Method and device for dynamically adjusting computing power resources of intelligent computing center

Abstract

The invention provides a computing power resource dynamic adjustment method and device of an intelligent computing center, and relates to the technical field of computing power infrastructure, and the method comprises the steps: receiving a computing power operation task execution request of a user; according to the type of the computing power operation task, a computing power resource adjustment strategy corresponding to the computing power operation task is configured, and the computing power resource adjustment strategy comprises a computing power instance number range and a computing power resource use threshold value; and dynamically adjusting the computing power resources allocated to the computing power operation task according to the computing power resource use condition, the computing power instance quantity range and the computing power resource use threshold value in the execution process of the computing power operation task. Therefore, based on the type of the computing power operation task, the computing power resource adjustment strategy of the computing power operation task is configured in a targeted manner, and furthermore, the dynamic adjustment of the computing power resource of the computing power operation task can be realized according to the use condition of the computing power resource in the execution process of the computing power operation task and the computing power resource adjustment strategy; the performance of the computing power operation task can be ensured, and the utilization rate of computing power resources can be improved.

Description

Technical Field

[0001] The present invention relates to the technical fields of intelligent computing centers, intelligent computing centers, and computing power infrastructure, and particularly relates to a method and device for dynamically adjusting the computing power resources of an intelligent computing center. Background Art

[0002] With the rapid development of artificial intelligence technology, "intelligent computing centers" and "intelligent computing centers" have emerged as the times require.

[0003] An "intelligent computing center" refers to a facility that provides the required computing power, data, and algorithms for artificial intelligence applications (such as scenarios of artificial intelligence deep learning model development, model training, and model inference) by using large-scale heterogeneous computing power resources, including general computing power and intelligent computing power. The intelligent computing center covers facilities, hardware, and software, and can provide full-stack capabilities from underlying computing power to top-level application enabling.

[0004] The "intelligent computing center" includes, but is not limited to, the "intelligent computing center".

[0005] An "intelligent computing center", that is, an artificial intelligence computing center, is a type of computing power infrastructure that provides computing power services, data services, and algorithm services required for artificial intelligence applications based on artificial intelligence theory and using an artificial intelligence computing architecture.

[0006] "Computing power" is the core of "intelligent computing centers" and "intelligent computing centers", and is the ability of computer devices or computing / data centers to process information. It is the ability of computer hardware and software to cooperate to jointly execute a certain computing requirement. It is the computing ability to process information data and achieve the output of the target result. It is a new type of productive force integrating information computing power, network carrying capacity, and data storage capacity, and mainly provides services to society through computing power infrastructure.

[0007] As the core hub for processing massive data and complex computing tasks, the intelligent computing center shoulders the important task of providing strong computing power support for numerous enterprises, scientific research institutions, and various intelligent applications. In some business scenarios, the computing power requirements of different tasks vary greatly and change dynamically over time. When the computing power resources are insufficiently configured, it will lead to slow or even stuck task processing, seriously affecting business efficiency and user experience; while if the computing power resources are overconfigured, it will cause idle waste of resources and increase operating costs. Therefore, how to dynamically adjust the computing power resources of the intelligent computing center has become an urgent technical problem to be solved. Summary of the Invention

[0008] The present invention provides a method and device for dynamically adjusting the computing power resources of an intelligent computing center to solve the problem of dynamically adjusting the computing power resources of the intelligent computing center.

[0009] To solve the above problems, the present invention is implemented as follows:

[0010] In a first aspect, the present invention provides a method for dynamically adjusting computing power resources of an intelligent computing center, including:

[0011] Step S1, receiving a request for executing a computing power operation task from a user, where the request for executing the computing power operation task includes the type of the computing power operation task;

[0012] Step S2, configuring a computing power resource adjustment strategy corresponding to the computing power operation task according to the type of the computing power operation task, where the computing power resource adjustment strategy includes a range of the number of computing power instances and a threshold for using computing power resources;

[0013] Step S3, dynamically adjusting the computing power resources allocated to the computing power operation task according to the usage of computing power resources during the execution of the computing power operation task, the range of the number of computing power instances, and the threshold for using computing power resources.

[0014] In one embodiment, the usage of computing power resources of the computing power operation task includes the utilization rate of computing power resources of the computing power instances allocated to the computing power operation task, and the threshold for using computing power resources includes a maximum usage threshold and a minimum usage threshold. Step S3 includes at least one of the following:

[0015] Step S31, when the utilization rate of computing power resources of the computing power instances allocated to the computing power operation task is greater than the maximum usage threshold, increasing the number of computing power instances allocated to the computing power operation task within the range of the number of computing power instances to increase the computing power resources allocated to the computing power operation task;

[0016] Step S32, when the utilization rate of computing power resources of the computing power instances allocated to the computing power operation task is less than the minimum usage threshold, releasing the computing power instances allocated to the computing power operation task within the range of the number of computing power instances to reduce the computing power resources allocated to the computing power operation task.

[0017] In one embodiment, after step S3, the method further includes:

[0018] Step S4, monitoring the load condition of the execution of the computing power operation task;

[0019] Step S5, adjusting the range of the number of computing power instances according to the load condition of the computing power operation task.

[0020] In one embodiment, the range of the number of computing power instances includes a minimum number of computing power instances and a maximum number of computing power instances. Step S5 includes at least one of the following:

[0021] Step S51: When the load of the computing power operation task remains below the first adjustment threshold for a preset duration, reduce the number of minimum computing power instances;

[0022] Step S52: When the load of the computing power operation task remains above the second adjustment threshold for the preset duration, increase the number of maximum computing power instances, where the first adjustment threshold is less than the second adjustment threshold.

[0023] In one embodiment, step S2 includes:

[0024] Step S21: Determine the computational complexity, execution time, and memory requirements of the computing power operation task according to the type of the computing power operation task;

[0025] Step S22: Configure a computing power resource adjustment strategy corresponding to the computing power operation task according to the computational complexity, execution time, and memory requirements of the computing power operation task.

[0026] In one embodiment, the computing power operation task execution request further includes the priority of the computing power operation task. Before step S3, the method further includes:

[0027] Step 6: Determine the priority of the computing power resource adjustment strategy according to the priority of the computing power operation task;

[0028] Step S3 includes:

[0029] Step S33: Based on the priority of the computing power resource adjustment strategy, dynamically adjust the computing power resources allocated to the computing power operation task according to the computing power resource usage situation, the range of the number of computing power instances, and the computing power resource usage threshold during the execution of the computing power operation task.

[0030] In a second aspect, the present invention further provides a device for dynamically adjusting computing power resources in an intelligent computing center, including:

[0031] A first receiving module, configured to receive a computing power operation task execution request from a user, where the computing power operation task execution request includes the type of the computing power operation task;

[0032] A first configuration module, configured to configure a computing power resource adjustment strategy corresponding to the computing power operation task according to the type of the computing power operation task, where the computing power resource adjustment strategy includes a range of the number of computing power instances and a computing power resource usage threshold;

[0033] A first adjustment module, configured to dynamically adjust the computing power resources allocated to the computing power operation task according to the computing power resource usage situation, the range of the number of computing power instances, and the computing power resource usage threshold during the execution of the computing power operation task.

[0034] In a third aspect, the present invention further provides an electronic device, including a processor, a memory, and a computer program stored on the memory and executable on the processor. When the computer program is executed by the processor, the steps in the method for dynamically adjusting computing power resources of the intelligent computing center as described in the first aspect above are implemented.

[0035] In a fourth aspect, the present invention further provides a computer-readable storage medium, on which a computer program is stored. When the computer program is executed by a processor, the steps in the method for dynamically adjusting computing power resources of the intelligent computing center as described in the first aspect above are implemented.

[0036] In a fifth aspect, the present invention further provides a computer program product, including computer instructions. When the computer instructions are executed by a processor, the steps in the method for dynamically adjusting computing power resources of the intelligent computing center as described in the first aspect above are implemented.

[0037] In the present invention, a computing power operation task execution request from a user is received, and the type of the computing power operation task is included in the computing power operation task execution request; according to the type of the computing power operation task, a computing power resource adjustment strategy corresponding to the computing power operation task is configured, and the computing power resource adjustment strategy includes a computing power instance quantity range and a computing power resource usage threshold; according to the computing power resource usage situation of the computing power operation task during execution, the computing power instance quantity range, and the computing power resource usage threshold, the computing power resources allocated to the computing power operation task are dynamically adjusted. In this way, based on the type of the computing power operation task, the computing power resource adjustment strategy for the computing power operation task is configured specifically. Further, the computing power resources of the computing power operation task can be dynamically adjusted according to the computing power resource usage situation of the computing power operation task during execution and the computing power resource adjustment strategy, which can not only ensure the performance of the computing power operation task but also improve the utilization rate of the computing power resources. BRIEF DESCRIPTION OF THE DRAWINGS

[0038] To more clearly illustrate the technical solutions of the present invention, the drawings required for the description of the present invention will be briefly introduced below. Obviously, the drawings in the following description are only some embodiments of the present invention. For those of ordinary skill in the art, other drawings can be obtained based on these drawings without creative efforts.

[0039] Figure 1 is a flowchart of a method for dynamically adjusting computing power resources of an intelligent computing center provided by the present invention;

[0040] Figure 2 is a deployment schematic diagram of a computing power model provided by the present invention;

[0041] Figure 3 It is a schematic diagram for configuring the computing power resource adjustment strategy provided by the present invention;

[0042] Figure 4 It is a schematic diagram for using the computing power resources provided by the present invention;

[0043] Figure 5 It is a structural diagram of a dynamic adjustment device for computing power resources of an intelligent computing center provided by the present invention;

[0044] Figure 6 It is a structural diagram of an electronic device provided by the present invention. Detailed implementation manners

[0045] Next, the technical solutions in the present invention will be clearly and completely described in conjunction with the accompanying drawings in the present invention. Obviously, the described embodiments are part of the embodiments of the present invention, rather than all of the embodiments. Based on the embodiments in the present invention, all other embodiments obtained by those of ordinary skill in the art without making creative efforts shall fall within the protection scope of the present invention.

[0046] The "computing power" described in the present invention refers to: the ability of a computer device or a computing / data center to process information, the ability of computer hardware and software to cooperate to jointly execute a certain computing requirement, the computing ability to achieve the output of a target result by processing information data, a new type of productive force integrating information computing power, network carrying capacity, and data storage capacity, and mainly providing services to society through computing power infrastructure.

[0047] The "computational power" (ComputationalPower, CP) described in the present invention refers to: the ability of a data center server to process data and achieve result output, a comprehensive index for measuring the computing ability of a data center, including general computing ability, supercomputing ability, and intelligent computing ability. The commonly used measurement unit is the number of floating-point operations per second (FLOPS, 1EFLOPS = 10^18 FLOPS), and the larger the value, the stronger the comprehensive computing ability. It is estimated that 1EFLOPS is approximately the computing power output of 5 Tianhe 2A or 500,000 mainstream server CPUs or 2 million mainstream laptops. The calculation formula is: CP = CP 通用 + CP 智能 + CP 超级 .

[0048] The "network power" (NP) described in the present invention refers to: the manifestation of the data transmission ability of computing power facilities, a comprehensive ability including network architecture, network bandwidth, transmission delay, intelligent management and scheduling, etc., involving network transmission inside and between data centers, and a comprehensive index for measuring network transmission scheduling ability.

[0049] The "Storage Power" (SP) described in the present invention refers to the comprehensive ability of a data center in four aspects: data storage capacity, performance, security and reliability, and green and low-carbon. It is a comprehensive indicator for measuring the data storage capacity of a data center and includes external storage devices such as storage arrays and built-in storage devices in servers. The commonly used measurement unit for storage capacity is exabyte (EB, 1EB = 2^60 bytes), the commonly used measurement unit for performance is the number of read and write operations per second per unit capacity (IOPS / TB, Input / Output Operations Per Second / TB), and the disaster recovery ratio is an important manifestation of security and reliability.

[0050] The "computing power infrastructure" described in the present invention refers to a new type of information infrastructure that integrates information computing power, network carrying capacity, and data storage power, and can realize the centralized computing, storage, transmission, and application of information.

[0051] The "new type of information infrastructure" described in the present invention mainly includes network infrastructures such as 5G networks, fiber broadband networks, backbone networks, international communication networks, and satellite Internet, computing power infrastructures such as data centers, general computing power centers, intelligent computing centers, and supercomputing centers, and new technology facilities such as artificial intelligence, blockchain, and quantum computing.

[0052] The "computing power" described in the present invention includes: general computing power, intelligent computing power, and super computing power.

[0053] The "general computing power" described in the present invention refers to the computing power provided by servers based on central processing unit (CPU) chips, which is used to support basic general computing such as cloud computing and edge computing.

[0054] The "intelligent computing power" described in the present invention refers to a computing platform that is scaled for various artificial intelligence innovation applications and is based on dedicated chips such as graphics processing unit (GPU), field programmable gate array (FPGA), and application specific integrated circuit (ASIC), such as natural language processing, machine vision, etc.

[0055] The "super computing power" described in the present invention refers to: mainly the computing power provided by high-performance computing clusters such as supercomputers. It utilizes the centralized computing resources of multiple computer systems working in parallel and processes extremely complex or data-intensive problems through a dedicated operating system. It is mainly used for computing in cutting-edge scientific fields, such as planetary simulation, drug molecule design, gene analysis, etc.

[0056] The "intelligent computing center" described in the present invention refers to: a facility that provides the required computing power, data, and algorithms mainly for artificial intelligence applications (such as scenarios like artificial intelligence deep learning model development, model training, and model inference) by using large-scale heterogeneous computing power resources, including general computing power (CPU) and intelligent computing power (GPU, FPGA, ASIC, etc.). The intelligent computing center covers facilities, hardware, and software, and can provide full-stack capabilities from underlying computing power to top-level application enabling.

[0057] The "intelligent computing center" described in the present invention includes, but is not limited to, the "intelligent computing center".

[0058] The "intelligent computing center" described in the present invention, namely the artificial intelligence computing center, is a type of computing power infrastructure that provides computing power services, data services, and algorithm services required for artificial intelligence applications based on artificial intelligence theory and using an artificial intelligence computing architecture.

[0059] The "computing power center" described in the present invention refers to: a facility mainly composed of infrastructure such as wind, fire, water, and electricity and IT software and hardware devices, with computing power, transportation power, and storage power, including general data centers, intelligent computing centers, supercomputing centers, etc.

[0060] The "supercomputing center" described in the present invention refers to: namely the supercomputing data center, which is a data center based on supercomputers or large-scale computing clusters and can provide functions such as large-scale computing, storage, and network services, and is widely used in application scenarios such as aerospace, national defense, oil exploration, climate modeling, and genome sequencing.

[0061] The "computing power resources" described in the present invention refers to: technologies and facilities required for the development of the digital society with information computing, transmission, storage, and application capabilities, including but not limited to computing resources such as CPU and GPU, network resources such as switches and routers, storage resources such as storage arrays and distributed storage, security resources such as firewalls and intrusion detection systems, and support and guarantee resources such as wind, fire, water, and electricity.

[0062] The "computing power operation task" described in the present invention refers to: specific workloads or jobs that are executed on computing power resources and require a certain amount of computing power support, usually involving scenarios such as complex data processing, numerical calculation, model training, or simulation.

[0063] In the prior art, as the core hub for massive data processing and complex computing tasks, the intelligent computing center undertakes the important task of providing powerful computing power support for numerous enterprises, research institutions, and various intelligent applications. In some business scenarios, the computing power requirements of different tasks vary greatly and change dynamically over time. When the computing power resource configuration is insufficient, it will lead to slow or even stuck task processing, seriously affecting business efficiency and user experience; while if the computing power resources are overconfigured, it will cause idle waste of resources and increase operating costs. Therefore, how to dynamically adjust the computing power resources of the intelligent computing center has become a technical problem to be solved urgently. To dynamically adjust the computing power resources of the intelligent computing center, in the present invention, a computing power operation task execution request from a user is received, and the type of the computing power operation task is included in the computing power operation task execution request; according to the type of the computing power operation task, a computing power resource adjustment strategy corresponding to the computing power operation task is configured, and the computing power resource adjustment strategy includes a computing power instance quantity range and a computing power resource usage threshold; according to the computing power resource usage situation, the computing power instance quantity range, and the computing power resource usage threshold during the execution of the computing power operation task, the computing power resources allocated to the computing power operation task are dynamically adjusted. In this way, based on the type of the computing power operation task, the computing power resource adjustment strategy for the computing power operation task is configured specifically. Further, the computing power resources of the computing power operation task can be dynamically adjusted according to the computing power resource usage situation and the computing power resource adjustment strategy during the execution of the computing power operation task, which can not only ensure the performance of the computing power operation task but also improve the utilization rate of the computing power resources.

[0064] Specifically, please refer to Figure 1 , Figure 1 which is a flowchart of a method for dynamically adjusting the computing power resources of an intelligent computing center provided by the present invention. As Figure 1 shown, it includes the following steps:

[0065] Step S1: Receive a computing power operation task execution request from a user, and the type of the computing power operation task is included in the computing power operation task execution request.

[0066] The type of the computing power operation task may include model inference tasks, model training tasks, etc. Refer to Figure 2 , the model can be deployed in the intelligent computing center in advance, and then according to the computing power operation task execution request sent by the user, the corresponding computing power operation task is executed on the deployed model.

[0067] Step S2: According to the type of the computing power operation task, configure a computing power resource adjustment strategy corresponding to the computing power operation task, and the computing power resource adjustment strategy includes a computing power instance quantity range and a computing power resource usage threshold.

[0068] Since the computing power operation tasks of different types have different resource requirements, the intelligent computing center can configure a computing power resource adjustment strategy corresponding to the computing power operation task according to the type of the computing power operation task, that is, different task types have different resource allocation schemes. Specifically, configuring a computing power resource adjustment strategy corresponding to the computing power operation task includes configuring a range of the number of computing power instances corresponding to the computing power operation task and a threshold for using the computing power resources corresponding to the computing power operation task. The computing power instance can be a virtual or physical resource unit that provides computing power, such as a virtual machine, a container, a GPU server, etc. The range of the number of computing power instances consists of the minimum number of computing power instances allowed to be allocated and the maximum number of computing power instances allowed to be allocated. The threshold for using the computing power resources includes the lower limit and the upper limit of the utilization rate of the computing power resources.

[0069] Exemplarily, refer to Figure 3 , for a certain model inference task, the range of the number of computing power instances can be set to 2 to 8, and the threshold for using the computing power resources can be set to 20% to 80%.

[0070] Step S3, dynamically adjust the computing power resources allocated to the computing power operation task according to the usage of the computing power resources during the execution of the computing power operation task, the range of the number of computing power instances, and the threshold for using the computing power resources.

[0071] During the execution of the computing power operation task, the usage of the computing power resources of the computing power operation task can be continuously monitored, such as the GPU utilization rate, etc., and then the usage of the computing power resources of the computing power operation task is compared with the threshold for using the computing power resources. According to the comparison result, the computing power resources of the computing power operation task are increased, decreased, or kept unchanged within the range of the number of computing power instances. Exemplarily, refer to Figure 4 , during the execution of a certain model inference task, the range of the number of computing power instances is set to 2 to 8, the threshold for using the computing power resources is set to 20% to 80%, the number of instances allocated to the model inference task is 2, and the GPU utilization rate of each instance exceeds 80%. Then, the number of instances can be appropriately increased, but not too much at one time, and it needs to be maintained within the set range of the number of computing power instances.

[0072] In the present invention, a computing power operation task execution request from a user is received, and the type of the computing power operation task is included in the computing power operation task execution request; according to the type of the computing power operation task, a computing power resource adjustment strategy corresponding to the computing power operation task is configured, and the computing power resource adjustment strategy includes a computing power instance quantity range and a computing power resource usage threshold; according to the computing power resource usage situation of the computing power operation task during execution, the computing power instance quantity range, and the computing power resource usage threshold, the computing power resources allocated to the computing power operation task are dynamically adjusted. In this way, based on the type of the computing power operation task, a targeted configuration of the computing power resource adjustment strategy for the computing power operation task is performed. Further, the computing power resources of the computing power operation task can be dynamically adjusted according to the computing power resource usage situation of the computing power operation task during execution and the computing power resource adjustment strategy, which can not only ensure the performance of the computing power operation task but also improve the utilization rate of the computing power resources.

[0073] In one embodiment, the computing power resource usage situation of the computing power operation task includes the computing power resource utilization rate of the computing power instances allocated to the computing power operation task, the computing power resource usage threshold includes a maximum usage threshold and a minimum usage threshold, and step S3 includes at least one of the following:

[0074] Step S31: When the computing power resource utilization rate of the computing power instances allocated to the computing power operation task is greater than the maximum usage threshold, increase the computing power instances allocated to the computing power operation task within the computing power instance quantity range to increase the computing power resources allocated to the computing power operation task;

[0075] Step S32: When the computing power resource utilization rate of the computing power instances allocated to the computing power operation task is less than the minimum usage threshold, release the computing power instances allocated to the computing power operation task within the computing power instance quantity range to reduce the computing power resources allocated to the computing power operation task.

[0076] The computing power resource usage situation of the computing power operation task includes the computing power resource utilization rate of the computing power instances allocated to the computing power operation task. The computing power resource utilization rate can be understood as the degree of utilization of resources such as GPUs. The computing power resource usage threshold includes a maximum usage threshold and a minimum usage threshold. The maximum usage threshold can be understood as the upper limit allowing the computing power resources to be used, and the minimum usage threshold can be understood as the lower limit where the computing power resources must be used.

[0077] When the computing power resource utilization rate of the computing power instances allocated to the computing power operation task is greater than the maximum usage threshold, it indicates that the computing power operation task needs to obtain more computing power resources at this time to ensure the normal execution of the computing power operation task. At this time, the intelligent computing center can increase the number of computing power instances allocated to the computing power operation task within the range of the number of computing power instances, so as to increase the computing power resources allocated to the computing power operation task. Exemplarily, during the execution of a certain model inference task, the set range of the number of computing power instances is 2 to 8, the computing power resource usage threshold is 20% to 80%, the number of instances allocated to the model inference task is 3, and the GPU utilization rate of each instance exceeds 80%. Then, the number of instances can be appropriately increased, increased to 4 or 5, until reaching 8, so as to ensure the normal execution of the model inference task.

[0078] When the computing power resource utilization rate of the computing power instances allocated to the computing power operation task is less than the minimum usage threshold, it indicates that some of the computing power resources already allocated to the computing power operation task are in an idle or under-utilized state. Then, the intelligent computing center can appropriately release the number of computing power instances allocated to the computing power operation task within the range of the number of computing power instances, so as to reduce the computing power resources allocated to the computing power operation task. Exemplarily, during the execution of a certain model inference task, the set range of the number of computing power instances is 2 to 8, the computing power resource usage threshold is 20% to 80%, the number of instances allocated to the model inference task is 3, and the GPU utilization rate of one instance is lower than 20%. Then, this instance can be released and allocated to other tasks with requirements, so as to improve the utilization rate of resources.

[0079] In one embodiment, after the step S3, the method further includes:

[0080] Step S4, monitoring the load condition of the execution of the computing power operation task;

[0081] Step S5, adjusting the range of the number of computing power instances according to the load condition of the computing power operation task.

[0082] The intelligent computing center continuously monitors the load condition of the execution of the computing power operation task. The load condition of the execution of the computing power operation task may include GPU load, CPU load, memory load, etc. When the load of the computing power operation task continuously increases, the range of the number of computing power instances can be expanded; when the load of the computing power operation task continuously decreases, the range of the number of computing power instances can be reduced.

[0083] In the above embodiment, the intelligent computing center continuously monitors the load condition of the task and dynamically adjusts the range of the number of computing power instances according to the load change, so as to achieve the maximization of resource utilization rate and the minimization of cost.

[0084] In one embodiment, the range of the number of computing power instances includes a minimum number of computing power instances and a maximum number of computing power instances, and the step S5 includes at least one of the following:

[0085] Step S51: When the load of the computing power operation task lasts for a preset duration and is lower than the first adjustment threshold, reduce the minimum number of computing power instances;

[0086] Step S52: When the load of the computing power operation task lasts for the preset duration and is higher than the second adjustment threshold, increase the maximum number of computing power instances, where the first adjustment threshold is less than the second adjustment threshold.

[0087] To avoid unnecessary resource adjustments due to short-term load fluctuations, a preset duration can be used as a time window, that is, the intelligent computing center will monitor the average load over a period of time, rather than just focusing on the instantaneous fluctuations of the load.

[0088] When the load of the computing power operation task lasts for a preset duration and is lower than the first adjustment threshold, the intelligent computing center will reduce the minimum number of computing power instances that the task can be allocated. Exemplarily, the minimum number of computing power instances for the computing power operation task is 2 virtual machines, the preset duration is 5 minutes, and the first adjustment threshold is 30% CPU utilization. If the CPU utilization continuously remains below 30% for more than 5 minutes, then the intelligent computing center will reduce the minimum number of computing power instances to 1 to reduce resource waste.

[0089] When the load of the computing power operation task lasts for a preset duration and is higher than the second adjustment threshold, the intelligent computing center will increase the maximum number of computing power instances that the task can be allocated. Exemplarily, the maximum number of computing power instances for the computing power operation task is 10 virtual machines, the preset duration is 5 minutes, and the second adjustment threshold is 70% CPU utilization. If the CPU utilization continuously remains above 70% for more than 5 minutes, the system will increase the maximum number of computing power instances to 12 to provide more computing resources and ensure the stable operation of the computing power operation task.

[0090] In one embodiment, the step S2 includes:

[0091] Step S21: Determine the computational complexity, execution time, and memory requirements of the computing power operation task according to the type of the computing power operation task;

[0092] Step S22: Configure a computing power resource adjustment strategy corresponding to the computing power operation task according to the computational complexity, execution time, and memory requirements of the computing power operation task.

[0093] The intelligent computing center first determines the computational complexity, execution time, and memory requirements of the computing power operation task according to the type of the computing power operation task. Computational complexity: refers to the amount of computation required for the task, usually measured by the number of floating-point operations (FLOPS) or the number of instructions. The higher the computational complexity, the more computing resources are required. Execution time: refers to the time required to complete the task. The longer the execution time, the more continuous computing resources are needed. Memory requirement: refers to the amount of memory required by the task during execution. The higher the memory requirement, the more memory resources need to be allocated. Exemplarily:

[0094] Deep learning training tasks: high computational complexity, long execution time, and large memory requirements.

[0095] Data analysis tasks: medium computational complexity, medium execution time, and medium memory requirements.

[0096] Video rendering tasks: high computational complexity, long execution time, and large memory requirements.

[0097] Then, according to the above analysis results, a suitable resource adjustment strategy is configured for the task.

[0098] In the above embodiments, by analyzing the type and characteristics of the task, a suitable resource configuration and adjustment strategy are determined in advance, thereby improving resource utilization and system performance. This method can avoid frequent resource adjustments during task execution, thereby reducing system overhead and latency.

[0099] In one embodiment, the request for the execution of the computing power operation task further includes the priority of the computing power operation task. Before step S3, the method further includes:

[0100] Step 6: Determine the priority of the computing power resource adjustment strategy according to the priority of the computing power operation task;

[0101] Step S3 includes:

[0102] Step S33: Dynamically adjust the computing power resources allocated to the computing power operation task based on the priority of the computing power resource adjustment strategy, according to the computing power resource usage situation of the computing power operation task during execution, the range of the number of computing power instances, and the computing power resource usage threshold.

[0103] The importance of tasks running with different computing powers varies. For example, the priority of a real-time computing task for a critical business is surely higher than that of a non-urgent background data analysis task. According to the priority of the computing power running tasks, the priority of the computing power resource adjustment strategy is determined, and then, based on the priority of the computing power resource adjustment strategy, the computing power resources allocated to the computing power running tasks are dynamically adjusted. That is, in the allocation of computing power resources, the priority of the tasks should be taken as the guidance to ensure that critical computing power running tasks receive sufficient computing power support.

[0104] In the above embodiments, by adjusting the priority of the strategy according to the task priority, it can be ensured that critical tasks always obtain sufficient computing power resources, thereby guaranteeing their performance and reliability.

[0105] Please refer to Figure 5 , Figure 5 which is the structural diagram of a dynamic adjustment device for computing power resources of an intelligent computing center provided by the present invention. As Figure 5 shown, the dynamic adjustment device 500 for computing power resources of the intelligent computing center includes:

[0106] A first receiving module 501, configured to receive a computing power running task execution request from a user, where the computing power running task execution request includes the type of the computing power running task;

[0107] A first configuration module 502, configured to configure a computing power resource adjustment strategy corresponding to the computing power running task according to the type of the computing power running task, where the computing power resource adjustment strategy includes a computing power instance quantity range and a computing power resource usage threshold;

[0108] A first adjustment module 503, configured to dynamically adjust the computing power resources allocated to the computing power running task according to the computing power resource usage situation of the computing power running task during execution, the computing power instance quantity range, and the computing power resource usage threshold.

[0109] In one embodiment, the computing power resource usage situation of the computing power running task includes the computing power resource utilization rate of the computing power instances allocated to the computing power running task, and the computing power resource usage threshold includes a maximum usage threshold and a minimum usage threshold. The first adjustment module 503 includes at least one of the following:

[0110] A first increasing unit, configured to, when the computing power resource utilization rate of the computing power instances allocated to the computing power running task is greater than the maximum usage threshold, increase the computing power instances allocated to the computing power running task within the computing power instance quantity range to increase the computing power resources allocated to the computing power running task;

[0111] A first release unit, configured to release the computing power instances allocated to the computing power operation task within the range of the number of computing power instances when the utilization rate of the computing power resources of the computing power instances allocated to the computing power operation task is less than the minimum usage threshold, so as to reduce the computing power resources allocated to the computing power operation task.

[0112] In one embodiment, the apparatus further includes:

[0113] A first monitoring module, configured to monitor the load condition of the execution of the computing power operation task;

[0114] A first adjustment module, configured to adjust the range of the number of computing power instances according to the load condition of the computing power operation task.

[0115] In one embodiment, the range of the number of computing power instances includes a minimum number of computing power instances and a maximum number of computing power instances, and the first adjustment module includes at least one of the following:

[0116] A first reduction unit, configured to reduce the minimum number of computing power instances when the load of the computing power operation task remains below a first adjustment threshold for a preset duration;

[0117] A second increase unit, configured to increase the maximum number of computing power instances when the load of the computing power operation task remains above a second adjustment threshold for the preset duration, where the first adjustment threshold is less than the second adjustment threshold.

[0118] In one embodiment, the first configuration module 502 includes:

[0119] A first determination unit, configured to determine the computing complexity, execution time, and memory requirement of the computing power operation task according to the type of the computing power operation task;

[0120] A first configuration unit, configured to configure a computing power resource adjustment policy corresponding to the computing power operation task according to the computing complexity, execution time, and memory requirement of the computing power operation task.

[0121] In one embodiment, the computing power operation task execution request further includes the priority of the computing power operation task, and the apparatus further includes:

[0122] A first determination module, configured to determine the priority of the computing power resource adjustment policy according to the priority of the computing power operation task;

[0123] The first adjustment module 503 includes:

[0124] The first adjustment unit is configured to dynamically adjust the computing power resources allocated to the computing power operation task based on the priority of the computing power resource adjustment policy, according to the computing power resource usage situation during the execution of the computing power operation task, the computing power instance quantity range, and the computing power resource usage threshold.

[0125] The computing power resource dynamic adjustment device of the intelligent computing center provided by the present invention can implement each process of the above-mentioned computing power resource dynamic adjustment method of the intelligent computing center. The technical features correspond one by one and can achieve the same technical effects. To avoid repetition, they will not be elaborated here.

[0126] It should be noted that the computing power resource dynamic adjustment device of the intelligent computing center in the present invention can be a device, or a component, an integrated circuit, or a chip in an electronic device.

[0127] The present invention also provides an electronic device. Refer to Figure 6 , Figure 6 which is a schematic structural diagram of an electronic device provided in an embodiment of the present invention. The electronic device includes a memory 601, a processor 602, and a program or instruction running on the memory 601. When the program or instruction is executed by the processor 602, it can implement Figure 1 any step in the corresponding embodiment of the computing power resource dynamic adjustment method of the intelligent computing center and achieve the same beneficial effects. Details will not be repeated here.

[0128] Among them, the processor 602 can be a CPU, an ASIC, an FPGA, or a GPU.

[0129] Those of ordinary skill in the art can understand that all or part of the steps of implementing the above-mentioned embodiment of the computing power resource dynamic adjustment method of the intelligent computing center can be completed by hardware related to program instructions. The program can be stored in a readable medium.

[0130] The present invention also provides a readable storage medium, on which a computer program is stored. When the computer program is executed by a processor, it can implement the above-mentioned Figure 1 any step in the corresponding embodiment of the computing power resource dynamic adjustment method of the intelligent computing center and can achieve the same technical effects. To avoid repetition, they will not be elaborated here. The storage medium is, for example, a read-only memory (ROM), a random access memory (RAM), a magnetic disk, or an optical disc, etc.

[0131] The present invention also provides a computer program product, including computer instructions. When the computer instructions are executed by a processor, they implement the above-mentioned Figure 1The various processes of the embodiment of the method for dynamically adjusting the computing power resources of the corresponding intelligent computing center can achieve the same technical effects. To avoid repetition, they will not be elaborated here.

[0132] The terms "first", "second", etc. in the present invention are used to distinguish similar objects and do not necessarily describe a specific order or sequence. In addition, the terms "comprising" and "having" and any variations thereof are intended to cover non-exclusive inclusion. For example, a process, method, system, product, or device comprising a series of steps or units does not necessarily have to be limited to those clearly listed steps or units, but may include other steps or units not clearly listed or inherent to these processes, methods, products, or devices. In addition, in this application, the use of "and / or" means at least one of the connected objects. For example, A and / or B and / or C means including the 7 cases of A alone, B alone, C alone, A and B both present, B and C both present, A and C both present, and A, B, and C all present.

[0133] It should be noted that in this article, the term "comprising", "including" or any other variant thereof is intended to cover non-exclusive inclusion, so that a process, method, article or device comprising a series of elements not only includes those elements, but also includes other elements not explicitly listed, or also includes elements inherent to such a process, method, article or device. Without further limitation, an element defined by the statement "comprising one..." does not exclude the existence of another identical element in the process, method, article or device comprising that element.

[0134] Through the description of the above embodiments, those skilled in the art can clearly understand that the above-described embodiment methods can be implemented by means of software plus a necessary general hardware platform. Of course, they can also be implemented by hardware, but in many cases the former is a better implementation. Based on such an understanding, the technical solution of this application, in essence, or the part that contributes to the prior art, can be embodied in the form of a software product. This computer software product is stored in a storage medium (such as ROM / RAM, magnetic disk, optical disk) and includes several instructions to enable a terminal (which can be a mobile phone, computer, server, air conditioner, or a second terminal device, etc.) to execute the methods of the various embodiments of this application.

[0135] The above describes the embodiments of this application in conjunction with the accompanying drawings. However, this application is not limited to the above specific embodiments. The above specific embodiments are merely illustrative and not restrictive. Under the inspiration of this application, those of ordinary skill in the art can also make many forms without departing from the purpose of this application and the scope protected by the claims, and all of them belong to the protection scope of this application.

Claims

1. A method for dynamically adjusting computing power resources of an intelligent computing center, characterized in that, Including: Step S1: Receive a computing power operation task execution request from a user, where the computing power operation task execution request includes the type of the computing power operation task; Step S2: Configure a computing power resource adjustment strategy corresponding to the computing power operation task according to the type of the computing power operation task, where the computing power resource adjustment strategy includes a computing power instance quantity range and a computing power resource usage threshold; Step S3: Dynamically adjust the computing power resources allocated to the computing power operation task according to the computing power resource usage situation of the computing power operation task during execution, the computing power instance quantity range, and the computing power resource usage threshold.

2. The method according to claim 1, wherein The computing power resource usage situation of the computing power operation task includes the computing power resource utilization rate of the computing power instances allocated to the computing power operation task, and the computing power resource usage threshold includes a maximum usage threshold and a minimum usage threshold. Step S3 includes at least one of the following: Step S31: When the computing power resource utilization rate of the computing power instances allocated to the computing power operation task is greater than the maximum usage threshold, increase the computing power instances allocated to the computing power operation task within the computing power instance quantity range to increase the computing power resources allocated to the computing power operation task; Step S32: When the computing power resource utilization rate of the computing power instances allocated to the computing power operation task is less than the minimum usage threshold, release the computing power instances allocated to the computing power operation task within the computing power instance quantity range to reduce the computing power resources allocated to the computing power operation task.

3. The method according to claim 1, wherein After Step S3, the method further includes: Step S4: Monitor the load situation of the execution of the computing power operation task; Step S5: Adjust the computing power instance quantity range according to the load situation of the computing power operation task.

4. The method according to claim 3, wherein The computing power instance quantity range includes a minimum computing power instance quantity and a maximum computing power instance quantity. Step S5 includes at least one of the following: Step S51: When the load of the computing power operation task continuously lasts for a preset duration and is lower than a first adjustment threshold, reduce the minimum computing power instance quantity; Step S52: When the load of the computing power operation task continuously lasts for the preset duration and is higher than a second adjustment threshold, increase the maximum computing power instance quantity, where the first adjustment threshold is less than the second adjustment threshold.

5. The method according to any one of claims 1 to 4, characterized in that Step S2 includes: Step S21: Determine the computing complexity, execution time, and memory requirement of the computing power operation task according to the type of the computing power operation task; Step S22: Configure a computing power resource adjustment strategy corresponding to the computing power operation task according to the computing complexity, execution time, and memory requirement of the computing power operation task.

6. The method according to any one of claims 1 to 4, characterized in that The computing power operation task execution request further includes the priority of the computing power operation task. Before Step S3, the method further includes: Step 6: Determine the priority of the computing power resource adjustment strategy according to the priority of the computing power operation task; Step S3 includes: Step S33: Based on the priority of the computing power resource adjustment policy, dynamically adjust the computing power resources allocated to the computing power operation task according to the computing power resource usage of the computing power operation task during execution, the computing power instance quantity range, and the computing power resource usage threshold.

7. A computing power resource dynamic adjustment device for an intelligent computing center, characterized in that, Including: A first receiving module, configured to receive a computing power operation task execution request from a user, where the computing power operation task execution request includes the type of the computing power operation task; A first configuration module, configured to configure a computing power resource adjustment policy corresponding to the computing power operation task according to the type of the computing power operation task, where the computing power resource adjustment policy includes a computing power instance quantity range and a computing power resource usage threshold; A first adjustment module, configured to dynamically adjust the computing power resources allocated to the computing power operation task according to the computing power resource usage of the computing power operation task during execution, the computing power instance quantity range, and the computing power resource usage threshold.

8. An electronic device, characterized in that, Including: A processor, a memory, and a program stored on the memory and executable on the processor, where when the program is executed by the processor, the steps of the method for dynamically adjusting the computing power resources of the intelligent computing center according to any one of claims 1 to 6 are implemented.

9. A computer-readable storage medium, characterized in that, A computer program is stored on the computer-readable storage medium, and when the computer program is executed by a processor, the steps of the method for dynamically adjusting the computing power resources of the intelligent computing center according to any one of claims 1 to 6 are implemented.

10. A computer program product, characterized in that, Including computer instructions, and when the computer instructions are executed by a processor, the steps of the method for dynamically adjusting the computing power resources of the intelligent computing center according to any one of claims 1 to 6 are implemented.

Images