer-readable storage medium storing computer-executable instructions, which, when executed by a processor, are used to implement the computing network operation method based on a computing power message bus as described in any of the first aspects.

[0067] This application provides a method, device, and storage medium for operating a computing power network based on a computing power message bus. The computing power network includes an entry node, an exit node, and a computing power message bus. The method includes: in response to a computing power resource registration request, obtaining service information of the computing power resource based on the exit node and assigning a service identifier to the computing power resource; obtaining the service identifier and corresponding service information of the computing power resource conforming to preset rules from the computing power message bus based on the entry node, and writing them into the computing power resource registry of the entry node; in response to a computing power task request, obtaining the computing power task based on the entry node, performing resource scheduling on the computing power task, and determining the exit node corresponding to the computing power task; and sending the computing power task to the network address corresponding to the computing power resource based on the exit node, so that the computing power resource can execute the computing power task. Communication between nodes in the computing power network is achieved through a computing power message bus. Computing power resources are registered at the egress node, and a unique service identifier for each resource is obtained within the network based on this identifier. This service identifier is used to locate the computing power resource. The egress node submits the computing power resource information to the storage node, which then publishes the information to the computing power message bus using a publish / subscribe model. The ingress node retrieves the corresponding computing power resource information from the message bus based on its subscription requests and subscribes to the storage node for this information, enabling real-time monitoring of the computing power resource status. The system uses information and, based on the status information of computing resources, allocates computing resources to computing tasks submitted at the entry node. The computing task, based on the allocated computing resources, obtains the egress information of the registered computing resources through the service identifier of the computing resources, resolves the network address of the computing resources based on the egress node, and sends the computing task to the network address corresponding to the computing resources, thereby executing the computing task based on the computing resources. By utilizing a message bus as the computing message transmission path for the computing network, a low-cost computing network construction is achieved, realizing the technical effect of reducing the cost and complexity of computing network construction. Attached Figure Description

[0068] The accompanying drawings, which are incorporated in and form part of this specification, illustrate embodiments consistent with this application and, together with the description, serve to explain the principles of this application.

[0069] Figure 1 The flowchart of the computing power network operation method based on the computing power message bus provided in the embodiments of this application Figure 1 ;

[0070] Figure 2 The flowchart of the computing power network operation method based on the computing power message bus provided in the embodiments of this application Figure 2 ;

[0071] Figure 3 A diagram of an enterprise computing power network architecture based on a computing power message bus is provided for embodiments of this application.

[0072] Figure 4 A schematic diagram of the computing power message bus provided in this application;

[0073] Figure 5 A schematic diagram of the structure of a computing network operation device based on a computing power message bus provided in an embodiment of this application;

[0074] Figure 6 This is a hardware structure diagram of a computing network operation device based on a computing power message bus, provided in an embodiment of this application.

[0075] The accompanying drawings illustrate specific embodiments of this application, which will be described in more detail below. These drawings and descriptions are not intended to limit the scope of the concept in any way, but rather to illustrate the concept of this application to those skilled in the art through reference to particular embodiments. Detailed Implementation

[0076] Exemplary embodiments will now be described in detail, examples of which are illustrated in the accompanying drawings. When the following description relates to the drawings, unless otherwise indicated, the same numbers in different drawings denote the same or similar elements. The embodiments described in the following exemplary embodiments do not represent all embodiments consistent with this application. Rather, they are merely examples of apparatuses and methods consistent with some aspects of this application as detailed in the appended claims.

[0077] First, let me explain the terms used in this application:

[0078] Compute-first networking (CFN) refers to deploying a computation graph on available computing platforms within a network to perform flexible load management and performance optimization, taking into account the location of functions / participants and data, as well as platform load and network performance.

[0079] In the implementation of existing enterprise computing networks, it is often necessary to connect the distributed computing resource nodes within the enterprise, dynamically and in real-time perceive the status of computing and network resources, and coordinate the allocation and scheduling of computing tasks based on the status information of computing and network resources. This achieves a network that allows for the perception, allocation, and scheduling of computing resources across all nodes within the enterprise. However, existing technologies suffer from several drawbacks. Firstly, enterprise computing networks are highly sensitive to complexity and cost, resulting in low compatibility with existing computing network technologies. Secondly, the diverse and complex types of enterprise computing resources make it impossible to use a unified network technology to connect all enterprise computing resources. Thirdly, the non-fixed network addresses of enterprise computing resources lead to high complexity in locating and routing them. Furthermore, the distribution of enterprise computing resources across different operating systems necessitates cross-platform deployment, further increasing the complexity of enterprise computing network construction. Therefore, existing computing network technologies suffer from both high construction costs and high complexity.

[0080] This application provides a method, device, and storage medium for operating a computing power network based on a computing power message bus. The computing power network includes an entry node, an exit node, and a computing power message bus. The method includes: in response to a computing power resource registration request, obtaining service information of the computing power resource based on the exit node and assigning a service identifier to the computing power resource; obtaining the service identifier and corresponding service information of the computing power resource conforming to preset rules from the computing power message bus based on the entry node, and writing them into the computing power resource registry of the entry node; in response to a computing power task request, obtaining the computing power task based on the entry node, performing resource scheduling on the computing power task, and determining the exit node corresponding to the computing power task; and sending the computing power task to the network address corresponding to the computing power resource based on the exit node, so that the computing power resource can execute the computing power task. Communication between nodes in the computing power network is achieved through a computing power message bus. Computing power resources are registered at the egress node, and a unique service identifier for each resource is obtained within the network based on this identifier. This service identifier is used to locate the computing power resource. The egress node submits the computing power resource information to the storage node. The storage node publishes the information to the computing power message bus using a publish / subscribe model. The ingress node retrieves the corresponding computing power resource information from the message bus based on its subscription requirements and subscribes to the storage node, enabling real-time access to the status information of the computing power resources. Based on the status information of computing resources, computing resources are allocated to computing tasks submitted at the entry node. The computing task, based on the allocated computing resources, obtains the exit information of the registered computing resources through the service identifier of the computing resources, and resolves the network address of the computing resources based on the exit node. Based on the obtained network address, the computing task is sent to the network address corresponding to the computing resources, thereby executing the computing task based on the computing resources. The message bus is used as the computing message transmission path of the computing network, thereby realizing low-cost computing network construction and solving the technical problems of high cost and high complexity of computing network construction in the existing technology.

[0081] The technical solution of this application and how the technical solution of this application solves the above-mentioned technical problems are described in detail below with specific embodiments. These specific embodiments can be combined with each other, and the same or similar concepts or processes may not be described again in some embodiments. The embodiments of this application will now be described with reference to the accompanying drawings.

[0082] Figure 1 The flowchart of the computing power network operation method based on the computing power message bus provided in the embodiments of this application Figure 1 .like Figure 1 As shown, the computing power network in this embodiment includes: an entry node, an exit node, and a computing power message bus. The method includes:

[0083] S101. In response to the computing power resource registration request, obtain the service information of the computing power resource based on the exit node and allocate service identifiers to the computing power resource.

[0084] In this embodiment, the service identifier for the allocation of computing resources by the exit node is unique. Each computing resource needs to obtain a unique service identifier to identify the computing resource when registering with the exit node.

[0085] S102. Based on the entry node, obtain the service identifier and corresponding service information of the computing resources that conform to the preset rules from the computing power message bus, and write them into the computing power resource registry of the entry node.

[0086] In this embodiment, the preset rule for the entry node is a limitation on the range of computing power resources that meet the resource requirements of the entry node; in the first example, the entry node is an entry node in the office area, which has high performance requirements for computing power resources. The entry node in the office area will selectively obtain computing power resources that meet the high performance requirements from the computing power message bus.

[0087] S103. In response to a computing power task request, obtain the computing power task based on the entry node, perform resource scheduling on the computing power task, and determine the exit node corresponding to the computing power task.

[0088] In this embodiment, the entry node connects to the users of computing resources. The entry node provides the users of computing resources with the ability to provide computing network services. The entry node receives computing tasks submitted by the users of computing resources, submits the computing tasks to the computing message bus, and realizes the computing network to process the computing tasks and schedule the computing resources and routes required by the computing tasks.

[0089] S104. Based on the exit node, the computing power task is sent to the network address corresponding to the computing power resource so that the computing power resource can execute the computing power task.

[0090] In this embodiment, the computing task is submitted at the entry node. The entry node schedules the computing task based on the computing resource information of the entry node, determines the information of the computing resource corresponding to the computing task, and sends the service identifier of the computing resource and the information of the computing task to the exit node corresponding to the computing resource. The exit node resolves the network address of the computing resource and sends the computing task to the network address of the computing resource, thereby enabling the computing resource to execute the corresponding computing task.

[0091] This application provides a method for operating a computing power network based on a computing power message bus. The computing power network includes an entry node, an exit node, and a computing power message bus. The method includes: responding to a computing power resource registration request, obtaining service information of the computing power resource based on the exit node and assigning a service identifier to the computing power resource; obtaining the service identifier and corresponding service information of the computing power resource conforming to preset rules from the computing power message bus based on the entry node, and writing it into the computing power resource registry of the entry node; responding to a computing power task request, obtaining the computing power task based on the entry node, performing resource scheduling on the computing power task, and determining the exit node corresponding to the computing power task; and sending the computing power task to the network address corresponding to the computing power resource based on the exit node, so that the computing power resource can execute the computing power task. Communication between nodes in the computing power network is achieved through a computing power message bus. Computing power resources are registered at the egress node, and a unique service identifier for each resource is obtained within the network based on this identifier. This service identifier is used to locate the computing power resource. The egress node submits the computing power resource information to the storage node. The storage node publishes the information to the computing power message bus using a publish / subscribe model. The ingress node retrieves the corresponding computing power resource information from the message bus based on its subscription requirements and subscribes to the storage node, enabling real-time access to the status information of the computing power resources. Based on the status information of computing resources, computing resources are allocated to computing tasks submitted at the entry node. The computing task, based on the allocated computing resources, obtains the exit information of the registered computing resources through the service identifier of the computing resources, and resolves the network address of the computing resources based on the exit node. Based on the obtained network address, the computing task is sent to the network address corresponding to the computing resources, thereby executing the computing task based on the computing resources. The message bus is used as the computing message transmission path of the computing network, thereby realizing low-cost computing network construction and solving the technical problems of high cost and high complexity of computing network construction in the existing technology.

[0092] Figure 2 The flowchart of the computing power network operation method based on the computing power message bus provided in the embodiments of this application Figure 2 .like Figure 2 As shown, the method includes:

[0093] S201. In response to the computing power resource registration request, obtain the service information of the computing power resource based on the exit node and allocate service identifiers to the computing power resource.

[0094] In this embodiment, the service information of computing resources can be network address, computing power, service capabilities, and billing method.

[0095] In this embodiment, the exit node faces the computing resource providing node and provides the computing resource information and load status to the computing network, realizing the perception function of computing resources in the computing network; the computing resources periodically send status information to the exit node, and the exit node synchronously updates the status information of the computing resources to the storage node. The entry node subscribing to the computing resources dynamically updates the status information of the computing resources to the computing resource registry of the entry node based on periodic updates, thereby realizing real-time perception of the status of computing resources.

[0096] S202. Determine the subscription scope of the entry node based on the entry node; determine whether the computing resources in the computing power message bus are within the subscription scope based on the subscription scope. If so, subscribe to the computing resources based on the entry node and write the service identifier and service information of the computing resources into the computing resources registry of the entry node.

[0097] In this embodiment, the subscription scope of the entry node is determined based on the resource requirements of the entry node in the actual deployment; in the second example, the entry node is located in a residential area, and the demand for computing resources in the residential area mainly considers cost-effectiveness, so the entry node will prioritize cheap computing resources when subscribing to computing resources.

[0098] S203. Obtain the status information of computing resources based on the exit node and the preset time interval, and send the status information to the computing message bus;

[0099] In this embodiment, the status information of computing resources can be: service health status, load status, and remaining computing power.

[0100] S204. Obtain status information based on the entry node and the computing power message bus, and update the computing power resource registry of the entry node based on the status information;

[0101] S205. The computing power resource scheduling module performs performance evaluation on the corresponding computing power resources based on the status information, determines the evaluation results, and allocates the corresponding computing power resources to the computing power tasks based on the evaluation results.

[0102] In this embodiment, evaluating computing resources based on status information can be done by: evaluating computing resources based on their current load and performance, and / or determining the network transmission distance between computing resources and the computing task submission node based on their location information, and then evaluating the computing resources based on the network transmission distance.

[0103] S206. Based on the exit node, send the service identifier and service information of the computing power resources to the storage node; based on the storage node, publish the service identifier and service information to the computing power resource bus; based on the entry node, subscribe to the computing power resource information from the storage node, and obtain the computing power resource information based on the computing power resource bus;

[0104] In this embodiment, the storage node is a broker node, which is used to publish messages in the computing power message bus. In this embodiment, the storage node receives computing power resource information submitted by the exit node and broadcasts the computing power resource information through the computing power message bus.

[0105] In this embodiment, there is a many-to-many relationship between exit nodes and entry nodes. An entry node can subscribe to the computing power resource information of multiple exit nodes, and an exit node can send computing power resource information to multiple entry nodes.

[0106] S207. In response to a computing power task request, obtain the computing power task based on the entry node and send the computing power task to the computing power resource scheduling queue.

[0107] In this embodiment, the information stored in the computing power resource scheduling queue can be: computing power task description information, computing power task identifier, and corresponding computing power resource service identifier; wherein the computing power task description information can be: the required computing power size, usage time, and expected cost.

[0108] S208. Based on the computing power resource registry of the entry node, determine the evaluation results of the computing power resources in the computing power resource registry; based on the evaluation results, select computing power resources that meet the computing power task requirements from the computing power resource registry of the entry node, and determine the service identifier of the computing power resources.

[0109] S209. Update the service identifier of the computing resources to the computing resource scheduling list; based on the computing resource scheduling list, send the computing tasks to the computing message queue of the exit node corresponding to the service identifier;

[0110] In this embodiment, the information stored in the computing power message queue includes: computing power task description information, computing power task identifier, and the service identifier of the corresponding computing power resource; wherein the computing power task description information may include: the required computing power size, usage time, and expected cost.

[0111] S210. Subscribe to computing power tasks based on the exit node, and determine the network address of the computing power resource based on the service identifier of the computing power resource corresponding to the computing power task and resolve the network address; send the computing power task to the network address corresponding to the computing power resource, and execute the computing power task based on the computing power resource;

[0112] In this embodiment, the exit node determines the service information of the computing resource and the network address information of the computing resource based on the service identifier of the computing resource. The exit node then resolves the network address of the computing resource to obtain the specific network address of the computing resource.

[0113] By executing S201 to S210, efficient communication between nodes in the computing power network is achieved using the computing power message bus, which improves the efficiency of computing power resource scheduling and reduces the cost of building the computing power network, thereby achieving the technical effect of reducing the cost of building the computing power network and improving the operating efficiency of the computing power network.

[0114] Figure 3 This is a diagram illustrating an enterprise computing power network architecture based on a computing power message bus, provided as an embodiment of this application. Figure 3 As shown, the enterprise computing network architecture includes: a computing application layer, a CFN layer, and an IP layer. In this embodiment, the computing application layer includes computing resource providers and users, as well as computing application software; computing resources include internal enterprise computing resources; these resources can be: the enterprise's supercomputing center, cloud computing, data center, intelligent computing center, and spare shared computing resources in the office network; the CFN layer includes: ingress nodes, engress nodes, computing network nodes, and computing routing and scheduling nodes; the CFN layer is used to realize real-time perception, collaborative processing, and scheduling of computing resources. It achieves real-time perception of computing resources through various messages on the message bus, and integrates collection, evaluation, and allocation based on the needs of computing tasks using the message bus, dynamically allocating appropriate computing resources to computing tasks based on the real-time load status of computing resources; the IP layer is the IP underlay network, which can be a physical network interconnected by multiple devices, used to implement service identification of computing resources. The binding of the SID (Signal ID) to the actual network address enables the resolution of the network address of the computing resource based on its SID and the acquisition of the specific network address of the computing resource. In this embodiment, the computing resources are characterized by dispersed deployment, changing network addresses, and complex and dynamically changing attributes. The attributes of the computing resources include: location information, network access method, computing performance, quality of service, cost, settlement method, access bandwidth, and response time. In this embodiment, the computing resource user submits the computing task to the computing network, the network allocates appropriate computing resources to complete the computing task, and returns the result of the completed computing task to the computing resource user.

[0115] Figure 4 This is a schematic diagram of the computing power message bus provided in this application. Figure 4 As shown, in this embodiment, the computing power message bus is used to implement retrieval and routing functions between computing power resource providers and computing power resource consumers. Each node in the computing power network can access the computing power message bus through a programmable interface. The architecture of the computing power message bus in this embodiment includes storage node (broker) nodes, global management nodes and network management nodes, service brokers, configuration centers, and security management centers.

[0116] In this embodiment, the broker node is used to store computing power messages, receive computing power messages published by computing power resource providers, and save the computing power messages to the corresponding area according to the SID of the computing power resources. After receiving a request from a computing power consumer, the broker node responds to the request and returns the computing power resource messages stored in the specified area. In this embodiment, the broker can be expanded in a cluster manner. Each cluster has one broker as the cluster controller, which is used to manage the work of the cluster: allocating partitions to the broker and monitoring the broker.

[0117] In this embodiment, the global management node and the network management node are used to provide global and local discovery and routing of computing resources. The global management node manages information on computing resources across all brokers, while the network management node manages information on computing resources within its local area, and these nodes are deployed in different regions. Brokers report their SIDs to the network management node, which then aggregates the information and reports it to the global management node. When a computing resource user requests a service, they do not need to be aware of the region of the computing resource. After the global management node locates the specific service region, it forwards the request to the network management node in that region, thus completing the global routing function.

[0118] In this embodiment, the service proxy provides proxy services for non-standard interface computing nodes, public computing networks, and operator computing network access messaging networks. Functions include protocol conversion, security management, and application programming interfaces (APIs).

[0119] In this embodiment, the configuration center is used to complete the service discovery, configuration, and management of broker nodes and clusters, network management nodes, and global management nodes. This includes:

[0120] Service discovery and service health monitoring: After a broker node starts, it automatically registers with the configuration center, implementing a node discovery mechanism. Simultaneously, the configuration center performs real-time health checks on nodes, identifying malfunctioning nodes through periodic heartbeat data and preventing messages from being sent to these nodes.

[0121] Dynamic Configuration Service: The dynamic configuration service manages the service configuration of nodes in a centralized, externalized, and dynamic manner. When a broker node starts and initializes, it automatically downloads configuration parameters from the configuration center and configures them to ensure that the node can work normally in different environments.

[0122] Dynamic DNS service: Dynamic DNS service supports weighted routing, realizes intermediate layer load balancing, and provides more flexible cluster routing policies and traffic control.

[0123] Metadata management: Manages various management-related data of the system, including service descriptions, lifecycles, health status, traffic management, routing and security policies, and statistical data.

[0124] In this embodiment, the security management center is used to provide system authentication and access security control services, as well as node access control.

[0125] This application provides a method for operating a computing power network based on a computing power message bus. The computing power network includes an entry node, an exit node, and a computing power message bus. The method includes: responding to a computing power resource registration request, obtaining service information of the computing power resource based on the exit node and assigning a service identifier to the computing power resource; obtaining the service identifier and corresponding service information of the computing power resource conforming to preset rules from the computing power message bus based on the entry node, and writing it into the computing power resource registry of the entry node; responding to a computing power task request, obtaining the computing power task based on the entry node, performing resource scheduling on the computing power task, and determining the exit node corresponding to the computing power task; and sending the computing power task to the network address corresponding to the computing power resource based on the exit node, so that the computing power resource can execute the computing power task. This application utilizes a message bus to facilitate communication between nodes in a network, leveraging its message propagation capabilities to achieve efficient information transmission. The application broadcasts computing resource information submitted by exit nodes to entry nodes via the computing power message bus. Entry nodes acquire submitted computing tasks and match them with their subscribed computing resource information to schedule computing resources, thereby allocating resources to computing tasks. Computing tasks then search for exit nodes based on the allocated resources, sending them to the computing resource network address to complete the task. The computing messages are propagated through the message bus using a publish-subscribe model, enabling coordinated scheduling of computing resource information and computing tasks. This solves the technical problems of high construction costs and complexity in existing computing power networks.

[0126] Figure 5 This is a schematic diagram of the structure of a computing network operation device based on a computing power message bus, provided as an embodiment of this application. The device in this embodiment can be in the form of software and / or hardware. For example... Figure 5 As shown in the embodiment of this application, a computing network operation device 500 based on a computing power message bus is provided. The computing power network includes: an entry node, an exit node, and a computing power message bus. The device includes: a first acquisition module 501, a first processing module 502, a second acquisition module 503, and a second processing module 504.

[0127] The first acquisition module 501 is used to respond to the computing power resource registration request, acquire the service information of the computing power resource based on the exit node, and allocate service identifiers to the computing power resource.

[0128] The first processing module 502 is used to obtain the service identifier and corresponding service information of computing resources that conform to preset rules from the computing power message bus based on the entry node, and write them into the computing power resource registry of the entry node.

[0129] The second acquisition module 503 is used to respond to a computing power task request, acquire a computing power task based on the entry node, perform resource scheduling on the computing power task, and send the computing power task corresponding to the resource scheduling to the exit node.

[0130] The second processing module 504 is used to send computing power tasks to the network address corresponding to the computing power resources based on the exit node, so as to enable and execute the computing power tasks based on the computing power resources.

[0131] In one possible implementation, the device is also used for:

[0132] The status information of computing resources is obtained based on the exit node and the preset time interval, and the status information is sent to the computing message bus.

[0133] Status information is obtained based on the entry node and the computing power message bus, and the computing power resource registry of the entry node is updated based on the status information;

[0134] The computing resource scheduling module evaluates the performance of the corresponding computing resources based on the status information, determines the evaluation results, and allocates the corresponding computing resources to the computing tasks based on the evaluation results.

[0135] In one possible implementation, the device is also used for:

[0136] Obtain computing power tasks based on the entry node and send the computing power tasks to the computing power resource scheduling queue;

[0137] Obtain the evaluation results of the computing power resources of the entry node, determine the computing power resources corresponding to the computing power tasks based on the evaluation results and scheduling algorithms, and update the service identifier of the computing power resources to the computing power resource scheduling list.

[0138] Based on the computing power resource scheduling list, the computing power tasks are sent to the computing power message queue of the exit node corresponding to the service identifier;

[0139] The computing resource scheduling queue includes: computing task description information, computing task identifier, and corresponding computing resource service identifier;

[0140] The computing power message queue includes: computing power task description information, computing power task identifier, and the service identifier of the corresponding computing power resource.

[0141] In one possible implementation, the device is also used for:

[0142] The evaluation results of computing resources in the computing resource registry are determined based on the entry node.

[0143] Based on the evaluation results, computing resources that meet the computing task requirements are selected from the computing resource registry of the entry node, and the service identifier of the computing resources is determined.

[0144] In one possible implementation, the device is also used for:

[0145] Subscribe to computing power tasks based on the exit node, and determine and resolve the network address of the computing power resource based on the service identifier of the computing power resource corresponding to the computing power task.

[0146] The computing task is sent to the network address corresponding to the computing resource, and the computing task is executed based on the computing resource.

[0147] In one possible implementation, the device is also used for:

[0148] Based on the exit node, the service identifier and service information of the computing power resources are sent to the storage node;

[0149] Based on storage nodes, service identifiers and service information are published to the computing resource bus;

[0150] The entry node subscribes to computing resource information from the storage node and obtains computing resource information based on the computing resource bus.

[0151] In one possible implementation, the device is also used for:

[0152] The subscription scope of the entry node is determined based on the entry node;

[0153] Based on the subscription scope, determine whether the computing resources in the computing power message bus are within the subscription scope. If so, subscribe to the computing resources based on the entry node and write the service identifier and service information of the computing resources into the computing resources registry of the entry node.

[0154] This application provides a computing network operation device based on a computing power message bus. The computing power network includes an entry node, an exit node, and a computing power message bus. The device includes: a first acquisition module, used to acquire service information of computing power resources based on the exit node and assign service identifiers to the computing power resources in response to a computing power resource registration request; a first processing module, used to acquire service identifiers and corresponding service information of computing power resources conforming to preset rules from the computing power message bus based on the entry node, and write them into the computing power resource registry of the entry node; a second acquisition module, used to acquire computing power tasks based on the entry node in response to computing power task requests, perform resource scheduling on the computing power tasks, and determine the exit node corresponding to the computing power tasks; and a second processing module, used to send the computing power tasks to the network address corresponding to the computing power resources based on the exit nodes, so that the computing power resources can execute the computing power tasks. This application utilizes a message bus to facilitate communication between nodes in a network, leveraging its message propagation capabilities to achieve efficient information transmission. The application broadcasts computing resource information submitted by exit nodes to entry nodes via the computing power message bus. Entry nodes acquire submitted computing tasks and match them with their subscribed computing resource information to schedule computing resources, thereby allocating resources to computing tasks. Computing tasks then search for exit nodes based on the allocated resources, sending them to the computing resource network address to complete the task. The computing messages are propagated through the message bus using a publish-subscribe model, enabling coordinated scheduling of computing resource information and computing tasks. This solves the technical problems of high construction costs and complexity in existing computing power networks.

[0155] Figure 6 This is a hardware structure diagram of a computing network operation device based on a computing power message bus, provided as an embodiment of this application. Figure 6 As shown, the computing power network operation device 600 based on the computing power message bus includes:

[0156] Processor 601 and memory 602;

[0157] The memory stores the instructions that the computer executes;

[0158] The processor executes the computer execution instructions stored in memory 602, causing the electronic device to perform the computing network operation method based on the computing power message bus described above.

[0159] It should be understood that the processor 601 described above can be a Central Processing Unit (CPU), or other general-purpose processors, digital signal processors (DSPs), application-specific integrated circuits (ASICs), etc. The general-purpose processor can be a microprocessor or any conventional processor. The steps of the method disclosed in this invention can be directly implemented by a hardware processor, or implemented by a combination of hardware and software modules within the processor. The memory 602 may include high-speed random access memory (RAM), and may also include non-volatile memory (NVM), such as at least one disk storage device, and may also be a USB flash drive, external hard drive, read-only memory, disk, or optical disc, etc.

[0160] This application also provides a computer-readable storage medium storing computer-executable instructions, which, when executed by a processor, are used to implement a computing network operation method based on a computing power message bus.

[0161] It should be noted that, for the sake of simplicity, the foregoing method embodiments are all described as a series of actions. However, those skilled in the art should understand that this application is not limited to the described order of actions, as some steps may be performed in other orders or simultaneously according to this application. Furthermore, those skilled in the art should also understand that the embodiments described in the specification are all optional embodiments, and the actions and modules involved are not necessarily essential to this application.

[0162] It should be further noted that although the steps in the flowchart are shown sequentially according to the arrows, these steps are not necessarily executed in the order indicated by the arrows. Unless explicitly stated herein, there is no strict order restriction on the execution of these steps, and they can be executed in other orders. Moreover, at least some steps in the flowchart may include multiple sub-steps or multiple stages. These sub-steps or stages are not necessarily completed at the same time, but can be executed at different times. The execution order of these sub-steps or stages is not necessarily sequential, but can be performed alternately or in turn with other steps or at least some of the sub-steps or stages of other steps.

[0163] It should be understood that the above-described device embodiments are merely illustrative, and the device of this application can also be implemented in other ways. For example, the division of units / modules in the above embodiments is only a logical functional division, and there may be other division methods in actual implementation. For example, multiple units, modules, or components may be combined, or integrated into another system, or some features may be ignored or not executed.

[0164] Furthermore, unless otherwise specified, the functional units / modules in the various embodiments of this application can be integrated into one unit / module, or each unit / module can exist physically separately, or two or more units / modules can be integrated together. The integrated units / modules described above can be implemented in hardware or as software program modules.

[0165] When integrated units / modules are implemented in hardware, the hardware can be digital circuits, analog circuits, etc. The physical implementation of the hardware structure includes, but is not limited to, transistors, memristors, etc. Unless otherwise specified, the processor can be any suitable hardware processor, such as a CPU, GPU, FPGA, DSP, and ASIC, etc. Unless otherwise specified, the storage unit can be any suitable magnetic or magneto-optical storage medium, such as Resistive Random Access Memory (RRAM), Dynamic Random Access Memory (DRAM), Static Random Access Memory (SRAM), Enhanced Dynamic Random Access Memory (EDRAM), High-Bandwidth Memory (HBM), Hybrid Memory Cube (HMC), etc.

[0166] If the integrated unit / module is implemented as a software program module and sold or used as an independent product, it can be stored in a computer-readable storage device (CMD). Based on this understanding, the technical solution of this application, in essence, or the part that contributes to the prior art, or all or part of the technical solution, can be embodied in the form of a software product. This computer software product is stored in a memory and includes several instructions to cause a computer device (which may be a personal computer, server, or network device, etc.) to execute all or part of the steps of the methods of the various embodiments of this application. The aforementioned memory includes various media capable of storing program code, such as a USB flash drive, read-only memory (ROM), random access memory (RAM), portable hard drive, magnetic disk, or optical disk.

[0167] In the above embodiments, the descriptions of each embodiment have their own emphasis. For parts not described in detail in a certain embodiment, please refer to the relevant descriptions of other embodiments. The technical features of the above embodiments can be combined arbitrarily. For the sake of brevity, not all possible combinations of the technical features in the above embodiments are described. However, as long as the combination of these technical features does not contradict each other, it should be considered within the scope of this specification.

[0168] Other embodiments of this application will readily occur to those skilled in the art upon consideration of the specification and practice of the invention disclosed herein. This application is intended to cover any variations, uses, or adaptations of this application that follow the general principles of this application and include common knowledge or customary techniques in the art not disclosed herein. The specification and examples are to be considered exemplary only, and the true scope and spirit of this application are indicated by the following claims.

[0169] It should be understood that this application is not limited to the precise structure described above and shown in the accompanying drawings, and various modifications and changes can be made without departing from its scope. The scope of this application is limited only by the appended claims.

Claims

1. A method for operating a computing power network based on a computing power message bus, characterized in that, The computing power network includes: an entry node, an exit node, a storage node, and a computing power message bus; the method includes: In response to a computing resource registration request, the service information of the computing resource is obtained based on the exit node, and a service identifier is assigned to the computing resource. Based on the exit node, the service identifier and service information of the computing power resource are sent to the storage node; based on the storage node, the service identifier and service information are published to the computing power message bus; based on the entry node, the information of the computing power resource is subscribed to by the storage node, and the service identifier and corresponding service information of the computing power resource are obtained from the computing power message bus, and the service identifier and service information are written into the computing power resource registry of the entry node; In response to a computing power task request, the computing power task is obtained based on the entry node, and resource scheduling is performed on the computing power task to determine the exit node corresponding to the computing power task. The computing task is sent to the network address corresponding to the computing resource based on the exit node, so that the computing resource can execute the computing task.

2. The method according to claim 1, characterized in that, The computing power network further includes a computing power resource scheduling module, and the method includes: The status information of the computing power resources is obtained based on the exit node and the preset time interval, and the status information is sent to the computing power message bus; The status information is obtained based on the entry node and the computing power message bus, and the computing power resource registry of the entry node is updated based on the status information; Based on the status information, the computing resource scheduling module performs performance evaluation on the corresponding computing resources, determines the evaluation result, and allocates the corresponding computing resources to the computing task based on the evaluation result.

3. The method according to claim 2, characterized in that, The step of obtaining the computing power task based on the entry node, performing resource scheduling on the computing power task, and determining the exit node corresponding to the computing power task includes: The computing power task is obtained based on the entry node and the computing power task is sent to the computing power resource scheduling queue. The evaluation result of the computing power resources of the entry node is obtained, and the computing power resources corresponding to the computing power task are determined based on the evaluation result and the scheduling algorithm. The service identifier of the computing power resources is then updated to the computing power resource scheduling list. Based on the computing power resource scheduling list, the computing power task is sent to the computing power message queue of the exit node corresponding to the service identifier; The computing power resource scheduling queue includes: computing power task description information, computing power task identifier, and the service identifier of the corresponding computing power resource; The computing power message queue includes: computing power task description information, computing power task identifier, and the service identifier of the corresponding computing power resource.

4. The method according to claim 3, characterized in that, The step of obtaining the evaluation result of the computing power resources of the entry node and determining the computing power resources corresponding to the computing power task based on the evaluation result and the scheduling algorithm includes: The evaluation result of the computing resources in the computing resources registry is determined based on the computing resources registry of the entry node; Based on the evaluation results, the computing resources that meet the computing task requirements are selected from the computing resource registry of the entry node, and the service identifier of the computing resources is determined.

5. The method according to claim 4, characterized in that, The step of sending the computing power task to the network address corresponding to the computing power resource based on the exit node, so that the computing power resource can execute the computing power task, includes: Based on the exit node, subscribe to the computing power task, and based on the service identifier of the computing power resource corresponding to the computing power task, determine the network address of the computing power resource and resolve the network address; The computing task is sent to the network address corresponding to the computing resource, and the computing task is executed based on the computing resource.

6. The method according to claim 1, characterized in that, The step of subscribing to the computing power resource information from the storage node based on the entry node, obtaining the service identifier and corresponding service information of the computing power resource from the computing power message bus, and writing the service identifier and the service information into the computing power resource registry of the entry node includes: The subscription scope of the entry node is determined based on the entry node; Based on the subscription scope, determine whether the computing power resource in the computing power message bus is within the subscription scope. If so, subscribe to the computing power resource based on the entry node, and write the service identifier and service information of the computing power resource into the computing power resource registry of the entry node.

7. A computing network operation device based on a computing power message bus, characterized in that, The computing power network includes: an entry node, an exit node, a storage node, and a computing power message bus, including: The first acquisition module is used to respond to a computing resource registration request, acquire the service information of the computing resource based on the exit node, and allocate a service identifier to the computing resource. The first sending module is used to send the service identifier and service information of the computing power resource to the storage node based on the exit node; The publishing module is used to publish the service identifier and the service information to the computing power message bus based on the storage node; The first processing module is used to subscribe to the information of the computing power resources from the storage node based on the entry node, and to obtain the service identifier and the corresponding service information of the computing power resources from the computing power message bus, and to write the service identifier and the service information into the computing power resource registry of the entry node; The second acquisition module, in response to a computing power task request, acquires the computing power task based on the entry node, performs resource scheduling on the computing power task, and determines the exit node corresponding to the computing power task. The second processing module is used to send the computing power task to the network address corresponding to the computing power resource based on the exit node, so as to execute the computing power task based on the computing power resource.

8. A computing network operation device based on a computing power message bus, characterized in that, include: A processor, and a memory communicatively connected to the processor; The memory stores computer-executed instructions; The processor executes the computer execution instructions stored in the memory to implement the computing network operation method based on the computing power message bus as described in any one of claims 1 to 6.

9. A computer-readable storage medium, characterized in that, The computer-readable storage medium stores computer-executable instructions, which, when executed by a processor, are used to implement the computing network operation method based on a computing power message bus as described in any one of claims 1 to 6.

Images