Scheduling management method and device for cloud computing resources, equipment and storage medium

Abstract

The invention discloses a scheduling management method, device and equipment for cloud computing resources and a storage medium, and relates to the technical field of computers, and the method comprises the steps: inputting a current index of the cloud computing resources into a pre-trained resource scheduling model, so that the resource scheduling model determines a prediction index corresponding to a prediction moment according to the current index, the prediction moment is a moment of a preset time period after the current moment corresponding to the current index; by comparing each prediction index with an index threshold value, determining a prediction capacity expansion and contraction demand at a prediction moment; according to the real-time index and the index threshold value corresponding to the prediction moment, determining a real-time capacity expansion and contraction demand of the prediction moment; and performing scheduling management on the cloud computing resources according to the predicted capacity expansion and contraction demand and the real-time capacity expansion and contraction demand at the prediction moment. According to the technical scheme, the cloud computing resources are dynamically allocated according to the actual capacity expansion and contraction demand determined by combining the predicted capacity expansion and contraction demand and the real-time capacity expansion and contraction demand of the cloud computing resources at the prediction moment, and the utilization rate of the cloud computing resources is increased.

Description

Technical Field

[0001] Embodiments of the present invention relate to the field of computer technology, and in particular to a scheduling management method, apparatus, device, and storage medium for cloud computing resources. Background Art

[0002] With the rapid development of information technology, financial enterprises are increasingly demanding data processing and analysis. Data processing based on traditional local computing models suffers from problems such as low resource utilization, poor scalability, high maintenance costs, and low data timeliness.

[0003] In the prior art, business systems can process and analyze data through cloud computing resources. To maximize efficiency, cloud computing resources are usually operated with maximum online resources and maximum batch resources.

[0004] However, given that the financial sector experiences higher online transaction volumes during the day and higher batch transaction volumes at night, cloud computing resources are more frequently used online during the day, while batch resources are more frequently used at night. This means that cloud computing resources have different demands at different times of the day. Continuously operating cloud computing resources at maximum online and batch capacity would result in significant resource waste. Summary of the Invention

[0005] The present invention provides a scheduling management method, device, equipment and storage medium for cloud computing resources, which realizes reasonable dynamic allocation of cloud computing resources through scheduling management of cloud computing resources.

[0006] In a first aspect, an embodiment of the present invention provides a scheduling and management method for cloud computing resources, including:

[0007] Inputting the current indicator of the cloud computing resource into a pre-trained resource scheduling model, so that the resource scheduling model determines the prediction indicator corresponding to the prediction moment according to the current indicator, wherein the prediction moment is a moment within a preset time period after the current moment corresponding to the current indicator;

[0008] Determining the predicted expansion and contraction requirements at the predicted time by comparing the prediction indicators and indicator thresholds;

[0009] Determine the real-time scaling requirement at the predicted time according to the real-time indicator corresponding to the predicted time and the indicator threshold;

[0010] The cloud computing resources are scheduled and managed according to the predicted scaling demand at the predicted time and the real-time scaling demand.

[0011] The technical solution of an embodiment of the present invention provides a scheduling and management method for cloud computing resources, including: inputting current indicators of cloud computing resources into a pre-trained resource scheduling model, so that the resource scheduling model determines the prediction indicators corresponding to the prediction moment based on the current indicators, wherein the prediction moment is a moment within a preset time period after the current moment corresponding to the current indicators; determining the predicted scaling demand at the prediction moment by comparing each of the prediction indicators and the indicator threshold; determining the real-time scaling demand at the prediction moment based on the real-time indicators corresponding to the prediction moment and the indicator threshold; and scheduling and managing the cloud computing resources based on the predicted scaling demand and the real-time scaling demand at the prediction moment. The above technical solution, after obtaining the current indicators of the cloud computing resources corresponding to each business system, inputs the current indicators of the cloud computing resources into the resource scheduling model, and determines the predicted indicators of the cloud computing resources at the predicted time within a preset period after the current time corresponding to the current indicators are obtained based on the resource scheduling model, thereby achieving a reasonable prediction of the cloud computing resource indicators. Next, the predicted indicators at the predicted time output by the resource scheduling model can be compared with the indicator threshold to determine the predicted scaling demand of the cloud computing resources at the predicted time, thereby achieving a prediction of the scaling demand of the cloud computing resources at the predicted time. After determining that the predicted time has arrived, the real-time indicators obtained in real time at the predicted time can be compared with the indicator threshold to determine the real-time scaling demand of the cloud computing resources at the predicted time, thereby achieving a determination of the real-time scaling demand of the cloud computing resources at the predicted time. Furthermore, the actual scaling demand of the cloud computing resources can be determined by combining the predicted scaling demand and the real-time scaling demand of the cloud computing resources at the predicted time. The cloud computing resources are then scheduled and managed based on the actual scaling demand of the cloud computing resources, thereby achieving dynamic allocation of cloud computing resources, improving the utilization rate of cloud computing resources, and thereby reducing the waste of cloud computing resources and lowering data processing costs.

[0012] Furthermore, the indicator threshold includes an indicator upper limit and an indicator lower limit. Accordingly, by comparing each of the prediction indicators and the indicator threshold, the predicted expansion and contraction requirements at the prediction moment are determined, including:

[0013] When it is determined that any of the predicted indicators is greater than the indicator upper limit, determining that the predicted expansion and contraction demand at the predicted moment requires expansion;

[0014] When it is determined that each of the prediction indicators is not greater than the indicator lower limit, determining that the predicted expansion and contraction demand at the prediction moment requires contraction;

[0015] Accordingly, determining the real-time scaling requirement at the prediction moment according to the real-time indicator corresponding to the prediction moment and the indicator threshold includes:

[0016] When it is determined that any of the real-time indicators is greater than the indicator upper limit, determining that the real-time expansion and contraction demand at the predicted moment requires expansion;

[0017] When it is determined that each of the real-time indicators is not greater than the indicator lower limit, it is determined that the real-time expansion and contraction demand at the predicted moment requires capacity reduction.

[0018] Furthermore, the cloud computing resource indicators include at least central processing unit (CPU) usage, memory usage, number of threads, disk IO usage, and network bandwidth usage.

[0019] Furthermore, the indicator threshold includes an indicator upper limit and an indicator lower limit corresponding to each indicator. Accordingly, by comparing each of the predicted indicators and the indicator threshold, the predicted expansion and contraction requirements at the predicted time are determined, including:

[0020] When it is determined that any of the predicted indicators is greater than the corresponding indicator upper limit, determining that the predicted expansion and contraction demand at the predicted moment requires expansion;

[0021] When it is determined that each of the prediction indicators is not greater than the corresponding indicator lower limit, determining that the predicted expansion and contraction demand at the prediction time is that capacity reduction is required;

[0022] Accordingly, determining the real-time scaling requirement at the prediction moment according to the real-time indicator corresponding to the prediction moment and the indicator threshold includes:

[0023] When it is determined that any of the real-time indicators is greater than the corresponding indicator upper limit, determining that the real-time scaling demand at the predicted moment requires expansion;

[0024] When it is determined that each of the real-time indicators is not greater than the corresponding indicator lower limit, it is determined that the real-time expansion and contraction demand at the predicted moment requires contraction.

[0025] Furthermore, scheduling and managing the cloud computing resources according to the predicted scaling demand at the predicted time and the real-time scaling demand includes:

[0026] When it is determined that the predicted capacity expansion demand and / or the real-time capacity expansion demand at the predicted time is capacity expansion, expanding the cloud computing resources according to the predicted capacity expansion demand and the real-time capacity expansion demand;

[0027] When it is determined that the predicted scaling demand and / or the real-time scaling demand at the prediction moment is scaling down, the cloud computing resources are scaled down according to the predicted scaling demand and the real-time scaling demand.

[0028] Furthermore, the cloud computing resources are used to process the business data stored in the server by the business system.

[0029] Furthermore, the resource scheduling model is trained by the following method:

[0030] Obtaining historical indicators of the cloud computing resources in a historical time period;

[0031] Determining a historical prediction indicator corresponding to the historical indicator, wherein the historical prediction indicator is obtained within a preset time period after the historical indicator;

[0032] The resource scheduling model is obtained by performing network training using the historical indicators as training inputs and the historical prediction indicators corresponding to the historical indicators as guidance for training outputs.

[0033] In a second aspect, an embodiment of the present invention further provides a scheduling and management device for cloud computing resources, including:

[0034] A prediction module, configured to input current indicators of cloud computing resources into a pre-trained resource scheduling model, so that the resource scheduling model determines a prediction indicator corresponding to a prediction moment based on the current indicators;

[0035] A comparison module, configured to determine the predicted expansion and contraction requirements at the predicted moment by comparing the prediction indicators with the indicator thresholds;

[0036] A determination module, configured to determine the real-time scaling requirement at the predicted moment based on the real-time indicator corresponding to the predicted moment and the indicator threshold;

[0037] A management module is used to schedule and manage the cloud computing resources according to the predicted expansion and contraction requirements at the predicted time and the real-time expansion and contraction requirements.

[0038] In a third aspect, an embodiment of the present invention further provides an electronic device, comprising:

[0039] at least one processor; and a memory communicatively coupled to the at least one processor;

[0040] In which, the memory stores a computer program that can be executed by the at least one processor, and the computer program is executed by the at least one processor so that the at least one processor can execute the scheduling and management method of cloud computing resources as described in any one of the first aspects.

[0041] In a fourth aspect, an embodiment of the present invention further provides a storage medium comprising computer-executable instructions, which, when executed by a computer processor, are used to execute the scheduling and management method for cloud computing resources as described in any one of the first aspects.

[0042] In a fifth aspect, the present application provides a computer program product, which includes computer instructions. When the computer instructions are executed on a computer, the computer executes the scheduling and management method for cloud computing resources provided in the first aspect.

[0043] It should be noted that the aforementioned computer instructions may be stored in whole or in part on a computer-readable storage medium. The computer-readable storage medium may be packaged together with the processor of the cloud computing resource scheduling and management device, or may be packaged separately from the processor of the cloud computing resource scheduling and management device, and this application does not limit this.

[0044] The descriptions of the second, third, fourth and fifth aspects of this application can refer to the detailed description of the first aspect; and the beneficial effects of the descriptions of the second, third, fourth and fifth aspects can refer to the analysis of the beneficial effects of the first aspect, which will not be repeated here.

[0045] In this application, the name of the cloud computing resource scheduling and management device does not limit the device or functional module itself. In actual implementation, these devices or functional modules may appear with other names. As long as the functions of each device or functional module are similar to those of this application, they are within the scope of the claims of this application and their equivalents.

[0046] These and other aspects of the present application will become more readily apparent from the following description. BRIEF DESCRIPTION OF THE DRAWINGS

[0047] In order to more clearly illustrate the technical solutions in the embodiments of the present invention, the following briefly introduces the drawings required for use in the description of the embodiments. Obviously, the drawings described below are only some embodiments of the present invention. For ordinary technicians in this field, other drawings can be obtained based on these drawings without creative work.

[0048] Figure 1 A flowchart of a method for scheduling and managing cloud computing resources provided by an embodiment of the present invention;

[0049] Figure 2 A schematic diagram of a data processing system in a scheduling and management method for cloud computing resources provided by an embodiment of the present invention;

[0050] Figure 3 A flowchart of another method for scheduling and managing cloud computing resources provided by an embodiment of the present invention;

[0051] Figure 4 A schematic diagram of the structure of a scheduling and management device for cloud computing resources provided by an embodiment of the present invention;

[0052] Figure 5 A schematic structural diagram of an electronic device provided by an embodiment of the present invention. DETAILED DESCRIPTION

[0053] The present invention will be further described in detail below with reference to the accompanying drawings and examples. It will be understood that the specific embodiments described herein are intended only to illustrate the present invention and are not intended to limit the present invention. It should also be noted that, for ease of description, the accompanying drawings only illustrate portions relevant to the present invention, not all structures.

[0054] The term "and / or" in this article is merely a description of the association relationship between associated objects, indicating that three relationships may exist. For example, A and / or B can mean: A exists alone, A and B exist at the same time, and B exists alone.

[0055] The terms "first" and "second" and the like in the specification and drawings of this application are used to distinguish different objects, or to distinguish different processing of the same object, rather than to describe a specific order of objects.

[0056] Furthermore, the terms "including," "having," and any variations thereof, as used in the description of this application are intended to cover non-exclusive inclusions. For example, a process, method, system, product, or apparatus comprising a series of steps or units is not limited to the listed steps or units but may optionally include other steps or units not listed, or may optionally include other steps or units inherent to the process, method, product, or apparatus.

[0057] It should be mentioned before discussing exemplary embodiments in more detail that some exemplary embodiments are described as processes or methods depicted as flow charts. Although flow charts describe various operations (or steps) as sequential processes, many operations therein can be implemented in parallel, concurrently or simultaneously. In addition, the order of various operations can be rearranged. When its operation is completed, the process can be terminated, but can also have additional steps not included in the accompanying drawings. The process can correspond to methods, functions, procedures, subroutines, subprograms, etc. In addition, the features in the embodiments of the present invention and the embodiments can be combined with each other without conflict.

[0058] It should be noted that in the embodiments of this application, words such as "exemplary" or "for example" are used to indicate examples, illustrations, or descriptions. Any embodiment or design described as "exemplary" or "for example" in the embodiments of this application should not be interpreted as being more preferred or advantageous over other embodiments or designs. Rather, the use of words such as "exemplary" or "for example" is intended to present the relevant concepts in a concrete manner.

[0059] In the description of the present application, unless otherwise specified, “plurality” means two or more.

[0060] Figure 1 This is a flow chart of a scheduling management method for cloud computing resources provided by an embodiment of the present invention. This embodiment is applicable to situations where cloud computing resources need to be scheduled according to their usage. The method can be executed by a scheduling management device for cloud computing resources, such as Figure 1 As shown, the specific steps include:

[0061] Step 110: Input the current indicators of the cloud computing resources into a pre-trained resource scheduling model, so that the resource scheduling model determines the prediction indicators corresponding to the prediction time according to the current indicators.

[0062] The predicted time is a time within a preset time period after the current time corresponding to the current indicator.

[0063] Figure 2 A schematic diagram of a data processing system in a scheduling and management method for cloud computing resources provided by an embodiment of the present invention, such as Figure 2 As shown, the data processing system includes at least one business system ( Figure 2 The cloud computing resources in the embodiment of the present invention can be understood as cloud computing resources allocated to each business system.

[0064] The resource scheduling model is trained based on the historical indicators of cloud computing resources within a historical time period, and can be used to determine the indicators of cloud computing resources after a preset time period based on their indicators at the current moment.

[0065] Specifically, first, the current indicators of each business system can be obtained. For each cloud computing resource, the current indicators of the cloud computing resource can be input into a pre-trained resource scheduling model. The resource scheduling model can predict the indicators of the predicted time in the preset period after the current moment corresponding to the current indicator is obtained based on the current indicators of the cloud computing resource, and determine the predicted indicators corresponding to the predicted time.

[0066] In an embodiment of the present invention, by inputting the current indicators of cloud computing resources into a resource scheduling model, the predicted indicators of the cloud computing resources at a predicted time in a preset period after the current time corresponding to the current indicators are obtained are determined based on the resource scheduling model, thereby achieving a reasonable prediction of the cloud computing resource indicators.

[0067] Step 120: Determine the predicted expansion / contraction requirements at the predicted time by comparing the prediction indicators with the indicator thresholds.

[0068] The indicator threshold may include an upper limit and a lower limit of the prediction indicator. If the prediction indicator exceeds the upper limit, it indicates that the cloud computing resources need to be expanded. If the prediction indicator does not exceed the lower limit, it indicates that the cloud computing resources need to be reduced.

[0069] Specifically, after the resource scheduling model outputs the prediction indicators corresponding to the prediction time, each prediction indicator and the indicator threshold can be compared. If any prediction indicator is greater than the upper limit of the indicator contained in the indicator threshold, it indicates that the predicted expansion and contraction demand at the prediction time requires expansion. If each prediction indicator is less than the lower limit of the indicator contained in the indicator threshold, it indicates that the predicted expansion and contraction demand at the prediction time requires contraction. Otherwise, it is determined that the predicted expansion and contraction demand at the prediction time does not require expansion or contraction.

[0070] In an embodiment of the present invention, by comparing the prediction indicators and indicator thresholds at the prediction time output by the resource scheduling model, the predicted expansion and contraction requirements of the cloud computing resources at the prediction time are determined, thereby realizing the prediction of the expansion and contraction requirements of the cloud computing resources at the prediction time.

[0071] Step 130: Determine the real-time scaling requirement at the prediction time based on the real-time indicator corresponding to the prediction time and the indicator threshold.

[0072] Specifically, after determining that the predicted time has arrived, the real-time indicators of the cloud computing resources corresponding to each business system at the predicted time can first be obtained in the scheduling module. Secondly, the real-time scaling requirements at the predicted time can be determined based on the real-time indicators of the cloud computing resources at the predicted time and the indicator threshold. Specifically, each real-time indicator and the indicator threshold can be compared. If any real-time indicator is greater than the indicator upper limit contained in the indicator threshold, it indicates that the real-time scaling requirement at the predicted time requires expansion. If all real-time indicators are less than the indicator lower limit contained in the indicator threshold, it indicates that the real-time scaling requirement at the predicted time requires scaling. Otherwise, it is determined that the real-time scaling requirement at the predicted time does not require scaling.

[0073] In an embodiment of the present invention, by comparing the real-time indicators and indicator thresholds obtained in real time at the prediction time, the real-time expansion and contraction requirements of cloud computing resources at the prediction time are determined, thereby realizing the determination of the real-time expansion and contraction requirements of cloud computing resources at the prediction time.

[0074] Step 140: Schedule and manage the cloud computing resources according to the predicted scaling demand at the predicted time and the real-time scaling demand.

[0075] The aforementioned steps have determined the predicted scaling requirements and real-time scaling requirements at the prediction time. Therefore, cloud computing resources can be scheduled and managed in a manner that combines the predicted scaling requirements and real-time scaling requirements at the prediction time.

[0076] Specifically, if the predicted scaling requirements at the prediction time match the real-time scaling requirements, then if both scaling requirements indicate a need for expansion, the cloud computing resources will be expanded; if both scaling requirements indicate a need for contraction, the cloud computing resources will be contracted. If the predicted scaling requirements at the prediction time do not match the real-time scaling requirements, then if one scaling requirement indicates no need for expansion, the cloud computing resources will be expanded or contracted based on the other scaling requirement.

[0077] In an embodiment of the present invention, the actual scaling demand of cloud computing resources is determined by combining the predicted scaling demand and real-time scaling demand of cloud computing resources at the predicted time, and cloud computing resources are scheduled and managed based on the actual scaling demand of cloud computing resources to achieve dynamic allocation of cloud computing resources.

[0078] The scheduling and management method for cloud computing resources provided by an embodiment of the present invention includes: inputting the current indicators of cloud computing resources into a pre-trained resource scheduling model, so that the resource scheduling model determines the prediction indicators corresponding to the prediction moment based on the current indicators, wherein the prediction moment is a moment within a preset time period after the current moment corresponding to the current indicators; determining the predicted scaling demand at the prediction moment by comparing each of the prediction indicators and the indicator threshold; determining the real-time scaling demand at the prediction moment based on the real-time indicators corresponding to the prediction moment and the indicator threshold; and scheduling and managing the cloud computing resources based on the predicted scaling demand and the real-time scaling demand at the prediction moment. The above technical solution, after obtaining the current indicators of the cloud computing resources corresponding to each business system, inputs the current indicators of the cloud computing resources into the resource scheduling model, and determines the predicted indicators of the cloud computing resources at the predicted time within a preset period after the current time corresponding to the current indicators are obtained based on the resource scheduling model, thereby achieving a reasonable prediction of the cloud computing resource indicators. Next, the predicted indicators at the predicted time output by the resource scheduling model can be compared with the indicator threshold to determine the predicted scaling demand of the cloud computing resources at the predicted time, thereby achieving a prediction of the scaling demand of the cloud computing resources at the predicted time. After determining that the predicted time has arrived, the real-time indicators obtained in real time at the predicted time can be compared with the indicator threshold to determine the real-time scaling demand of the cloud computing resources at the predicted time, thereby achieving a determination of the real-time scaling demand of the cloud computing resources at the predicted time. Furthermore, the actual scaling demand of the cloud computing resources can be determined by combining the predicted scaling demand and the real-time scaling demand of the cloud computing resources at the predicted time. The cloud computing resources are then scheduled and managed based on the actual scaling demand of the cloud computing resources, thereby achieving dynamic allocation of cloud computing resources, improving the utilization rate of cloud computing resources, and thereby reducing the waste of cloud computing resources and lowering data processing costs.

[0079] Figure 3 This is a flow chart of another method for scheduling and managing cloud computing resources provided by an embodiment of the present invention. This embodiment is specific based on the above embodiment. Figure 3 As shown, in this embodiment, the method may further include:

[0080] Step 310: Input the current indicators of the cloud computing resources into a pre-trained resource scheduling model, so that the resource scheduling model determines the prediction indicators corresponding to the prediction time according to the current indicators.

[0081] Cloud computing resources are used to process business data stored in the server by the business system, such as Figure 2As shown, after the first business system sends the first business data to the corresponding cloud computing resource, the cloud computing resource processes the first business data. The first business system accesses the shared storage module based on the first username. The shared storage module stores the processed first business data in the directory corresponding to the first business system in the shared storage module based on permission control. For business flow, the business data processed by the first business system still needs to be processed by the second business system. Based on this business flow, the second business system can monitor the directory corresponding to the first business system in the shared storage module. If the target contains a new file, the second business system accesses the shared storage module based on the second username. The shared storage module allows the second user to access the processed first business data based on permission control. Then, the second business system can continue to process the processed first business data to obtain result data. The shared storage module can store the result data in the directory corresponding to the second business system in the shared storage module based on permission control for subsequent business flow. Of course, if there are no new files in the directory corresponding to the first business system in the shared storage module, the monitoring will be repeated after a preset time to ensure the normal operation of the business flow.

[0082] In actual applications, you can set permissions for shared storage module directories using user names. For example, the first business system has rwx permissions for the / user / 1 / directory, and the second business system has rwx permissions for the / user / 2 / directory and r-- permissions for the / user / 1 / directory. The first digit in the rwx and r-- permissions represents read permission (r means permission granted, - means no permission granted). The second digit represents write permission (w means permission granted, - means no permission granted). The third digit represents execute permission (x means permission granted, - means no permission granted).

[0083] The cloud computing resource indicators include at least CPU usage, memory usage, number of threads, disk IO usage, and network bandwidth usage. The prediction time is the time within a preset time period after the current time corresponding to the current indicator.

[0084] Specifically, the real-time indicators of the cloud computing resources corresponding to each business system at the current moment, i.e., the current indicators of the cloud computing resources, can be first obtained. For each cloud computing resource, the current indicators of the cloud computing resource can be input into a pre-trained resource scheduling model. Based on the current indicators of the cloud computing resource, the resource scheduling model can predict the indicators at a predicted moment in a preset period after the current moment corresponding to the obtained current indicators, and determine the predicted indicators corresponding to the predicted moments.

[0085] In one embodiment, the resource scheduling model is trained by the following method:

[0086] Obtain historical indicators of the cloud computing resources in a historical time period; determine historical prediction indicators corresponding to the historical indicators, wherein the historical prediction indicators are obtained in a preset time period after the historical indicators; perform network training using the historical indicators as training input and the historical prediction indicators corresponding to the historical indicators to guide training output, to obtain the resource scheduling model.

[0087] Specifically, first, the historical indicators of cloud computing resources in the historical time period can be obtained. Since the resource scheduling model needs to predict the indicators of the second moment in the preset time period after the first moment based on the indicators of the first moment, the historical moment indicators of each historical moment in the historical time period can be determined based on the historical indicators of the historical time period, and then the historical prediction indicators corresponding to each historical moment can be determined based on the historical moment indicators of each historical moment. That is, for each historical moment, the indicators of the moment in the preset time period after the historical moment can be determined as the historical prediction indicators corresponding to the historical moment, and then the historical indicators and the historical prediction indicators corresponding to the historical indicators can be used as training sets to train the network model. The resource scheduling model obtained by training can be used to determine the indicators of the cloud computing resources after the preset time period based on the indicators of the current moment.

[0088] In an embodiment of the present invention, by inputting the current indicators of cloud computing resources into a resource scheduling model, the predicted indicators of the cloud computing resources at a predicted time in a preset period after the current time corresponding to the current indicators are obtained are determined based on the resource scheduling model, thereby achieving a reasonable prediction of the cloud computing resource indicators.

[0089] Step 320: Determine the predicted expansion / contraction requirements at the predicted time by comparing the prediction indicators with the indicator thresholds.

[0090] In one embodiment, the indicator threshold includes an indicator upper limit and an indicator lower limit. Accordingly, step 320 may specifically include:

[0091] When it is determined that any of the predicted indicators is greater than the upper limit of the indicator, the predicted expansion and contraction demand at the predicted time is determined to require expansion; when it is determined that each of the predicted indicators is not greater than the lower limit of the indicator, the predicted expansion and contraction demand at the predicted time is determined to require contraction.

[0092] Among them, the upper limit of the indicator and the lower limit of the indicator can be understood as the upper limit percentage and the lower limit percentage. For example, the upper limit percentage can be 80% and the lower limit percentage can be 1%. That is, if any prediction indicator is greater than 80% of its peak value, it indicates that the cloud computing resources need to be expanded at the prediction time. If each prediction indicator is less than 1% of its peak value, it indicates that the cloud computing resources need to be reduced at the prediction time.

[0093] Specifically, after the resource scheduling model outputs the prediction indicators corresponding to the prediction time, each prediction indicator and the indicator threshold can be compared. If any prediction indicator is greater than the upper limit of the indicator contained in the indicator threshold, it indicates that the predicted expansion and contraction demand at the prediction time requires expansion. If each prediction indicator is less than the lower limit of the indicator contained in the indicator threshold, it indicates that the predicted expansion and contraction demand at the prediction time requires contraction. Otherwise, it is determined that the predicted expansion and contraction demand at the prediction time does not require expansion or contraction.

[0094] In another embodiment, the indicator threshold includes an indicator upper limit and an indicator lower limit corresponding to each indicator. Accordingly, step 320 may specifically include:

[0095] When it is determined that any of the predicted indicators is greater than the corresponding indicator upper limit, the predicted expansion and contraction demand at the predicted time is determined to require expansion; when it is determined that each of the predicted indicators is not greater than the corresponding indicator lower limit, the predicted expansion and contraction demand at the predicted time is determined to require contraction.

[0096] Among them, the indicator upper limit and indicator lower limit can be understood as the numerical upper limit and numerical lower limit, that is, if any prediction indicator is greater than its corresponding numerical upper limit, it indicates that the cloud computing resources need to be expanded at the prediction time; if all prediction indicators are less than their corresponding numerical lower limits, it indicates that the cloud computing resources need to be reduced at the prediction time.

[0097] Specifically, after the resource scheduling model outputs the prediction indicators corresponding to the prediction time, each prediction indicator can be compared with the corresponding indicator threshold. If any prediction indicator is greater than its corresponding indicator upper limit, it indicates that the predicted expansion and contraction demand at the prediction time requires expansion. If each prediction indicator is less than its corresponding indicator lower limit, it indicates that the predicted expansion and contraction demand at the prediction time requires contraction. Otherwise, it is determined that the predicted expansion and contraction demand at the prediction time does not require expansion or contraction.

[0098] In an embodiment of the present invention, by comparing the prediction indicators and indicator thresholds at the prediction time output by the resource scheduling model, the predicted expansion and contraction requirements of the cloud computing resources at the prediction time are determined, thereby realizing the prediction of the expansion and contraction requirements of the cloud computing resources at the prediction time.

[0099] Step 330: Determine the real-time scaling requirement at the prediction time based on the real-time indicator corresponding to the prediction time and the indicator threshold.

[0100] In one embodiment, the indicator threshold includes an indicator upper limit and an indicator lower limit. Accordingly, step 330 may specifically include:

[0101] When it is determined that any of the real-time indicators is greater than the indicator upper limit, the real-time expansion and contraction demand at the predicted time is determined to require expansion; when it is determined that none of the real-time indicators is greater than the indicator lower limit, the real-time expansion and contraction demand at the predicted time is determined to require contraction.

[0102] Specifically, each real-time indicator and indicator threshold can be compared. If any real-time indicator is greater than the indicator upper limit included in the indicator threshold, it indicates that the real-time scaling demand at the predicted time requires expansion. If each real-time indicator is less than the indicator lower limit included in the indicator threshold, it indicates that the real-time scaling demand at the predicted time requires reduction. Otherwise, it is determined that the real-time scaling demand at the predicted time does not require expansion.

[0103] In another embodiment, the indicator threshold includes an indicator upper limit and an indicator lower limit corresponding to each indicator. Accordingly, step 330 may specifically include:

[0104] When it is determined that any of the real-time indicators is greater than the corresponding indicator upper limit, the real-time scaling demand at the predicted time is determined to require expansion; when it is determined that each of the real-time indicators is not greater than the corresponding indicator lower limit, the real-time scaling demand at the predicted time is determined to require reduction.

[0105] Specifically, each real-time indicator can be compared with the corresponding indicator threshold. If any real-time indicator is greater than its corresponding indicator upper limit, it indicates that the real-time scaling demand at the prediction moment requires expansion. If each real-time indicator is less than its corresponding indicator lower limit, it indicates that the real-time scaling demand at the prediction moment requires reduction. Otherwise, it is determined that the real-time scaling demand at the prediction moment does not require expansion.

[0106] In an embodiment of the present invention, by comparing the real-time indicators and indicator thresholds obtained in real time at the prediction time, the real-time expansion and contraction requirements of cloud computing resources at the prediction time are determined, thereby realizing the determination of the real-time expansion and contraction requirements of cloud computing resources at the prediction time.

[0107] Step 340: Schedule and manage the cloud computing resources according to the predicted scaling demand at the predicted time and the real-time scaling demand.

[0108] In one implementation, step 340 may specifically include:

[0109] When it is determined that the predicted expansion and contraction demand and / or the real-time expansion and contraction demand at the prediction moment is expansion, the cloud computing resources are expanded according to the predicted expansion and contraction demand and the real-time expansion and contraction demand; when it is determined that the predicted expansion and contraction demand and / or the real-time expansion and contraction demand at the prediction moment is contraction, the cloud computing resources are contracted according to the predicted expansion and contraction demand and the real-time expansion and contraction demand.

[0110] Specifically, if the predicted scaling demand at the prediction moment is consistent with the real-time scaling demand, then when both scaling demands indicate that expansion is required, the cloud computing resources are scaled; and when both scaling demands indicate that contraction is required, the cloud computing resources are scaled. If the predicted scaling demand at the prediction moment is inconsistent with the real-time scaling demand, then when one scaling demand does not require scaling, the cloud computing resources are scaled up or down based on the other scaling demand. For example, when the predicted scaling demand indicates that scaling is not required and the real-time scaling demand indicates that expansion is required, the cloud computing resources are scaled up; when the predicted scaling demand indicates that scaling is not required and the real-time scaling demand indicates that contraction is required, the cloud computing resources are scaled down; when the real-time scaling demand indicates that scaling is not required and the predicted scaling demand indicates that expansion is required, the cloud computing resources are scaled up; and when the real-time scaling demand indicates that scaling is not required and the predicted scaling demand indicates that contraction is required, the cloud computing resources are scaled down.

[0111] Of course, if the predicted scaling demand and the real-time scaling demand at the prediction time are inconsistent, and one of the scaling demands requires expansion and the other requires contraction, it indicates that the predicted scaling demand and / or the real-time scaling demand are incorrectly determined. At this time, an alarm message can be generated to remind the staff to check the relevant information and manually schedule and manage the cloud computing resources.

[0112] It should be noted that when expanding cloud computing resources, a step-by-step approach can be used. This means that you can first expand to a first preset capacity, and if the need for expansion persists after a preset period, you can expand to the first preset capacity again. Similarly, when scaling down cloud computing resources, a step-by-step approach can be used. This means that you can first scale down to a second preset capacity, and if the need for expansion persists after a preset period, you can scale down to the second preset capacity again.

[0113] In addition, the values of the first preset capacity and the second preset capacity can be set according to actual needs and are not specifically limited here.

[0114] In an embodiment of the present invention, the actual scaling demand of cloud computing resources is determined by combining the predicted scaling demand and real-time scaling demand of cloud computing resources at the predicted time, and cloud computing resources are scheduled and managed based on the actual scaling demand of cloud computing resources to achieve dynamic allocation of cloud computing resources.

[0115] The scheduling and management method for cloud computing resources provided by an embodiment of the present invention includes: inputting the current indicators of cloud computing resources into a pre-trained resource scheduling model, so that the resource scheduling model determines the prediction indicators corresponding to the prediction moment based on the current indicators, wherein the prediction moment is a moment within a preset time period after the current moment corresponding to the current indicators; determining the predicted scaling demand at the prediction moment by comparing each of the prediction indicators and the indicator threshold; determining the real-time scaling demand at the prediction moment based on the real-time indicators corresponding to the prediction moment and the indicator threshold; and scheduling and managing the cloud computing resources based on the predicted scaling demand and the real-time scaling demand at the prediction moment. The above technical solution, after obtaining the current indicators of the cloud computing resources corresponding to each business system, inputs the current indicators of the cloud computing resources into the resource scheduling model, and determines the predicted indicators of the cloud computing resources at the predicted time of the preset period after the current time corresponding to the current indicators are obtained based on the resource scheduling model, so as to realize the reasonable prediction of the cloud computing resource indicators. Then, the predicted indicators and indicator thresholds at the predicted time output by the resource scheduling model can be compared to determine the predicted expansion and contraction requirements of the cloud computing resources at the predicted time, so as to realize the prediction of the expansion and contraction requirements of the cloud computing resources at the predicted time. After determining that the predicted time has arrived, the predicted indicators obtained in real time at the predicted time can be compared. The real-time indicators and indicator thresholds are taken to determine the real-time expansion and contraction requirements of cloud computing resources at the prediction time, so as to realize the determination of the real-time expansion and contraction requirements of cloud computing resources at the prediction time, and then the actual expansion and contraction requirements of cloud computing resources can be determined in combination with the predicted expansion and contraction requirements and the real-time expansion and contraction requirements of cloud computing resources at the prediction time, and cloud computing resources can be scheduled and managed based on the actual expansion and contraction requirements of cloud computing resources, so as to realize the dynamic increase or decrease of cloud computing resources according to the changes in the cloud computing resource load, and then realize the dynamic allocation of cloud computing resources, improve the utilization rate of cloud computing resources, and reduce the waste of cloud computing resources and reduce data processing costs.

[0116] Furthermore, existing data storage models require that data be exported after processing and then transferred to downstream systems. Downstream systems monitor data import before processing begins. Large amounts of data can result in extended export, transfer, and import times. Furthermore, excessively long data transfer chains can significantly reduce data timeliness. The shared storage module controls access to different business systems based on permissions, resolving timeliness delays caused by data transmission and data waiting times. This enhances the stability and reliability of the data processing process, reduces data transmission losses, and improves data timeliness.

[0117] Figure 4This is a schematic diagram of the structure of a cloud computing resource scheduling and management device provided in an embodiment of the present invention. This device is applicable to situations where cloud computing resources need to be scheduled based on their usage, thereby improving the utilization of cloud computing resources. This device can be implemented using software and / or hardware and is generally integrated into electronic devices, such as computers.

[0118] like Figure 4 As shown, the device includes:

[0119] Prediction module 410, configured to input current indicators of cloud computing resources into a pre-trained resource scheduling model, so that the resource scheduling model determines a prediction indicator corresponding to a prediction moment based on the current indicators;

[0120] A comparison module 420 is configured to determine the predicted scaling requirements at the prediction moment by comparing the prediction indicators with the indicator thresholds;

[0121] A determination module 430 is configured to determine the real-time scaling requirement at the prediction moment based on the real-time indicator corresponding to the prediction moment and the indicator threshold;

[0122] The management module 440 is configured to schedule and manage the cloud computing resources according to the predicted scaling requirements at the predicted time and the real-time scaling requirements.

[0123] The scheduling and management device for cloud computing resources provided in this embodiment inputs the current indicators of cloud computing resources into a pre-trained resource scheduling model, so that the resource scheduling model determines the prediction indicators corresponding to the prediction moment based on the current indicators, wherein the prediction moment is a moment within a preset time period after the current moment corresponding to the current indicators; determines the predicted scaling demand at the prediction moment by comparing each of the prediction indicators and the indicator threshold; determines the real-time scaling demand at the prediction moment based on the real-time indicators corresponding to the prediction moment and the indicator threshold; and schedules and manages the cloud computing resources based on the predicted scaling demand and the real-time scaling demand at the prediction moment. The above technical solution, after obtaining the current indicators of the cloud computing resources corresponding to each business system, inputs the current indicators of the cloud computing resources into the resource scheduling model, and determines the predicted indicators of the cloud computing resources at the predicted time within a preset period after the current time corresponding to the current indicators are obtained based on the resource scheduling model, thereby achieving a reasonable prediction of the cloud computing resource indicators. Next, the predicted indicators at the predicted time output by the resource scheduling model can be compared with the indicator threshold to determine the predicted scaling demand of the cloud computing resources at the predicted time, thereby achieving a prediction of the scaling demand of the cloud computing resources at the predicted time. After determining that the predicted time has arrived, the real-time indicators obtained in real time at the predicted time can be compared with the indicator threshold to determine the real-time scaling demand of the cloud computing resources at the predicted time, thereby achieving a determination of the real-time scaling demand of the cloud computing resources at the predicted time. Furthermore, the actual scaling demand of the cloud computing resources can be determined by combining the predicted scaling demand and the real-time scaling demand of the cloud computing resources at the predicted time. The cloud computing resources are then scheduled and managed based on the actual scaling demand of the cloud computing resources, thereby achieving dynamic allocation of cloud computing resources, improving the utilization rate of cloud computing resources, and thereby reducing the waste of cloud computing resources and lowering data processing costs.

[0124] Based on the above embodiment, the indicator threshold includes an indicator upper limit and an indicator lower limit. Accordingly,

[0125] The comparison module 420 is specifically configured to: determine that the predicted expansion / contraction demand at the prediction moment requires expansion when it is determined that any of the prediction indicators is greater than the indicator upper limit; and determine that the predicted expansion / contraction demand at the prediction moment requires contraction when it is determined that none of the prediction indicators is greater than the indicator lower limit;

[0126] Determination module 430 is specifically used to: when it is determined that any of the real-time indicators is greater than the indicator upper limit, determine that the real-time expansion and contraction demand at the predicted moment requires expansion; when it is determined that each of the real-time indicators is not greater than the indicator lower limit, determine that the real-time expansion and contraction demand at the predicted moment requires contraction.

[0127] In one embodiment, the cloud computing resource indicators include at least CPU usage, memory usage, number of threads, disk IO usage, and network bandwidth usage.

[0128] Based on the above embodiment, the indicator threshold includes the indicator upper limit and indicator lower limit corresponding to each indicator. Accordingly,

[0129] The comparison module 420 is specifically configured to: determine that the predicted expansion / contraction demand at the prediction moment requires expansion when it is determined that any of the prediction indicators is greater than the corresponding indicator upper limit; and determine that the predicted expansion / contraction demand at the prediction moment requires contraction when it is determined that none of the prediction indicators is greater than the corresponding indicator lower limit.

[0130] Determination module 430 is specifically used to: when it is determined that any of the real-time indicators is greater than the corresponding indicator upper limit, determine that the real-time expansion and contraction demand at the predicted moment requires expansion; when it is determined that each of the real-time indicators is not greater than the corresponding indicator lower limit, determine that the real-time expansion and contraction demand at the predicted moment requires contraction.

[0131] Based on the above embodiment, the management module 440 is specifically configured to:

[0132] When it is determined that the predicted expansion and contraction demand and / or the real-time expansion and contraction demand at the prediction moment is expansion, the cloud computing resources are expanded according to the predicted expansion and contraction demand and the real-time expansion and contraction demand; when it is determined that the predicted expansion and contraction demand and / or the real-time expansion and contraction demand at the prediction moment is contraction, the cloud computing resources are contracted according to the predicted expansion and contraction demand and the real-time expansion and contraction demand.

[0133] In one embodiment, the cloud computing resources are used to process business data stored in the server by the business system.

[0134] Based on the above embodiment, the device further includes:

[0135] A training module is used to obtain historical indicators of the cloud computing resources in a historical time period; determine historical prediction indicators corresponding to the historical indicators, wherein the historical prediction indicators are obtained in a preset time period after the historical indicators; use the historical indicators as training inputs and the historical prediction indicators corresponding to the historical indicators to guide training outputs to perform network training to obtain the resource scheduling model.

[0136] The scheduling and management device for cloud computing resources provided in an embodiment of the present invention can execute the scheduling and management method for cloud computing resources provided in any embodiment of the present invention, and has the corresponding functional modules and beneficial effects of executing the scheduling and management method for cloud computing resources.

[0137] It is worth noting that in the embodiment of the scheduling and management device for cloud computing resources mentioned above, the various units and modules included are only divided according to functional logic, but are not limited to the above division, as long as the corresponding functions can be achieved; in addition, the specific names of the functional units are only for the convenience of distinguishing each other, and are not used to limit the scope of protection of the present invention.

[0138] Figure 5 A schematic structural diagram of an electronic device provided by an embodiment of the present invention. Figure 5 A block diagram of an exemplary electronic device 5 suitable for implementing embodiments of the present invention is shown. Figure 5 The electronic device 5 shown is only an example and should not bring any limitation to the functions and scope of use of the embodiments of the present invention.

[0139] like Figure 5 As shown, the electronic device 5 is in the form of a general-purpose computing electronic device. Components of the electronic device 5 may include, but are not limited to, one or more processors or processing units 16, a system memory 28, and a bus 18 connecting various system components (including the system memory 28 and the processing unit 16).

[0140] Bus 18 represents one or more of several types of bus structures, including a memory bus or memory controller, a peripheral bus, an accelerated graphics port, a processor, or a local bus using any of a variety of bus architectures. Examples of these architectures include, but are not limited to, an Industry Standard Architecture (ISA) bus, a Micro Channel Architecture (MAC) bus, an Enhanced ISA bus, a Video Electronics Standards Association (VESA) local bus, and a Peripheral Component Interconnect (PCI) bus.

[0141] The electronic device 5 typically includes a variety of computer system readable media. These media can be any available media that can be accessed by the electronic device 5, including volatile and non-volatile media, removable and non-removable media.

[0142] The system memory 28 may include computer system readable media in the form of volatile memory, such as random access memory (RAM) 30 and / or cache memory 32. The electronic device 5 may further include other removable / non-removable, volatile / non-volatile computer system storage media. By way of example only, the storage system 34 may be configured to read and write non-removable, non-volatile magnetic media ( Figure 5 Not shown, often called a "hard drive"). Although Figure 5Not shown, a magnetic disk drive for reading and writing to a removable non-volatile magnetic disk (e.g., a "floppy disk"), and an optical disk drive for reading and writing to a removable non-volatile optical disk (e.g., a CD-ROM, DVD-ROM, or other optical media) may be provided. In these cases, each drive may be connected to bus 18 via one or more data media interfaces. System memory 28 may include at least one program product having a set (e.g., at least one) of program modules configured to perform the functions of various embodiments of the present invention.

[0143] A program / utility 40 having a set (at least one) of program modules 42 may be stored, for example, in system memory 28. Such program modules 42 include, but are not limited to, an operating system, one or more application programs, other program modules, and program data, each of which, or some combination thereof, may include an implementation of a network environment. Program modules 42 generally perform the functions and / or methods of the embodiments described herein.

[0144] The electronic device 5 may also communicate with one or more external devices 14 (e.g., a keyboard, a pointing device, a display 24, etc.), one or more devices that enable a user to interact with the electronic device 5, and / or any device that enables the electronic device 5 to communicate with one or more other computing devices (e.g., a network card, a modem, etc.). Such communication may be performed via an input / output (I / O) interface 22. Furthermore, the electronic device 5 may also communicate with one or more networks (e.g., a local area network (LAN), a wide area network (WAN), and / or a public network, such as the Internet) via a network adapter 20. Figure 5 As shown, the network adapter 20 communicates with other modules of the electronic device 5 via the bus 18. Figure 5 Not shown, other hardware and / or software modules may be used in conjunction with the electronic device 5, including but not limited to microcode, device drivers, redundant processing units, external disk drive arrays, RAID systems, tape drives, and data backup storage systems.

[0145] The processing unit 16 executes various functional applications and page displays by running programs stored in the system memory 28, for example, implementing the scheduling and management method for cloud computing resources provided by an embodiment of the present invention, which includes:

[0146] Inputting the current indicator of the cloud computing resource into a pre-trained resource scheduling model, so that the resource scheduling model determines the prediction indicator corresponding to the prediction moment according to the current indicator, wherein the prediction moment is a moment within a preset time period after the current moment corresponding to the current indicator;

[0147] Determining the predicted expansion and contraction requirements at the predicted time by comparing the prediction indicators and indicator thresholds;

[0148] Determine the real-time scaling requirement at the predicted time according to the real-time indicator corresponding to the predicted time and the indicator threshold;

[0149] The cloud computing resources are scheduled and managed according to the predicted scaling demand at the predicted time and the real-time scaling demand.

[0150] Of course, those skilled in the art will appreciate that the processor may also implement the technical solution of the scheduling and management method for cloud computing resources provided by any embodiment of the present invention.

[0151] An embodiment of the present invention provides a computer-readable storage medium having a computer program stored thereon. When the program is executed by a processor, the method for scheduling and managing cloud computing resources provided in an embodiment of the present invention is implemented. The method includes:

[0152] Inputting the current indicator of the cloud computing resource into a pre-trained resource scheduling model, so that the resource scheduling model determines the prediction indicator corresponding to the prediction moment according to the current indicator, wherein the prediction moment is a moment within a preset time period after the current moment corresponding to the current indicator;

[0153] Determining the predicted expansion and contraction requirements at the predicted time by comparing the prediction indicators and indicator thresholds;

[0154] Determining the real-time scaling requirements at the predicted time based on the real-time indicators corresponding to the predicted time and the indicator threshold;

[0155] The cloud computing resources are scheduled and managed according to the predicted scaling demand at the predicted time and the real-time scaling demand.

[0156] The computer storage medium of the embodiment of the present invention can adopt any combination of one or more computer-readable media. The computer-readable medium can be a computer-readable signal medium or a computer-readable storage medium. The computer-readable storage medium can be, for example, but not limited to: an electrical, magnetic, optical, electromagnetic, infrared, or semiconductor system, device or component, or any combination of the above. More specific examples (non-exhaustive list) of computer-readable storage media include: an electrical connection with one or more wires, a portable computer disk, a hard disk, a random access memory (RAM), a read-only memory (ROM), an erasable programmable read-only memory (EPROM or flash memory), an optical fiber, a portable compact disk read-only memory (CD-ROM), an optical storage device, a magnetic storage device, or any suitable combination of the above. In this document, a computer-readable storage medium can be any tangible medium containing or storing a program that can be used by or in combination with an instruction execution system, device or device.

[0157] A computer-readable signal medium may include a data signal propagated in baseband or as part of a carrier wave, which carries computer-readable program code. Such propagated data signals may take various forms, including but not limited to electromagnetic signals, optical signals, or any suitable combination thereof. A computer-readable signal medium may also be any computer-readable medium other than a computer-readable storage medium that can transmit, propagate, or transport a program for use by or in conjunction with an instruction execution system, apparatus, or device.

[0158] Program code embodied on a computer-readable medium may be transmitted using any appropriate medium, including but not limited to wireless, wireline, optical fiber cable, RF, etc., or any suitable combination of the foregoing.

[0159] Computer program code for performing the operations of the present invention may be written in one or more programming languages, or a combination thereof, including object-oriented programming languages such as Java, Smalltalk, C++, and conventional procedural programming languages such as "C" or similar programming languages. The program code may be executed entirely on the user's computer, partially on the user's computer, as a stand-alone software package, partially on the user's computer and partially on a remote computer, or entirely on a remote computer or server. In cases involving a remote computer, the remote computer may be connected to the user's computer through any type of network, including a local area network (LAN) or a wide area network (WAN), or may be connected to an external computer (e.g., through the Internet using an Internet service provider).

[0160] Those skilled in the art will appreciate that the modules or steps of the present invention described above can be implemented using a general-purpose computing device. They can be centralized on a single computing device or distributed across a network of multiple computing devices. Alternatively, they can be implemented using program code executable by a computer device, which can then be stored in a storage device and executed by the computing device. Alternatively, they can be fabricated into separate integrated circuit modules, or multiple modules or steps can be fabricated into a single integrated circuit module. Thus, the present invention is not limited to any specific combination of hardware and software.

[0161] In addition, the acquisition, storage, use, and processing of data in the technical solution of the present invention comply with relevant provisions of laws and regulations.

[0162] Note that the above are only preferred embodiments of the present invention and the technical principles employed. Those skilled in the art will appreciate that the present invention is not limited to the specific embodiments herein, and that various obvious changes, readjustments, and substitutions are possible for those skilled in the art without departing from the scope of protection of the present invention. Therefore, although the present invention has been described in detail through the above embodiments, the present invention is not limited to the above embodiments and may include many other equivalent embodiments without departing from the scope of the present invention. The scope of the present invention is determined by the scope of the appended claims.

Claims

1. A scheduling and management method for cloud computing resources, characterized in that: include: Inputting the current indicator of the cloud computing resource into a pre-trained resource scheduling model, so that the resource scheduling model determines the prediction indicator corresponding to the prediction moment according to the current indicator, wherein the prediction moment is a moment within a preset time period after the current moment corresponding to the current indicator; Determining the predicted expansion and contraction requirements at the predicted time by comparing the prediction indicators and indicator thresholds; Determine the real-time scaling requirement at the predicted time according to the real-time indicator corresponding to the predicted time and the indicator threshold; The cloud computing resources are scheduled and managed according to the predicted scaling demand at the predicted time and the real-time scaling demand.

2. The method for scheduling and managing cloud computing resources according to claim 1, wherein: The indicator threshold includes an indicator upper limit and an indicator lower limit. Accordingly, by comparing each of the prediction indicators and the indicator threshold, the predicted expansion and contraction requirements at the prediction time are determined, including: When it is determined that any of the predicted indicators is greater than the indicator upper limit, determining that the predicted expansion and contraction demand at the predicted moment requires expansion; When it is determined that each of the prediction indicators is not greater than the indicator lower limit, determining that the predicted expansion and contraction demand at the prediction moment requires contraction; Accordingly, determining the real-time scaling requirement at the prediction moment according to the real-time indicator corresponding to the prediction moment and the indicator threshold includes: When it is determined that any of the real-time indicators is greater than the indicator upper limit, determining that the real-time expansion and contraction demand at the predicted moment requires expansion; When it is determined that each of the real-time indicators is not greater than the indicator lower limit, it is determined that the real-time expansion and contraction demand at the predicted moment requires capacity reduction.

3. The scheduling and management method for cloud computing resources according to claim 2, characterized in that: The cloud computing resource indicators include at least central processing unit (CPU) usage, memory usage, number of threads, disk read / write IO usage, and network bandwidth usage.

4. The method for scheduling and managing cloud computing resources according to claim 3, wherein: The indicator threshold includes an indicator upper limit and an indicator lower limit corresponding to each indicator. Accordingly, by comparing each predicted indicator with the indicator threshold, the predicted expansion and contraction demand at the predicted time is determined, including: When it is determined that any of the predicted indicators is greater than the corresponding indicator upper limit, determining that the predicted expansion and contraction demand at the predicted moment requires expansion; When it is determined that each of the prediction indicators is not greater than the corresponding indicator lower limit, determining that the predicted expansion and contraction demand at the prediction time is that capacity reduction is required; Accordingly, determining the real-time scaling requirement at the prediction moment according to the real-time indicator corresponding to the prediction moment and the indicator threshold includes: When it is determined that any of the real-time indicators is greater than the corresponding indicator upper limit, determining that the real-time scaling demand at the predicted moment requires expansion; When it is determined that each of the real-time indicators is not greater than the corresponding indicator lower limit, it is determined that the real-time expansion and contraction demand at the predicted moment requires contraction.

5. The method for scheduling and managing cloud computing resources according to claim 1, wherein: Scheduling and managing the cloud computing resources according to the predicted scaling demand at the predicted time and the real-time scaling demand includes: When it is determined that the predicted capacity expansion demand and / or the real-time capacity expansion demand at the predicted time is capacity expansion, expanding the cloud computing resources according to the predicted capacity expansion demand and the real-time capacity expansion demand; When it is determined that the predicted scaling demand and / or the real-time scaling demand at the prediction moment is scaling down, the cloud computing resources are scaled down according to the predicted scaling demand and the real-time scaling demand.

6. The method for scheduling and managing cloud computing resources according to claim 1, wherein: The cloud computing resources are used to process the business data stored in the server by the business system.

7. The method for scheduling and managing cloud computing resources according to claim 1, wherein: The resource scheduling model is trained by the following method: Obtaining historical indicators of the cloud computing resources in a historical time period; Determining a historical prediction indicator corresponding to the historical indicator, wherein the historical prediction indicator is obtained within a preset time period after the historical indicator; The resource scheduling model is obtained by performing network training using the historical indicators as training inputs and the historical prediction indicators corresponding to the historical indicators as guidance for training outputs.

8. A scheduling and management device for cloud computing resources, characterized in that: include: A prediction module, configured to input current indicators of cloud computing resources into a pre-trained resource scheduling model, so that the resource scheduling model determines a prediction indicator corresponding to a prediction moment based on the current indicators; A comparison module, configured to determine the predicted expansion and contraction requirements at the predicted moment by comparing the prediction indicators with the indicator thresholds; A determination module, configured to determine the real-time scaling requirement at the predicted moment based on the real-time indicator corresponding to the predicted moment and the indicator threshold; A management module is used to schedule and manage the cloud computing resources according to the predicted expansion and contraction requirements at the predicted time and the real-time expansion and contraction requirements.

9. An electronic device, characterized in that: The electronic device comprises: at least one processor; and a memory communicatively coupled to the at least one processor; The memory stores a computer program that can be executed by the at least one processor, and the computer program is executed by the at least one processor so that the at least one processor can execute the scheduling and management method for cloud computing resources as described in any one of claims 1 to 7.

10. A storage medium containing computer-executable instructions, characterized in that: When executed by a computer processor, the computer executable instructions are used to execute the scheduling and management method for cloud computing resources as described in any one of claims 1 to 7.

Images