Cloud resource optimization method and device, computer equipment and storage medium

Abstract

The invention relates to a cloud resource optimization method and device, computer equipment and a storage medium. Comprising the steps of obtaining time sequence index data of a target cloud resource in a historical preset time period; inputting the time sequence index data into a preset intelligent prediction model to obtain a resource use prediction value of the target cloud resource in a future preset time period; and extracting feature parameters of services carried by the target cloud resources. And dynamically adjusting an allocation strategy of the target cloud resources according to the resource use predicted value and the feature parameters. Therefore, according to the technical scheme of the invention, the resource usage amount of the target cloud resource in the future preset time period is predicted by using the preset intelligent prediction model, and the distribution strategy of the target cloud resource is dynamically adjusted in combination with the business characteristics borne by the target cloud resource. The scheme not only can efficiently correspond to the multi-dimensional data to generate the optimal configuration suggestion, but also can realize dynamic and timely adjustment of the target cloud resource configuration, thereby effectively improving the resource utilization rate of the target cloud resources.

Description

Technical Field

[0001] This application relates to the field of cloud computing, and in particular to a cloud resource optimization method, apparatus, computer equipment, and storage medium. Background Technology

[0002] With the development of the Internet, more and more enterprises are migrating their business systems to cloud platforms, and the elastic allocation capability of cloud resources has brought significant convenience to enterprises.

[0003] Currently, traditional cloud resource allocation methods mainly rely on regular manual inspections. Specifically, administrators need to periodically collect cloud resource metrics data, and then manually analyze this data to generate optimization suggestions for cloud resources.

[0004] However, the more complex the business scenario, the more diverse the dimensions of the metrics data that managers need to collect. Limited by the processing capabilities of manual analysis, it is difficult to efficiently handle multi-dimensional data, and thus impossible to generate optimal configuration recommendations for cloud resources. Summary of the Invention

[0005] This application provides a cloud resource optimization method, apparatus, computer equipment, and storage medium, aiming to solve the technical problem that the optimal configuration suggestions for cloud resources cannot be generated due to the difficulty of efficiently responding to multi-dimensional data through manual analysis.

[0006] In a first aspect, embodiments of this application provide a cloud resource optimization method, which includes:

[0007] Obtain time-series indicator data of the target cloud resources within a preset historical time period;

[0008] The time-series index data is input into a preset intelligent prediction model to obtain the predicted resource usage value of the target cloud resource in a future preset time period. The preset intelligent prediction model is used to predict the resource usage of the cloud resource in the future preset time period.

[0009] Extract the characteristic parameters of the services carried by the target cloud resources;

[0010] The allocation strategy for the target cloud resources is dynamically adjusted based on the predicted resource usage and the characteristic parameters.

[0011] Optionally, the step of dynamically adjusting the allocation strategy of the target cloud resources based on the predicted resource usage value and the feature parameters includes:

[0012] The optimal configuration parameters of the target cloud resource are obtained from a preset experience base based on the predicted resource usage value and the feature parameters. The preset experience base includes multiple sets of optimized configuration records of cloud resources. Each set of optimized configuration records is associated with the optimal configuration parameters corresponding to a specific predicted resource usage value and feature parameters.

[0013] Based on the optimal configuration parameters, perform at least one of the following operations: resource scaling up / down, merging cloud resource instances, automatically shutting down cloud resources, or resource migration.

[0014] Optionally, the feature parameters include the service type, and the step of dynamically adjusting the allocation strategy of the target cloud resources based on the predicted resource usage and the feature parameters includes:

[0015] The predicted resource usage value is compared with a first preset threshold.

[0016] If the predicted resource usage value is lower than the first preset threshold at multiple consecutive time points, and the service type belongs to off-peak service or cold backup service, then the specification parameters of the target cloud resource are lowered based on the first preset specification adjustment threshold.

[0017] Optionally, after comparing the predicted resource usage value with a first preset threshold, the method further includes:

[0018] If the predicted resource usage value is lower than the first preset threshold at multiple consecutive time points, and the service type belongs to any one of test service, temporary service, or offline service, then the target cloud resource is shut down.

[0019] Optionally, the step of dynamically adjusting the allocation strategy of the target cloud resources based on the predicted resource usage value and the feature parameters includes:

[0020] The predicted resource usage value is compared with a second preset threshold.

[0021] If the predicted resource usage value is greater than the second preset threshold at multiple consecutive time points, the specification parameters of the target cloud resource will be adjusted upwards.

[0022] Optionally, the characteristic parameters include the elastic scaling capability of the service, and the upward adjustment of the specification parameters of the target cloud resource includes:

[0023] The second preset specification adjustment threshold is determined based on the elastic expansion and contraction capacity;

[0024] The specification parameters of the target cloud resource are adjusted upward based on the second preset specification adjustment threshold.

[0025] Optionally, the target cloud resources include first cloud resources and second cloud resources, and the step of dynamically adjusting the allocation strategy of the target cloud resources based on the predicted resource usage and the characteristic parameters includes:

[0026] Compare the predicted usage value of the first cloud resource with the third preset threshold;

[0027] The predicted usage value of the second cloud resource is compared with the fourth preset threshold.

[0028] If the predicted usage value of the first cloud resource is lower than the third preset threshold at multiple consecutive time points, and the predicted usage value of the second cloud resource is lower than the fourth preset threshold at multiple consecutive time points, then it is determined whether the first cloud resource and the second cloud resource have business isolation. If so, the first cloud resource and the second cloud resource are merged.

[0029] Secondly, embodiments of this application also provide a cloud resource optimization apparatus, which includes a unit for performing the above-described method.

[0030] Thirdly, embodiments of this application also provide a computer device, which includes a memory and a processor, wherein the memory stores a computer program, and the processor executes the computer program to implement the above-described method.

[0031] Fourthly, embodiments of this application also provide a computer-readable storage medium storing a computer program that, when executed by a processor, can implement the above-described method.

[0032] This application provides a cloud resource optimization method, apparatus, computer device, and storage medium. The method includes: acquiring time-series indicator data of a target cloud resource within a historical preset time period; inputting the time-series indicator data into a preset intelligent prediction model to obtain a predicted resource usage value of the target cloud resource within a future preset time period, wherein the preset intelligent prediction model is used to predict the resource usage of the cloud resource within the future preset time period; extracting characteristic parameters of the services carried by the target cloud resource; and dynamically adjusting the allocation strategy of the target cloud resource based on the predicted resource usage value and the characteristic parameters. Therefore, this application's technical solution acquires time-series indicator data of a target cloud resource within a historical preset time period. Then, the time-series indicator data is input into a preset intelligent prediction model to obtain a predicted resource usage value of the target cloud resource within a future preset time period. Finally, the allocation strategy of the target cloud resource is dynamically adjusted based on the predicted resource usage value and the characteristic parameters. Thus, this application's technical solution uses a preset intelligent prediction model to predict the resource usage of a target cloud resource within a future preset time period and, combined with the characteristics of the services carried by the target cloud resource, dynamically adjusts its allocation strategy. This solution can not only efficiently respond to multi-dimensional data to generate optimal configuration suggestions, but also enable dynamic and timely adjustment of target cloud resource configuration, thereby effectively improving the resource utilization rate of target cloud resources. Attached Figure Description

[0033] The accompanying drawings, which are incorporated in and form part of this specification, illustrate embodiments consistent with this application and, together with the description, serve to explain the principles of this application.

[0034] To more clearly illustrate the technical solutions in the embodiments of this application or the prior art, the drawings used in the description of the embodiments or the prior art will be briefly introduced below. Obviously, for those skilled in the art, other drawings can be obtained based on these drawings without creative effort.

[0035] One or more embodiments are illustrated by way of example with reference numerals in the accompanying drawings. These illustrations do not constitute a limitation on the embodiments. Elements with the same reference numerals in the drawings are denoted as similar elements. Unless otherwise stated, the figures in the drawings are not to be limited by scale.

[0036] Figure 1 A flowchart illustrating a cloud resource optimization method provided in an embodiment of this application;

[0037] Figure 2 A schematic block diagram of a cloud resource optimization device provided in an embodiment of this application;

[0038] Figure 3 A computer device provided in an embodiment of this application. Detailed Implementation

[0039] To make the objectives, technical solutions, and advantages of the embodiments of this application clearer, the technical solutions of the embodiments of this application will be clearly and completely described below with reference to the accompanying drawings. Obviously, the described embodiments are only some embodiments of this application, not all embodiments. Based on the embodiments of this application, all other embodiments obtained by those skilled in the art without creative effort are within the scope of protection of this application.

[0040] The following disclosure provides numerous different embodiments or examples for implementing various structures of this application. To simplify the disclosure, specific examples of components and arrangements are described below. These are merely examples and are not intended to limit the scope of this application. Furthermore, reference numerals and / or letters may be repeated in different examples. Such repetition is for simplification and clarity and does not in itself indicate a relationship between the various embodiments and / or arrangements discussed.

[0041] It should be understood that, when used in this specification and the appended claims, the terms "comprising" and "including" indicate the presence of the described features, integrals, steps, operations, elements and / or components, but do not exclude the presence or addition of one or more other features, integrals, steps, operations, elements, components and / or collections thereof.

[0042] It should also be understood that the terminology used in this specification is for the purpose of describing particular embodiments only and is not intended to limit the scope of the application. As used in this specification and the appended claims, the singular forms “a,” “an,” and “the” are intended to include the plural forms unless the context clearly indicates otherwise.

[0043] It should also be further understood that the term “and / or” as used in this application specification and the appended claims means any combination of one or more of the associated listed items and all possible combinations, and includes such combinations.

[0044] As used in this specification and the appended claims, the term "if" may be interpreted, depending on the context, as "when," "once," "in response to determination," or "in response to detection." Similarly, the phrases "if determined" or "if [described condition or event] is detected" may be interpreted, depending on the context, as "once determined," "in response to determination," "once [described condition or event] is detected," or "in response to detection of [described condition or event]."

[0045] To address the technical problem in existing technologies where manual analysis is insufficient to efficiently handle multi-dimensional data, thus preventing the generation of optimal cloud resource configuration recommendations, this application provides a cloud resource optimization device capable of generating optimal cloud resource configuration recommendations.

[0046] Figure 1 This is a flowchart illustrating a cloud resource optimization method provided in an embodiment of this application. In one embodiment, the method includes the following steps: S101-S104.

[0047] S101. Obtain time-series indicator data of the target cloud resource within a historical preset time period.

[0048] Target cloud resources include, but are not limited to, cloud servers, cloud databases, cloud message queues, and cloud storage. Time-series metrics data consist of multiple metrics for the target cloud resources. These metrics include, but are not limited to, CPU utilization, memory utilization, connection utilization, bandwidth, and disk read / write speeds. It should be noted that different types of target cloud resources require different time-series metric data. For example, when the target cloud resource is a cloud database, the required metric types include, but are not limited to, SQL service CPU utilization and SQL service disk utilization.

[0049] The historical preset time period is set by the applicant based on different cloud resource types. Optionally, the historical preset time period can be the past day. Of course, the historical preset time period can also be set to the past week. This application does not restrict this.

[0050] S102. Input the time series index data into the preset intelligent prediction model to obtain the predicted value of the resource usage of the target cloud resources in the future preset time period.

[0051] A preset intelligent prediction model is used to predict the resource usage of cloud resources within a preset future time period. Preferably, the preset future time period can be within the next day or within the next week. This application does not impose any restrictions on this.

[0052] It should be noted that there may be one or more resource usage forecasts. Each resource usage forecast includes at least one resource usage forecast. For example, resource usage forecasts include, but are not limited to, CPU usage forecasts, memory usage forecasts, and disk usage forecasts.

[0053] The following describes the process of constructing a pre-defined intelligent prediction model.

[0054] This application employs a two-layer, cascaded network model. The first layer is a GRU recurrent neural network, and the second layer is a regression network. The input to the first layer is the historical resource utilization time series of the target cloud resource. For example, the time series of CPU, memory, or disk utilization of the target cloud resource over the past N minutes. The output of the first layer is multiple sets of time-series feature vectors. It should be noted that the output of the first layer serves as the input to the second layer. Based on these multiple time-series feature vectors, the second layer outputs a predicted resource utilization value for the target cloud resource at a future point in time.

[0055] In this embodiment, the training data includes, but is not limited to, data on multiple metrics of various cloud resources over historical time periods. These metrics include, but are not limited to, CPU utilization, memory utilization, number of requests, I / O rate, network bandwidth, and network latency.

[0056] This application embodiment performs preprocessing operations on the training data. These preprocessing operations include, but are not limited to, outlier handling, missing value imputation, normalization, and feature extraction.

[0057] In this embodiment, the hidden layer of the GRU recurrent neural network model uses the ReLU activation function or the LeakyReLU activation function, and the output layer uses the sigmoid activation function or the softmax activation function.

[0058] In this embodiment, the loss function of the regression network model is either the mean squared error loss function or the mean absolute error loss function. The evaluation metric for the regression network model is either the mean squared error or the mean absolute error.

[0059] S103. Extract the characteristic parameters of the services carried by the target cloud resources.

[0060] This application embodiment can extract feature parameters from the service information carried by the target cloud resource. These feature parameters include, but are not limited to, service type and the elastic scaling capability of the service.

[0061] S104. Based on the predicted resource usage and characteristic parameters, dynamically adjust the allocation strategy of the target cloud resources.

[0062] This application embodiment combines predicted resource usage values ​​with characteristic parameters of the services carried by the target cloud resources to dynamically adjust the allocation strategy of the target cloud resources. This application embodiment will describe in detail later how to dynamically adjust the allocation strategy of the target cloud resources based on predicted resource usage values ​​and characteristic parameters. Further details will not be elaborated here.

[0063] This application provides a cloud resource optimization method. The method includes: acquiring time-series indicator data of a target cloud resource within a historical preset time period; inputting the time-series indicator data into a preset intelligent prediction model to obtain a predicted resource usage value of the target cloud resource within a future preset time period, wherein the preset intelligent prediction model is used to predict the resource usage of the cloud resource within the future preset time period; extracting characteristic parameters of the services carried by the target cloud resource; and dynamically adjusting the allocation strategy of the target cloud resource based on the predicted resource usage value and the characteristic parameters. Therefore, this application's technical solution acquires time-series indicator data of a target cloud resource within a historical preset time period. Then, the time-series indicator data is input into a preset intelligent prediction model to obtain a predicted resource usage value of the target cloud resource within a future preset time period. Finally, the allocation strategy of the target cloud resource is dynamically adjusted based on the predicted resource usage value and the characteristic parameters. Thus, this application's technical solution uses a preset intelligent prediction model to predict the resource usage of a target cloud resource within a future preset time period and, combined with the characteristics of the services carried by the target cloud resource, dynamically adjusts its allocation strategy. This solution can not only efficiently respond to multi-dimensional data to generate optimal configuration suggestions, but also enable dynamic and timely adjustment of target cloud resource configuration, thereby effectively improving the resource utilization rate of target cloud resources.

[0064] In one embodiment, S104 specifically includes the following steps: S1041-S1042.

[0065] S1041. Obtain the optimal configuration parameters of the target cloud resources from the preset experience base based on the predicted resource usage values ​​and characteristic parameters.

[0066] The pre-set experience base includes multiple sets of optimized configuration records for cloud resources. Each set of optimized configuration records is associated with the optimal configuration parameters corresponding to the predicted usage values ​​and feature parameters of a specific resource. It should be noted that the pre-set experience base is derived by the applicant based on historical optimization experience.

[0067] S1042. Based on the optimal configuration parameters, perform at least one of the following operations: resource scaling up / down, merging cloud resource instances, automatically shutting down cloud resources, or resource migration.

[0068] Resource expansion operations include, but are not limited to, CPU resource expansion, disk resource expansion, and memory resource expansion. Merging cloud resource instances combines services hosted on multiple cloud resources into a single cloud resource. Automatically shutting down cloud resources shuts down cloud resources. Resource migration moves services from one cloud resource to another. This approach conserves cloud resources while providing sufficient resources to ensure normal service operation.

[0069] In one embodiment, the feature parameter includes the service type, and S104 specifically includes the following steps: S1043-S1044.

[0070] S1043. Compare the predicted resource usage value with the first preset threshold.

[0071] In this embodiment, a preset intelligent prediction model is used to obtain predicted resource usage values ​​for the target cloud resource at multiple future time points. Then, these predicted resource usage values ​​are compared with a first preset threshold. It should be noted that the predicted resource usage values ​​include the usage prediction value for at least one resource. The usage prediction value for each resource is compared with the first preset threshold separately. Of course, in this embodiment, different first preset thresholds can be set for each resource according to actual conditions. For example, for CPU resources, the first preset threshold can be set to 2%. For memory resources, the first preset threshold can be set to 5%. This application does not impose any limitations on this.

[0072] S1044. If the predicted resource usage value is lower than the first preset threshold at multiple consecutive time points, and the business type is an off-peak business or a cold backup business, then the specification parameters of the target cloud resource are lowered based on the first preset specification adjustment threshold.

[0073] The multiple consecutive time points can be multiple time points within a day or multiple time points within a week. This application does not impose any restrictions. When the predicted resource usage value is consistently lower than the first preset threshold, it indicates that the target cloud resource may experience peak and off-peak traffic, or it may be in an idle state. When the traffic carried by the target cloud resource is off-peak traffic or cold backup traffic, this application embodiment adjusts the specification parameters of the target cloud resource according to the first preset specification adjustment threshold to reduce the capacity of the target cloud resource, thereby reducing the configuration of the target cloud resource during off-peak periods or during backup periods and improving cloud resource utilization.

[0074] In one embodiment, the feature parameter includes the service type, and the method further includes the following step: Step A.

[0075] A. If the predicted resource usage value is lower than the first preset threshold at multiple consecutive time points, and the business type belongs to any one of test business, temporary business, or offline business, then the target cloud resource is shut down.

[0076] When the service carried by the target cloud resource is any of the following: a test service, a temporary service, or a service that is no longer in operation, the predicted resource usage of the target cloud resource will remain at a low level for an extended period, indicating that the target cloud resource is currently idle. Therefore, this embodiment can shut down the target cloud resource to avoid resource waste.

[0077] In one embodiment, S104 specifically includes the following steps: S1045-S1046.

[0078] S1045. Compare the predicted resource usage value with the second preset threshold.

[0079] In this embodiment, a preset intelligent prediction model is used to obtain predicted resource usage values ​​for the target cloud resource at multiple future time points. Then, these predicted resource usage values ​​are compared with a second preset threshold. It should be noted that the predicted resource usage values ​​include the usage prediction value for at least one resource. The usage prediction value for each resource is compared with the second preset threshold separately. Of course, in this embodiment, different second preset thresholds can be set for each resource according to actual conditions. For example, for CPU resources, the second preset threshold can be set to 98%. For memory resources, the second preset threshold can be set to 95%. This application does not impose any limitations on this.

[0080] S1046. If the predicted resource usage value is greater than the second preset threshold at multiple consecutive time points, then the specification parameters of the target cloud resource are adjusted upwards.

[0081] The multiple consecutive time points can be multiple time points within a day or multiple time points within a week. This application does not impose any restrictions. When the predicted resource usage value is consistently higher than the first preset threshold, it indicates that there may be a performance bottleneck on the target cloud resource, requiring an adjustment of the target cloud resource's specifications and an increase in its resource configuration to ensure normal business operation.

[0082] In one embodiment, the characteristic parameters include the elastic scaling capability of the service, and S1046 specifically includes the following steps: ab.

[0083] a. Determine the second preset specification adjustment threshold based on the elastic expansion and contraction capacity.

[0084] b. Adjust the specification parameters of the target cloud resource upward based on the second preset specification adjustment threshold.

[0085] The following provides a detailed explanation of steps a and b.

[0086] This application embodiment determines a second preset specification adjustment threshold based on the elastic scaling capability of the target cloud resources. It should be noted that the second preset specification adjustment threshold can be different for different resources. For example, for CPU resources, the second preset specification adjustment threshold can be set to 2, meaning the number of CPUs is increased by 2 each time. For memory resources, the second preset specification adjustment threshold can be set to 4G, meaning the memory space is increased by 4G each time.

[0087] In one embodiment, the target cloud resource includes a first cloud resource and a second cloud resource, and S104 specifically includes the following steps: S1047-S1049.

[0088] S1047. Compare the predicted usage value of the first cloud resource with the third preset threshold.

[0089] S1048. Compare the predicted usage value of the second cloud resource with the fourth preset threshold.

[0090] S1049. If the predicted usage value of the first cloud resource is lower than the third preset threshold at multiple consecutive time points, and the predicted usage value of the second cloud resource is lower than the fourth preset threshold at multiple consecutive time points, then determine whether the first cloud resource and the second cloud resource are business isolated. If so, then merge the first cloud resource and the second cloud resource.

[0091] The following provides a detailed explanation of S1047-S1049.

[0092] The third and fourth preset thresholds may be the same as or different from the first preset threshold. This application does not impose any restrictions on this. S1047 and S1048 are the same as or similar to S1043, and will not be described in detail here.

[0093] It should be noted that when the predicted utilization values ​​of both the first and second cloud resources are at a low level, it indicates that neither cloud resource requires excessive resource allocation. If the services carried by the first and second cloud resources are isolated, services carried on the first cloud resource can be migrated to the second cloud resource, or vice versa, to fully utilize the cloud resources and improve their utilization rate. In this embodiment, after merging the cloud resources, performance indicators are collected to determine whether the services carried by the merged cloud resources can operate normally.

[0094] In one embodiment, each time the allocation strategy of the target cloud resources is adjusted, various indicator data of the target cloud resources are collected in real time. If the services carried on the target cloud resources are running normally, the preset experience base is updated according to the allocation strategy and the predicted value of resource usage for subsequent reference.

[0095] See Figure 2 , Figure 2 This is a schematic block diagram of a cloud resource optimization device provided in an embodiment of this application. Corresponding to the above-described cloud resource optimization method, this application also provides a cloud resource optimization device. This cloud resource optimization device includes a unit for executing the above-described cloud resource optimization method, and can be configured in a terminal such as a desktop computer, tablet computer, or laptop computer. Specifically, the cloud resource optimization device includes:

[0096] The acquisition unit 201 is used to acquire time-series indicator data of the target cloud resources within a historical preset time period;

[0097] Input unit 202 is used to input the time series index data into a preset intelligent prediction model to obtain the predicted value of the resource usage of the target cloud resource in a future preset time period. The preset intelligent prediction model is used to predict the resource usage of the cloud resource in the future preset time period.

[0098] Extraction unit 203 is used to extract the characteristic parameters of the services carried by the target cloud resources;

[0099] The adjustment unit 204 is used to dynamically adjust the allocation strategy of the target cloud resources based on the predicted resource usage value and the characteristic parameters.

[0100] In one embodiment, the adjustment unit 204 is specifically used to obtain the optimal configuration parameters of the target cloud resource from a preset experience base based on the resource usage prediction value and the feature parameters. The preset experience base includes multiple sets of optimized configuration records of cloud resources, and each set of optimized configuration records is associated with the optimal configuration parameters corresponding to a specific resource usage prediction value and feature parameters.

[0101] Based on the optimal configuration parameters, perform at least one of the following operations: resource scaling up / down, merging cloud resource instances, automatically shutting down cloud resources, or resource migration.

[0102] In one embodiment, the feature parameters include the service type, and the adjustment unit 204 is further specifically used to compare the predicted resource usage value with a first preset threshold.

[0103] If the predicted resource usage value is lower than the first preset threshold at multiple consecutive time points, and the service type belongs to off-peak service or cold backup service, then the specification parameters of the target cloud resource are lowered based on the first preset specification adjustment threshold.

[0104] In one embodiment, the device further includes a shutdown unit 205, which is specifically used to shut down the target cloud resource if the predicted resource usage value is lower than the first preset threshold at multiple consecutive time points, and the service type belongs to any one of test service, temporary service, or offline service.

[0105] In one embodiment, the adjustment unit 204 is further configured to compare the predicted resource usage value with a second preset threshold based on the predicted resource usage value and the feature parameters.

[0106] If the predicted resource usage value is greater than the second preset threshold at multiple consecutive time points, the specification parameters of the target cloud resource will be adjusted upwards.

[0107] In one embodiment, the feature parameters include the elastic scaling capability of the service, and the adjustment unit 204 is further specifically used to determine a second preset specification adjustment threshold based on the elastic scaling capability;

[0108] The specification parameters of the target cloud resource are adjusted upward based on the second preset specification adjustment threshold.

[0109] In one embodiment, the target cloud resource includes a first cloud resource and a second cloud resource, and the adjustment unit 204 is further specifically used to compare the predicted usage value of the first cloud resource with a third preset threshold.

[0110] The predicted usage value of the second cloud resource is compared with the fourth preset threshold.

[0111] If the predicted usage value of the first cloud resource is lower than the third preset threshold at multiple consecutive time points, and the predicted usage value of the second cloud resource is lower than the fourth preset threshold at multiple consecutive time points, then it is determined whether the first cloud resource and the second cloud resource have business isolation. If so, the first cloud resource and the second cloud resource are merged.

[0112] like Figure 3 As shown, this application provides a computer device including a processor 31, a communication interface 32, a memory 33, and a communication bus 34. The processor 31, the communication interface 32, and the memory 33 communicate with each other through the communication bus 34. The memory 33 is used to store computer programs.

[0113] In one embodiment of this application, when the processor 31 executes the program stored in the memory 33, it implements the cloud resource optimization control method provided in any of the foregoing method embodiments.

[0114] It will be understood by those skilled in the art that all or part of the processes in the methods of the above embodiments can be implemented by a computer program instructing related hardware. The computer program may be stored in a storage medium, which is a computer-readable storage medium. The computer program is executed by at least one processor in the computer system to implement the process steps of the embodiments of the above methods.

[0115] Therefore, embodiments of this application also provide a computer-readable storage medium having a computer program stored thereon, wherein the computer program, when executed by a processor, implements the steps of the cloud resource optimization method provided in any of the foregoing method embodiments.

[0116] The storage medium is a physical, non-transient storage medium, such as a USB flash drive, external hard drive, read-only memory (ROM), magnetic disk, or optical disk, or any other physical storage medium capable of storing program code. The computer-readable storage medium can be non-volatile or volatile.

[0117] Those skilled in the art will recognize that the units and algorithm steps of the various examples described in conjunction with the embodiments disclosed herein can be implemented in electronic hardware, computer software, or a combination of both. To clearly illustrate the interchangeability of hardware and software, the components and steps of the various examples have been generally described in terms of functionality in the foregoing description. Whether these functions are implemented in hardware or software depends on the specific application and design constraints of the technical solution. Those skilled in the art can use different methods to implement the described functions for each specific application, but such implementations should not be considered beyond the scope of this application.

[0118] In the several embodiments provided in this application, it should be understood that the disclosed apparatus and methods can be implemented in other ways. For example, the apparatus embodiments described above are merely illustrative. For example, the division of each unit is merely a logical functional division, and there may be other division methods in actual implementation. For example, multiple units or components may be combined or integrated into another system, or some features may be ignored or not executed.

[0119] The steps in the methods of this application embodiment can be adjusted, merged, or deleted according to actual needs. The units in the apparatus of this application embodiment can be merged, divided, or deleted according to actual needs. Furthermore, the functional units in the various embodiments of this application can be integrated into one processing unit, or each unit can exist physically separately, or two or more units can be integrated into one unit.

[0120] If the integrated unit is implemented as a software functional unit and sold or used as an independent product, it can be stored in a storage medium. Based on this understanding, the technical solution of this application, in essence, or the part that contributes to the prior art, or all or part of the technical solution, can be embodied in the form of a software product. This computer software product is stored in a storage medium and includes several instructions to cause a computer device (which may be a personal computer, a terminal, or a network device, etc.) to execute all or part of the steps of the methods described in the various embodiments of this application.

[0121] In the above embodiments, the descriptions of each embodiment have different focuses. For parts that are not described in detail in a certain embodiment, please refer to the relevant descriptions in other embodiments.

[0122] Obviously, those skilled in the art can make various modifications and variations to this application without departing from the spirit and scope of this application. Since these modifications and variations fall within the scope of the claims and their equivalents, this application also intends to include these modifications and variations.

[0123] The above description is merely a specific embodiment of this application, but the scope of protection of this application is not limited thereto. Any person skilled in the art can easily conceive of various equivalent modifications or substitutions within the technical scope disclosed in this application, and these modifications or substitutions should all be covered within the scope of protection of this application. Therefore, the scope of protection of this application should be determined by the scope of the claims.

Claims

1. A cloud resource optimization method, characterized in that, The method includes: Obtain time-series indicator data of the target cloud resources within a preset historical time period; The time-series index data is input into a preset intelligent prediction model to obtain the predicted resource usage value of the target cloud resource in a future preset time period. The preset intelligent prediction model is used to predict the resource usage of the cloud resource in the future preset time period. Extract the characteristic parameters of the services carried by the target cloud resources; The allocation strategy for the target cloud resources is dynamically adjusted based on the predicted resource usage and the characteristic parameters.

2. The method according to claim 1, characterized in that, The step of dynamically adjusting the allocation strategy of the target cloud resources based on the predicted resource usage and the characteristic parameters includes: The optimal configuration parameters of the target cloud resource are obtained from a preset experience base based on the predicted resource usage value and the feature parameters. The preset experience base includes multiple sets of optimized configuration records of cloud resources. Each set of optimized configuration records is associated with the optimal configuration parameters corresponding to a specific predicted resource usage value and feature parameters. Based on the optimal configuration parameters, perform at least one of the following operations: resource scaling up / down, merging cloud resource instances, automatically shutting down cloud resources, or resource migration.

3. The method according to claim 1, characterized in that, The feature parameters include the service type. The step of dynamically adjusting the allocation strategy of the target cloud resources based on the predicted resource usage and the feature parameters includes: The predicted resource usage value is compared with a first preset threshold. If the predicted resource usage value is lower than the first preset threshold at multiple consecutive time points, and the service type belongs to off-peak service or cold backup service, then the specification parameters of the target cloud resource are lowered based on the first preset specification adjustment threshold.

4. The method according to claim 3, characterized in that, After comparing the predicted resource usage value with a first preset threshold, the method further includes: If the predicted resource usage value is lower than the first preset threshold at multiple consecutive time points, and the service type belongs to any one of test service, temporary service, or offline service, then the target cloud resource is shut down.

5. The method according to claim 1, characterized in that, The step of dynamically adjusting the allocation strategy of the target cloud resources based on the predicted resource usage and the characteristic parameters includes: The predicted resource usage value is compared with a second preset threshold. If the predicted resource usage value is greater than the second preset threshold at multiple consecutive time points, the specification parameters of the target cloud resource will be adjusted upwards.

6. The method according to claim 5, characterized in that, The characteristic parameters include the elastic scaling capability of the service, and the upward adjustment of the specification parameters of the target cloud resource includes: The second preset specification adjustment threshold is determined based on the elastic expansion and contraction capacity; The specification parameters of the target cloud resource are adjusted upward based on the second preset specification adjustment threshold.

7. The method according to claim 1, characterized in that, The target cloud resources include first cloud resources and second cloud resources. The step of dynamically adjusting the allocation strategy of the target cloud resources based on the predicted resource usage and the characteristic parameters includes: Compare the predicted usage value of the first cloud resource with the third preset threshold; The predicted usage value of the second cloud resource is compared with the fourth preset threshold. If the predicted usage value of the first cloud resource is lower than the third preset threshold at multiple consecutive time points, and the predicted usage value of the second cloud resource is lower than the fourth preset threshold at multiple consecutive time points, then it is determined whether the first cloud resource and the second cloud resource have business isolation. If so, the first cloud resource and the second cloud resource are merged.

8. A cloud resource optimization device, characterized in that, include: The acquisition unit is used to acquire time-series indicator data of the target cloud resources within a historical preset time period. The input unit is used to input the time-series index data into a preset intelligent prediction model to obtain the predicted resource usage value of the target cloud resource in a future preset time period. The preset intelligent prediction model is used to predict the resource usage of the cloud resource in the future preset time period. The extraction unit is used to extract the characteristic parameters of the services carried by the target cloud resources; The adjustment unit is used to dynamically adjust the allocation strategy of the target cloud resources based on the predicted resource usage value and the characteristic parameters.

9. A computer device, characterized in that, The computer device includes a memory and a processor, the memory storing a computer program, and the processor executing the computer program to implement the method as described in any one of claims 1 to 7.

10. A computer-readable storage medium, characterized in that, The storage medium stores a computer program that, when executed by a processor, can implement the method as described in any one of claims 1 to 7.

Images