Calculation network resource scheduling method, device and system

Abstract

The invention discloses a computing network resource scheduling method, device and system, and solves the problem that a large number of deterministic services coexist and compete with each other in computing power and communication. A computing network resource scheduling method comprises the following steps: monitoring a running deterministic service; the deterministic service is an integral process formed by executing a plurality of applications in sequence; determining a computing power and computing network resource scheduling strategy according to the deterministic service; the computing network resource scheduling strategy comprises an independent deterministic service processing queue; and in response to existence of the upper and lower boundaries in which at least one deterministic service index does not meet convergence, updating the computing power and computing network resource scheduling strategy. The method can be used for designing an independent strategy algorithm for each deterministic service, and then adjustment and optimization are continuously carried out in the operation process according to the deterministic service monitoring result.

Description

Technical Field

[0001] The present application relates to the technical field of computing network resource scheduling, and in particular to a computing network resource scheduling method, device and system. Background Art

[0002] The Industrial Internet is a new type of infrastructure, application model and industrial ecology that deeply integrates the new generation of information and communication technology with the industrial economy. Through the comprehensive connection of people, machines, objects, systems, etc., a new manufacturing and service system covering the entire industrial chain and the entire value chain is built. The Industrial Internet is not a simple application of the Internet in industry, but an infrastructure for the digitalization, networking and intelligent transformation of industry. After adding edge computing and cloud computing services to traditional industrial control systems, there will be a large number of multi-application collaborative production scenarios in the Industrial Internet in the future, such as visual inspection, data mining and analysis, edge control, etc. There are strict timing and logical dependencies between industrial terminal applications, edge computing applications and cloud services, that is, some computing tasks are completed through remote edge computing or cloud services, and there are execution steps that are consistent with the industrial production process. The communication delay and computing delay of all steps will affect the overall performance indicators. This method calls the overall process composed of multiple application collaborative processes a deterministic service, which requires unified scheduling of computing network resources, so as to achieve the upper / lower boundaries of convergence for the entire service on multiple key indicators.

[0003] In industrial production lines, workshops, and parks, a large number of deterministic services will coexist, competing with each other in terms of computing power, communication, etc., and unified management and control are required. In the industrial Internet scenario, various types of equipment generally belong to the same owner and have a good foundation for global management and control.

[0004] Existing solutions generally configure industrial terminals, edge computing, network controllers, and cloud platforms independently, and each device runs tasks according to pre-set parameters or algorithms. The disadvantage is that there is no interface for dynamically coordinating configuration parameters between devices, resulting in the inability to adaptively adjust the configuration when the performance of some devices is affected by load changes, so that the entire multi-application collaboration process meets the overall deterministic service indicators. Considering that the collaborative process of multiple applications in industrial scenarios is a whole,

[0005] Therefore, there is an urgent need to design an independent strategy algorithm for all deterministic services, and then continuously adjust and optimize the technical solution based on the deterministic service monitoring results during operation. Summary of the invention

[0006] The embodiments of the present application provide a computing network resource scheduling method, device and system, which solve the problem of a large number of deterministic services coexisting and competing for computing power and communication with each other.

[0007] In a first aspect, an embodiment of the present application provides a computing network resource scheduling method, comprising the steps of:

[0008] Monitoring the running of deterministic services; the deterministic service is an overall process consisting of multiple applications executing in sequence;

[0009] Determining computing power and computing network resource scheduling strategies according to deterministic services; the computing network resource scheduling strategies include independent deterministic service processing queues;

[0010] In response to at least one deterministic service indicator not satisfying the upper and lower bounds of convergence, the computing power and computing network resource scheduling strategy is updated.

[0011] In one embodiment, monitoring a deterministic service comprises the following steps:

[0012] Determine a target application and a target device; the target application and the target device are applications and devices involved in the deterministic service;

[0013] Determining the performance of the local deterministic service link of the target device;

[0014] At least one deterministic service monitoring result of the deterministic service is saved in each detection cycle; the deterministic service monitoring result includes original data, calculation result data and configuration data.

[0015] In one embodiment, updating the computing power and computing network resource scheduling strategy specifically includes the following steps:

[0016] Obtain the mapping relationship between configuration data and computing network resource scheduling strategy;

[0017] Obtaining deterministic service monitoring results; the deterministic service monitoring results include configuration data; the configuration data includes a computing network resource scheduling strategy and corresponding strategy parameters mapped by the deterministic service;

[0018] A policy decision result is calculated according to the configuration data, the deterministic service monitoring result and the deterministic service demand; the policy decision result is used to modify the configuration of each device involved in the deterministic service.

[0019] In one of the embodiments, the policy decision result is saved in the form of a matrix, and the parameters include computing power configuration and network configuration.

[0020] In one of the embodiments, a deterministic service indicator includes at least one indicator of the deterministic service monitoring result.

[0021] In one embodiment, calculating the deterministic service indicator specifically includes the steps of:

[0022] Obtain monitoring results of the target device;

[0023] The deterministic service index is calculated according to the monitoring result of the target device; the deterministic service index includes the deterministic service demand, the monitoring result and the configuration parameter; the deterministic service demand is a set of target values ​​that meet the performance requirements of the deterministic service initiating device.

[0024] In the second aspect, the embodiment of the present application also provides a computing network resource scheduling device, which is used to implement the computing network resource scheduling method described in any one of the embodiments of the first aspect, including: a policy and service mapping submodule, which is used to determine the computing power and computing network resource scheduling strategy according to the deterministic service; and is also used to update the computing power and computing network resource scheduling strategy in response to the existence of at least one deterministic service indicator that does not meet the upper and lower boundaries of convergence. A service determinism evaluation submodule is used to monitor the running deterministic service.

[0025] In a third aspect, the embodiment of the present application further provides a computing network resource scheduling system, including the computing network resource scheduling device described in the second aspect, and further including: an edge computing server, which is a computing power facility that deploys a computing framework and supports the creation of new computing tasks based on remote requests. An industrial terminal, which is used to initiate deterministic services and upload deterministic demand parameters. A deterministic network, which is a network used to ensure the determinism of data flow performance.

[0026] In a fourth aspect, an embodiment of the present application further provides a computer-readable storage medium having a computer program stored thereon, wherein the program, when executed by a processor, implements a method as described in any embodiment of the first aspect.

[0027] In a fifth aspect, an embodiment of the present application further provides an electronic device, comprising a memory, a processor, and a computer program stored in the memory and executable on the processor, wherein the processor implements a method as described in any embodiment of the first aspect when executing the computer program.

[0028] At least one of the above technical solutions adopted in the embodiments of the present application can achieve the following beneficial effects:

[0029] It can be used to design independent strategy algorithms for each deterministic service, and then continuously adjust and optimize according to the deterministic service monitoring results during operation.

[0030] This application starts from the perspective of unified deterministic control of computing network resources, and designs a heterogeneous resource scheduling engine composed of multiple resource scheduling algorithms. This scheduling can be used to design independent policy algorithms for each deterministic service, and then continuously adjust and optimize according to the deterministic service monitoring results during operation. The engine monitors the application collaboration process of multiple devices and defines the multi-application workflow as a deterministic service. When the load of a device in the deterministic service changes and affects the performance of the deterministic service, the computing network resources of multiple devices are comprehensively adjusted to complete the deterministic service optimization. BRIEF DESCRIPTION OF THE DRAWINGS

[0031] The drawings described herein are used to provide a further understanding of the present application and constitute a part of the present application. The illustrative embodiments of the present application and their descriptions are used to explain the present application and do not constitute an improper limitation on the present application. In the drawings:

[0032] Figure 1 This is a flow chart of a computing network resource scheduling method according to an embodiment of the present application;

[0033] Figure 2 This is a schematic diagram of deterministic service indicators for an embodiment of the present application;

[0034] Figure 3 This is another flow chart of a computing network resource scheduling method according to an embodiment of the present application;

[0035] Figure 4 This is a structural diagram of a computing network resource scheduling device according to an embodiment of the present application;

[0036] Figure 5 This is a schematic diagram of network configuration parameters for an embodiment of the present application;

[0037] Figure 6 This is a structural diagram of a computing network resource scheduling system according to an embodiment of the present application;

[0038] Figure 7 It is a structural schematic diagram of an electronic device provided in an embodiment of the present application. DETAILED DESCRIPTION

[0039] In order to make the purpose, technical solution and advantages of the present application clearer, the technical solution of the present application will be clearly and completely described below in combination with the specific embodiments of the present application and the corresponding drawings. Obviously, the described embodiments are only part of the embodiments of the present application, not all of the embodiments. Based on the embodiments in the present application, all other embodiments obtained by ordinary technicians in this field without making creative work are within the scope of protection of the present application.

[0040] This application designs a computing network resource scheduling method, device and system for deterministic services. The device receives deterministic requirements and performance monitoring data uploaded by industrial terminals, and configures deterministic services composed of multiple applications according to the computing network scheduling strategy to ensure that the performance indicators of the entire deterministic service are within an acceptable range. This technology can be used in industrial scenarios, especially in cases where multiple devices collaborate to complete industrial processes, and the computing network resources of multiple devices are managed in a unified manner. Selecting different tasks for each deterministic service ensures the flexibility of resource scheduling, reduces the difficulty of system configuration, and realizes overall control of the computing network.

[0041] The technical solutions provided by various embodiments of the present application are described in detail below in conjunction with the accompanying drawings.

[0042] Figure 1 This is a flow chart of a computing network resource scheduling method according to an embodiment of the present application, including steps: 110 to 130.

[0043] Step 110: monitor the running deterministic service; the deterministic service is an overall process consisting of multiple applications executing in sequence;

[0044] In one embodiment, monitoring the deterministic service in step 110 specifically includes the steps of:

[0045] Step 110-1, determining a target application and a target device; the target application and the target device are applications and devices involved in a deterministic service;

[0046] Maintain deterministic services and record the target applications and target devices involved.

[0047] Step 110-2, determining the performance of the local deterministic service link of the target device;

[0048] Record the performance of each target device processing the local deterministic service link.

[0049] Step 110 - 3 : Save at least one deterministic service monitoring result of the deterministic service in each detection cycle; the deterministic service monitoring result includes original data, calculation result data and configuration data.

[0050] Each monitoring cycle saves a monitoring result of the deterministic service, including raw data, calculation result data, and configuration data.

[0051] For example, the original data includes a timestamp, a device number, and an application number.

[0052] The calculation result data includes delay, jitter, and deterministic service length.

[0053] The configuration data includes the scheduling strategy and strategy parameters selected by the deterministic service.

[0054] For example, the deterministic service monitoring module actively calls the remote interface to obtain real-time monitoring information of each device in a certain period. Each device actively reports the start and end timestamps of its own processing of deterministic services. When an abnormal event occurs or performance degradation is severe, the device needs to report information in a timely manner.

[0055] Calculate the monitoring results of indicators such as latency and latency jitter based on timestamps.

[0056] Step 120: Determine computing power and computing network resource scheduling strategies based on deterministic services; the computing network resource scheduling strategies include independent deterministic service processing queues;

[0057] For example, when a deterministic service monitoring result is updated, the mapping relationship between the deterministic service and the computing network resource scheduling policy in the deterministic service database will be searched. The deterministic service database records the computing network resource scheduling policy configured for each deterministic service. A deterministic service can only select one computing network resource scheduling policy, and one computing network resource scheduling policy can be used for multiple deterministic services.

[0058] The computing network resource scheduling strategy is an algorithm for scheduling computing power and network resources of various devices, taking deterministic service requirements, deterministic service monitoring data, and configuration parameters as inputs, and outputting strategy decision results. The strategy decision results can be used to modify the configuration of each device involved in the deterministic service, and support the optimization of the execution performance of the deterministic service.

[0059] Step 130: In response to at least one deterministic service indicator not satisfying the upper and lower boundaries of convergence, update the computing power and computing network resource scheduling strategy.

[0060] For example, the deterministic service monitoring result is a set of monitoring data for the deterministic service, and the number of monitoring result indicators should not be less than the number of indicators required by the deterministic service.

[0061] For another example, the service determinism evaluation module evaluates the service performance monitoring results. If the determinism of the entire deterministic service is acceptable, resource scheduling calculation and parameter deployment are not re-performed. If the determinism is unacceptable, the deterministic service indicator SLA is used as input and passed to the corresponding instance of the selected strategy for processing.

[0062] For example, a computing network deterministic controller manages the network controllers, edge computing devices, terminal devices, and cloud services in the network, monitors the deterministic services running on these devices, selects computing power and network scheduling strategies for deterministic services, and periodically optimizes the configuration of each device in the deterministic service.

[0063] The deterministic service is an overall process consisting of multiple applications executing in sequence, which requires unified scheduling of computing network resources. Multiple key indicators of the entire service meet the upper / lower boundaries of convergence, such as deterministic service delay, deterministic service delay jitter, deterministic service bandwidth, deterministic service throughput, etc.

[0064] In one embodiment, the updating of computing power and computing network resource scheduling strategy in step 130 specifically includes the following steps:

[0065] Step 130-1, obtaining a mapping relationship between configuration data and computing network resource scheduling strategy;

[0066] After the deterministic service monitoring results are updated, the deterministic service and policy mapping relationship in the deterministic service database will be searched. The deterministic service database records the computing network resource scheduling policy configured for each deterministic service. A deterministic service can only select one computing network resource scheduling policy, and one computing network resource scheduling policy can be used for multiple deterministic services.

[0067] Step 130-2, obtaining a deterministic service monitoring result; the deterministic service monitoring result includes configuration data; the configuration data includes a computing network resource scheduling strategy and corresponding strategy parameters mapped by the deterministic service;

[0068] The service performance monitoring results are evaluated by the service certainty evaluation module.

[0069] Step 130-3: Calculate a policy decision result based on the configuration data, the deterministic service monitoring result and the deterministic service demand; the policy decision result is used to modify the configuration of each device involved in the deterministic service.

[0070] If the determinism of the entire deterministic service is acceptable, resource scheduling calculation and parameter deployment will not be re-performed. If the determinism is unacceptable, the deterministic service indicator SLA is used as input and passed to the corresponding instance of the selected strategy for processing.

[0071] It should be noted that when the policy instance runs an algorithm that requires training, determinism is not considered and all monitoring results are handled by the policy instance. After the policy instance obtains the deterministic service indicator, it first extracts valid monitoring data based on the algorithm, then performs training or classification operations, and obtains the parameter adjustment results of each device based on the weight of the computing network resources.

[0072] Each policy instance only runs one computing network resource scheduling strategy. Each instance is independent and can process a large number of deterministic service optimizations concurrently.

[0073] It should be noted that a policy instance cluster is a plurality of policy threads running in parallel, each thread processing a specific policy calculation task, forming a multi-queue for processing a variety of policies.

[0074] The policy decision result can be saved in a variety of forms, but since the matrix is ​​more efficient when implemented in hardware and is more convenient to index, it is faster to process using matrix operations. Therefore, preferably, the policy decision result is saved in the form of a matrix, and the parameters include computing power configuration and network configuration.

[0075] The policy instance outputs a new computing network resource scheduling plan and outputs the parameter adjustment results in the form of a policy decision matrix. The policy matrix is ​​a matrix that only contains quantitative parameters and needs to be translated by the southbound interface conversion module into the configuration interface data of each device. The policy matrix can be a matrix consisting of all device parameters or a separate matrix for each device.

[0076] For example, the policy decision results are saved in the form of a matrix, and the parameters include computing power configuration and network configuration. The matrix data can be the absolute value or relative value of each device configuration, which is determined by the actual system.

[0077] The policy decision results can be split into configuration change parameters for each device. Network configuration parameters include but are not limited to latency update value, jitter update value, and bandwidth update value. Edge computing configuration parameters include but are not limited to computing latency update value, computing jitter update value, throughput update value, and periodic update value. Industrial terminal configuration parameters include but are not limited to periodic update value, computing migration parameter update, and throughput update value.

[0078] In one of the embodiments, a deterministic service indicator includes at least one indicator of the deterministic service monitoring result.

[0079] Furthermore, if Figure 2 As shown, in one embodiment, calculating the deterministic service indicator described in step 130 specifically includes the steps of:

[0080] Step 210: Obtain monitoring results of the target device;

[0081] The deterministic service monitoring module actively calls the remote interface to obtain real-time monitoring information of each device in a certain period. Each device actively reports the start and end timestamps of its own processing of deterministic services. When an abnormal event occurs or performance degradation is severe, the device needs to report information in a timely manner.

[0082] Calculate the monitoring results of indicators such as latency and latency jitter based on timestamps.

[0083] Step 220: Calculate a deterministic service index based on the monitoring result of the target device; the deterministic service index includes a deterministic service requirement, a monitoring result, and a configuration parameter; the deterministic service requirement is a set of target values ​​that meet the performance requirements of the deterministic service initiating device.

[0084] It should be noted that the closer the execution result of the entire process is to the deterministic service requirements, the higher the determinism and the better the efficiency of deterministic service execution;

[0085] The deterministic service index needs to be calculated based on the performance indicators of all participating devices, and mainly includes five relationships: sum, maximum value, minimum value, least common multiple, and greatest common divisor.

[0086] The summation means that the deterministic service indicator is equal to the algebraic sum of all link indicators, such as latency, deterministic service chain length, etc.

[0087] The maximum value means that the deterministic service indicator is equal to the maximum value of all link indicators, such as delay jitter, data packet length, etc.

[0088] The minimum value means that the deterministic service indicator is equal to the minimum value of all link indicators, such as bandwidth, throughput, etc.

[0089] The least common multiple means that the deterministic service indicator is equal to the least common multiple of all link indicators, such as cycle.

[0090] The greatest common divisor means that the deterministic service indicator is equal to the greatest common divisor of all link indicators, such as computing time slices.

[0091] Finally, all data is stored in the deterministic service database for training, analysis and statistics of the algorithms in the strategy.

[0092] The process of summarizing deterministic service indicators is as follows: Figure 3 As shown in Figure 2, deterministic service requirements, monitoring results, and configuration parameters together constitute deterministic service indicators.

[0093] In one embodiment, the method further comprises the steps of:

[0094] Classified deterministic services pass input data to specific policy instances based on the mapped resource scheduling strategy.

[0095] In one embodiment, the method further comprises the steps of:

[0096] Evaluate the current performance of deterministic services and determine whether to recalculate the configuration of each device.

[0097] In one embodiment, the method further comprises the steps of:

[0098] Build a database to store multiple computing network integrated scheduling algorithms, which is used to store the mapping relationship between configuration data and computing network resource scheduling strategies.

[0099] In one embodiment, the method further comprises the steps of:

[0100] The multi-dimensional deterministic service indicators of multiple devices form an output matrix.

[0101] In one embodiment, the method further comprises the steps of:

[0102] Store the computing and communication links of deterministic services, and record the execution order and association of each link;

[0103] Historical data is the recent performance monitoring results of various deterministic services and is used for training and analysis.

[0104] In one embodiment, the deterministic service includes configuration of industrial terminals, network controllers, edge computing devices, and cloud services.

[0105] In one embodiment, the method further comprises the steps of:

[0106] Translating indicators into the configuration of industrial terminals, network controllers, edge computing devices, and cloud services involved in deterministic services.

[0107] Figure 4 This is a structural diagram of a computing network resource scheduling device according to an embodiment of the present application, which is used to implement the computing network resource scheduling method according to any one of the embodiments of the first aspect. The computing network resource scheduling device 510 (i.e., the computing network deterministic controller) is responsible for the management, maintenance and control of deterministic services, including:

[0108] The computing-network integrated scheduling engine 511 is composed of a policy and service mapping submodule 5111 , a service certainty evaluation submodule 5112 , a policy instance cluster submodule 5113 , a policy library 5114 and a policy decision matrix 5115 .

[0109] like Figure 4 As shown, the computing network integrated scheduling engine is responsible for performing calculations based on the monitoring results, and outputting the adjustment results of each link of the deterministic service using the computing network resource scheduling algorithm in the policy library.

[0110] The policy and service mapping submodule is used to classify deterministic services and pass the input data to a specific policy instance according to the mapped computing network resource scheduling policy.

[0111] Specifically used to determine the computing power and computing network resource scheduling strategy based on the deterministic service; also used to update the computing power and computing network resource scheduling strategy in response to the existence of at least one deterministic service indicator that does not meet the upper and lower boundaries of convergence

[0112] The service determinism evaluation submodule is used to evaluate the current performance of the deterministic service and determine whether to recalculate the configuration of each device.

[0113] Specifically used to monitor the running deterministic services; evaluate the current performance of deterministic services, and determine to recalculate the configuration of each device.

[0114] The policy instance cluster submodule is a group of independently running policy execution entities.

[0115] For example, the policy instance cluster submodule is a group of independently run policy execution entities, which can be threads or specific functions. Each policy instance can handle the computing network scheduling calculation of a policy. The overall multi-objective planning can be performed on the indicators related to computing power and network, and the algorithms include those based on parameter prediction strategies, machine learning algorithms, and particle swarm algorithms. The deterministic configuration can be obtained through multiple rounds of self-learning, and the initialization configuration can be obtained through historical data training. Throughout the life cycle of the deterministic service, the deterministic performance of the deterministic service will be continuously monitored, and then continuously optimized according to the strategy.

[0116] The policy library is used to store the mapping relationship between configuration data and computing network resource scheduling policies.

[0117] The strategy library is a database that stores multiple computing-network integrated scheduling algorithms, which facilitates the unified management of multiple strategies in industrial scenarios.

[0118] The policy decision matrix is ​​used to construct an output matrix of multi-dimensional deterministic service indicators of multiple devices.

[0119] The policy decision matrix is ​​the network scheduling result of the policy, and the multi-dimensional indicators of multiple devices form an output matrix.

[0120] Furthermore, the computing network integrated scheduling engine saves multiple policy files, which are used to store each resource scheduling policy. The computing network integrated scheduling engine generates a series of policy instances based on the policy files. Each policy instance has an independent deterministic service processing queue, which supports parallel optimization of a large number of deterministic services in the entire system.

[0121] Figure 6 This is a structural diagram of a computing network resource scheduling system according to an embodiment of the present application, including the computing network resource scheduling device described in the second aspect,

[0122] The deterministic service database 512 is a module for storing deterministic service information and historical data. It stores the computing and communication links of deterministic services, and records the execution order and association of each link. The historical data is the recent performance monitoring results of each deterministic service, which is used for training and analysis.

[0123] The management module 513 is used to provide control functions for the monitoring module and the computing-network integrated scheduling engine, configure monitoring parameters and monitoring cycles of deterministic services, and configure mapping relationships between deterministic services and policies.

[0124] The deterministic service monitoring module 514 monitors each device involved in the deterministic service and obtains monitoring results such as latency, jitter, packet loss rate, throughput, bandwidth, and cycle in real time.

[0125] The southbound interface conversion module 515 is a module that translates the indicators in the policy decision matrix into the configuration of industrial terminals, network controllers, edge computing devices, and cloud services involved in deterministic services.

[0126] The southbound interface conversion module translates the policy matrix, generates network configuration parameters, edge computing configuration parameters, and industrial terminal configuration parameters, then calls the southbound interface to send them to various devices, receives feedback from each device, and determines whether the configuration is successful.

[0127] The computing network deterministic controller is a software or device that globally controls the network and computing power determinism. It supports deterministic control of multi-application collaboration processes and can configure deterministic policies for deterministic services. Deterministic services are the sum of a series of applications that have business logic dependencies and communication dependencies, including application execution processes and inter-application communication processes. The guarantee of deterministic services means scheduling resources in communication processes and computing processes to ensure that parameters such as latency, jitter, and bandwidth in the deterministic service links converge within upper and lower boundary values. The computing network integrated scheduling engine adjusts the performance indicators of deterministic services based on the monitoring results of deterministic services and different strategies, and splits the overall indicators into the configuration of each device and distributes them.

[0128] Furthermore, the computing network resource scheduling device also includes:

[0129] The edge computing server 520 is a computing facility that deploys a computing framework and supports the creation of new computing tasks based on remote requests.

[0130] The industrial terminal 530 is used to initiate a deterministic service and upload deterministic demand parameters.

[0131] For example, the industrial terminal is a digital device used to implement the production process, supports unified management of the computing network deterministic controller, and can actively initiate deterministic services and upload deterministic demand parameters.

[0132] The deterministic network 540 is a network used to ensure the determinism of data flow performance, such as TSN and Detnet.

[0133] Furthermore, a cloud service 550 is also included for remote calling.

[0134] This application proposes a computing network resource scheduling method, device and system for deterministic services. Through the requirements, monitoring results and policy configuration of deterministic services, the application collaborative process of multiple devices configures the computing network integrated scheduling strategy to achieve top-down indicator regulation. When the equipment in some deterministic services changes load, fails or even crashes, the new network edge cloud configuration can be dynamically adjusted from the perspective of the entire deterministic service business flow.

[0135] Those skilled in the art will appreciate that embodiments of the present invention may be provided as methods, systems, or computer program products. Therefore, the present invention may take the form of a complete hardware embodiment, a complete software embodiment, or an embodiment combining software and hardware. Moreover, the present invention may take the form of a computer program product implemented on one or more computer-usable storage media (including but not limited to disk storage, CD-ROM, optical storage, etc.) containing computer-usable program code.

[0136] Therefore, the present application also proposes a computer-readable storage medium on which a computer program is stored. When the program is executed by a processor, the method described in any embodiment of the present application is implemented.

[0137] Furthermore, the present application also proposes an electronic device, comprising a memory, a processor, and a computer program stored in the memory and executable on the processor, wherein the processor implements the method described in any embodiment of the present application when executing the computer program.

[0138] The present invention is described with reference to flowcharts and / or block diagrams of methods, devices (systems), and computer program products according to embodiments of the present invention. It should be understood that each process and / or block in the flowchart and / or block diagram, as well as the combination of processes and / or blocks in the flowchart and / or block diagram, can be implemented by computer program instructions. These computer program instructions can be provided to a processor of a general-purpose computer, a special-purpose computer, an embedded processor, or other programmable data processing device to produce a machine, so that the instructions executed by the processor of the computer or other programmable data processing device generate instructions for implementing the processes in the flowchart and / or block diagram. Figure 1 A process or multiple processes and / or boxes Figure 1 A device that provides the functions specified in a block or multiple blocks.

[0139] These computer program instructions may also be stored in a computer-readable memory capable of directing a computer or other programmable data processing device to operate in a specific manner, so that the instructions stored in the computer-readable memory produce an article of manufacture comprising an instruction device, which implements the process Figure 1 A process or multiple processes and / or boxes Figure 1 A function specified in one or more boxes.

[0140] These computer program instructions can also be loaded onto a computer or other programmable data processing device so that a series of operating steps are executed on the computer or other programmable device to produce a computer-implemented process, thereby providing instructions for implementing the process. Figure 1 A process or multiple processes and / or boxes Figure 1 The steps for the functions specified in one or more boxes.

[0141] In a typical configuration, a computing device includes one or more processors (CPU), input / output interfaces, network interfaces, and memory. The memory may include non-permanent storage in a computer-readable medium, random access memory (RAM) and / or non-volatile memory in the form of read-only memory (ROM) or flash RAM. Memory is an example of a computer-readable medium.

[0142] Figure 7 600 is a schematic diagram of the structure of an electronic device provided in an embodiment of the present application. The electronic device 600 shown is only an example and should not bring any limitation to the functions and scope of use of the embodiment of the present application. It includes: one or more processors 620; a storage device 610, which is used to store one or more programs. When the one or more programs are run by the one or more processors 620, the one or more processors 620 implement the computing network resource scheduling method provided in the embodiment of the present application. The method includes:

[0143] Monitoring the running of deterministic services; the deterministic service is an overall process consisting of multiple applications executing in sequence;

[0144] Determining computing power and computing network resource scheduling strategies according to deterministic services; the computing network resource scheduling strategies include independent deterministic service processing queues;

[0145] In response to at least one deterministic service indicator not satisfying the upper and lower bounds of convergence, the computing power and computing network resource scheduling strategy is updated.

[0146] The electronic device 600 further includes an input device 630 and an output device 640; the processor 620, storage device 610, input device 630 and output device 640 in the electronic device can be connected via a bus or other means, and the figure takes the connection via a bus 650 as an example.

[0147] The storage device 610, as a computer-readable storage medium, can be used to store software programs, computer executable programs, and module units, such as program instructions corresponding to the method for determining the cloud bottom height in the embodiment of the present application. The storage device 610 may mainly include a storage program area and a storage data area, wherein the storage program area may store an operating system, an application required for at least one function; the storage data area may store data created according to the use of the terminal, etc. In addition, the storage device 610 may include a high-speed random access memory, and may also include a non-volatile memory, such as at least one disk storage device, a flash memory device, or other non-volatile solid-state storage device. In some instances, the storage device 610 may further include a memory remotely arranged relative to the processor 620, and these remote memories may be connected via a network. Examples of the above-mentioned network include, but are not limited to, the Internet, an intranet, a local area network, a mobile communication network, and combinations thereof.

[0148] The input device 630 may be used to receive input numbers, character information or voice information, and generate key signal input related to user settings and function control of the electronic device. The output device 640 may include electronic devices such as a display screen and a speaker.

[0149] It should also be noted that the terms "include", "comprises" or any other variations thereof are intended to cover non-exclusive inclusion, so that a process, method, commodity or device including a series of elements includes not only those elements, but also other elements not explicitly listed, or also includes elements inherent to such process, method, commodity or device. In the absence of more restrictions, the elements defined by the sentence "comprises a ..." do not exclude the existence of other identical elements in the process, method, commodity or device including the elements.

[0150] The above is only an embodiment of the present application and is not intended to limit the present application. For those skilled in the art, the present application may have various changes and variations. Any modification, equivalent replacement, improvement, etc. made within the spirit and principle of the present application should be included in the scope of the claims of the present application.

Claims

1. A computing network resource scheduling method, characterized in that: Includes steps: Monitoring the running of deterministic services; the deterministic service is an overall process consisting of multiple applications executing in sequence; Determining computing power and computing network resource scheduling strategies according to deterministic services; the computing network resource scheduling strategies include independent deterministic service processing queues; In response to at least one deterministic service indicator not satisfying the upper and lower bounds of convergence, the computing power and computing network resource scheduling strategy is updated.

2. The computing network resource scheduling method according to claim 1, characterized in that: Monitoring deterministic services includes the following steps: Determine a target application and a target device; the target application and the target device are applications and devices involved in the deterministic service; Determining the performance of the local deterministic service link of the target device; At least one deterministic service monitoring result of the deterministic service is saved in each detection cycle; the deterministic service monitoring result includes original data, calculation result data and configuration data.

3. The computing network resource scheduling method according to claim 1, characterized in that: Update the computing power and computing network resource scheduling strategy, including the following steps: Obtain the mapping relationship between configuration data and computing network resource scheduling strategy; Obtaining deterministic service monitoring results; the deterministic service monitoring results include configuration data; the configuration data includes a computing network resource scheduling strategy and corresponding strategy parameters mapped by the deterministic service; Calculating a policy decision result based on the configuration data, the deterministic service monitoring result and the deterministic service demand; The policy decision result is used to modify the configuration of each device involved in the deterministic service.

4. The computing network resource scheduling method according to claim 1, characterized in that: Calculate the deterministic service indicator, including the following steps: Obtain monitoring results of the target device; The deterministic service index is calculated according to the monitoring result of the target device; the deterministic service index includes the deterministic service demand, the monitoring result and the configuration parameter; the deterministic service demand is a set of target values ​​that meet the performance requirements of the deterministic service initiating device.

5. The computing network resource scheduling method according to claim 3, characterized in that: The policy decision results are saved in the form of a matrix, and the parameters include computing power configuration and network configuration.

6. The computing network resource scheduling method according to claim 3, characterized in that: A deterministic service indicator has at least one indicator of the deterministic service monitoring result.

7. A computing network resource scheduling device, characterized in that: The method for implementing the computing network resource scheduling method according to any one of claims 1 to 6 comprises: A policy and service mapping submodule, used to determine the computing power and computing network resource scheduling strategy according to the deterministic service; and also used to update the computing power and computing network resource scheduling strategy in response to the existence of at least one deterministic service indicator that does not meet the upper and lower boundaries of convergence; The service determinism assessment submodule is used to monitor the running deterministic services.

8. A computing network resource scheduling system, characterized in that: The computing network resource scheduling device according to claim 7 further comprises: Edge computing servers are computing facilities that deploy computing frameworks and support the creation of new computing tasks based on remote requests. Industrial terminals are used to initiate deterministic services and upload deterministic demand parameters; Deterministic network, a network used to ensure the determinism of data flow performance.

9. A computer-readable storage medium having a computer program stored thereon, characterized in that: When the program is executed by a processor, the method according to any one of claims 1 to 6 is implemented.

10. An electronic device comprising a memory, a processor and a computer program stored in the memory and executable on the processor, characterized in that: When the processor executes the computer program, the method according to any one of claims 1 to 6 is implemented.

Images