Computing power resource scheduling method, passive optical network system, communication device and storage medium

Abstract

The invention relates to a computing power resource scheduling method, a passive optical network system, communication equipment and a computer readable storage medium. The passive optical network system comprises computing power arrangement equipment and a plurality of computing power gateways connected with the computing power arrangement equipment, each computing power gateway is connected with at least one computing power node, and the computing power nodes comprise at least one of equipment nodes and cluster nodes; the computing power arrangement equipment obtains a current service demand; determining at least one target computing power node from the passive optical network system according to the current service requirement; and controlling at least one target computing power node to process a task corresponding to the current service demand. By means of the mode, the computing power network is deployed in the passive optical network system, the equipment computing power of the passive optical network system is expressed in a unified mode, the equipment heterogeneity is ignored, and the utilization efficiency of network resources of the passive optical network system can be improved. And computing power resources are allocated according to the service requirements, so that quick response to the service requirements is realized.

Description

Technical Field

[0001] The present application relates to the field of communication technology, and in particular to a computing resource scheduling method, a passive optical network system, a communication device, and a computer-readable storage medium. Background Art

[0002] With the continuous development of technologies such as 5G (5th Generation Mobile Communication Technology), the Internet of Things, and artificial intelligence, the application scenarios of computing power networks are also expanding. As the latest technological trend of further integration of computing power resources and network resources, computing power networks can not only support high-performance computing needs such as large-scale data analysis and artificial intelligence training, but also provide powerful computing support for emerging fields such as edge computing, smart cities, and smart medical care. It can be foreseen that computing power networks will play an increasingly important role in the future information society and become an important engine for promoting scientific and technological progress and economic development.

[0003] Although the computing power of the PON network (Passive Optical Network) is limited, the rational use of the computing power of the PON network can significantly improve network performance and resource utilization efficiency. At present, the PON network has various equipment forms and different hardware architectures, which cannot provide users with efficient edge computing power, limiting the efficient use of PON network resources. Summary of the invention

[0004] Based on this, it is necessary to provide a computing resource scheduling method, a passive optical network system, a communication device and a computer-readable storage medium to address the above-mentioned technical problems, which can deploy a computing network in the passive optical network system and improve the utilization efficiency of network resources of the passive optical network system.

[0005] In a first aspect, the present application provides a computing resource scheduling method, which is applied to a computing power orchestration device of a passive optical network system, wherein the passive optical network system further includes a plurality of computing power gateways connected to the computing power orchestration device, each computing power gateway is respectively connected to at least one computing power node, and the computing power node includes at least one of a device node and a cluster node; the method includes:

[0006] Obtain current business needs;

[0007] According to current business needs, determine at least one target computing power node from the passive optical network system;

[0008] Control at least one target computing power node to process tasks corresponding to current business needs.

[0009] In one embodiment, the method further comprises:

[0010] Receive the node access request sent by the current computing power gateway; after detecting that the current computing power node is accessed for the first time, the current computing power gateway generates and sends a node access request;

[0011] A computing power identifier is allocated to the current computing power node according to the node access request, so that the current computing power node is registered in the passive optical network system.

[0012] In one of the embodiments, according to current business requirements, determining at least one target computing power node from the passive optical network system includes:

[0013] Analyze current business needs and determine the current computing power scenario; the current computing power scenario includes at least one expected device type and the computing power specifications corresponding to each expected device type;

[0014] According to the expected device type and computing power specifications, the corresponding target computing power node is determined from the passive optical network system.

[0015] In one of the embodiments, the computing power identifier includes a computing power attribute identifier, the computing power attribute identifier includes a device type and a computing power level, and according to the expected device type and computing power specification, determining a corresponding target computing power node from the passive optical network system includes:

[0016] Searching for a candidate computing power node from the passive optical network system, whose device type is consistent with the expected device type and whose computing power level matches the computing power specification;

[0017] If multiple candidate computing nodes are found, the computing node with the highest performance score among the candidate computing nodes is determined as the target computing node.

[0018] In one embodiment, the method further comprises:

[0019] For each candidate computing power node, obtain the hardware performance information and resource usage information of the candidate computing power node;

[0020] Determine the basic performance score based on the hardware performance information;

[0021] Determine the dynamic performance score based on the resource occupancy information;

[0022] The performance score of the candidate computing power node is determined based on the basic performance score and the dynamic performance score.

[0023] In one embodiment, the current business demand is sent by an external network system to a computing power orchestration device, and the method further includes:

[0024] Mapping the computing power identifier of at least one target computing power node to a target computing power identifier corresponding to the external network system;

[0025] Generate response information according to the target computing power identifier;

[0026] Feedback the response information to the external network system.

[0027] In one of the embodiments, the computing power orchestration device is a main edge server in a passive optical network system; the computing power gateway is a white box switching device connected to the computing power orchestration device; the device node includes at least one of an optical line terminal, an optical network terminal, an optical network unit, and a resource board of the optical line terminal; and the cluster node includes an edge server.

[0028] In a second aspect, the present application further provides a passive optical network system, the passive optical network system comprising a computing power orchestration device, and a plurality of computing power gateways connected to the computing power orchestration device, each computing power gateway being respectively connected to at least one computing power node, and the computing power node comprising at least one of a device node and a cluster node; the computing power orchestration device is used to perform the following steps:

[0029] Obtain current business needs;

[0030] According to current business needs, determine at least one target computing power node from the passive optical network system;

[0031] Control at least one target computing power node to process tasks corresponding to current business needs.

[0032] In a third aspect, the present application further provides a communication device, including a memory and a processor, wherein the memory stores a computer program, and when the processor executes the computer program, the following steps are implemented:

[0033] Obtain current business needs;

[0034] According to current business needs, determine at least one target computing power node from the passive optical network system;

[0035] Control at least one target computing power node to process tasks corresponding to current business needs.

[0036] In a fourth aspect, the present application further provides a computer-readable storage medium having a computer program stored thereon, wherein when the computer program is executed by a processor, the following steps are implemented:

[0037] Obtain current business needs;

[0038] According to current business needs, determine at least one target computing power node from the passive optical network system;

[0039] Control at least one target computing power node to process tasks corresponding to current business needs.

[0040] The above-mentioned computing power resource scheduling method, passive optical network system, communication equipment and computer-readable storage medium, the passive optical network system includes a computing power orchestration device, and multiple computing power gateways connected to the computing power orchestration device, each computing power gateway is respectively connected to at least one computing power node, and the computing power node includes at least one of a device node and a cluster node; the computing power orchestration device obtains the current business demand; according to the current business demand, at least one target computing power node is determined from the passive optical network system; at least one target computing power node is controlled to process tasks corresponding to the current business demand. Through the above method, a computing power network is deployed in the passive optical network system, and the computing power of the equipment of the passive optical network system is expressed in a unified manner, ignoring the heterogeneity of the equipment, which can improve the utilization efficiency of the network resources of the passive optical network system. Allocate computing power resources according to business needs to achieve rapid response to business needs. BRIEF DESCRIPTION OF THE DRAWINGS

[0041] 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.

[0042] FIG1 is a schematic diagram of a flow chart of a computing resource scheduling method in one embodiment;

[0043] FIG2 is a schematic diagram of a passive optical network system according to an embodiment;

[0044] FIG3 is a schematic diagram of a process flow of a node registration step in one embodiment;

[0045] FIG4 is a schematic diagram of a computing power network in one embodiment;

[0046] FIG. 5 is a diagram showing the internal structure of a communication device in one embodiment. DETAILED DESCRIPTION

[0047] 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.

[0048] In an exemplary embodiment, as shown in FIG1 , a computing resource scheduling method is provided, the method is applied to a computing orchestration device of a passive optical network system, the passive optical network system further includes a plurality of computing gateways connected to the computing orchestration device, each computing gateway is respectively connected to at least one computing node, and the computing node includes at least one of a device node and a cluster node; the method includes:

[0049] Step 102, obtaining current business requirements.

[0050] It can be understood that, with reference to FIG. 2, FIG. 2 is a schematic diagram of a passive optical network system in an embodiment; the passive optical network system of the embodiment of the present application includes a computing power orchestration device 201 and a plurality of computing power gateways 202 connected to the computing power orchestration device 201, each computing power gateway 202 is respectively connected to at least one computing power node 203, and the computing power node 203 in the passive optical network system can be a device node or a cluster node. Among them, the computing power orchestration device 201, the computing power gateway 202, and the computing power node 203 are obtained by dividing according to the type of each device in the passive optical network system (PON network), and can realize different functions. The computing power orchestration device 201 uniformly manages and orchestrates services, computing power resources, and network resources, and has registration functions and OAM (Operation Administration and Maintenance) functions. As an important access point for computing power resources in the network, the computing power gateway 202 is responsible for the perception, aggregation, and distribution of computing power information. The computing power gateway 202 can sense and collect computing power resource information within its management scope in real time, including cloud resource pools, virtual resources and computing power routing information. Through relevant protocol extension technology, the computing power gateway 202 can interconnect with other computing power gateways 202, so that the computing power orchestration device 201 can obtain all cloud resource pools, virtual resources and computing power routing information managed within the computing power network. The computing power node 203 is a computing node that provides computing power. The computing power node 203 can have various forms, such as cloud data centers, edge computing centers, terminals, servers, etc.

[0051] Among them, the current business demand carries the computing power demand information that needs to be realized through the passive optical network system, which refers to the computing power resource requirements of the current business. Optionally, the current business demand includes capability requirements and performance requirements. Capacity requirements are used to constrain the computing power resources provided by the passive optical network system to have the ability to realize the current business, such as model training capabilities, data storage capabilities, etc. Performance requirements are used to constrain the computing power resources provided by the passive optical network system to meet the performance requirements of the current business, such as storage space requirements, latency requirements, etc.

[0052] Optionally, the current business demand is sent to the computing power orchestration device by an external network system, and the external network system is a network other than the passive optical network system, such as a large network, the Internet, etc. The large network usually refers to a large-scale network infrastructure used to connect data communications between multiple locations and organizations. The computing power network implemented by the PON network can be connected to the large network, so that the computing power network of the large network can call the computing power of the PON network.

[0053] Optionally, the current business demand is sent by the user to the computing power orchestration device through the terminal device in the passive optical network system. Through the PON network, the service originally deployed on the cloud side can be deployed on the edge side or the terminal side, so as to achieve rapid response of the service to the user request.

[0054] Step 104: determine at least one target computing power node from the passive optical network system according to current business needs.

[0055] Among them, the computing power orchestration device manages the computing power of each computing power node in the passive optical network system, and searches for target computing power nodes that meet the requirements from the passive optical network system according to current business needs. It is understandable that some businesses require multiple computing power nodes to provide computing power resources, and multiple target computing power nodes need to be searched out. Optionally, by managing multiple computing power nodes through computing power orchestration equipment, on-demand allocation and dynamic scheduling of PON network resources are realized, and deterministic delay of the PON network is introduced to ensure the reliability and predictability of data transmission.

[0056] Step 106, control at least one target computing node to process tasks corresponding to current business needs.

[0057] Among them, control refers to the management and scheduling of target computing nodes by issuing tasks to them. Control can include starting calculations, stopping calculations, adjusting performance parameters, allocating resources and other parameters. The target computing node can perform various computing tasks. The current business needs correspond to a series of tasks that need to be calculated or processed, such as data analysis, image processing, video rendering, model training, and so on. Specifically, now, the current business needs are analyzed, and the tasks corresponding to each target computing node are planned and issued, so as to control at least one target computing node to process the tasks corresponding to the current business needs.

[0058] In an optional implementation, deploying a computing network in a PON network can achieve high availability of services. Optionally, if a computing node where a service is located fails in a passive optical network system, the computing orchestration device can quickly migrate data related to the service to other available computing nodes.

[0059] In the above-mentioned computing power resource scheduling method, the passive optical network system includes a computing power orchestration device and multiple computing power gateways connected to the computing power orchestration device, each computing power gateway is respectively connected to at least one computing power node, and the computing power node includes at least one of a device node and a cluster node; the computing power orchestration device obtains the current business demand; according to the current business demand, at least one target computing power node is determined from the passive optical network system; and at least one target computing power node is controlled to process tasks corresponding to the current business demand. Through the above-mentioned method, a computing power network is deployed in the passive optical network system, and the computing power of the equipment of the passive optical network system is expressed in a unified manner, ignoring the heterogeneity of the equipment, which can improve the utilization efficiency of the network resources of the passive optical network system. Computing power resources are allocated according to business needs to achieve rapid response to business needs.

[0060] In an exemplary embodiment, as shown in FIG3 , the method further includes:

[0061] Step 302, receiving a node access request sent by the current computing power gateway; after detecting that the current computing power node accesses for the first time, the current computing power gateway generates and sends a node access request.

[0062] Among them, the computing power orchestration device provided in the embodiment of the present application has a registration function. The current computing power gateway is any computing power gateway in the passive optical network system. When a new computing power node attempts to connect to the computing power gateway for the first time, the computing power node will send an access request to the computing power gateway. The request carries the basic information of the computing power node, such as address, hardware configuration, available resources, etc., so that the computing power gateway can identify the performance of the computing power node. When the computing power node detects that a new computing power node has been connected, it will trigger the registration process and send a node access request to the computing power orchestration device. The node access request carries the basic information of the current computing power node and the basic information of the current computing power gateway. The current computing power node is a new computing power node that is currently accessing the current computing power gateway for the first time.

[0063] Step 304: allocate a computing power identifier to the current computing power node according to the node access request, so that the current computing power node is registered in the passive optical network system.

[0064] Among them, the computing power identifier is an independent and unique identifier used to identify computing power resources in the computing power network, and is not affected by changes in other resources and users in the network. The computing power orchestration device manages and schedules computing power nodes based on the computing power identifier of each computing power node. The computing power orchestration device parses the node access request and assigns a computing power identifier to the newly connected current computing power node based on the information carried in the node access request, so that the current computing power node is registered in the passive optical network system to complete the registration process.

[0065] Optionally, the computing power identification includes a computing power location identification, a computing power identity identification, and a computing power attribute identification. The computing power location identification is a computer room and a rack, the computing power identity identification includes a computing power provider and a product code, and the computing power attribute identification includes a computing power form, a computing power model, and a computing power level. The computing power form indicates the device type.

[0066] In this embodiment, by allocating computing power identifiers, the computing power scheduling device can uniquely identify and uniformly manage each connected computing power node, which is convenient for subsequent scheduling and allocation. By accessing new computing power nodes, the computing power capacity of the passive optical network system can be expanded to meet the growing computing power demand.

[0067] In an exemplary embodiment, step 204 includes: analyzing current business needs and determining a current computing power scenario; the current computing power scenario includes at least one expected device type and a computing power specification corresponding to each expected device type; and determining a corresponding target computing power node from the passive optical network system based on the expected device type and computing power specification.

[0068] It is understandable that the computing power orchestration equipment has the ability to measure computing power, effectively identify and measure the computing power in the passive optical network system, and can use the computing power measurement method currently used in large networks. Optionally, based on the characteristics and parameters of computing power resources, the computing power is abstractly modeled to form a unified computing power measurement standard, including various types of computing power resources such as logical computing power, parallel computing power, and neural network computing power.

[0069] The computing power orchestration equipment analyzes the current business needs and plans specific computing power scenarios under the PON network, such as cloud computing scenarios, artificial intelligence scenarios, blockchain scenarios, etc., and small-scale computing power scenarios, medium-scale computing power scenarios, and large-scale computing power scenarios, etc. The types and specifications of computing power nodes involved in each computing power scenario are different.

[0070] Among them, according to the current business needs, identify key applications, such as image classification, text generation, big data analysis, etc., determine the task types involved in the current business (such as real-time processing, batch processing, offline analysis, etc.), and analyze the complexity of the tasks. According to information such as key applications, task types, and task complexity, select the appropriate device type, number of devices, and computing power specifications, that is, analyze the current computing power scenario. The computing power orchestration device determines at least one target computing power node that meets the requirements from the passive optical network system based on the expected device type, number of devices, computing power specifications, and other parameters obtained by analysis.

[0071] In this embodiment, business requirements and computing resources are accurately matched to achieve reasonable utilization of computing resources in the PON network.

[0072] In an exemplary embodiment, the computing power identifier includes a computing power attribute identifier, and the computing power attribute identifier includes a device type and a computing power level. According to the expected device type and computing power specification, the corresponding target computing power node is determined from the passive optical network system, including: searching from the passive optical network system for a candidate computing power node whose device type is consistent with the expected device type and whose computing power level matches the computing power specification; if multiple candidate computing power nodes are searched, then the computing power node with the highest performance score among the multiple candidate computing power nodes is determined as the target computing power node.

[0073] Among them, when the computing power orchestration device allocates computing power identification to the computing power node, it adopts the aforementioned computing power measurement method according to the hardware configuration, available resources and other information submitted by the computing power node, configures the computing power attribute identification of the computing power level for the computing power node, and configures the computing power attribute identification of the device type, such as the optical line terminal, optical network terminal, optical network unit, resource board of the optical line terminal, edge server, etc.

[0074] The computing power scheduling device searches for a candidate computing power node whose device type is consistent with the expected device type and whose computing power level matches the computing power specification based on the computing power identifier of each computing power node in the passive optical network system. If a candidate computing power node is searched, the searched candidate computing power node is used as the target computing power node. If multiple candidate computing power nodes are searched, the candidate computing power node with the highest performance score is selected as the target computing power node. The performance score is information used to evaluate the computing power capacity of each computing power node. It can be a score obtained by evaluating static information such as the processor performance, memory performance, storage performance, etc. of the computing power node, or it can be a score obtained by evaluating static information and dynamic resource utilization.

[0075] It can be understood that for each group of expected device types and computing power specifications, a target computing power node is determined through the method provided in this embodiment.

[0076] In this embodiment, by matching the device type and computing power specifications, it can be ensured that the selected computing power node can adapt to the business needs. Selecting the one with the highest performance score as the target computing power node among multiple candidate computing power nodes can ensure the best performance in the business processing process and improve the overall business processing efficiency.

[0077] In an exemplary embodiment, the method also includes: for each candidate computing power node, obtaining the hardware performance information and resource occupancy information of the candidate computing power node; determining the basic performance score based on the hardware performance information; determining the dynamic performance score based on the resource occupancy information; and determining the performance score of the candidate computing power node based on the basic performance score and the dynamic performance score.

[0078] Among them, hardware performance information includes static information such as processor performance, memory performance, storage performance, and network performance, which are the hardware configuration parameters of the computing power node. Resource occupancy information is used to characterize the consumption of various resources during the operation of the computing power node, including dynamic information such as processor resource occupancy rate, memory resource occupancy rate, storage resource occupancy rate, and network resource occupancy rate.

[0079] According to the preset scoring strategy, the hardware performance information of the selected computing power node is evaluated to determine the basic performance score. According to the preset scoring strategy, the resource occupancy information of the selected computing power node is evaluated to determine the dynamic performance score. The preset scoring strategy of this embodiment can adopt the scoring method that has been implemented in other computing power networks, and this embodiment does not limit the specific method of the preset scoring strategy.

[0080] In an optional implementation, a preset first weight and a second weight are obtained, and a weighted sum is performed on the basic performance score and the dynamic performance score according to the first weight and the second weight to obtain a performance score of the computing power node to be selected.

[0081] It is understandable that the performance score depends not only on the hardware performance of the computing power node, but also on the resource usage of the computing power node during operation, so as to select the computing power node with the best performance.

[0082] In this embodiment, a combination of static and dynamic methods is adopted to comprehensively evaluate the performance status of computing nodes and measure the performance score of each computing node, so that the computing power orchestration device can allocate computing power resources more reasonably.

[0083] In an exemplary embodiment, the current business demand is sent by an external network system to a computing power orchestration device, and the method further includes: mapping a computing power identifier of at least one target computing power node to a target computing power identifier corresponding to the external network system; generating response information based on the target computing power identifier; and feeding back the response information to the external network system.

[0084] Among them, the computing power network deployed in the PON network of this embodiment can be connected to the external network system to achieve the integration of computing power with the external network system, so that the external network system can call the computing power of the PON network. The computing power orchestration device can be regarded as a computing power gateway in the external network system. Optionally, the external network system is a large network, and this embodiment can achieve the integration of computing power between the PON network and the large network.

[0085] It is understandable that in the big network, the computing power identification is presented in the form of an abstract hierarchical tree of computing power resources, including computing power location identification, computing power identity identification and computing power attribute identification. The computing power location identification includes the national domain and computing power domain, which refers to the location attribute of the computing power resources; the computing power identity identification includes the computing power provider and product code; the computing power attribute identifier includes the computing power form, computing power model, and computing power level, indicating the computing power's own attribute information.

[0086] In the PON network of this embodiment, the management method of the computing power identification is used, and the computing power identification includes the computing power location identification, computing power identity identification and computing power attribute identification. Different from the large network, the computing power location identification is the computer room and the rack, and the computing power form indicates the equipment type.

[0087] In the process of the external network system using the computing power resources of the PON network, the computing power orchestration device needs to feedback response information to the external network system to inform the external network system of the call status of the computing power resources. A mapping mechanism for computing power identifiers is defined in advance. According to the mapping mechanism, this embodiment maps the computing power identifier in the PON network to the target computing power identifier used by the external network system, integrates other data that need to be fed back based on the target computing power identifier, generates response information, and feeds back the response information to the external network system. The computing power resources of the PON network are mounted in the external network system. Through the mapping of the computing power identifier, the computing power orchestration device does not need to expose the specific implementation details of the computing power resources to the external network system. The external network system obtains the mapped computing power identifier, so that the external network system does not need to care whether the source of the computing power resources is the PON network, and can use the computing power resources of the PON network like local resources.

[0088] In this embodiment, by mapping the computing power identifier, the computing power network deployed in the PON network can be connected to the external network system, thereby realizing the sharing of computing power resources between the PON network and the external network system.

[0089] In an exemplary embodiment, the computing power orchestration device is a main edge server in a passive optical network system; the computing power gateway is a white box switching device connected to the computing power orchestration device; the device node includes at least one of an optical line terminal, an optical network terminal, an optical network unit, and a resource board of the optical line terminal; and the cluster node includes an edge server.

[0090] Wherein, referring to FIG. 4, FIG. 4 is a schematic diagram of a computing power network in an embodiment. Wherein, the white box switching device in the PON network is set as a computing power gateway to realize the perception and distribution of computing power resources. The white box switching device manages a computing power resource pool, and the computing power resource pool includes at least one computing power node. The white box switching device is mainly composed of programmable switching devices such as white box switches, white box gateways, and white box routers. An edge server in the PON network is selected as a computing power orchestration device. The edge server is called a primary edge server, and its performance (for example, processor performance, memory performance, storage performance, network performance, etc.) meets certain requirements. It is responsible for generating resource table items, formulating policies, and allocating cloud resources or computing network resources. Optionally, the edge server with the highest performance in the PON network is set as a computing power orchestration device. Other devices with certain computing power in the PON network are set as computing power nodes (which can be device nodes, or device nodes and cluster nodes), and connected to the computing power gateway. The device node includes at least one of an optical line terminal (OLT), an optical network terminal (ONT), an optical network unit (ONU), and a resource board of the optical line terminal. The cluster node includes an edge server, which can be set in the cloud, but the embodiments of the present application are not limited thereto.

[0091] It can be understood that the devices in the PON network mainly include OLT, ONU / ONT, edge server, OLT resource board and white box switching equipment, etc., among which OLT, ONU / ONT, edge server and white box switching equipment as computing power orchestration equipment are necessary components for building the PON network computing power framework, and edge server and OLT resource board as computing power nodes are optional components. Referring to Table 1, Table 1 is a description information table of each device of the PON network in an embodiment.

[0092] Table 1:

[0093]

[0094] It can be understood that in this embodiment, a computing power framework is defined in the PON network, the roles of each device in the PON network are set, and the basic logic of the PIN network computing power framework is standardized, providing a theoretical basis for the subsequent realization of computing power network functions through the PON network. Through the PON network computing power framework provided by this embodiment, the computing power of various devices in the PON network can be fully mobilized, and the high availability of applications in the PON network can be guaranteed as much as possible. The PON network computing power framework provided by this embodiment can pave the way for the inclusion of PON computing power into the large network.

[0095] 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.

[0096] In an exemplary embodiment, a communication device is provided, which may be a server, and its internal structure diagram may be shown in FIG5. The communication device includes a processor, a memory, an input / output interface (Input / Output, referred to as I / O) and a communication interface. Among them, the processor, the memory and the input / output interface are connected through a system bus, and the communication interface is connected to the system bus through the input / output interface. Among them, the processor of the communication device is used to provide computing and control capabilities. The memory of the communication device includes a non-volatile storage medium and an internal memory. The non-volatile storage medium stores an operating system and a computer program. The internal memory provides an environment for the operation of the operating system and the computer program in the non-volatile storage medium. The input / output interface of the communication device is used to exchange information between the processor and an external device. The communication interface of the communication device is used to communicate with an external terminal through a network connection. Optionally, the communication device is arranged in a passive optical network system, and the passive optical network system also includes a plurality of computing power gateways connected to the computing power orchestration device, and each of the computing power gateways is respectively connected to at least one computing power node, and the computing power node includes at least one of a device node and a cluster node. When the computer program is executed by a processor, a computing resource scheduling method is implemented.

[0097] Those skilled in the art will understand that the structure shown in FIG. 5 is merely a block diagram of a partial structure related to the scheme of the present application, and does not constitute a limitation on the communication device to which the scheme of the present application is applied. The specific communication device may include more or fewer components than shown in the figure, or combine certain components, or have a different arrangement of components.

[0098] In an exemplary embodiment, a communication device is provided, including a memory and a processor, wherein a computer program is stored in the memory, and the processor implements the following steps when executing the computer program: obtaining current business needs; determining at least one target computing power node from a passive optical network system based on the current business needs; and controlling at least one target computing power node to process tasks corresponding to the current business needs.

[0099] In one embodiment, when the processor executes the computer program, the following steps are also implemented: receiving a node access request sent by the current computing power gateway; after the current computing power gateway detects that the current computing power node has accessed for the first time, the current computing power gateway generates and sends a node access request; and according to the node access request, a computing power identifier is assigned to the current computing power node so that the current computing power node is registered in the passive optical network system.

[0100] In one embodiment, when the processor executes the computer program, the following steps are also implemented: analyzing current business needs and determining the current computing power scenario; the current computing power scenario includes at least one expected device type and computing power specifications corresponding to each expected device type; based on the expected device type and computing power specifications, determining the corresponding target computing power node from the passive optical network system.

[0101] In one embodiment, when the processor executes the computer program, the following steps are also implemented: searching from the passive optical network system for a candidate computing power node whose device type is consistent with the expected device type and whose computing power level matches the computing power specification; if multiple candidate computing power nodes are searched, the computing power node with the highest performance score among the multiple candidate computing power nodes is determined as the target computing power node.

[0102] In one embodiment, when the processor executes the computer program, the following steps are also implemented: for each candidate computing power node, the hardware performance information and resource occupancy information of the candidate computing power node are obtained; based on the hardware performance information, a basic performance score is determined; based on the resource occupancy information, a dynamic performance score is determined; based on the basic performance score and the dynamic performance score, a performance score of the candidate computing power node is determined.

[0103] In one embodiment, when the processor executes the computer program, the following steps are also implemented: mapping the computing power identifier of at least one target computing power node to the target computing power identifier corresponding to the external network system; generating response information according to the target computing power identifier; and feeding back the response information to the external network system.

[0104] In one embodiment, a computer-readable storage medium is provided, on which a computer program is stored. When the computer program is executed by a processor, the following steps are implemented: obtaining current business needs; determining at least one target computing power node from a passive optical network system based on the current business needs; and controlling at least one target computing power node to process tasks corresponding to the current business needs.

[0105] In one embodiment, when the computer program is executed by the processor, the following steps are also implemented: receiving a node access request sent by the current computing power gateway; after detecting that the current computing power node has accessed for the first time, the current computing power gateway generates and sends a node access request; and according to the node access request, a computing power identifier is assigned to the current computing power node so that the current computing power node is registered in the passive optical network system.

[0106] In one embodiment, when the computer program is executed by the processor, the following steps are also implemented: analyzing current business needs and determining the current computing power scenario; the current computing power scenario includes at least one expected device type and computing power specifications corresponding to each expected device type; based on the expected device type and computing power specifications, determining the corresponding target computing power node from the passive optical network system.

[0107] In one embodiment, when the computer program is executed by the processor, the following steps are also implemented: searching from the passive optical network system for a candidate computing power node whose device type is consistent with the expected device type and whose computing power level matches the computing power specification; if multiple candidate computing power nodes are searched, the computing power node with the highest performance score among the multiple candidate computing power nodes is determined as the target computing power node.

[0108] In one embodiment, when the computer program is executed by the processor, the following steps are also implemented: for each candidate computing power node, the hardware performance information and resource occupancy information of the candidate computing power node are obtained; based on the hardware performance information, a basic performance score is determined; based on the resource occupancy information, a dynamic performance score is determined; based on the basic performance score and the dynamic performance score, a performance score of the candidate computing power node is determined.

[0109] In one embodiment, when the computer program is executed by the processor, the following steps are also implemented: mapping the computing power identifier of at least one target computing power node to the target computing power identifier corresponding to the external network system; generating response information based on the target computing power identifier; and feeding back the response information to the external network system.

[0110] It should be noted that the user information (including but not limited to user device information, user personal information, etc.) and data (including but not limited to data used for analysis, stored data, displayed data, etc.) involved in this application are all information and data authorized by the user or fully authorized by all parties, and the collection, use and processing of relevant data must comply with relevant regulations.

[0111] 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.

[0112] 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.

[0113] 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 understood as limiting the scope of the present application. It should be pointed out that, for a person of ordinary skill in the art, several variations 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 computing resource scheduling method, It is characterized in that The method is applied to a computing power orchestration device of a passive optical network system, wherein the passive optical network system further comprises a plurality of computing power gateways connected to the computing power orchestration device, each of the computing power gateways is respectively connected to at least one computing power node, and the computing power node comprises at least one of a device node and a cluster node; the method comprises: Obtain current business needs; According to the current business demand, determining at least one target computing power node from the passive optical network system; Control the at least one target computing power node to process tasks corresponding to the current business needs.

2. The method according to claim 1, It is characterized in that The method further comprises: Receiving a node access request sent by the current computing power gateway; after detecting that the current computing power node is accessed for the first time, the current computing power gateway generates and sends the node access request; A computing power identifier is allocated to the current computing power node according to the node access request, so that the current computing power node is registered in the passive optical network system.

3. The method according to claim 2, It is characterized in that The determining at least one target computing power node from the passive optical network system according to the current business demand includes: Analyze the current business demand and determine the current computing power scenario; the current computing power scenario includes at least one expected device type and a computing power specification corresponding to each expected device type; According to the expected device type and the computing power specification, a corresponding target computing power node is determined from the passive optical network system.

4. The method according to claim 3, It is characterized in that The computing power identifier includes a computing power attribute identifier, and the computing power attribute identifier includes a device type and a computing power level. The determining a corresponding target computing power node from the passive optical network system according to the expected device type and the computing power specification includes: Searching, from the passive optical network system, a candidate computing power node whose device type is consistent with the expected device type and whose computing power level matches the computing power specification; If multiple candidate computing nodes are found, the computing node with the highest performance score among the candidate computing nodes is determined as the target computing node.

5. The method according to claim 4, It is characterized in that The method further comprises: For each candidate computing power node, obtain the hardware performance information and resource occupancy information of the candidate computing power node; Determine a basic performance score based on the hardware performance information; Determining a dynamic performance score according to the resource occupancy information; The performance score of the candidate computing power node is determined according to the basic performance score and the dynamic performance score.

6. The method according to claim 2, It is characterized in that The current business demand is sent by the external network system to the computing power orchestration device, and the method further includes: Mapping the computing power identifier of the at least one target computing power node to a target computing power identifier corresponding to the external network system; Generate response information according to the target computing power identifier; The response information is fed back to the external network system.

7. The method according to any one of claims 1 to 6, It is characterized in that The computing power orchestration device is a primary edge server in the passive optical network system; the computing power gateway is a white box switching device connected to the computing power orchestration device; the device node includes at least one of an optical line terminal, an optical network terminal, an optical network unit, and a resource board of an optical line terminal; The cluster nodes include edge servers.

8. A passive optical network system, It is characterized in that The passive optical network system includes a computing power orchestration device and a plurality of computing power gateways connected to the computing power orchestration device, each of the computing power gateways is respectively connected to at least one computing power node, and the computing power node includes at least one of a device node and a cluster node; the computing power orchestration device is used to execute the steps of the method as described in any one of claims 1 to 7.

9. A communication device comprising a memory and a processor, wherein the memory stores a computer program, It is characterized in that When the processor executes the computer program, the steps of the method according to any one of claims 1 to 7 are implemented.

10. A computer-readable storage medium having a computer program stored thereon, It is characterized in that When the computer program is executed by a processor, the steps of the method according to any one of claims 1 to 7 are implemented.

Images