Computing power collaboration method and system in passive optical network, communication equipment and storage medium

Abstract

The invention relates to a computing power cooperation method, a computing power cooperation system, communication equipment and a computer readable storage medium in a passive optical network. The method comprises the following steps that: an OLT (Optical Line Terminal) computing power gateway receives a computing power calling request from a computing power arrangement system through a network management system of a passive optical network, or receives a computing power calling request from a service unit in the passive optical network; the computing power arrangement system calls computing power resources of the edge side computing power network and / or the passive optical network according to arrangement requirements; determining a corresponding scheduling strategy according to the business service level protocol and the computing power calling request; and calling a computing power node in the passive optical network to execute a computing task corresponding to the computing power calling request according to the scheduling strategy. According to the method, the OLT computing power gateway is used for achieving computing power cooperative scheduling of the OLT side in the PON network, the service SLA requirement can be met, computing power resources in the PON network are provided for the computing power network, and the maximization of the computing power utilization rate of the whole network is achieved.

Description

Technical Field

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

[0002] The computing network is a new computing architecture that integrates computing resources distributed in various locations into a unified computing platform through the network for users to obtain and use on demand. Computing resources such as CPU (Central Processing Unit), GPU (Graphics Processing Unit), storage, etc. The computing network introduces virtualization, scheduling and management technologies for computing resources, allowing decentralized computing resources to work together flexibly and efficiently, forming a highly scalable and elastic computing environment.

[0003] The core idea of ​​the computing network is to share and dispatch computing power as a service, similar to the traditional power network, where users can access the required computing resources through the network anytime and anywhere. Through this network, computing tasks can be dynamically allocated to the most suitable nodes for processing according to actual needs, thereby improving resource utilization, reducing latency, and enhancing system reliability and fault tolerance.

[0004] At present, computing power networks have broad application prospects in edge computing, 5G, smart manufacturing, smart cities, etc. It provides a distributed and efficient solution for complex computing tasks, which helps promote the construction and development of the next generation of information technology infrastructure.

[0005] With the rapid development of technologies such as big data, artificial intelligence, and the Internet of Things, the demand for computing resources has increased significantly. However, the traditional way of allocating computing resources has exposed several problems in responding to this challenge, especially in the comprehensive management and efficient use of computing resources. The traditional way of allocating computing resources mainly focuses on the computing resources in the computing network, which fails to fully utilize the computing resources in the PON (Passive Optical Network) system. In the traditional computing resource allocation system, there are differences between the computing network and the PON system in terms of technical standards, communication protocols, and interface design, which makes the sharing and scheduling of computing resources across systems complicated and inefficient. Summary of the invention

[0006] Based on this, it is necessary to provide a computing power coordination method, a computing power coordination system, a communication device and a computer-readable storage medium in a passive optical network to address the above-mentioned technical problems, which can provide computing power resources in the PON network for the computing power network and maximize the computing power utilization of the entire network.

[0007] In a first aspect, the present application provides a computing power coordination method in a passive optical network, the method being applied to an OLT computing power gateway of a passive optical network, comprising:

[0008] The network management system of the passive optical network receives a computing power call request from the computing power orchestration system, or receives a computing power call request from a business unit in the passive optical network; the computing power orchestration system is used to call the computing power resources of the edge side computing power network and / or the passive optical network according to the orchestration requirements;

[0009] Determine the corresponding scheduling strategy based on the business service level agreement and computing power call request;

[0010] According to the scheduling strategy, the computing power nodes in the passive optical network are called to execute the computing tasks corresponding to the computing power call request.

[0011] In one embodiment, the method further comprises:

[0012] If, according to the business service level agreement and the computing power call request, it is determined that the computing amount is not less than the first set value and the parallel amount is less than the second set value, the corresponding scheduling strategy is determined to be the first scheduling strategy;

[0013] According to the first scheduling strategy, the OLT general computing board in the passive optical network is called to execute the computing task corresponding to the computing power call request.

[0014] In one embodiment, the method further comprises:

[0015] If, according to the business service level agreement and the computing power call request, it is determined that the computing amount is less than the first set value and the parallel amount is not less than the second set value, the corresponding scheduling strategy is determined to be the second scheduling strategy;

[0016] According to the second scheduling strategy, multiple ONU computing nodes in the passive optical network are called to execute computing tasks corresponding to the computing power call request.

[0017] In one embodiment, the method further comprises:

[0018] If, according to the business service level agreement and the computing power call request, it is determined that the computing amount is not less than the first set value and the parallel amount is not less than the second set value, then the corresponding scheduling strategy is determined to be the third scheduling strategy;

[0019] According to the third scheduling strategy, the OLT general computing board and at least one ONU computing power node in the passive optical network are called to execute the computing task corresponding to the computing power call request.

[0020] In one embodiment, the method further comprises:

[0021] Receive computing power registration request sent by OLT general computing board or ONU computing power node;

[0022] The computing power is registered based on the computing power registration request, and the computing power identification information is issued.

[0023] In one embodiment, the method further comprises:

[0024] Receive resource allocation information from the computing power orchestration system through the network management system of the passive optical network;

[0025] According to the resource allocation information, corresponding resources are allocated to the OLT general computing board or ONU computing node.

[0026] In one embodiment, the method further comprises:

[0027] If it is detected that the computing power resources in the passive optical network do not match the computing power call request of the business unit, the computing power call request of the business unit is reported to the computing power orchestration system through the network management system.

[0028] In the second aspect, the present application also provides a computing power coordination system, which includes: a computing power orchestration system, an edge computing power network and a passive optical network; the passive optical network includes a network management system, an OLT computing power gateway and a computing power node; wherein:

[0029] A computing power orchestration system is used to call computing power resources of the edge computing power network and / or passive optical network according to the orchestration requirements;

[0030] The OLT computing power gateway is used to execute the steps of the method described in the first aspect above.

[0031] 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 steps of the method described in the first aspect above are implemented.

[0032] In a fourth aspect, the present application further provides a computer-readable storage medium having a computer program stored thereon, and when the computer program is executed by a processor, the steps of the method described in the first aspect above are implemented.

[0033] The computing power coordination method, computing power coordination system, communication equipment and computer-readable storage medium in the above-mentioned passive optical network, the OLT computing power gateway receives a computing power call request from the computing power orchestration system through the network management system of the passive optical network, or receives a computing power call request from a business unit in the passive optical network; the computing power orchestration system is used to call the computing power resources of the edge computing power network and / or the passive optical network according to the orchestration requirements; determine the corresponding scheduling strategy according to the business service level agreement and the computing power call request; according to the scheduling strategy, call the computing power node in the passive optical network to perform the computing task corresponding to the computing power call request. Through the above method, the OLT computing power gateway is used to realize the collaborative scheduling of computing power on the OLT side in the PON network, which can meet the business SLA requirements, provide the computing power network with computing power resources in the PON network, and maximize the computing power utilization of the entire network. It is suitable for access network scenarios such as homes, offices, factories, etc. that require collaborative scheduling of computing power. BRIEF DESCRIPTION OF THE DRAWINGS

[0034] 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.

[0035] FIG1 is a structural block diagram of a computing power coordination system in one embodiment;

[0036] FIG2 is a schematic diagram of a flow chart of a computing power coordination method in a passive optical network according to an embodiment;

[0037] FIG3 is a schematic flow chart of a computing power coordination method in a passive optical network according to another embodiment;

[0038] FIG4 is an overall architecture diagram of a computing power coordination system in one embodiment;

[0039] FIG. 5 is a diagram showing the internal structure of a communication device in one embodiment. DETAILED DESCRIPTION

[0040] 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.

[0041] The computing power coordination method in the passive optical network provided in the embodiment of the present application can be applied to the application environment as shown in Figure 1. Among them, the computing power orchestration system 102 is used to uniformly manage the computing power resources of the edge-side computing power network 104 and the passive optical network 106. Computing power coordination mainly divides computing power into two parts: edge computing power and PON-side computing power. The computing power management platform 1041 set in the edge-side computing power network 104 uniformly manages all edge computing power clusters. The network management system 1061 set in the passive optical network 106 sends specific scheduling tasks to the OLT (Optical Line Terminal) computing power gateway 1062. The OLT computing power gateway 1062 acts as an agent to uniformly manage the computing power resources in the PON network, including the computing power of the OLT general computing board and the computing power of the ONU (Optical Network Unit) computing power node.

[0042] In an exemplary embodiment, as shown in FIG. 2 , a computing power coordination method in a passive optical network is provided, and the method is applied to the OLT computing power gateway 1062 in FIG. 1 as an example for explanation, including:

[0043] Step 202, through the network management system of the passive optical network, receives a computing power call request from the computing power orchestration system, or receives a computing power call request from a business unit in the passive optical network; the computing power orchestration system is used to call the computing power resources of the edge side computing power network and / or the passive optical network according to the orchestration requirements.

[0044] It can be understood that this embodiment introduces a computing power coordination mechanism in the passive optical network (PON), manages the computing power on the PON side based on the network management system (Network Management System, referred to as NMS), so that the computing power orchestration system can realize the coordinated orchestration and scheduling of the edge side computing power and the PON side computing power. Among them, the NMS does not need to care about the details of the computing power, but only needs to send the specific computing power call request to the corresponding OLT computing power gateway. The OLT computing power gateway refers to the OLT device in the PON network. As the middleware for computing power coordination, it plans and executes the computing power orchestration tasks within the jurisdiction based on the traditional PON network model, and realizes the unified management of the PON network computing power. The PON network includes multiple OLT computing power gateways, and each OLT computing power gateway can perform computing power scheduling based on the computing power coordination method in the passive optical network provided in this application.

[0045] It should be noted that the OLT computing power gateway can be oriented to external users, that is, responding to the computing power call request issued by other network devices through the computing power orchestration system to perform computing power scheduling; it can also be oriented to users in the PON network, that is, responding to the computing power call request of the business unit in the passive optical network to perform computing power scheduling. Business units include OLT devices, ONU devices under the OLT computing power gateway, and so on.

[0046] Among them, the computing power orchestration system as the orchestration layer is responsible for coordinating the computing power and network scheduling on the edge side and PON side, decomposing the computing power tasks according to business needs, and formulating resource allocation strategies and network allocation strategies, which are sent to the computing power management platform in the edge computing power network and the network management system in the PON network to execute the scheduling strategy and realize one-time computing power scheduling. In the edge computing power network, each edge computing power cluster completes the perception and measurement of its own computing power equipment, and registers computing power to the computing power management platform, which sends computing power identification information and uniformly manages all edge computing power clusters. In the PON network, the OLT computing power gateway can perceive the OLT built-in general computing board (bureau-side computing power) and ONU (end-side computing power), and perform computing power registration, computing power measurement, computing power perception and other functions through the OLT device; the OLT computing power gateway receives the computing power call request sent by the NMS system to realize secondary computing power scheduling. In an optional implementation, the OLT computing power gateway receives a computing power call request from the upper-layer computing power orchestration system, and based on the secondary computing power scheduling method, schedules the computing tasks to the computing power nodes within the jurisdiction of the OLT computing power gateway according to business demands. In an optional implementation, the OLT computing power gateway receives a computing power call request sent by other business units within the jurisdiction, and performs subsequent operations based on the computing power call initiated by the OLT or ONU.

[0047] Step 204: Determine a corresponding scheduling strategy based on the business service level agreement and the computing power call request.

[0048] Among them, the business service level agreement (SLA) is a guarantee of the service quality provided by the computing network reached between the computing network customers and the computing network operators, which aims to clarify and quantify the service quality of computing power. The OLT computing power gateway takes the business SLA as the goal, comprehensively considers the computing power type (CPU / NPU / GPU), system load, storage consumption, network load, etc. within the jurisdiction, and reasonably schedules and determines the scheduling strategy corresponding to the business SLA and computing power call request.

[0049] It can be understood that the OLT computing power gateway can perceive the computing power information of each computing power node within the jurisdiction, determine the computing power nodes that meet the business SLA requirements based on the computing power information, and select appropriate computing power nodes from the computing power nodes that meet the business SLA requirements for computing power scheduling based on the key information such as the task type, computing amount, resource requirements, and priority corresponding to the computing power call request.

[0050] The scheduling strategy is a strategy for scheduling the computing resources of a specific computing node. In the specific implementation, different business SLAs and different computing call requests correspond to different scheduling strategies. By executing the scheduling strategy, the computing call request can be responded to and the requirements of the business SLA can be met.

[0051] It should be noted that the OLT computing power gateway can adopt the computing power scheduling method used by the traditional computing power management platform to determine the scheduling strategy, or it can adopt a specific computing power scheduling method, which is not limited in this embodiment.

[0052] Step 206: According to the scheduling strategy, the computing power node in the passive optical network is called to execute the computing task corresponding to the computing power call request.

[0053] Among them, the possible scheduling methods in the OLT computing power gateway include: (1) scheduling the computing task to the general computing board in the OLT frame, and the computing power node in the OLT completes the computing task and notifies the computing power caller of the execution result; (2) scheduling the computing task to a single or multiple ONUs under the jurisdiction of the OLT, and a single or multiple ONU computing power nodes jointly complete the computing task and notify the computing power caller of the execution result; (3) scheduling the computing task to the general computing board and at least one ONU in the OLT frame at the same time, and notifying the computing power caller of the execution result after the computing task is completed. Based on the computing power measurement function, the OLT computing power gateway comprehensively considers the load balancing of each computing power node in the jurisdiction, and maximizes the computing power utilization of the entire network while meeting the computing power service SLA.

[0054] In the above-mentioned computing power coordination method in the passive optical network, the OLT computing power gateway receives a computing power call request from the computing power orchestration system through the network management system of the passive optical network, or receives a computing power call request from the business unit in the passive optical network; the computing power orchestration system is used to call the computing power resources of the edge computing power network and / or the passive optical network according to the orchestration requirements; determine the corresponding scheduling strategy according to the business service level agreement and the computing power call request; according to the scheduling strategy, call the computing power node in the passive optical network to execute the computing task corresponding to the computing power call request. Through the above method, the OLT computing power gateway is used to realize the collaborative scheduling of computing power on the OLT side in the PON network, which can meet the business SLA requirements, provide the computing power network with computing power resources in the PON network, and maximize the computing power utilization of the entire network. It is suitable for access network scenarios such as homes, offices, and factories that require collaborative scheduling of computing power.

[0055] In an exemplary embodiment, the method also includes: if it is determined according to the business service level agreement and the computing power call request that the computing amount is not less than the first set value and the parallel amount is less than the second set value, then the corresponding scheduling strategy is determined to be the first scheduling strategy; according to the first scheduling strategy, the OLT general computing board in the passive optical network is called to execute the computing task corresponding to the computing power call request.

[0056] Among them, the first set value is a critical value set in advance for evaluating the scale of calculation. If the amount of calculation is not less than the first set value, the computing task corresponding to the computing power call request is a large-scale computing task; if the amount of calculation is less than the first set value, the computing task corresponding to the computing power call request is a small-scale computing task. The second set value is a critical value set in advance for evaluating the amount of parallelism. If the amount of calculation is not less than the second set value, the computing task corresponding to the computing power call request is a high-concurrency computing task; if the amount of calculation is less than the second set value, the computing task corresponding to the computing power call request is a low-concurrency computing task. Both the first set value and the second set value can be adjusted according to actual needs.

[0057] The OLT computing power gateway determines the corresponding resource guarantee and service level based on the business service level agreement. By analyzing the computing power call request, the computing amount of the computing task can be determined; by analyzing the business SLA, the response time can be determined. The OLT computing power gateway considers the load of each computing power node and determines the concurrency corresponding to the response time. Compare the computing amount with the first set value, and compare the parallel amount with the second set value. When the computing amount is not less than the first set value and the parallel amount is less than the second set value, it means that the computing task is a large-scale, low-concurrency task, and the first scheduling strategy is selected at this time.

[0058] Under the first scheduling strategy, the OLT computing power gateway considers the load balancing of each computing power node in the jurisdiction, selects the idlest OLT general computing board, and issues the computing task corresponding to the computing power call request. The first scheduling strategy is used to schedule the idlest OLT general computing board in the jurisdiction to execute the computing task corresponding to the computing power call request.

[0059] In this embodiment, for large-scale, low-concurrency computing tasks, the OLT general computing board is called to execute the computing tasks, which can meet the service SLA requirements and scheduling needs.

[0060] In an exemplary embodiment, the method also includes: if it is determined according to the business service level agreement and the computing power call request that the computing amount is less than the first set value and the parallel amount is not less than the second set value, then the corresponding scheduling strategy is determined to be the second scheduling strategy; according to the second scheduling strategy, multiple ONU computing power nodes in the passive optical network are called to execute the computing tasks corresponding to the computing power call request.

[0061] The OLT computing power gateway compares the amount of computation with the first set value and the amount of parallelism with the second set value. If the amount of computation is less than the first set value and the amount of parallelism is not less than the second set value, it means that the computing task is a small-scale, high-concurrency task, and the second scheduling strategy is selected.

[0062] Under the second scheduling strategy, the OLT computing power gateway considers the load balancing of each computing power node in the jurisdiction, selects the idlest multiple ONU computing power nodes, and divides the computing task corresponding to the computing power call request into multiple subtasks, which are sent to the selected multiple ONU computing power nodes respectively. The second scheduling strategy is used to schedule the idlest multiple ONU computing power nodes in the jurisdiction to execute the computing tasks corresponding to the computing power call request.

[0063] In this embodiment, for small-scale, high-concurrency computing tasks, multiple ONU computing nodes are called to perform computing tasks, which can meet business SLA requirements and scheduling needs.

[0064] In an exemplary embodiment, the method also includes: if it is determined according to the business service level agreement and the computing power call request that the computing amount is not less than the first set value and the parallel amount is not less than the second set value, then the corresponding scheduling strategy is determined to be a third scheduling strategy; according to the third scheduling strategy, the OLT general computing board and at least one ONU computing power node in the passive optical network are called to execute the computing task corresponding to the computing power call request.

[0065] The OLT computing power gateway compares the amount of calculation with the first set value and the amount of parallelism with the second set value. If the amount of calculation is not less than the first set value and the amount of parallelism is not less than the second set value, it means that the computing task is a large-scale, high-concurrency task, and the third scheduling strategy is selected at this time.

[0066] Under the third scheduling strategy, the OLT computing power gateway considers the load balancing of each computing power node in the jurisdiction, selects the idlest OLT general computing board and at least one ONU computing power node, and divides the computing task corresponding to the computing power call request into multiple subtasks, which are sent to the selected OLT general computing board and ONU computing power node respectively. The third scheduling strategy is used to schedule the idlest OLT general computing board and ONU computing power node in the jurisdiction to perform the computing task corresponding to the computing power call request.

[0067] In this embodiment, for large-scale, high-concurrency computing tasks, OLT general computing boards and ONU computing nodes are called to perform computing tasks, which can meet service SLA requirements and scheduling needs.

[0068] In an optional implementation, if it is determined that the amount of calculation is less than the first set value and the amount of parallelism is less than the second set value, the corresponding scheduling strategy is determined to be the fourth scheduling strategy; according to the fourth scheduling strategy, the idlest ONU computing power node in the passive optical network is called to execute the computing task corresponding to the computing power call request.

[0069] In an exemplary embodiment, the method further includes: receiving a computing power registration request sent by an OLT general computing board or an ONU computing power node; performing computing power registration based on the computing power registration request, and issuing computing power identification information.

[0070] Among them, the computing power registration method in the PON network includes: (1) the OLT computing power gateway performs the computing power registration process with the NMS system, and the NMS system sends the computing power identification information to the OLT computing power gateway; (2) the ONU and OLT general computing board card perform the computing power registration process with the OLT computing power gateway, and the OLT computing power gateway sends the computing power identification information to the OLT general computing board card or the ONU computing power node.

[0071] Optionally, OLT acts as a computing power gateway. When receiving a computing power registration request sent by the OLT general computing board or ONU computing power node, it needs to authenticate and authorize the device, and finally send the computing power identification information of the device to complete the registration process.

[0072] Computing power perception can provide a basis for computing power network orchestration and scheduling by capturing business computing power demand information and computing power resource information, thereby optimizing resource allocation. Computing power perception includes multi-dimensional perception of computing power nodes and business demand perception. For PON networks, the sources of business demand include external demand and PON side user terminal demand. In an optional implementation method, the OLT computing power gateway also has computing power perception capabilities. It can be understood that the computing power perception methods in the PON network include: (1) The OLT computing power gateway supports the perception of the computing power information of the OLT general computing board and the ONU computing power node; (2) The NMS system supports the overall computing power information perception of the OLT device.

[0073] Optionally, the computing power orchestration system supports the perception of business needs and achieves accurate matching of business with computing power by formulating computing power scheduling strategies. User demand from the PON side can be reported to the computing power orchestration system through the OLT computing power gateway to make subsequent decisions.

[0074] In an exemplary embodiment, as shown in FIG3 , the method further includes:

[0075] Step 302: Receive resource allocation information from the computing power orchestration system through the network management system of the passive optical network.

[0076] Step 304: allocate corresponding resources to the OLT general computing board or ONU computing node according to the resource allocation information.

[0077] Among them, the computing power orchestration system supports the allocation of resources for edge computing power networks and / or passive optical networks. The OLT computing power gateway receives resource allocation information through the NMS system and allocates computing, storage, and network resources to OLT general computing boards or ONU computing power nodes within the jurisdiction.

[0078] In this embodiment, the OLT computing power gateway can quickly respond to resource adjustments of the computing power orchestration system to achieve unified resource allocation.

[0079] In an exemplary embodiment, if it is detected that the computing power resources in the passive optical network do not match the computing power call request of the business unit, the computing power call request of the business unit is reported to the computing power orchestration system through the network management system.

[0080] Among them, for the computing power call request from the PON side, the OLT computing power gateway senses the computing power information of each computing power node in the PON network. If it is detected that the computing power scale of the PON network is small and the computing power resources cannot meet the needs of the computing power call request, the computing power call request is reported to the computing power orchestration system through the NMS system, and the computing power orchestration system makes subsequent decisions. In this way, when the computing power scale of the PON network is small, the edge side computing power can be added to expand the computing power scale.

[0081] 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.

[0082] Based on the same inventive concept, the embodiment of the present application also provides a computing power coordination system for implementing the computing power coordination method in the passive optical network involved above. The implementation scheme for solving the problem provided by the computing power coordination system is similar to the implementation scheme recorded in the above method, so the specific limitations in one or more computing power coordination system embodiments provided below can refer to the limitations of the computing power coordination method in the passive optical network above, and will not be repeated here.

[0083] In an exemplary embodiment, as shown in FIG1 , a computing power coordination system is provided, and the computing power coordination system includes: a computing power orchestration system 102, an edge computing power network 104, and a passive optical network 106; the passive optical network 106 includes a network management system 1061, an OLT computing power gateway 1062, and a computing power node (such as the ONU in FIG1 ); wherein:

[0084] The computing power orchestration system 102 is used to call the computing power resources of the edge computing power network 104 and / or the passive optical network 106 according to the orchestration requirements.

[0085] The OLT computing power gateway 1062 is used to execute the steps of the method described in any embodiment of the present application.

[0086] In the computing power coordination system in the above passive optical network, the OLT computing power gateway is used to realize the computing power coordination scheduling on the OLT side in the PON network, which can meet the service SLA requirements, provide computing power resources in the PON network for the computing power network, and maximize the computing power utilization of the entire network. It is suitable for access network scenarios such as homes, offices, and factories that require computing power coordination scheduling.

[0087] In an optional implementation, referring to FIG4 , the computing network collaborative scheduling adopted by the computing power collaborative system includes two parts: the computing network collaborative scheduling of the computing power orchestration layer (the primary computing power scheduling as shown in FIG4 ) and the secondary computing power collaborative scheduling (secondary computing power scheduling) on ​​the OLT side. The secondary computing power collaborative scheduling scheme on the OLT side is explained in the method embodiment of the present application. The computing network collaborative scheduling scheme of the computing power orchestration layer is further explained in this implementation.

[0088] It is understandable that computing network orchestration technology is used to solve the joint optimization problem of multi-dimensional resources. According to the resources or business needs of different users, heterogeneous computing resources and network resources are uniformly managed, integrated, and orchestrated, and the optimal resource selection and policy allocation are performed from a global perspective, thereby achieving flexible scheduling, elasticity, and release of resources, meeting the needs of different computing scenarios for bandwidth, latency, computing power, etc., and providing customers with on-demand, scenario-diverse, quality-aware cloud-network-edge integrated computing services. The computing network collaborative scheduling of the computing power orchestration layer mainly includes the following contents:

[0089] (1) Resource demand analysis: Analyze user business needs and convert user needs into different computing resource requirements according to different scenarios.

[0090] (2) Computing network orchestration: Based on the results of resource demand analysis, computing network orchestration technology decomposes some diverse and complex computing tasks into simplified and less complex computing tasks, comprehensively considers the computing processing capabilities of edge and PON computing nodes, as well as environmental factors such as data flow and user location, and performs integrated orchestration and unified policy scheduling of various factors, unified orchestration / encapsulation, seeks the optimal match of computing network resources, and formulates resource allocation strategies and network scheduling strategies. When the computing nodes on the PON side accept the orchestration of the computing orchestration layer, they will only send the accepted computing tasks to the OLT computing gateway, and will not schedule them to specific bureau-side or terminal-side computing power.

[0091] (3) Resource allocation: Inform each resource node to reserve resources according to the resource allocation strategy and update resource information data; allocate corresponding computing, storage, and network resources to users, and flexibly adjust according to changes in business needs.

[0092] (4) Network connection scheduling: Obtain network connection requirements based on network resource allocation. For example, what size of network connection needs to be established between which nodes, and what kind of service quality assurance is provided. According to these business requirements, the network control component is used to complete the computing network resource scheduling, route the business traffic to the optimal resource node, realize cross-domain network interoperability, improve user experience and network efficiency, and provide external services in an integrated form of computing power and network.

[0093] In addition, the computing network collaborative scheduling of the computing power orchestration layer also supports the reporting of computing power node performance through the computing power management platform on the edge side and the OLT computing power gateway on the PON side, so as to monitor the computing power performance of the equipment, and select the optimal computing power node in real time through various types of computing power information collection and reporting strategy configuration, and repair it in case of failure.

[0094] In an exemplary embodiment, the OLT computing power gateway 1062 is used to perform the following steps: receiving a computing power call request from a computing power orchestration system through a network management system of a passive optical network, or receiving a computing power call request from a business unit in a passive optical network; determining a corresponding scheduling strategy based on a business service level agreement and a computing power call request; and calling a computing power node in the passive optical network to execute a computing task corresponding to the computing power call request based on the scheduling strategy.

[0095] In an exemplary embodiment, the OLT computing power gateway 1062 is used to perform the following steps: if it is determined that the computing amount is not less than the first set value and the parallel amount is less than the second set value according to the business service level agreement and the computing power call request, then the corresponding scheduling strategy is determined to be the first scheduling strategy; according to the first scheduling strategy, the OLT general computing board in the passive optical network is called to execute the computing task corresponding to the computing power call request.

[0096] In an exemplary embodiment, the OLT computing power gateway 1062 is used to perform the following steps: if it is determined that the computing amount is less than the first set value and the parallel amount is not less than the second set value according to the business service level agreement and the computing power call request, then the corresponding scheduling strategy is determined to be the second scheduling strategy; according to the second scheduling strategy, multiple ONU computing power nodes in the passive optical network are called to execute the computing tasks corresponding to the computing power call request.

[0097] In an exemplary embodiment, the OLT computing power gateway 1062 is used to perform the following steps: if it is determined that the computing amount is not less than the first set value and the parallel amount is not less than the second set value according to the business service level agreement and the computing power call request, then the corresponding scheduling strategy is determined to be a third scheduling strategy; according to the third scheduling strategy, the OLT general computing board and at least one ONU computing power node in the passive optical network are called to execute the computing task corresponding to the computing power call request.

[0098] In an exemplary embodiment, the OLT computing power gateway 1062 is used to perform the following steps: receiving a computing power registration request sent by an OLT general computing board or an ONU computing power node; performing computing power registration based on the computing power registration request, and issuing computing power identification information.

[0099] In an exemplary embodiment, the OLT computing power gateway 1062 is used to perform the following steps: receiving resource allocation information from the computing power orchestration system through the network management system of the passive optical network; and allocating corresponding resources to the OLT general computing board or ONU computing power node according to the resource allocation information.

[0100] In an exemplary embodiment, the OLT computing power gateway 1062 is used to perform the following steps: if it is detected that the computing power resources in the passive optical network do not match the computing power call request of the business unit, the computing power call request of the business unit is reported to the computing power orchestration system through the network management system.

[0101] 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. The processor, the memory and the input / output interface are connected via a system bus, and the communication interface is connected to the system bus via the input / output interface. 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. When the computer program is executed by the processor, a computing power coordination method in a passive optical network is implemented.

[0102] 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.

[0103] 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: receiving a computing power call request from a computing power orchestration system through a network management system of a passive optical network, or receiving a computing power call request from a business unit in a passive optical network; the computing power orchestration system is used to call the computing power resources of an edge-side computing power network and / or a passive optical network according to the orchestration requirements; determining a corresponding scheduling strategy according to a business service level agreement and the computing power call request; and calling a computing power node in the passive optical network to execute a computing task corresponding to the computing power call request according to the scheduling strategy.

[0104] In one embodiment, when the processor executes the computer program, the following steps are also implemented: if it is determined that the computing amount is not less than the first set value and the parallel amount is less than the second set value according to the business service level agreement and the computing power call request, then the corresponding scheduling strategy is determined to be the first scheduling strategy; according to the first scheduling strategy, the OLT general computing board in the passive optical network is called to execute the computing task corresponding to the computing power call request.

[0105] In one embodiment, when the processor executes the computer program, the following steps are also implemented: if it is determined that the computing amount is less than the first set value and the parallel amount is not less than the second set value according to the business service level agreement and the computing power call request, then the corresponding scheduling strategy is determined to be the second scheduling strategy; according to the second scheduling strategy, multiple ONU computing power nodes in the passive optical network are called to execute the computing tasks corresponding to the computing power call request.

[0106] In one embodiment, when the processor executes the computer program, the following steps are also implemented: if it is determined that the computing amount is not less than the first set value and the parallel amount is not less than the second set value according to the business service level agreement and the computing power call request, then the corresponding scheduling strategy is determined to be the third scheduling strategy; according to the third scheduling strategy, the OLT general computing board and at least one ONU computing power node in the passive optical network are called to execute the computing task corresponding to the computing power call request.

[0107] In one embodiment, when the processor executes the computer program, the following steps are also implemented: receiving a computing power registration request sent by an OLT general computing board or an ONU computing power node; performing computing power registration based on the computing power registration request, and issuing computing power identification information.

[0108] In one embodiment, when the processor executes the computer program, the following steps are also implemented: receiving resource allocation information from the computing power orchestration system through the network management system of the passive optical network; and allocating corresponding resources to the OLT general computing board or ONU computing power node according to the resource allocation information.

[0109] In one embodiment, when the processor executes the computer program, the following steps are also implemented: if it is detected that the computing power resources in the passive optical network do not match the computing power call request of the business unit, the computing power call request of the business unit is reported to the computing power orchestration system through the network management system.

[0110] In one embodiment, a computer-readable storage medium is provided, on which a computer program is stored, and when the computer program is executed by a processor, the following steps are implemented: receiving a computing power call request from a computing power orchestration system through a network management system of a passive optical network, or receiving a computing power call request from a business unit in a passive optical network; the computing power orchestration system is used to call the computing power resources of an edge-side computing power network and / or a passive optical network according to the orchestration requirements; determining a corresponding scheduling strategy according to a business service level agreement and the computing power call request; and calling a computing power node in the passive optical network to execute a computing task corresponding to the computing power call request according to the scheduling strategy.

[0111] In one embodiment, when the computer program is executed by the processor, the following steps are also implemented: if it is determined that the computing amount is not less than the first set value and the parallel amount is less than the second set value according to the business service level agreement and the computing power call request, then the corresponding scheduling strategy is determined to be the first scheduling strategy; according to the first scheduling strategy, the OLT general computing board in the passive optical network is called to execute the computing task corresponding to the computing power call request.

[0112] In one embodiment, when the computer program is executed by the processor, the following steps are also implemented: if it is determined that the computing amount is less than the first set value and the parallel amount is not less than the second set value according to the business service level agreement and the computing power call request, then the corresponding scheduling strategy is determined to be the second scheduling strategy; according to the second scheduling strategy, multiple ONU computing power nodes in the passive optical network are called to execute the computing tasks corresponding to the computing power call request.

[0113] In one embodiment, when the computer program is executed by the processor, the following steps are also implemented: if it is determined that the computing amount is not less than the first set value and the parallel amount is not less than the second set value according to the business service level agreement and the computing power call request, then the corresponding scheduling strategy is determined to be the third scheduling strategy; according to the third scheduling strategy, the OLT general computing board and at least one ONU computing power node in the passive optical network are called to execute the computing task corresponding to the computing power call request.

[0114] In one embodiment, when the computer program is executed by the processor, the following steps are also implemented: receiving a computing power registration request sent by an OLT general computing board or an ONU computing power node; performing computing power registration based on the computing power registration request, and issuing computing power identification information.

[0115] In one embodiment, when the computer program is executed by the processor, the following steps are also implemented: receiving resource allocation information from the computing power orchestration system through the network management system of the passive optical network; and allocating corresponding resources to the OLT general computing board or ONU computing power node according to the resource allocation information.

[0116] In one embodiment, when the computer program is executed by the processor, the following steps are also implemented: if it is detected that the computing power resources in the passive optical network do not match the computing power call request of the business unit, the computing power call request of the business unit is reported to the computing power orchestration system through the network management system.

[0117] 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.

[0118] 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.

[0119] 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.

[0120] 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 power coordination method in a passive optical network, characterized in that: The method is applied to an OLT computing power gateway of a passive optical network, and the method comprises: Receiving a computing power call request from a computing power orchestration system, or receiving a computing power call request from a business unit in a passive optical network through a network management system of the passive optical network; the computing power orchestration system is used to call computing power resources of an edge side computing power network and / or a passive optical network according to orchestration requirements; Determine a corresponding scheduling strategy according to the business service level agreement and the computing power call request; According to the scheduling strategy, a computing power node in the passive optical network is called to execute the computing task corresponding to the computing power call request.

2. The method according to claim 1, characterized in that: The method further comprises: If, according to the business service level agreement and the computing power call request, it is determined that the computing amount is not less than the first set value and the parallel amount is less than the second set value, then the corresponding scheduling strategy is determined to be the first scheduling strategy; According to the first scheduling strategy, the OLT general computing board in the passive optical network is called to execute the computing task corresponding to the computing power call request.

3. The method according to claim 1, characterized in that The method further comprises: If, according to the business service level agreement and the computing power call request, it is determined that the computing amount is less than the first set value and the parallel amount is not less than the second set value, then the corresponding scheduling strategy is determined to be the second scheduling strategy; According to the second scheduling strategy, multiple ONU computing nodes in the passive optical network are called to execute the computing tasks corresponding to the computing power call request.

4. The method according to claim 1, characterized in that: The method further comprises: If, according to the business service level agreement and the computing power call request, it is determined that the computing amount is not less than the first set value and the parallel amount is not less than the second set value, then the corresponding scheduling strategy is determined to be the third scheduling strategy; According to the third scheduling strategy, the OLT general computing board and at least one ONU computing power node in the passive optical network are called to execute the computing task corresponding to the computing power call request.

5. The method according to any one of claims 1 to 4, characterized in that: The method further comprises: Receive computing power registration request sent by OLT general computing board or ONU computing power node; The computing power registration is performed based on the computing power registration request, and the computing power identification information is issued.

6. The method according to any one of claims 1 to 4, characterized in that The method further comprises: Receive resource allocation information from the computing power orchestration system through the network management system of the passive optical network; According to the resource allocation information, corresponding resources are allocated to the OLT general computing board or the ONU computing power node.

7. The method according to any one of claims 1 to 4, characterized in that The method further comprises: If it is detected that the computing power resources in the passive optical network do not match the computing power call request of the business unit, the computing power call request of the business unit is reported to the computing power orchestration system through the network management system.

8. A computing power coordination system, characterized in that: The computing power coordination system includes: a computing power orchestration system, an edge computing power network and a passive optical network; the passive optical network includes a network management system, an OLT computing power gateway and a computing power node; wherein: The computing power orchestration system is used to call the computing power resources of the edge-side computing power network and / or the passive optical network according to the orchestration requirements; The OLT computing power gateway is used to execute the steps of the method according to any one of claims 1 to 7.

9. A communication device, comprising a memory and a processor, wherein the memory stores a computer program, 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, 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