Calculation network resource configuration and scheduling method

Abstract

The invention relates to a computing network resource configuration and scheduling method. The method comprises the following steps: deconstructing computing power resources based on a user demand; performing scheduling operation on a to-be-processed task required by a user based on the computing power resource and a preset idle resource; and idle resources, computing power resources and corresponding scheduling algorithms are monitored and updated. According to the method, the requirements are collected in a guiding mode, a question and answer mode and other modes, the service attributes in the requirements are extracted, and the service requirements are converted into the detailed requirements and parameters of the computing network resources in combination with the resource template library and the application requirement analysis algorithm; based on operational performance, network performance, load balancing, cost, energy consumption and other arrangement factors, a multi-factor library oriented to multiple scenes is established, measurement and calculation of the factors are supported, and time delay priority, cost priority, energy consumption priority, performance priority and other arrangement scheduling strategies are provided.

Description

Technical Field

[0001] The present application relates to the technical field of electronic information technology, and in particular to a method for configuring and scheduling computing network resources. Background Art

[0002] With the advent of the intelligent era, more and more industries and even people's lives require a lot of computing power and network resources. Algorithmic resource allocation and scheduling are key issues in computer systems, cloud computing, distributed systems, and operating systems. They involve how to effectively allocate and manage computing resources (such as CPU, memory, storage, network bandwidth, etc.) to perform tasks or jobs. These tasks may include computing-intensive applications, data processing tasks, virtual machine scheduling, etc. Algorithmic resource allocation and scheduling aims to optimize resource utilization efficiency, improve system performance, meet service quality requirements, and ensure fairness and real-time performance.

[0003] In the existing technology, computing network resources are scattered. There are not enough in places with high demand, and there are many idle resources in private data rooms in other places, resulting in insufficient use of the entire domestic computing network resources and low utilization rate of domestic computing network resources. Summary of the invention

[0004] Based on this, it is necessary to provide a network resource configuration and scheduling method, device, computer equipment, computer-readable storage medium and computer program product to enhance the utilization rate of network resources in response to the above technical problems.

[0005] In a first aspect, the present application provides a computing network resource scheduling method. The method includes:

[0006] Deconstruct computing resources based on user needs;

[0007] Scheduling tasks to be processed based on the computing resources and preset idle resources;

[0008] Monitor and update idle resources and computing resources as well as the corresponding scheduling algorithms.

[0009] In one embodiment, the operation of scheduling tasks to be processed based on computing resources and preset idle resources includes:

[0010] Construct required tasks and corresponding initial priorities based on user needs;

[0011] Update required tasks and corresponding update priorities under preset conditions;

[0012] The tasks to be processed according to user requirements are scheduled based on the update priority and preset idle resources.

[0013] In one embodiment, updating the required tasks and the corresponding update priorities under preset conditions include:

[0014] Statistics on waiting time corresponding to user needs;

[0015] The corresponding update priority is calculated based on the waiting time, the preset update coefficient and the initial priority.

[0016] In one embodiment, the response time and completion time corresponding to the user demand are counted, the response time is the time corresponding to the uploading of the user demand to the start of the scheduling process, and the completion time is the time corresponding to the start of the scheduling process of the user demand to the completion of the user demand processing;

[0017] The update coefficient is optimized based on the response time and the completion time.

[0018] In one of the embodiments, after optimizing the update coefficient based on the response time and completion time, the method further includes:

[0019] Obtain similarity update coefficients and corresponding historical scheduling data;

[0020] Compare historical dispatch data with dispatch data;

[0021] If the historical scheduling data is not greater than the scheduling data, the pending tasks required by the user are scheduled based on the initial priority and the preset idle resources;

[0022] If the historical scheduling data is greater than the scheduling data, the pending tasks required by the user are scheduled based on the update priority and the preset idle resources.

[0023] In one of the embodiments, the corresponding increase trend of historical scheduling data within a preset time is counted;

[0024] If the historical growth trend is greater than the growth trend, the pending tasks required by the user are scheduled based on the initial priority and the preset idle resources;

[0025] If the historical increase trend is not greater than the increase trend, then the increase efficiency corresponding to the increase trend is calculated based on the waiting time to see whether it is greater than the historical increase efficiency corresponding to the historical increase trend;

[0026] If the amplification efficiency is greater than the historical amplification efficiency, the pending tasks required by the user are scheduled based on the update priority and the preset idle resources.

[0027] In a second aspect, the present application also provides a computing network resource configuration, which includes:

[0028] The computing power structure module is used to deconstruct computing power resources based on user needs;

[0029] An algorithm scheduling module is used to select a corresponding scheduling algorithm based on the computing power resources and preset idle resources to schedule the pending tasks required by the user;

[0030] The resource update module is used to update idle resources and computing resources as well as the corresponding scheduling algorithms in real time.

[0031] In a third aspect, the present application further provides a computer device. The computer device includes a memory and a processor, the memory stores a computer program, and the processor implements the following steps when executing the computer program:

[0032] Deconstruct computing resources based on user needs;

[0033] Scheduling tasks to be processed based on the computing resources and preset idle resources;

[0034] Monitor and update idle resources and computing resources as well as the corresponding scheduling algorithms.

[0035] In a fourth aspect, the present application further provides a computer-readable storage medium. The computer-readable storage medium stores a computer program, and when the computer program is executed by a processor, the following steps are implemented:

[0036] Deconstruct computing resources based on user needs;

[0037] Scheduling tasks to be processed based on the computing resources and preset idle resources;

[0038] Monitor and update idle resources and computing resources as well as the corresponding scheduling algorithms.

[0039] In a fifth aspect, the present application further provides a computer program product. The computer program product includes a computer program, and when the computer program is executed by a processor, the following steps are implemented:

[0040] Deconstruct computing resources based on user needs;

[0041] Scheduling tasks to be processed based on the computing resources and preset idle resources;

[0042] Monitor and update idle resources and computing resources as well as the corresponding scheduling algorithms.

[0043] The above-mentioned computing network resource configuration and scheduling method, device, computer equipment, storage medium and computer program product deconstruct computing power resources based on user needs; schedule pending tasks of user needs based on the computing power resources and preset idle resources; monitor and update idle resources and computing power resources and corresponding scheduling algorithms. This application adopts the above-mentioned method to collect requirements through various methods such as guidance and question-and-answer, extract business attributes in the requirements, and convert business requirements into detailed requirements and parameters of computing network resources in combination with resource template library and application requirement parsing algorithm; based on scheduling factors such as computing performance, network performance, load balancing, cost, energy consumption, etc., a multi-factor library for multiple scenarios is established to support the measurement and calculation of factors, and provide scheduling and scheduling strategies such as latency priority, cost priority, energy consumption priority, and performance priority; by perceiving basic resource information, operation status information and other data of computing power and network, real-time collection, cleaning and combing are carried out, and resources are dynamically scheduled and elastically scaled based on operation status scheduling rules and scenario scheduling strategies. Provide automatic deployment of various types of applications in computing power resources. BRIEF DESCRIPTION OF THE DRAWINGS

[0044] Figure 1 This is an application environment diagram of a computing network resource configuration and scheduling method in an embodiment;

[0045] Figure 2 A flowchart of a computing network resource configuration and scheduling method in one embodiment;

[0046] Figure 3 A structural diagram of a computing network resource configuration and scheduling system in an embodiment

[0047] Figure 4 A structural block diagram of a computing network resource configuration and scheduling device in an embodiment;

[0048] Figure 5 FIG. 4 is a diagram showing the internal structure of a computer device in one embodiment. DETAILED DESCRIPTION

[0049] 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.

[0050] The computing network resource configuration and scheduling method provided in the embodiment of the present application can be applied to Figure 1In the application environment shown. Among them, the terminal communicates with the server through the network. The data storage system can store the data that the server needs to process. The data storage system can be integrated on the server, or it can be placed on the cloud or other network servers. Among them, the terminal can be but not limited to various personal computers, laptops, smart phones, tablets, Internet of Things devices and portable wearable devices. The Internet of Things devices can be smart speakers, smart TVs, smart air conditioners, smart car-mounted devices, etc. Portable wearable devices can be smart watches, smart bracelets, head-mounted devices, etc. The server can be implemented as an independent server or a server cluster consisting of multiple servers.

[0051] In one embodiment, Figure 2 As shown, in this embodiment, the method includes the following steps:

[0052] Step 202, deconstruct computing resources based on user needs.

[0053] Among them, the collection of user needs is to clarify the specific needs of users for services or applications, including computing power, data processing speed, network bandwidth, latency requirements, etc.; by providing users with a demand input interface or interface, users input computing power requirements through the interface, such as: business volume, number of concurrency, data volume, performance requirements, storage space requirements, network bandwidth requirements, network latency requirements, etc.

[0054] Deconstruct user needs, including establishing a mathematical model for demand deconstruction, and converting demand into computing power and network specification requirements to facilitate further resource allocation and scheduling algorithm design. Demand deconstruction models usually have business attributes and are adapted to business demand scenarios such as transactional, computing, and storage.

[0055] It is worth mentioning that the user business volume, concurrency, data volume, and performance requirements are converted into computing power resource requirements such as computing power, computing power specifications, and quantity through mathematical models; the computing power resource demand evaluation method is as follows:

[0056] CPU computing power requirement algorithm:

[0057] T op =C*S / CPU speed ;

[0058] Among them, T op The time required for each operation (processing a record), C is the algorithm complexity coefficient, S is the amount of memory required for single data processing (bytes), CPU speed is the processing speed of the CPU;

[0059] To meet the response time goal, the system needs to process at least D records per second:

[0060] NCPU ≈U*D / (R*T op );

[0061] Among them, N CPU is the number of CPU cores, U is the number of concurrent users, D is the CPU data processing capacity per second (number of records / second), R is the response time target (seconds), T op The time required for each operation (processing a record).

[0062] Memory requirement algorithm:

[0063] When processing concurrently, assume that memory space needs to be reserved for each user operation:

[0064] M memory ≈U*S;

[0065] Among them, M memory is the total memory requirement, U is the number of concurrent users, and S is the amount of memory (bytes) required for processing a single piece of data.

[0066] By calculating the total computing power demand of the user obtained above and the computing power value provided by the unit server, the number and specifications of servers required for the user's computing power demand can be obtained. The server computing power evaluation method includes:

[0067] Benchmark testing: Use professional tools to benchmark existing systems or similar systems to obtain benchmark computing power values ​​for servers of different specifications; Theoretical calculation: Perform theoretical calculations on server hardware configurations, such as the number of CPU cores, main frequency, cache size, parallel computing capability, memory, and other configuration information to obtain theoretical computing power values ​​for servers of different specifications; Theoretical calculation, actual testing, and adjustment: First obtain the calculation results through theoretical calculations, verify the calculation results through actual stress testing and performance monitoring, and adjust the configuration based on feedback.

[0068] Convert user data volume, network bandwidth requirements, and network latency requirements into network resource requirements such as network type and network bandwidth through algorithm formulas;

[0069] This technology is used in this application to collect and refine demand, converting the user's business needs into computing network resource requirements. The results of demand collection and deconstruction will serve as the basis and input for the scheduling of computing resources and network resources.

[0070] Step 204: Scheduling tasks to be processed according to user requirements based on the computing resources and preset idle resources.

[0071] Among them, the pending tasks required by users are scheduled through resource docking and resource allocation, including:

[0072] Resource connection: Connect with computing resources and network resources, and continuously monitor and record the number, specifications, availability, and performance parameters of computing nodes, storage devices, and network links;

[0073] Resource configuration: Add labels to computing resources and network resources, such as computing power type, network type, cost, geographic location, energy consumption, service quality level, etc., to facilitate subsequent multi-dimensional management and scheduling. Since the computing power and network types and specifications of resource docking vary greatly, the resource configuration module needs to abstract and standardize resource types and specifications.

[0074] This technology is used in this application to master the computing resources and network resources managed and allocated by the system, so as to allocate the computing resources and network resources required by the user in terms of quantity and specifications, as well as the user's preferences, to the computing resource pool and network resources that meet the user's needs. Therefore, it is necessary to first master the information such as the location and quantity of available resources.

[0075] It is worth mentioning that in this application, the intelligent scheduling algorithm used specifically includes:

[0076] 1. Round Robin:

[0077] Resources are allocated in the order in which requests arrive. The system allocates user resource requirements to the managed cloud computing resource pool in order according to the total amount of connected computing resources. When allocating resources, indicators such as total resources, used resources, and available resources can be comprehensively considered.

[0078] 1) Polling algorithm - Linear Regression:

[0079] Formula: y = β0 + β1 * x + ε;

[0080] Among them, the explanatory variable is x, the target variable is y, β0 is the intercept, β1 is the slope, and ε is the error term.

[0081] The least squares method is a common method for solving the parameters (β0 and β1) of the linear regression model, which makes the residual sum of squares minimize.

[0082] 2) Polling Algorithm - Gradient Descent:

[0083] The iterative formula for gradient descent is:

[0084] Among them, f(x) is the function to be optimized, and the current parameter is x t , the learning rate is η, where is the function at x t The gradient at .

[0085] 3) Polling algorithm - Quick Sort:

[0086] Quick sort is an efficient sorting algorithm that uses a divide-and-conquer strategy to sort. The array is divided into two sub-arrays: a sub-array consisting of elements smaller than the base element and a sub-array consisting of elements larger than the base element. The two sub-arrays are recursively sorted.

[0087] 2. Load Balancing:

[0088] Dynamically distribute the workload to multiple computing nodes to fully utilize cluster resources, reduce single point overload, and improve overall processing capabilities and response speed. Common strategies include minimum number of connections, hashing, polling, etc.

[0089] 1) Load Balancing - Weighted Round Robin:

[0090] Each cloud computing resource pool is assigned a weight value, which represents its ability to process requests. Requests are dispatched to each cloud pool in a cyclic manner according to the weight ratio. The formula is as follows:

[0091] Assume that there are N cloud computing resource pools, with weights W1, W2, ..., WN respectively.

[0092] The index of the cloud resource pool currently scheduled is i (initialized to 0).

[0093] The sum of weights (the sum of weights of all cloud resource pools) is SumW=W1+W2+...+WN.

[0094] During each scheduling, the resource pool corresponding to index i is selected, and i=(i+1)modN is updated.

[0095] In order to schedule according to the weight ratio, the number of requests that each resource pool should process or the number of resources that can be allocated can be calculated, which can be achieved by simulating the weighted polling process.

[0096] 2) Load balancing-dynamic adjustment:

[0097] Dynamically adjust the load balancing strategy based on the real-time load status of the resource pool (such as server load, network status, etc.). Monitor the performance indicators of the server (such as CPU usage, memory usage, response time, etc.). When a performance indicator exceeds the threshold, the load balancing strategy adjustment is triggered. The adjustment can include changing the weight distribution, switching the load balancing algorithm, etc.

[0098] 3. Intelligent scheduling algorithm (scheduling based on machine learning):

[0099] Use historical data and machine learning technology to predict future load conditions and task characteristics, and automatically generate or optimize scheduling decisions to improve resource utilization efficiency and user experience.

[0100] Scheduling strategy: Taking into account user business preferences, scheduling strategies such as location, delay, cost, and performance can be provided to users.

[0101] This technology is used in the present invention to dispatch user needs to computing resource pools and network resources that meet the requirements, and to allocate and activate the corresponding computing resources and network resources. The intelligent scheduling algorithm determines whether the scheduling plan and scheduling results are accurate and efficient, and the scheduling strategy is used to provide users with resources that meet their business preferences.

[0102] Step 206, monitor and update idle resources and computing resources and corresponding scheduling algorithms.

[0103] Among them, the status of computing power resources and network resources is dynamically collected and sensed, such as remaining capacity, usage, availability, etc. Continuous optimization is carried out based on the sensed data to achieve self-learning and adaptive adjustment; real-time monitoring of computing power and network resource performance indicators, timely detection of resource failures and anomalies, and ensuring the quality of scheduling services.

[0104] This application senses and monitors the status, faults and usage information of computing resources and network resources, and updates the sensed and monitored data to the system or presents it graphically.

[0105] In the above-mentioned computing network resource configuration and scheduling method, requirements are collected through various methods such as guidance and question-and-answer, and business attributes in the requirements are extracted. In combination with the resource template library and the application requirement analysis algorithm, the business requirements are converted into detailed requirements and parameters for computing network resources; based on the scheduling factors such as computing performance, network performance, load balancing, cost, and energy consumption, a multi-factor library for multiple scenarios is established to support the measurement and calculation of factors, and to provide scheduling and scheduling strategies such as latency priority, cost priority, energy consumption priority, and performance priority; by perceiving the basic resource information, operation status information, and other data of computing power and the network, real-time collection, cleaning, and sorting are performed, and dynamic resource scheduling and elastic scaling are performed based on the operation status scheduling rules and scenario scheduling strategies. Automatic deployment of various types of applications in computing power resources is provided.

[0106] In one embodiment, the specific scheduling operation may adopt a dynamic priority scheduling process, and the specific dynamic priority scheduling process includes:

[0107] Construct required tasks and corresponding initial priorities based on user needs;

[0108] The system recalculates the priority of each task periodically or under certain trigger conditions (such as task completion or new task arrival). Priority calculation is usually based on the following factors: Task deadline: The closer to the deadline, the higher the priority; Task remaining execution time: The less remaining time, the higher the priority; Task importance or weight: The higher the importance, the higher the priority; Task resource requirement vs. system resource status: The closer the resource requirement is to the current available resources of the system, the higher the priority.

[0109] Update required tasks and corresponding update priorities under preset conditions;

[0110] Among them, according to the priority of the current task, the task with the highest priority is selected for scheduling and execution. If multiple tasks have the same priority, polling, random selection or other strategies can be used to determine the scheduling order; if some tasks need to adjust their priorities due to changes in system status (such as reduced resources) or changes in execution conditions (such as increased delays), the system will recalculate the priority and adjust the scheduling order according to the new priority.

[0111] The tasks to be processed according to user requirements are scheduled based on the update priority and preset idle resources.

[0112] After a task is completed, it is removed from the task queue and the occupied resources are released. The system continues to schedule the next task with the highest priority.

[0113] In this embodiment, dynamic priority scheduling is a flexible scheduling strategy that can dynamically adjust the priority of tasks according to the real-time characteristics of the tasks (such as execution time, deadline, resource requirements, etc.), so that the scheduled tasks can select the priority of the tasks to be processed according to the corresponding real-time characteristics according to the actual situation, thereby improving the flexibility of task scheduling.

[0114] It is worth mentioning that several priority calculation formulas are commonly used in dynamic priority scheduling:

[0115] Earliest Deadline First (EDF):

[0116] Among them, P i is the priority of task i, D i is the deadline of the task, t is the current time, the closer the deadline is, the higher the priority;

[0117] Shortest Remaining Time First (SRTF):

[0118] Among them, P i is the priority of task i, R i is the remaining execution time of task i. The less the remaining time, the higher the priority;

[0119] Highest Response Ratio Next (HRRN):

[0120] Among them, P i is the priority of task i, W i is the waiting time of task i, T i is the service time (i.e., estimated completion time) of task i. The longer the waiting time or the shorter the service time, the higher the priority.

[0121] Weighted Priority Calculation:

[0122] Among them, P i is the priority of task i, D i is the deadline of the task, t is the current time, R i is the remaining execution time of task i, I i is the weight coefficient of task i, and α, β and γ are weight coefficients.

[0123] In one embodiment, corresponding scheduling optimization operations are performed for the starvation problem, and the specific operations include:

[0124] Starvation refers to the situation in which some tasks may not be scheduled or executed for a long time due to their low priority or fierce resource competition in a multi-task scheduling environment, resulting in their inability to be completed in time. Starvation is particularly prominent in dynamic priority scheduling algorithms, especially when the priority of tasks is dynamically adjusted with the system state. If the scheduling strategy is unreasonable, some tasks may always be at a disadvantage and unable to obtain the required resources.

[0125] Statistics on waiting time corresponding to user needs;

[0126] The corresponding update priority is calculated based on the waiting time, the preset update coefficient and the initial priority.

[0127] Priority aging is a method of dynamically adjusting the priority. As the waiting time increases, the priority of the task gradually increases. Tasks that have not been scheduled for a long time will gradually get higher priorities, and finally ensure that they can be scheduled for execution.

[0128] Priority aging can be achieved through a simple weighted formula, such as: i =P i initial +λ*W i ;

[0129] Among them, P i is the priority of task i, P i initial is the initial priority of task i, λ is the aging coefficient, which increases with time. i is the waiting time of task i. The longer the waiting time of a task, the higher its priority.

[0130] In this embodiment, by setting the priority aging method, the dynamic priority scheduling system can effectively avoid the starvation problem, thereby ensuring that all tasks are executed within a reasonable time and improving the overall efficiency and responsiveness of the system.

[0131] In one embodiment, the update coefficient is preset and may not match the actual scheduling. It is necessary to optimize the update coefficient. The specific optimization operation includes:

[0132] Statistics of response time and completion time corresponding to user requirements, where the response time is the time from uploading the user requirements to starting the scheduling process, and the completion time is the time from starting the scheduling process to completing the user requirements processing;

[0133] The update coefficient is optimized based on the response time and the completion time.

[0134] In this embodiment, the update coefficient is optimized by counting the response time and completion time of user needs, so that the update coefficient can be automatically optimized based on the response time and completion time, so that the optimized update coefficient improves the scheduling efficiency.

[0135] In one embodiment, after the update coefficient is optimized, if the scheduling efficiency after the update coefficient is optimized is lower than the scheduling efficiency before the update, the update coefficient needs to be verified. The specific verification operation includes:

[0136] Obtain similarity update coefficients and corresponding historical scheduling data;

[0137] Among them, the similar update coefficient is the update coefficient of the statistical factor of the same priority within the preset range, and the historical scheduling data is the scheduling efficiency monitored after the scheduling operation adopted by the system under the historical update coefficient;

[0138] Compare historical dispatch data with dispatch data;

[0139] If the historical scheduling data is not greater than the scheduling data, the pending tasks required by the user are scheduled based on the initial priority and the preset idle resources; if the historical scheduling data is greater than the scheduling data, the pending tasks required by the user are scheduled based on the updated priority and the preset idle resources.

[0140] In this embodiment, the update coefficient is verified twice by comparing the historical scheduling data with the scheduling data, and the update coefficient is optimized on the basis of passing the verification, thereby ensuring that the update coefficient can stably improve the scheduling efficiency.

[0141] In one embodiment, when the historical scheduling data is not greater than the scheduling data, there is still a need to use the update coefficient, specifically including:

[0142] Count the growth trend of historical dispatch data within a preset time period;

[0143] If the historical increase trend is greater than the increase trend, the pending tasks of the user's needs are scheduled based on the initial priority and the preset idle resources; if the historical increase trend is not greater than the increase trend, the increase efficiency corresponding to the increase trend is calculated based on the waiting time to see whether it is greater than the historical increase efficiency corresponding to the historical increase trend;

[0144] If the amplification efficiency is greater than the historical amplification efficiency, the pending tasks required by the user are scheduled based on the update priority and the preset idle resources.

[0145] In this embodiment, by comparing the increase trend, in special cases, the increase efficiency of the update coefficient within a specific time is less than the historical increase efficiency. The waiting time is comprehensively considered to decide whether to use the update priority for scheduling operations, thereby further improving the efficiency of handling the starvation problem.

[0146] 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.

[0147] Based on the same inventive concept, the embodiment of the present application also provides a computing network resource configuration and scheduling device for implementing the computing network resource configuration and scheduling method involved above. The implementation scheme for solving the problem provided by the device is similar to the implementation scheme recorded in the above method, so the specific limitations in one or more computing network resource configuration and scheduling device embodiments provided below can refer to the limitations of the computing network resource configuration and scheduling method above, and will not be repeated here.

[0148] In one embodiment, Figure 3 and Figure 4 As shown, a computing network resource configuration and scheduling device is provided, including: a computing power structure module, an algorithm scheduling module and a resource update module, wherein:

[0149] In one embodiment, the algorithm scheduling module is also used to construct demand tasks and corresponding initial priorities based on user needs; update demand tasks and corresponding update priorities under preset conditions; and schedule pending tasks of user needs based on the update priorities and preset idle resources.

[0150] In one embodiment, the algorithm scheduling module is further used to count the waiting time corresponding to the user demand; and calculate the corresponding update priority based on the waiting time, a preset update coefficient and an initial priority.

[0151] In one embodiment, the algorithm scheduling module is also used to count the response time and completion time corresponding to user needs, the response time is the time from the uploading of user needs to the start of scheduling processing, and the completion time is the time from the start of scheduling processing of user needs to the completion of user demand processing; based on the response time and completion time, the update coefficient is optimized.

[0152] In one embodiment, the algorithm scheduling module is also used to obtain similar update coefficients and corresponding historical scheduling data; compare historical scheduling data with scheduling data; if the historical scheduling data is not greater than the scheduling data, schedule the pending tasks required by the user based on the initial priority and preset idle resources; if the historical scheduling data is greater than the scheduling data, schedule the pending tasks required by the user based on the update priority and preset idle resources.

[0153] In one embodiment, the algorithm scheduling module is also used to count the increase trend corresponding to the historical scheduling data within a preset time; if the historical increase trend is greater than the increase trend, the pending tasks required by the user are scheduled based on the initial priority and the preset idle resources; if the historical increase trend is not greater than the increase trend, whether the increase efficiency corresponding to the increase trend is greater than the historical increase efficiency corresponding to the historical increase trend based on the waiting time; if the increase efficiency is greater than the historical increase efficiency, the pending tasks required by the user are scheduled based on the updated priority and the preset idle resources.

[0154] Each module in the above-mentioned computing network resource configuration and scheduling method device can be implemented in whole or in part by software, hardware and their combination. The above-mentioned modules can be embedded in or independent of the processor in the computer device in the form of hardware, or can be stored in the memory of the computer device in the form of software, so that the processor can call and execute the corresponding operations of each of the above modules.

[0155] In one embodiment, a computer device is provided, which may be a server, and includes a processor, a memory, and a network interface connected via a system bus. The processor of the computer device is used to provide computing and control capabilities. The memory of the computer device includes a non-volatile storage medium and an internal memory. The non-volatile storage medium stores an operating system, a computer program, and a database. The internal memory provides an environment for the operation of the operating system and the computer program in the non-volatile storage medium. The database of the computer device is used to store data. The network interface of the computer device is used to communicate with an external terminal via a network connection. When the computer program is executed by the processor, a method for coordinated investment in a power transmission and energy storage system is implemented.

[0156] Those skilled in the art will appreciate that a block diagram of only a portion of the structure related to the solution of the present application does not constitute a limitation on the computer device to which the solution of the present application is applied. The specific computer device may include more or fewer components than those shown in the figure, or combine certain components, or have a different arrangement of components.

[0157] In one embodiment, a computer device is provided, including a memory and a processor, wherein a computer program is stored in the memory, and the processor implements the steps in the above-mentioned method embodiments when executing the computer program.

[0158] In one embodiment, a computer-readable storage medium is provided, on which a computer program is stored. When the computer program is executed by a processor, the steps in the above-mentioned method embodiments are implemented.

[0159] In one embodiment, a computer program product is provided, including a computer program, which implements the steps in the above method embodiments when executed by a processor.

[0160] 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.

[0161] Those of ordinary skill in the art can understand that all or part of the processes in the above-mentioned embodiment methods 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 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 thereto. The processors involved in each embodiment provided in this application may be general-purpose processors, central processing units, graphics processors, digital signal processors, programmable logic devices, data processing logic devices based on quantum computing, etc., but are not limited thereto.

[0162] 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 specification.

[0163] 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 network resource scheduling method, characterized in that: The method comprises: Deconstruct computing resources based on user needs; Scheduling tasks to be processed based on the computing resources and preset idle resources; Monitor and update idle resources and computing resources as well as the corresponding scheduling algorithms.

2. The method according to claim 1, characterized in that The operation of scheduling the tasks to be processed based on the computing resources and the preset idle resources includes: Construct required tasks and corresponding initial priorities based on user needs; Update required tasks and corresponding update priorities under preset conditions; The tasks to be processed according to user requirements are scheduled based on the update priority and preset idle resources.

3. The method according to claim 2, characterized in that The updating requirement tasks and corresponding updating priorities under the preset conditions include: Statistics on waiting time corresponding to user needs; The corresponding update priority is calculated based on the waiting time, the preset update coefficient and the initial priority.

4. The method according to claim 3, characterized in that The method further comprises: Statistics of response time and completion time corresponding to user requirements, where the response time is the time from uploading the user requirements to starting the scheduling process, and the completion time is the time from starting the scheduling process to completing the user requirements processing; The update coefficient is optimized based on the response time and the completion time.

5. The method according to claim 4, characterized in that After the optimizing update coefficient based on the response time and the completion time, the method further includes: Obtain similarity update coefficients and corresponding historical scheduling data; Compare historical dispatch data with dispatch data; If the historical scheduling data is not greater than the scheduling data, the pending tasks required by the user are scheduled based on the initial priority and the preset idle resources; If the historical scheduling data is greater than the scheduling data, the pending tasks required by the user are scheduled based on the update priority and the preset idle resources.

6. The method according to claim 5, characterized in that The method further comprises: Count the growth trend of historical dispatch data within a preset time period; If the historical growth trend is greater than the growth trend, the pending tasks required by the user are scheduled based on the initial priority and the preset idle resources; If the historical increase trend is not greater than the increase trend, then the increase efficiency corresponding to the increase trend is calculated based on the waiting time to see whether it is greater than the historical increase efficiency corresponding to the historical increase trend; If the amplification efficiency is greater than the historical amplification efficiency, the pending tasks required by the user are scheduled based on the update priority and the preset idle resources.

7. A computing network resource configuration, characterized in that: The device comprises: The computing power structure module is used to deconstruct computing power resources based on user needs; An algorithm scheduling module is used to select a corresponding scheduling algorithm based on the computing power resources and preset idle resources to schedule the pending tasks required by the user; The resource update module is used to update idle resources and computing resources and the corresponding scheduling algorithms in real time.

8. A computer device comprising a memory and a processor, wherein the memory stores a computer program, wherein: When the processor executes the computer program, the steps of the method according to any one of claims 1 to 6 are implemented.

9. 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 6 are implemented.

10. A computer program product, comprising a computer program, 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 6 are implemented.

Images