A resource processing method and device for a private cloud

Abstract

Embodiments of the present application provide a resource processing method and device for a private cloud, comprising: obtaining a historical task amount and a historical user quantity of the private cloud; determining an estimated task amount of the private cloud according to the historical task amount, the historical user quantity and an estimated total user quantity of the private cloud; and determining an estimated resource usage amount required by the private cloud under the estimated task amount. The prediction of the resource usage amount required by the private cloud can be efficiently and accurately completed under the condition of only obtaining non-real-time online monitoring data.

Description

TECHNICAL FIELD

[0001] The present application relates to the technical field of cloud computing, in particular to a resource processing method of a private cloud and a resource processing device of a private cloud. BACKGROUND

[0002] A private cloud platform is a platform that provides virtualized resource services for a single organization. The private cloud platform provides services mainly through enterprise internal deployment or third-party hosting.

[0003] Generally speaking, for a public cloud platform, the provider of the cloud platform can easily complete online traffic monitoring, offline stress testing, and traffic playback, so that the provider of the public cloud platform can easily adjust the containers in the public cloud environment to keep the public cloud platform in a relatively stable running state. However, for a private cloud platform, the provider of the cloud platform, especially the third-party provider of the cloud platform, cannot complete real-time online traffic monitoring in the private cloud platform. The provider of the cloud platform also cannot easily perform offline stress testing and traffic playback, which may result in that the private cloud platform cannot well adapt to the needs of customers for adjustment. SUMMARY

[0004] In view of the above problems, the present application is proposed to provide a resource processing method of a private cloud and a corresponding resource processing device of a private cloud, which can overcome the above problems or at least partially solve the above problems.

[0005] To solve the above problems, the present application discloses a resource processing method of a private cloud, comprising:

[0006] obtaining a historical task amount and a historical user quantity of the private cloud;

[0007] determining an estimated task amount of the private cloud according to the historical task amount, the historical user quantity, and an estimated total user quantity of the private cloud;

[0008] determining an estimated resource usage amount required for the private cloud to run under the estimated task amount.

[0009] Optionally, the step of obtaining the historical task amount and the historical user quantity of the private cloud comprises:

[0010] selecting a plurality of first time points in a first preset historical period, and collecting a first task amount and a user quantity of the private cloud at the first time points;

[0011] determining the historical task amount of the private cloud according to a total of the collected first task amounts;

[0012] taking a total of the collected user quantities as the historical user quantity of the private cloud.

[0013] Optionally, the estimated resource usage includes estimated processor resources and estimated memory resources.

[0014] The step of determining the estimated resource usage required by the private cloud to run under the estimated task amount includes:

[0015] According to a preset first relationship formula, the estimated processor resources of the private cloud are determined according to the estimated task amount.

[0016] According to a preset second relationship formula, the estimated memory resources of the private cloud are determined according to the estimated task amount.

[0017] Optionally, the method further includes:

[0018] For an application running in the private cloud, a plurality of second time points are obtained in a plurality of second preset historical time periods, and a second task amount, used processor resources and used memory resources of the application at the second time points are obtained.

[0019] According to the second task amount and the used processor resources of the application, a first relationship formula between the task amount and the processor resources of the application is determined.

[0020] According to the second task amount and the used memory resources of the application, a second relationship formula between the task amount and the memory resources of the application is determined.

[0021] Optionally, the method further includes:

[0022] For an application running in the private cloud, a historical peak task amount of the application in a first preset historical time period is collected.

[0023] According to the historical task amount of the private cloud, the estimated task amount and the historical peak task amount of the application, an estimated peak task amount of the application is determined.

[0024] Optionally, the step of determining the estimated processor resources of the private cloud according to the estimated task amount and the preset first relationship formula includes:

[0025] The estimated peak task amount of the application and the first relationship formula are used to calculate the estimated processor resources corresponding to the application.

[0026] The sum of the estimated processor resources of all applications in the private cloud is taken as the estimated processor resources of the private cloud.

[0027] The step of determining the estimated memory resources of the private cloud according to the estimated task amount and the preset second relationship formula includes:

[0028] The estimated peak task quantity of the application and a second relationship are used to calculate the estimated memory resource corresponding to the application.

[0029] The sum of the estimated memory resources of all applications in the private cloud is taken as the estimated memory resource of the private cloud.

[0030] Optionally, the method further comprises:

[0031] The estimated resource usage is used to adjust the number of containers in the private cloud.

[0032] Optionally, the step of using the estimated resource usage to adjust the number of containers in the private cloud comprises:

[0033] According to the estimated resource usage and a preset container resource quantity, a target container deployment quantity is determined.

[0034] The number of containers in the private cloud is adjusted to the target container deployment quantity.

[0035] Optionally, the container resource quantity comprises a container processor resource quantity and a container memory resource quantity.

[0036] The step of determining the target container deployment quantity according to the estimated resource usage and the preset container resource quantity comprises:

[0037] According to the estimated processor resource and a preset container processor resource quantity, a first container deployment quantity is determined.

[0038] According to the estimated memory resource and a preset container memory resource quantity, a second container deployment quantity is determined.

[0039] The greater of the first container deployment quantity and the second container deployment quantity is selected as the target container deployment quantity.

[0040] Embodiments of the application also provide a resource processing device for a private cloud, comprising:

[0041] An acquisition module is configured to acquire historical task quantity and historical user quantity of a private cloud.

[0042] A task estimation module is configured to determine estimated task quantity of the private cloud according to the historical task quantity, the historical user quantity and estimated total user quantity of the private cloud.

[0043] A usage determination module is configured to determine estimated resource usage required by the private cloud to run under the estimated task quantity.

[0044] Optionally, the acquisition module comprises:

[0045] The acquisition sub-module is configured to select a plurality of first time points in a first preset historical period, and collect a first task amount and a user quantity of the special cloud at the first time points;

[0046] The historical task amount determination sub-module is configured to determine a historical task amount of the special cloud according to a total of the collected first task amounts;

[0047] The historical user quantity determination sub-module is configured to take a total of the collected user quantities as a historical user quantity of the special cloud.

[0048] Optionally, the estimated resource usage includes an estimated processor resource and an estimated memory resource.

[0049] The usage determination module includes:

[0050] The processor resource determination sub-module is configured to determine an estimated processor resource of the special cloud according to the estimated task amount and a preset first relationship.

[0051] The memory resource determination sub-module is configured to determine an estimated memory resource of the special cloud according to the estimated task amount and a preset second relationship.

[0052] Optionally, the device further includes:

[0053] The used resource acquisition module is configured to acquire, for an application running in the special cloud, a second task amount, a used processor resource, and a used memory resource of the application at a plurality of second time points in a plurality of second preset historical periods.

[0054] The first relationship determination module is configured to determine a first relationship between a task amount and a processor resource of the application according to the second task amount and the used processor resource of the application.

[0055] The second relationship determination module is configured to determine a second relationship between a task amount and a memory resource of the application according to the second task amount and the used memory resource of the application.

[0056] Optionally, the device further includes:

[0057] The historical peak task amount acquisition module is configured to acquire, for an application running in the special cloud, a historical peak task amount of the application in a first preset historical period.

[0058] The estimated peak task amount determination module is configured to determine an estimated peak task amount of the application according to the historical task amount of the special cloud, the estimated task amount, and the historical peak task amount of the application.

[0059] Optionally, the processor resource determination submodule includes:

[0060] An application processor resource calculation unit is used to calculate the estimated processor resources corresponding to the application using the estimated peak workload of the application and a first relational expression.

[0061] A private cloud processor resource computing unit is used to take the sum of the estimated processor resources of all applications in the private cloud as the estimated processor resources of the private cloud.

[0062] The memory resource determination submodule includes:

[0063] An application memory resource calculation unit is used to calculate the estimated memory resources corresponding to the application using the estimated peak task volume of the application and a second relational expression.

[0064] The private cloud memory resource calculation unit is used to take the sum of the estimated memory resources of all applications in the private cloud as the estimated memory resources of the private cloud.

[0065] Optionally, the device further includes:

[0066] The container adjustment module is used to adjust the number of containers in the private cloud based on the estimated resource usage.

[0067] Optionally, the container adjustment module includes:

[0068] The target container deployment quantity determination submodule is used to determine the target container deployment quantity based on the estimated resource usage and the preset container resource quantity.

[0069] The container adjustment submodule is used to adjust the number of containers in the private cloud to the target container deployment quantity.

[0070] Optionally, the container resource quantity includes the container processor resource quantity and the container memory resource quantity;

[0071] The target container deployment quantity determination submodule includes:

[0072] The first container deployment quantity determination unit is used to determine the first container deployment quantity based on the estimated processor resources and the preset container processor resource quantity.

[0073] The second container deployment quantity determination unit is used to determine the second container deployment quantity based on the estimated memory resources and the preset container memory resource quantity.

[0074] The target container deployment quantity determination unit is used to select the larger container deployment quantity between the first container deployment quantity and the second container deployment quantity as the target container deployment quantity.

[0075] This application also discloses an electronic device, including:

[0076] One or more processors; and

[0077] One or more machine-readable media having instructions stored thereon, which, when executed by the one or more processors, cause the electronic device to perform one or more methods as described in the embodiments of this application.

[0078] This application also discloses one or more machine-readable media storing instructions that, when executed by one or more processors, cause the processors to perform one or more methods as described in this application.

[0079] The embodiments of this application have the following advantages:

[0080] This invention obtains the historical task volume and historical user count of a private cloud; based on the historical task volume, historical user count, and estimated total user count, it determines the estimated task volume of the private cloud; and it determines the estimated resource usage required for the private cloud to operate under the estimated task volume. This allows for efficient and accurate prediction of the resource usage required by a private cloud, even with only non-real-time online monitoring data. Attached Figure Description

[0081] Figure 1 This is a flowchart illustrating the steps of a method for processing resources in a private cloud, as described in this application.

[0082] Figure 2 This is a flowchart illustrating the steps of another embodiment of a private cloud resource processing method according to this application.

[0083] Figure 3 This is a flowchart illustrating the steps of another embodiment of a private cloud resource processing method according to this application.

[0084] Figure 4 This is a flowchart illustrating the steps of another embodiment of a private cloud resource processing method according to this application.

[0085] Figure 5 This is a structural block diagram of a resource processing device embodiment for a private cloud, according to an embodiment of this application. Detailed Implementation

[0086] To make the above-mentioned objectives, features and advantages of this application more apparent and understandable, the application will be further described in detail below with reference to the accompanying drawings and specific embodiments.

[0087] Generally, existing methods for handling cloud platform resources are designed for situations where changes in cloud platform traffic are easily observable. Configuring cloud platform resources often involves real-time online traffic monitoring, and offline stress testing and traffic replay can simulate high-concurrency online scenarios, making it relatively easy to understand cloud platform traffic changes and accurately predict resource usage. However, for private clouds serving specific enterprises, real-time online traffic monitoring is typically impossible, and offline stress testing and traffic replay are even more difficult. Therefore, existing methods for handling cloud platform resources are difficult to apply to private clouds.

[0088] In situations where the resource usage requirements of a private cloud are not easily determined, this solution addresses the challenge of acquiring historical task volume and user counts (not requiring real-time data). Based on these historical data, the estimated task volume and user count are used to predict the potential resource usage of the private cloud, allowing for appropriate adjustments. This enables efficient prediction of resource usage for private clouds, even with only non-real-time online monitoring data. This ensures that the private cloud capacity meets user needs, improving the user experience. Furthermore, this solution can be applied to the initial deployment of other private clouds in the same industry, achieving efficient private cloud capacity planning.

[0089] Reference Figure 1 This document illustrates a flowchart of a method for processing resources in a private cloud, according to an embodiment of this application. The method may specifically include the following steps:

[0090] Step 101: Obtain the historical task volume and historical user count of the private cloud;

[0091] Specifically, in order to determine the number of containers required for the normal operation of a private cloud, the historical task volume and historical user volume of the private cloud can be obtained first, so that the capacity of the private cloud can be adjusted based on the private cloud's operational status data that can be obtained in non-real-time.

[0092] The historical task volume refers to the number of tasks processed by the private cloud within a historical period. The historical user count refers to the number of users who accessed the private cloud within a historical period. By analyzing the historical task volume and historical user count of the private cloud, the historical load status of the private cloud can be determined. Subsequently, based on the load status of the private cloud, the capacity of the private cloud can be adjusted accordingly to avoid the private cloud being under high load.

[0093] Step 102: Determine the estimated task volume of the private cloud based on the historical task volume, historical user number, and estimated total user volume of the private cloud.

[0094] During the construction of a private cloud, the specific number of users of the private cloud customer is obtained. Based on this user data, the total number of users that the private cloud may need to support can be determined, and an estimated total number of users can be obtained.

[0095] To ensure the proper functioning of a private cloud even with a large number of users accessing it simultaneously, and to prevent resource waste, the capacity of a private cloud is limited by external factors such as network and equipment. Unlike public clouds, it cannot be monitored and adjusted in real time. Therefore, the accuracy of the estimated total user count significantly impacts the deployment effectiveness of a private cloud. Through long-term practice, the inventors have predicted the corresponding task volume that a private cloud might generate when accessed by users with the estimated total user count, based on the historical task volume processed by the private cloud under historical user counts. This allows them to obtain the estimated task volume of the private cloud.

[0096] In practical implementation, the relationship between historical task volume and historical user number in the private cloud is analyzed to calculate the similarity of task correlation among private cloud users, thereby obtaining the correspondence between task volume and user number in the private cloud. Then, based on the obtained estimated total user number, the estimated task volume of the private cloud is obtained through the correspondence. For example, when users using the same private cloud have a high degree of similarity in their task requirements, by analyzing the relationship between historical task volume and historical user number in the private cloud, the correspondence between their task volume and user number is obtained, for example, user number × coefficient A = task volume. Based on this coefficient, the estimated task volume of the private cloud can be obtained as: estimated total user number × coefficient A.

[0097] Step 103: Determine the estimated resource usage required for the operation of the private cloud under the estimated task volume;

[0098] For a private cloud, the estimated workload refers to the workload generated when most users access the private cloud. If the private cloud's computing resources can handle this estimated workload, the private cloud can maintain stable operation in most cases. Therefore, after determining the estimated workload, the estimated resource usage for running the private cloud is predicted.

[0099] In practical implementation, customers using private clouds can belong to different types of industries, such as logistics, finance, education, and manufacturing. In one implementation, for industries of the same or similar types, such as education and training, a relationship between task volume and resource usage is generated based on historical operational status attribute data such as task volume and resource usage. Subsequently, the task volume can be estimated, and based on the relationship between task volume and resource usage, the estimated resource volume of the private cloud can be calculated.

[0100] Step 103 further includes obtaining the resource usage of industries that are the same as or similar to the industry mentioned in the private cloud deployment data. This is to enable a more accurate prediction of the resource usage required by the user based on the resource usage of the same or similar industries.

[0101] In another implementation, step 103 further includes saving the confirmed estimated resource usage and industry field data to iterate and adjust the existing data in the system so that the resource usage of private clouds in the same or similar industries can be more accurately predicted based on the saved estimated resource usage and industry field data.

[0102] In yet another embodiment of this application, Figure 2 This is a flowchart illustrating another embodiment of a private cloud resource processing method according to this application. The method may further include: Step 201, periodically collecting actual usage data of the private cloud to form a private cloud resource database, which at least includes industry field data, historical task volume, resource usage, and number of users of the private cloud. Step 202, based on the private cloud resource database, obtaining the correspondence between historical task volume and resource usage of the private cloud, and establishing an association between the corresponding relationship and the industry field data of the private cloud. Therefore, when it is necessary to predict the resource usage of private clouds in the same or similar industries, the historical correspondence between task volume and resource usage of private clouds in the same or similar industries can be extracted based on the private cloud resource database, allowing for efficient and accurate prediction of private cloud resource usage.

[0103] In practice, to maintain the healthy operation of a private cloud, the computing resources required can exceed the resources needed to handle the estimated workload. This is to prevent the private cloud from being under high load for extended periods, which could lead to its inability to cope with sudden increases in user volume or other anomalies. Furthermore, the amount of additional resources required for stable private cloud operation can vary across different industries.

[0104] Therefore, in one embodiment, it may further include setting a corresponding first increment ratio based on industry field data. The first increment ratio can be used to increase the estimated resource usage to ensure that the private cloud can operate relatively stably and avoid the private cloud being in a high-load state for a long time.

[0105] In one embodiment, Figure 3 This is a flowchart illustrating the steps of another embodiment of a private cloud resource processing method according to this application, the method further comprising:

[0106] Step 104: Increase the estimated resource usage by the first incremental ratio to obtain a new estimated resource usage.

[0107] Specifically, the required increase in resource usage can be calculated using the first increment ratio and the estimated resource usage. Then, based on the estimated resource usage, the resource usage increment is increased to obtain a new estimated resource usage.

[0108] For example, if the first increment ratio is 50%, after calculating the estimated resource usage, the product of the first increment ratio of 50% and the estimated resource usage is taken as the incremental increase in resource usage. Then, the incremental increase in resource usage is added to the estimated resource usage to obtain the new estimated resource usage.

[0109] In one implementation, the resource usage increment is further set based on industry field data.

[0110] The inventors discovered during extensive patent cloud deployments that, based on industry-specific data, resource usage increment levels can be further configured. Different increment levels correspond to different initial increment ratios. By setting corresponding resource usage increment levels, the same industry-specific data can be matched with more actual enterprises, thereby reducing database computation and storage requirements and improving matching efficiency. Different actual industries corresponding to the same industry-specific data can be matched with appropriate increment levels based on their different needs. For example, if an actual enterprise is relatively large within the same industry-specific data set, it can be configured with an increment level corresponding to a larger initial increment ratio. Similarly, if an actual enterprise uses the private cloud more frequently than other enterprises within the same industry-specific data set, it can be configured with an increment level corresponding to a larger initial increment ratio.

[0111] In practice, the industry field data can be set with the corresponding first incremental ratio and resource usage incremental level, which can also be stored in the private cloud resource database. This allows for more efficient resource configuration of the private cloud based on the private cloud resource database.

[0112] This invention obtains the historical task volume and historical user count of a private cloud; based on the historical task volume, historical user count, and estimated total user count, it determines the estimated task volume of the private cloud; and it determines the estimated resource usage required for the private cloud to operate under the estimated task volume. This allows for efficient and accurate prediction of the resource usage required by a private cloud scenario, even with only non-real-time online monitoring data.

[0113] Reference Figure 4 This document illustrates a flowchart of another embodiment of a private cloud resource processing method according to this application, which may specifically include the following steps:

[0114] Step 401: Select several first time points in the first preset historical period and collect the first task volume and number of users of the private cloud at the first time point;

[0115] To ensure the proper functioning of a private cloud even with a large number of users accessing it simultaneously, and to prevent resource waste, the capacity of a private cloud is limited by external factors such as network and equipment. Unlike public clouds, it cannot be monitored and adjusted in real time. Therefore, the accuracy of the estimated total user count significantly impacts the deployment effectiveness of a private cloud. Through long-term practice, the inventors have predicted the corresponding task volume that a private cloud might generate when accessed by users with the estimated total user count, based on the historical task volume processed by the private cloud under historical user counts. This allows them to obtain the estimated task volume of the private cloud.

[0116] Specifically, in order to determine the historical task volume and the number of historical users of the private cloud, a discrete random sampling method can be adopted. Several first time points are randomly selected in the first preset historical period, and the first task volume and the number of users of the private cloud at the first time point are collected. Based on the first task volume and the number of users at the several first time points, the total task volume and the total number of users within the historical period can be determined.

[0117] The historical time period can be determined according to actual needs, such as the past 24 hours, 0-24 hours of the previous day, 9-18 hours of the previous day, the previous week, a specified month, a specified week, etc., and this invention does not impose any restrictions on this. As an example of this invention, 50 first time points can be randomly selected discretely from 0-24 hours of the previous day, and the first task volume and number of users at the first time point can be collected.

[0118] In a practical implementation, the workload of the private cloud can be represented by queries per second (QPS). A higher QPS at the first point in time indicates a larger workload for the private cloud at that moment.

[0119] Step 402: Determine the historical task volume of the private cloud based on the total number of the collected first task volumes.

[0120] After obtaining the initial task volume and user count at several first time points, the historical task volume and historical user count within a first preset historical period can be further determined. Therefore, based on actual needs, a task volume change curve can be constructed based on the initial task volume at several collected first time points, and the task volume at all times within the historical period can be accumulated based on the task volume change curve to obtain the historical task volume. To more simply and efficiently determine the number of containers in the private cloud, the total number of all collected initial task volumes can also be directly used as the historical task volume of the private cloud within the historical period.

[0121] Step 403: The total number of the collected user counts is taken as the historical user count of the private cloud;

[0122] Depending on actual needs, a user count change curve can be constructed based on the number of users collected at several first time points. The user count at all times during the historical period can then be accumulated from this curve to obtain the historical user count. To more simply and efficiently determine the number of containers in the private cloud, the total number of all collected user counts can also be directly used as the historical user count of the private cloud during the historical period.

[0123] Step 404: Determine the estimated task volume of the private cloud based on the historical task volume, historical user number, and estimated total user volume of the private cloud.

[0124] During the construction of a private cloud, the specific number of users of the private cloud customer is obtained. Based on this user data, the total number of users that the private cloud may need to support can be determined, and an estimated total number of users can be obtained.

[0125] To ensure the private cloud can operate normally under normal circumstances, it should have the ability to remain operational even when a large number of users access it simultaneously. Therefore, based on the historical task volume processed by the private cloud with a historical number of users, the potential task volume of the private cloud when accessed by an estimated total number of users can be predicted, thus determining the estimated task volume of the private cloud.

[0126] In practical implementation, the relationship between historical task volume and historical user count of the private cloud is analyzed to calculate the similarity of task correlation among private cloud users, thereby obtaining the correspondence between task volume and user count in the private cloud. Then, based on the obtained estimated total user count, the estimated task volume of the private cloud is obtained through the correspondence. For example, when users using the same private cloud have a high degree of similarity in their task requirements, the correspondence between their task volume and user count can be obtained by analyzing the relationship between historical task volume and historical user count of the private cloud.

[0127] In one specific embodiment of the present invention, the estimated task volume can be calculated using the following formula:

[0128] Estimated task volume = (Estimated total number of users / Historical number of users) × Historical task volume.

[0129] In one implementation, customers using the private cloud can belong to different types of industries, such as logistics, finance, education, and manufacturing. For industries of the same or similar types, there can be a similar correspondence between task volume and number of users. Therefore, industry field data can be set during private cloud deployment, and the private cloud's industry field data, historical task volume, and the historical number of users corresponding to the historical task volume can be stored.

[0130] In one implementation, the method further includes: determining the estimated task volume of the current private cloud based on the historical task volume of private clouds in the same or similar industries, the historical number of users corresponding to the historical task volume, and the estimated total number of users of the current private cloud. Therefore, when a private cloud is initially deployed, or when the private cloud cannot monitor traffic data, task volume and user number data from the same or similar industries can be used to estimate the potential task volume of the current private cloud.

[0131] Step 405: Determine the estimated resource usage required for the operation of the private cloud under the estimated task volume;

[0132] For a private cloud, the estimated workload refers to the workload generated when most users access the private cloud. If the private cloud's computing resources can handle this estimated workload, the private cloud can maintain stable operation in most cases. Therefore, after determining the estimated workload, the estimated resource usage for running the private cloud is predicted.

[0133] In practical implementation, customers using private clouds can belong to different types of industries, such as logistics, finance, education, and manufacturing. In one implementation, for industries of the same or similar types, such as education and training, a relationship between task volume and resource usage is generated based on historical operational status attribute data such as task volume and resource usage. Subsequently, the task volume can be estimated, and based on the relationship between task volume and resource usage, the estimated resource volume of the private cloud can be calculated.

[0134] Step 405 further includes obtaining the resource usage of industries that are the same as or similar to the private cloud deployment based on the industry field data. This allows for a more accurate prediction of the resource usage required by the private cloud itself, based on the resource usage of the same or similar industries.

[0135] In another implementation, step 405 further includes saving the confirmed estimated resource usage and industry field data to iterate and adjust the existing data in the system, so that the resource usage of private clouds in the same or similar industries can be more accurately predicted based on the saved estimated resource usage and industry field data.

[0136] In another embodiment of this application, the method may further include: periodically collecting actual usage data of the private cloud to form a private cloud resource database, which at least includes industry field data, historical task volume, resource usage, and number of users of the private cloud. Based on the private cloud resource database, the correspondence between historical task volume and resource usage of the private cloud is obtained, and an association is established between the corresponding relationship and the industry field data of the private cloud. Therefore, when it is necessary to predict the resource usage of private clouds in the same or similar industries, the historical correspondence between task volume and resource usage of private clouds in the same or similar industries can be extracted based on the private cloud resource database, enabling efficient and accurate prediction of private cloud resource usage.

[0137] In one embodiment of this application, the method further includes:

[0138] S11, For the application running in the private cloud, collect the historical peak task volume of the application in the first preset historical period;

[0139] Specifically, a private cloud can simultaneously run multiple different types of applications, and these different types of applications can have different relationships between workload and resource usage. Therefore, in order to more accurately estimate the computing resources required by the private cloud, the historical peak workload of each application running in the private cloud can be collected during a first preset historical period.

[0140] The historical peak task volume can be defined as the highest task volume of an application at a specific point in time within a historical period. When using queries per second (SPS) to represent task volume, the historical peak task volume can be defined as the highest SPS of an application within a historical period.

[0141] S12, determine the estimated peak task volume of the application based on the historical task volume of the private cloud, the estimated task volume, and the historical peak task volume of the application.

[0142] To ensure that applications can maintain stable operation even during peak usage periods, the overall workload of the private cloud can be estimated by further calculating the total workload required for the private cloud based on the peak workload of each application. Therefore, the estimated peak workload of the application can be determined based on the historical workload of the private cloud, the historical number of users, and the historical peak workload of the application.

[0143] In practical implementation, the estimated peak workload of an application can be calculated in the following way:

[0144] Estimated peak task volume = (Estimated task volume / Historical task volume) × Historical peak task volume

[0145] Optionally, to maintain the healthy operation of the private cloud, the computing resources required by the application can exceed the computing resources needed to handle the estimated peak task volume. This avoids the private cloud being under high load for extended periods, which could prevent it from effectively handling unexpected situations such as sudden increases in the application's user base. Therefore, a second increment ratio can be set when determining the estimated peak task volume of the application. After determining a peak task volume for the application based on the historical task volume of the private cloud, the estimated task volume, and the application's historical peak task volume, the peak task volume can be further increased according to the second increment ratio to finally obtain the estimated peak task volume. The second increment ratio can be 40%, 50%, 70%, etc., and this invention does not impose any limitations on it.

[0146] In practical implementation, the estimated peak workload of an application can be calculated in the following way:

[0147] Estimated peak task volume = (Estimated task volume / Historical task volume) × Historical peak task volume × (1 + Second increment multiplier)

[0148] In one implementation, step S12 further includes saving the confirmed estimated peak task volume to iterate and adjust the existing data in the system. In another implementation, the historical peak task volume and the estimated peak task volume of each application in the private cloud can be stored in the private cloud resource database.

[0149] Specifically, the estimated resource usage includes estimated processor resources and estimated memory resources;

[0150] For private clouds, the computing resources required during operation can be processor resources and memory resources. Therefore, in the process of estimating resource usage, processor resources and memory resources can be predicted separately to ensure that the final number of containers can simultaneously meet the private cloud's requirements for processors and memory.

[0151] In one embodiment of this application, the step of determining the estimated resource usage required for the operation of the private cloud under the estimated task volume includes:

[0152] S21, determine the estimated processor resources of the private cloud based on the estimated task volume and the preset first relationship;

[0153] Specifically, a first relation can be preset. This first relation can be generated based on the relationship between the historical task volume and processor resources of the private cloud or private clouds in the same industry. Therefore, the estimated processor resources required for the operation of the private cloud can be determined based on the estimated task volume and the preset first relation.

[0154] In one implementation, step S21 further includes saving the confirmed estimated processor resources to iterate and adjust the existing data in the system. In one implementation, the estimated processor resources for each application in the private cloud can be stored in a private cloud resource database.

[0155] In one embodiment of this application, the step of determining the estimated processor resources of the private cloud based on the estimated task volume and a preset first relationship includes:

[0156] S211, using the estimated peak task volume of the application and the first relational expression, calculate the estimated processor resources corresponding to the application;

[0157] Specifically, a private cloud can simultaneously run multiple different types of applications, and these applications can have different relationships between workload and processor resources. Therefore, a first equation can be set for each application to express the relationship between its workload and processor resources. Subsequently, the estimated peak workload of the application and the first equation can be used to calculate the estimated processor resources corresponding to that application.

[0158] S212, take the sum of the estimated processor resources of all applications in the private cloud as the estimated processor resources of the private cloud.

[0159] For a private cloud, its estimated processor resources can be the sum of the estimated processor resources of all applications within the private cloud. Therefore, the sum of the estimated processor resources of all applications within the private cloud can be used as the estimated processor resources of the private cloud.

[0160] In one implementation, step S212 further includes saving the estimated processor resources corresponding to the confirmed application and the estimated processor resources of the private cloud, thereby iterating and adjusting the existing data in the system. In one implementation, the estimated processor resources corresponding to each application in the private cloud and the estimated processor resources of the private cloud can be stored in the private cloud resource database.

[0161] S22, determine the estimated memory resources of the private cloud based on the estimated task volume and the preset second relationship.

[0162] Specifically, a second relation can be preset. This second relation can be generated based on the relationship between the historical task volume and memory resources of the private cloud or private clouds in the same industry. Therefore, the estimated memory resources required for the operation of the private cloud can be determined based on the estimated task volume and the preset second relation.

[0163] In one implementation, step S22 further includes saving the confirmed estimated memory resources to iterate and adjust existing system data. In another implementation, the estimated memory resources for each application in the private cloud can be stored in a private cloud resource database.

[0164] In one embodiment of this application, the step of determining the estimated memory resources of the private cloud based on the estimated task volume and a preset second relationship includes:

[0165] S221, using the estimated peak task volume of the application and the second relational expression, calculate the estimated memory resources corresponding to the application;

[0166] Specifically, a private cloud can simultaneously run multiple different types of applications, and these applications can have different relationships between workload and memory resources. Therefore, a first equation can be set for each application to express the relationship between its workload and memory resources. Subsequently, the estimated peak workload of the application and the first equation can be used to calculate the estimated memory resources corresponding to that application.

[0167] S222, the sum of the estimated memory resources of all applications in the private cloud is taken as the estimated memory resources of the private cloud.

[0168] For a private cloud, its estimated memory resources can be the sum of the estimated memory resources of all applications within the private cloud. Therefore, the sum of the estimated memory resources of all applications within the private cloud can be used as the estimated memory resources of the private cloud.

[0169] In one implementation, step S222 further includes saving the estimated memory resources corresponding to the confirmed application and the estimated memory resources of the private cloud, thereby iterating and adjusting the existing data in the system. In one implementation, the estimated memory resources corresponding to each application in the private cloud and the estimated memory resources of the private cloud can be stored in the private cloud resource database.

[0170] In one embodiment of this application, the method further includes:

[0171] S31, for the application running in the private cloud, a number of second time points are obtained in a number of second preset historical time periods, and the second task volume, used processor resources, and used memory resources of the application at the second time point are obtained respectively.

[0172] Specifically, in order to generate the first relation and the second relation for applications running in the private cloud, several second time points can be obtained in several second preset historical periods. The second task volume, used processor resources, and used memory resources of the application at the second time point can be obtained so that the relationship between the task volume and processor resources, and the relationship between the task volume and memory resources of each application can be determined based on the historical information of task volume, processor resources, and memory resources.

[0173] S32, based on the second workload of the application and the processor resources used, determine a first relationship between the workload and processor resources for the application;

[0174] In a specific implementation, a first relational expression formula can be preset. The formula may have at least one undetermined coefficient. Fitting calculations such as least squares can be performed based on the second task load of the application and the processor resources used to determine the coefficients in the first relational expression, thereby obtaining a first relational expression that matches the application.

[0175] As an example of the present invention, the first relation can be expressed as follows:

[0176] Processor resources = Coefficient 1 × Task volume + Coefficient 2

[0177] S33, based on the second task volume of the application and the memory resources used, determine a second relationship between the task volume and memory resources of the application.

[0178] In a specific implementation, a second relational expression can be preset, which may contain at least one undetermined coefficient. The coefficients in the second relational expression can be determined by fitting calculations such as least squares based on the second task volume of the application and the memory resources used, thereby obtaining a second relational expression that matches the application.

[0179] As an example of the present invention, the second relation can be expressed as follows:

[0180] Memory resources = Coefficient 3 × Task volume + Coefficient 4

[0181] In one implementation, step S33 further includes saving the second workload, used processor resources, and used memory resources of the confirmed application at the second time point; and saving the first relationship between the application's workload and processor resources, and the second relationship between the application's workload and memory resources, thereby iterating and adjusting the existing data in the system. In one implementation, the second workload, used processor resources, and used memory resources of each application in the private cloud at the second time point; the first relationship between the application's workload and processor resources; and the second relationship between the application's workload and memory resources can be stored in the private cloud resource database. An association is established between the first relationship between the application's workload and processor resources and the industry field data of the private cloud, and an association is established between the second relationship between the application's workload and memory resources and the industry field data of the private cloud. Therefore, when it is necessary to predict the resource usage of private clouds in the same or similar industries in the future, the first and second relationships of private clouds in the same or similar industries can be extracted from the private cloud resource database to efficiently and accurately predict the resource usage of the private cloud.

[0182] In one embodiment of this application, the method further includes:

[0183] S41, using the estimated resource usage, adjust the number of containers in the private cloud.

[0184] In one implementation, the private cloud includes multiple containers. Step S104 further adjusts the amount of resources available to the private cloud by adjusting the number of containers in the private cloud, thereby ensuring the stable operation of the private cloud.

[0185] In practice, the number of containers required by the private cloud can be calculated based on the estimated resource usage and container resources, and the number of containers in the current private cloud can be adjusted accordingly.

[0186] In one embodiment of this application, the step of adjusting the number of containers in the private cloud using the estimated resource usage includes:

[0187] S51, Determine the target container deployment quantity based on the estimated resource usage and the preset container resource quantity;

[0188] Specifically, the computing resources that each container can provide can be configured by the user according to actual needs. Under normal circumstances, the container resource volume of a private cloud does not change frequently. Therefore, a preset period, such as three days, one week, or one month, can be used to obtain the container resource volume of the private cloud and determine the computing resources that each container can provide. Subsequently, the target container deployment quantity can be determined based on the estimated resource usage and the preset container resource volume.

[0189] In practical implementation, the target container deployment size can be calculated using the following formula:

[0190] Target container deployment size = Estimated resource usage / Container resource size

[0191] Specifically, the container resource quantity includes the container processor resource quantity and the container memory resource quantity;

[0192] For a private cloud, the computing resources required during operation can be processor resources and memory resources. Therefore, when determining the number of containers, the required number can be determined based on the amount of processor resources and memory resources of each container, ensuring that the final number of containers can simultaneously meet the private cloud's requirements for processors and memory.

[0193] In one embodiment of this application, the step of determining the target container deployment quantity based on the estimated resource usage and the preset container resource quantity includes:

[0194] S61, determine the first container deployment quantity based on the estimated processor resources and the preset container processor resource quantity;

[0195] Based on the estimated processor resources and the preset amount of container processor resources, the required initial container deployment quantity can be determined to meet the processor resource requirements of the private cloud.

[0196] In practice, the number of containers deployed can be calculated as follows:

[0197] First container deployment size = Estimated processor resources / Container processor resources

[0198] S62, determine the second container deployment quantity based on the estimated memory resources and the preset container memory resource quantity;

[0199] Based on the estimated memory resources and the preset container memory resources, the required initial container deployment quantity can be determined to meet the memory resource requirements of the private cloud.

[0200] In practice, the number of containers deployed can be calculated as follows:

[0201] First container deployment size = Estimated memory resources / Container memory resources

[0202] S63, Select the larger container deployment amount between the first container deployment amount and the second container deployment amount as the target container deployment amount.

[0203] Specifically, the first container deployment volume and the second container deployment volume can be different. In this case, in order to ensure that the private cloud can have sufficient processor resources and memory resources at the same time, the larger container deployment volume can be selected from the first container deployment volume and the second container deployment volume as the target container deployment volume.

[0204] For example, if the number of containers deployed in the first instance is greater than the number of containers deployed in the second instance, the number of containers deployed in the first instance will be used as the target number of containers deployed. If the number of containers deployed in the second instance is greater than the number of containers deployed in the first instance, the number of containers deployed in the second instance will be used as the target number of containers deployed.

[0205] S52, adjust the number of containers in the private cloud to the target container deployment amount.

[0206] Once the target container deployment volume required to meet the operational needs of the private cloud is determined, the number of containers in the private cloud can be adjusted to that target deployment volume. This ensures that the private cloud can maintain stable operation under most circumstances.

[0207] The private cloud adjustment method provided in this invention involves selecting several first time points within a first preset historical period, collecting the first task volume and user number of the private cloud at each of the first time points; determining the historical task volume of the private cloud based on the total number of the collected first task volumes; using the total number of the collected user numbers as the historical user number of the private cloud; determining the estimated task volume of the private cloud based on the historical task volume, historical user number, and estimated total user number; determining the estimated resource usage required for the private cloud to operate under the estimated task volume; and adjusting the number of containers in the private cloud using the estimated resource usage. This allows for non-real-time capacity adjustment of the private cloud, using only online monitoring data. This ensures that the private cloud capacity meets user needs and improves the user experience.

[0208] In one implementation, step S52 further includes saving the confirmed target container deployment quantity to iterate and adjust existing system data. In another implementation, the target container deployment quantity corresponding to the private cloud can be stored in the private cloud resource database. Subsequently, the correspondence between the estimated resource usage of the private cloud and the number of containers can be obtained, and an association can be established between this correspondence and the industry field data of the private cloud. Therefore, when it is necessary to predict the number of containers in private clouds for the same or similar industries in the future, the correspondence between the estimated resource usage of private clouds for the same or similar industries and the number of containers can be extracted from the private cloud resource database, allowing for efficient and accurate prediction of the container deployment quantity of the private cloud.

[0209] It should be noted that, for the sake of simplicity, the method embodiments are all described as a series of actions. However, those skilled in the art should understand that the embodiments of this application are not limited to the described order of actions, because according to the embodiments of this application, some steps can be performed in other orders or simultaneously. Secondly, those skilled in the art should also understand that the embodiments described in the specification are all preferred embodiments, and the actions involved are not necessarily required by the embodiments of this application.

[0210] Reference Figure 5 The diagram illustrates a structural block diagram of an embodiment of a private cloud adjustment device according to an embodiment of this application, which may specifically include the following modules:

[0211] The acquisition module is used to acquire the historical task volume and historical user count of the private cloud.

[0212] The task estimation module is used to determine the estimated task volume of the private cloud based on the historical task volume, historical user number, and estimated total user volume of the private cloud.

[0213] The usage determination module is used to determine the estimated resource usage required for the operation of the private cloud under the estimated task volume.

[0214] Optionally, the acquisition module includes:

[0215] The acquisition submodule is used to select several first time points in the first preset historical period and collect the first task volume and number of users of the private cloud at the first time point;

[0216] The historical task volume determination submodule is used to determine the historical task volume of the private cloud based on the total number of the collected first task volumes.

[0217] The historical user count determination submodule is used to take the total number of the collected user counts as the historical user count of the private cloud.

[0218] Optionally, the estimated resource usage includes estimated processor resources and estimated memory resources;

[0219] The usage determination module includes:

[0220] The processor resource determination submodule is used to determine the estimated processor resources of the private cloud based on the estimated task volume and a preset first relationship.

[0221] The memory resource determination submodule is used to determine the estimated memory resources of the private cloud based on the estimated task volume and the preset second relational formula.

[0222] Optionally, the device further includes:

[0223] The used resource acquisition module is used to acquire, within several second preset historical periods, several second time points for the application running in the private cloud, the second task volume, used processor resources, and used memory resources of the application at the second time point;

[0224] The first relation determination module is used to determine a first relation between the workload and processor resources of the application based on the second workload of the application and the processor resources used.

[0225] The second relation determination module is used to determine a second relation between the application's task volume and memory resources based on the application's second task volume and used memory resources.

[0226] Optionally, the device further includes:

[0227] The historical peak task volume collection module is used to collect the historical peak task volume of the application running in the private cloud during a first preset historical period.

[0228] The estimated peak task volume determination module is used to determine the estimated peak task volume of the application based on the historical task volume of the private cloud, the estimated task volume, and the historical peak task volume of the application.

[0229] Optionally, the processor resource determination submodule includes:

[0230] An application processor resource calculation unit is used to calculate the estimated processor resources corresponding to the application using the estimated peak task volume of the application and a first relational expression.

[0231] A private cloud processor resource computing unit is used to take the sum of the estimated processor resources of all applications in the private cloud as the estimated processor resources of the private cloud.

[0232] The memory resource determination submodule includes:

[0233] An application memory resource calculation unit is used to calculate the estimated memory resources corresponding to the application using the estimated peak task volume of the application and a second relational expression.

[0234] The private cloud memory resource calculation unit is used to take the sum of the estimated memory resources of all applications in the private cloud as the estimated memory resources of the private cloud.

[0235] Optionally, the device further includes:

[0236] The container adjustment module is used to adjust the number of containers in the private cloud based on the estimated resource usage.

[0237] Optionally, the container adjustment module includes:

[0238] The target container deployment quantity determination submodule is used to determine the target container deployment quantity based on the estimated resource usage and the preset container resource quantity.

[0239] The container adjustment submodule is used to adjust the number of containers in the private cloud to the target container deployment quantity.

[0240] Optionally, the container resource quantity includes the container processor resource quantity and the container memory resource quantity;

[0241] The target container deployment quantity determination submodule includes:

[0242] The first container deployment quantity determination unit is used to determine the first container deployment quantity based on the estimated processor resources and the preset container processor resource quantity.

[0243] The second container deployment quantity determination unit is used to determine the second container deployment quantity based on the estimated memory resources and the preset container memory resource quantity.

[0244] The target container deployment quantity determination unit is used to select the larger container deployment quantity between the first container deployment quantity and the second container deployment quantity as the target container deployment quantity.

[0245] As the device embodiment is basically similar to the method embodiment, the description is relatively simple, and relevant parts can be found in the description of the method embodiment.

[0246] This application also provides an electronic device, including:

[0247] One or more processors; and

[0248] One or more machine-readable media having instructions stored thereon, which, when executed by the one or more processors, cause the electronic device to perform the methods described in the embodiments of this application.

[0249] This application also provides one or more machine-readable media storing instructions that, when executed by one or more processors, cause the processors to perform the methods described in this application.

[0250] The various embodiments in this specification are described in a progressive manner, with each embodiment focusing on the differences from other embodiments. The same or similar parts between the various embodiments can be referred to each other.

[0251] Those skilled in the art will understand that embodiments of this application can be provided as methods, apparatus, or computer program products. Therefore, embodiments of this application can take the form of entirely hardware embodiments, entirely software embodiments, or embodiments combining software and hardware aspects. Furthermore, embodiments of this application can take the form of computer program products implemented on one or more computer-usable storage media (including but not limited to disk storage, CD-ROM, optical storage, etc.) containing computer-usable program code.

[0252] This application describes embodiments with reference to flowchart illustrations and / or block diagrams of methods, terminal devices (systems), and computer program products according to embodiments of this application. It should be understood that each block of the flowchart illustrations and / or block diagrams, and combinations of blocks in the flowchart illustrations and / or block diagrams, can be implemented by computer program instructions. These computer program instructions can be provided to a processor of a general-purpose computer, special-purpose computer, embedded processor, or other programmable data processing terminal device to produce a machine, such that the instructions, which execute via the processor of the computer or other programmable data processing terminal device, generate instructions for implementing the flowchart illustrations. Figure 1 One or more processes and / or boxes Figure 1 A device that provides the functions specified in one or more boxes.

[0253] These computer program instructions may also be stored in a computer-readable storage medium that can direct a computer or other programmable data processing terminal device to operate in a particular manner, such that the instructions stored in the computer-readable storage medium produce an article of manufacture including instruction means, which are implemented in a process Figure 1 One or more processes and / or boxes Figure 1 The function specified in one or more boxes.

[0254] These computer program instructions can also be loaded onto a computer or other programmable data processing terminal equipment, causing a series of operational steps to be performed on the computer or other programmable terminal equipment to produce a computer-implemented process, thereby providing instructions that execute on the computer or other programmable terminal equipment for implementing the process. Figure 1 One or more processes and / or boxes Figure 1 The steps of the function specified in one or more boxes.

[0255] Although preferred embodiments of the present application have been described, those skilled in the art, upon learning the basic inventive concept, can make other changes and modifications to these embodiments. Therefore, the appended claims are intended to be interpreted as including the preferred embodiments as well as all changes and modifications falling within the scope of the embodiments of the present application.

[0256] Finally, it should be noted that in this document, relational terms such as "first" and "second" are used only to distinguish one entity or operation from another, and do not necessarily require or imply any such actual relationship or order between these entities or operations. Furthermore, the terms "comprising," "including," or any other variations thereof are intended to cover non-exclusive inclusion, such that a process, method, article, or terminal device that comprises a list of elements includes not only those elements but also other elements not expressly listed, or elements inherent to such a process, method, article, or terminal device. Without further limitations, an element defined by the phrase "comprising one..." does not exclude the presence of other identical elements in the process, method, article, or terminal device that includes said element.

[0257] The above provides a detailed description of a private cloud resource processing method and apparatus. Specific examples have been used to illustrate the principles and implementation methods of this application. The descriptions of the above embodiments are only for the purpose of helping to understand the method and core ideas of this application. At the same time, those skilled in the art will recognize that there will be changes in the specific implementation methods and application scope based on the ideas of this application. Therefore, the content of this specification should not be construed as a limitation of this application.

Claims

1. A method for processing resources in a private cloud, characterized in that, include: Obtain the historical task volume and historical user count of the private cloud; The estimated task volume of the private cloud is determined based on its historical task volume, historical user count, and estimated total user count; the estimated total user count is the total number of users the private cloud needs to handle. Based on the estimated task volume and the industry to which the private cloud belongs, determine the estimated resource usage required for the operation of the private cloud under the estimated task volume. The steps for obtaining the historical task volume and historical user count of the private cloud include: Select several first time points within a first preset historical period and collect the first task volume and number of users of the private cloud at the first time point; The historical task volume of the private cloud is determined based on the total number of the first task volumes collected. The total number of the collected user counts shall be taken as the historical user count of the private cloud. The estimated resource usage includes estimated processor resources and estimated memory resources; The step of determining the estimated resource usage required for the operation of the private cloud under the estimated task volume includes: Based on the first relational formula relating the estimated task volume to the industry to which the private cloud belongs, the estimated processor resources of the private cloud are determined. The estimated memory resources of the private cloud are determined based on the second relational formula relating the estimated task volume to the industry to which the private cloud belongs; the method further includes: For the application running in the private cloud, several second time points are obtained in several second preset historical periods, and the second task volume, used processor resources, and used memory resources of the application at the second time point are obtained respectively. Based on the second workload of the application and the processor resources used, a first relationship between the workload and processor resources for the application is determined. Based on the second task volume of the application and the memory resources used, a second relationship between the task volume and memory resources of the application is determined; Establish the association between the first relation between the application's workload and the processor resources and the private cloud industry field data; Establish a relationship between the second relation between the application's workload and the memory resources and the private cloud industry field data.

2. The method according to claim 1, characterized in that, The method further includes: For applications running in the private cloud, the historical peak task volume of the applications during a first preset historical period is collected; The estimated peak task volume of the application is determined based on the historical task volume and estimated task volume of the private cloud, as well as the historical peak task volume of the application.

3. The method according to claim 2, characterized in that, The step of determining the estimated processor resources of the private cloud based on the first relational expression relating the estimated task volume to the industry to which the private cloud belongs includes: Using the estimated peak workload of the application and the first relational expression, calculate the estimated processor resources corresponding to the application; The sum of the estimated processor resources of all applications in the private cloud is taken as the estimated processor resources of the private cloud. The step of determining the estimated memory resources of the private cloud based on the second relational expression relating the estimated task volume to the industry to which the private cloud belongs includes: Using the estimated peak task volume of the application and the second relational expression, the estimated memory resources corresponding to the application are calculated. The sum of the estimated memory resources of all applications in the private cloud is taken as the estimated memory resources of the private cloud.

4. The method according to claim 1, characterized in that, The method further includes: The number of containers in the private cloud is adjusted based on the estimated resource usage.

5. The method according to claim 4, characterized in that, The step of adjusting the number of containers in the private cloud based on the estimated resource usage includes: The target container deployment quantity is determined based on the estimated resource usage and the preset container resource quantity. Adjust the number of containers in the private cloud to the target container deployment amount.

6. The method according to claim 5, wherein the container resource quantity includes the container processor resource quantity and the container memory resource quantity; The step of determining the target container deployment quantity based on the estimated resource usage and the preset container resource quantity includes: The first container deployment quantity is determined based on the estimated processor resources and the preset container processor resource quantity. The second container deployment quantity is determined based on the estimated memory resources and the preset container memory resource quantity. The larger of the first and second container deployment quantities is selected as the target container deployment quantity.

7. A resource processing device for a private cloud, characterized in that, include: The acquisition module is used to acquire the historical task volume and historical user count of the private cloud. The task estimation module is used to determine the estimated task volume of the private cloud based on the historical task volume, historical user number, and estimated total user volume of the private cloud; the estimated total user volume is the total number of users that the private cloud needs to handle. The usage determination module is used to determine the estimated resource usage required for the operation of the private cloud under the estimated task volume, based on the estimated task volume and the industry to which the private cloud belongs. The acquisition module includes: The acquisition submodule is used to select several first time points in the first preset historical period and collect the first task volume and number of users of the private cloud at the first time point; The historical task volume determination submodule is used to determine the historical task volume of the private cloud based on the total number of the collected first task volumes. The historical user count determination submodule is used to take the total number of the collected user counts as the historical user count of the private cloud. The estimated resource usage includes estimated processor resources and estimated memory resources; The usage determination module includes: The processor resource determination submodule is used to determine the estimated processor resources of the private cloud based on a first relational expression relating the estimated task volume to the industry to which the private cloud belongs. The memory resource determination submodule is used to determine the estimated memory resources of the private cloud based on the second relational formula relating the estimated task volume to the industry to which the private cloud belongs. The used resource acquisition module is used to acquire, within several second preset historical periods, several second time points for the application running in the private cloud, the second task volume, used processor resources, and used memory resources of the application at the second time point; The first relation determination module is used to determine a first relation between the workload and processor resources of the application based on the second workload of the application and the processor resources used. The second relation determination module is used to determine a second relation between the application's task volume and memory resources based on the application's second task volume and used memory resources. The device further includes: Establish the association between the first relation between the application's workload and the processor resources and the private cloud industry field data; Establish a relationship between the second relation between the application's workload and the memory resources and the private cloud industry field data.

8. An electronic device, characterized in that, include: One or more processors; and One or more machine-readable media having instructions stored thereon, which, when executed by the one or more processors, cause the electronic device to perform the method as described in any one of claims 1-6.

9. One or more machine-readable media having instructions stored thereon that, when executed by one or more processors, cause the processors to perform the method as described in any one of claims 1-6.

Images