A computing power analysis method and system based on big data
Through big data analysis and automatic computing power expansion mechanism, the problem of difficulty in accurately analyzing computing power in cloud computing is solved, and accurate calculation and prediction of real-time and expected computing power of cloud platform is achieved, which improves the resource utilization efficiency and resistance of cloud platform Shock capability.
Patent Information
- Application Number
- CN202410896069.0
- Authority / Receiving Office
- CN · China
- Patent Type
- Patents(China)
- Current Assignee / Owner
- Filing Date
- 2024-07-05
- Publication Date
- 2024-11-05
- Estimated Expiration
- 2044-07-05
AI Technical Summary
In cloud computing, it is difficult to accurately analyze the real-time computing power of a cloud platform and its expected computing power in the future, especially when the number of virtual machines and resource configurations change in real time.
Using a computing power analysis method based on big data, by obtaining the current computing request and expected computing request of the cloud platform, the resource usage of the virtual machine and computing power sharing pool is calculated, and combined with the computing power automatic expansion mechanism, the virtual machine and computing power are calculated. The expected computing power value of the shared pool is used to accurately analyze the current and expected computing power of the cloud platform.
It realizes accurate prediction and trend analysis of cloud platform computing power requirements, and can automatically adjust the number of virtual machines and resource configuration according to expected calculation requests, improving the cloud platform's resistance to demand shocks.
Smart Images

Figure CN118445031B_ABST
Abstract
Description
Technical Field
[0001] The present application relates to the field of cloud computing, and specifically to a computing power analysis method and system based on big data. Background Art
[0002] In cloud computing, how to accurately calculate the computing power of the cloud platform and reasonably allocate computing power is a crucial core technology. In existing cloud computing, different computing requests are mainly executed by setting up multiple virtual machines on the server. In addition, in order to make the cloud platform have strong resistance to demand shocks, the cloud platform often needs to configure a large number of redundant computing resources. In actual applications, the number of virtual machines, resource configuration, and resource usage in the cloud platform are different and change in real time. Therefore, it is difficult to accurately analyze the real-time computing power of the cloud platform, and it is even more difficult to accurately analyze the expected computing power of the cloud platform in the next period of time. Summary of the invention
[0003] In view of the above problems, the present application provides a computing power analysis method based on big data, which is used to solve the technical problem that the computing power in the above cloud computing is difficult to accurately analyze.
[0004] To achieve the above objectives, the present application provides a computing power analysis method based on big data, comprising the following steps:
[0005] Obtaining the current computing request of the cloud platform, and obtaining the expected computing request of the cloud platform within the next preset time according to big data analysis; the cloud platform includes multiple servers, each of which has multiple virtual machines for executing computing requests, and a computing power sharing pool for sharing the remaining computing power is established between the multiple servers;
[0006] Obtain computing resource usage information of each of the established virtual machines and the computing power sharing pool at the current moment, and respectively calculate a first computing power value of the virtual machine and a second computing power value of the computing power sharing pool according to the computing resource usage information; and calculate, according to the allocation of the current computing request, the first computing power value, and the second computing power value, the completion time of each of the virtual machines and the computing power sharing pool for the allocated computing request, and calculate, according to the completion time, a first expected computing power value to be released by each of the virtual machines within a preset time period;
[0007] According to the expected computing request, the first expected computing power value and the computing power automatic expansion mechanism, calculate the newly created virtual machine for executing the expected computing request and adjust the computing resources allocated to the computing power sharing pool; calculate the second expected computing power value of the computing power sharing pool based on the adjusted computing resources; and calculate the third expected computing power value of the newly added virtual machine based on the number of the newly added virtual machines and the allocated computing resources;
[0008] The current computing power of the cloud platform is calculated based on the first computing power value and the second computing power value, and the expected computing power value of the cloud platform is calculated based on the first expected computing power value, the second expected computing power value and the third expected computing power value.
[0009] In order to solve the above technical problems, this application also provides another technical solution:
[0010] A computing power analysis system based on big data, comprising:
[0011] An acquisition module is used to acquire the current computing request of the cloud platform, and to obtain the expected computing request of the cloud platform within the next preset time according to big data analysis; the cloud platform includes a plurality of servers, each of which has a plurality of virtual machines for executing computing requests, and a computing power sharing pool for sharing the remaining computing power is established between the plurality of servers;
[0012] A first analysis module is used to obtain computing resource usage information of each of the established virtual machines and the computing power sharing pool at the current moment, and calculate a first computing power value of the virtual machine and a second computing power value of the computing power sharing pool according to the computing resource usage information; and calculate a completion time of each of the virtual machines and the computing power sharing pool for the allocated computing request according to the allocation of the current computing request, the first computing power value and the second computing power value, and calculate a first expected computing power value to be released by each of the virtual machines within a preset time period according to the completion time;
[0013] A second analysis module is used to calculate, according to the expected computing request, the first expected computing power value and the computing power automatic expansion mechanism, the newly created virtual machine of the server for executing the expected computing request and the computing resources allocated to the computing power sharing pool; calculate the second expected computing power value of the computing power sharing pool based on the adjusted computing resources; and calculate the third expected computing power value of the newly added virtual machine based on the number of the newly added virtual machines and the allocated computing resources;
[0014] An output module is used to calculate the current computing power of the cloud platform based on the first computing power value and the second computing power value, and to calculate the expected computing power value of the cloud platform based on the first expected computing power value, the second expected computing power value and the third expected computing power value.
[0015] Different from the existing technology, the above technical solution can obtain the current computing request of the cloud platform, and obtain the expected computing request of the cloud platform in the next preset time based on big data analysis; and a computing power sharing pool is set up between servers, which can effectively utilize the remaining computing power to provide emergency computing power support for other servers, and the server is provided with an automatic computing power expansion mechanism, which can automatically increase the number of virtual machines and configure computing resources according to computing needs; the computing power analysis method based on big data can calculate the computing power demand of the cloud platform in the future period according to the expected computing requests, and take into account the impact of the expected computing requests on the computing resource allocation of the computing power sharing pool, as well as the impact of the expected computing requests and the automatic computing power expansion mechanism on the number of virtual machines and computing resource allocation, so as to more accurately calculate the current computing power and expected computing power of the cloud platform and the trend of the expected computing power.
[0016] The above-mentioned records related to the invention content are only an overview of the technical solution of the present application. In order to enable ordinary technicians in the field to more clearly understand the technical solution of the present application, and then implement it according to the text of the specification and the contents recorded in the drawings, and to make the above-mentioned purpose and other purposes, features and advantages of the present application easier to understand, the following is an explanation in combination with the specific implementation mode and drawings of the present application. BRIEF DESCRIPTION OF THE DRAWINGS
[0017] The drawings are only used to illustrate the principles, implementation methods, applications, characteristics and effects of the specific embodiments of the present invention and other related contents, and shall not be considered as limiting the present application.
[0018] In the drawings of the specification:
[0019] Figure 1 It is a flowchart of the computing power analysis method based on big data described in the specific implementation method;
[0020] Figure 2 A topological diagram of the cloud platform described in the specific implementation method;
[0021] Figure 3 A flowchart of analyzing the expected computing request for the specific implementation method;
[0022] Figure 4 A module block diagram of a computing power analysis system based on big data according to a specific implementation method;
[0023] The reference numerals in the above drawings are described as follows:
[0024] 400. Computing power analysis system based on big data; 401. Acquisition module; 402. First analysis module; 403. Second analysis module; 404. Output module; DETAILED DESCRIPTION
[0025] In order to explain in detail the possible application scenarios, technical principles, specific schemes that can be implemented, and the purposes and effects that can be achieved, the following is a detailed description of the specific embodiments listed in conjunction with the accompanying drawings. The embodiments described herein are only used to more clearly illustrate the technical solutions of the present application, and are therefore only used as examples, and cannot be used to limit the scope of protection of the present application.
[0026] Reference to "embodiment" herein means that the specific features, structures or characteristics described in conjunction with the embodiment may be included in at least one embodiment of the present application. The term "embodiment" appearing in various places in the specification does not necessarily refer to the same embodiment, nor does it particularly limit its independence or association with other embodiments. In principle, in the present application, as long as there is no technical contradiction or conflict, the various technical features mentioned in the embodiments can be combined in any way to form a corresponding implementable technical solution.
[0027] Unless otherwise defined, the technical terms used in this document have the same meanings as those generally understood by those skilled in the art to which this application belongs; the use of relevant terms in this document is only for describing specific embodiments and is not intended to limit this application.
[0028] In the description of this application, the term "and / or" is an expression used to describe the logical relationship between objects, indicating that three relationships may exist, for example, A and / or B, which means: A exists, B exists, and A and B exist at the same time. In addition, the character " / " in this article generally indicates that the objects before and after are in an "or" logical relationship.
[0029] In the present application, terms such as “first” and “second” are merely used to distinguish one entity or operation from another entity or operation, and do not necessarily require or imply any actual relationship of quantity, priority or sequence between these entities or operations.
[0030] Without further limitations, in this application, the words "include", "comprises", "has" or other similar open-ended expressions used in sentences are intended to cover non-exclusive inclusion. These expressions do not exclude the presence of additional elements in the process, method or product including the elements, so that the process, method or product including a series of elements may include not only those limited elements, but also other elements not explicitly listed, or also include elements inherent to such process, method or product.
[0031] In this application, expressions such as "greater than", "less than", "exceed" and the like are understood to exclude the number itself; expressions such as "above", "below", "within" and the like are understood to include the number itself. In addition, in the description of the embodiments of this application, "multiple" means more than two (including two), and similar expressions related to "multiple" are also understood in this way, such as "multiple groups", "multiple times", etc., unless otherwise clearly and specifically limited.
[0032] In the description of the embodiments of the present application, space-related expressions used, such as "center", "longitudinal", "lateral", "length", "width", "thickness", "up", "down", "front", "back", "left", "right", "vertical", "horizontal", "vertical", "top", "bottom", "inside", "outside", "clockwise", "counterclockwise", "axial", "radial", "circumferential", etc., indicate the orientation or position relationship based on the orientation or position relationship shown in the specific embodiments or drawings, and are only for the convenience of describing the specific embodiments of the present application or facilitating the reader's understanding, and do not indicate or imply that the referred device or component must have a specific position, a specific orientation, or be constructed or operated in a specific orientation, and therefore cannot be understood as a limitation on the embodiments of the present application.
[0033] Unless otherwise expressly specified or limited, in the description of the embodiments of the present application, the terms such as "install", "connect", "connect", "fix", "set", etc. used should be understood in a broad sense. For example, the "connection" can be a fixed connection, a detachable connection, or an integrated setting; it can be a mechanical connection, an electrical connection, or a communication connection; it can be a direct connection, or it can be indirectly connected through an intermediate medium; it can be the internal connection of two elements or the interaction relationship between two elements. For technicians in the technical field to which the present application belongs, the specific meanings of the above terms in the embodiments of the present application can be understood according to the specific circumstances.
[0034] See also Figures 1 to 4 This embodiment provides a computing power analysis method and system based on big data. The computing power analysis method and system based on big data can be applied to various cloud platforms that provide cloud computing services, and can be used to accurately calculate the real-time computing power and expected computing power of the cloud platform.
[0035] like Figure 1 As shown, in one embodiment, the computing power analysis method based on big data includes the following steps:
[0036] S101, obtaining the current computing request and the expected computing request of the cloud platform;
[0037] S102, calculating the current computing power and expected computing power of the cloud platform, and calculating the current computing power of the computing power sharing pool;
[0038] S103, calculating the expected computing power after adjustment of the computing power sharing pool and the expected computing power of the newly added virtual machines after automatic expansion;
[0039] S104: Output the current computing power and the expected computing power.
[0040] In step S101, the current computing request of the cloud platform is obtained, and the expected computing request of the cloud platform within the next preset time is obtained based on big data analysis. Figure 2 As shown, the cloud platform includes multiple servers, each of which has multiple virtual machines for executing computing requests, and a computing power sharing pool for sharing remaining computing power is established between the multiple servers.
[0041] Among them, multiple servers can be set in the same physical location and connected through a local area network, or multiple servers can be distributed in different physical locations and connected to each other through the Internet. The server includes hardware computing resources required for computing, such as processors, GPUs, memory, and hard disks. The server also includes software resources such as operating systems for assisting in the execution of calculations. Each virtual machine in the server is a unit for executing computing requests. More than one virtual machine can be set on a server, and each virtual machine is allocated computing resources such as CPU resources, memory capacity, and storage capacity. Each virtual machine is also provided with applications and computing models. Resource isolation can be achieved through virtual machines to avoid resource conflicts and interference between different virtual machines. In addition, the virtual machine isolates the operating system and application from the underlying physical hardware, so that the application can run on different hardware platforms, improving the portability and compatibility of the application.
[0042] And in step S101, the computing power in the computing power sharing pool changes dynamically according to the remaining computing resources of each server. The more remaining computing resources a server has, the more computing resources it can provide to the computing power sharing pool, and the more computing power the computing power sharing pool can support. The server can use first-in-first-out (FIFO), shortest job first (SJF), highest priority (HPF), etc. to allocate a reasonable part of the remaining computing resources to the computing power sharing pool. When the ratio of the allocated computing resources to the total computing resources of the server is greater than a preset threshold, the server no longer allocates computing resources to the computing power sharing pool. For example, when the allocated computing resources in the server account for 80% of the total computing resources of the server, considering the need for new virtual machines or the smooth operation of the server, the server will no longer allocate computing resources to the computing power sharing pool.
[0043] In step S102, the computing resource usage information of each established virtual machine and computing power sharing pool at the current moment is obtained, and the first computing power value of the virtual machine and the second computing power value of the computing power sharing pool are calculated respectively according to the computing resource usage information; and according to the allocation of the current computing request, the first computing power value and the second computing power value, the completion time of each virtual machine and the computing power sharing pool for the allocated computing request is calculated, and the first expected computing power value to be released by each virtual machine within a preset time period is calculated according to the completion time. In step S102, the number of established virtual machines and the computing resource usage information of the virtual machines can be obtained through the management tool or interface of the service provider. Similarly, the computing resource usage information of the computing power sharing pool can also be obtained through the management tool or interface. After the computing resource usage information is obtained, the current computing power and expected computing power of the cloud platform can be calculated, and the current computing power of the computing power sharing pool can be calculated. Taking the current computing power as an example, the computing power of each virtual machine in the server is calculated based on its computing resources (for example, the number of CPU cores, memory capacity, etc.), and the current computing power currently available on the server is obtained by multiplying the number of currently available virtual machines by the computing power of each virtual machine; the current computing power of each server is aggregated to obtain the current computing power of the cloud platform. Similarly, based on the computing resources that the virtual machine will release within a preset time, the expected computing power of each virtual machine, i.e., the first expected computing power value, can be calculated.
[0044] In step S103, based on the expected computing request, the first expected computing power value and the automatic computing power expansion mechanism, the newly created virtual machine of the server for executing the expected computing request and the computing resources allocated to the computing power sharing pool are calculated; the second expected computing power value of the computing power sharing pool is calculated based on the adjusted computing resources; and the third expected computing power value of the newly added virtual machines is calculated based on the number of the newly added virtual machines and the allocated computing resources.
[0045] In step S103, according to the automatic expansion mechanism of computing power, the number of virtual machine instances can be automatically increased or decreased according to the expected computing requests and the first expected computing power value to adapt to the load changes of the application. For example, a video streaming service needs to adjust computing power according to changes in user access. Administrators can set up automatic expansion groups to trigger automatic expansion or contraction based on load levels or specific indicators (such as CPU utilization, network traffic). When the load increases (that is, the expected computing requests are large), the automatic expansion group will automatically create new virtual machine instances; when the load decreases, it will automatically stop some virtual machine instances to save resources.
[0046] In step S104, the current computing power of the cloud platform is calculated based on the first computing power value and the second computing power value, and the expected computing power value of the cloud platform is calculated based on the first expected computing power value, the second expected computing power value and the third expected computing power value.
[0047] In this embodiment, when the computing power required by the computing request allocated by the server reaches the safety ratio of the first computing power value, the server calls computing resources from the computing power sharing pool according to the signed computing power sharing smart contract.
[0048] In this embodiment, the cloud platform is provided with a computing power sharing pool and a computing power automatic expansion mechanism, which can effectively utilize the remaining computing power to provide emergency computing power support for other servers, and automatically increase the number of virtual machines and configure computing resources according to computing needs, so that it can adapt well to load changes. In addition, this embodiment can calculate the computing power requirements of the cloud platform in the future period of time according to the expected computing requests, and take into account the impact of the expected computing requests on the computing resource allocation of the computing power sharing pool, as well as the impact of the expected computing requests and the computing power automatic expansion mechanism on the number of virtual machines and computing resource allocation, so as to more accurately calculate the current computing power and expected computing power of the cloud platform and the trend of the expected computing power.
[0049] In the above embodiment, the method of calculating the newly created virtual machine for executing the expected computing request and adjusting the computing resources allocated to the computing power sharing pool according to the expected computing request, the first expected computing power value and the computing power automatic expansion mechanism includes the steps of:
[0050] Allocating the expected computing request to two or more servers according to an allocation mechanism;
[0051] The server calculates the computing power required to execute the allocated computing request, and generates the number of newly added virtual machines and the allocated computing resources according to the difference between the required computing power and the first expected computing power value, wherein the number of newly added virtual machines is proportional to the difference;
[0052] The server calculates the allocated computing resources occupied by the established virtual machines and the newly added virtual machines, and adjusts the computing resources allocated to the computing power sharing pool by each server according to the ratio of the allocated computing resources to the total computing resources of the server, and the computing resources reallocated to the computing power sharing pool are inversely proportional to the ratio.
[0053] like Figure 3 As shown, in one embodiment, obtaining the expected computing request of the cloud platform within the next preset time according to big data analysis includes the steps of:
[0054] S201. Collect computing resource usage data from the monitoring data of the cloud platform over a period of time; these data may include the start and stop time of the virtual machine instance, CPU utilization, memory usage, network traffic, etc. For example, a monitoring tool or a custom script may be used to regularly collect resource usage data of the virtual machine instances on the cloud platform.
[0055] S202: Clean and process the collected computing resource usage data, remove duplicate data, fill missing values, and process abnormal values. For example, for CPU utilization data, missing values can be filled by the average, median, or other statistical methods; for abnormal values, anomaly detection algorithms can be used to identify and process them.
[0056] S203, extracting features related to the expected computing request from the cleaned and processed computing resource usage data; these features may include time-related features (such as hours, days of the week), historical resource usage, holidays or promotional activities, etc. Illustratively, features such as average CPU utilization per hour and maximum memory usage may be extracted from historical data.
[0057] S204, establishing an ARIMA model and using the processed standard sample data for training and optimization; wherein the ARIMA model is a type of sequence model, and in other embodiments, a regression model (such as linear regression, decision tree) or a machine learning model (such as neural network, random forest) may also be used.
[0058] S205: Use the ARIMA model to predict the expected computing requests of the cloud platform within the next preset time. For example, based on historical data and the trained model, the average CPU utilization rate of each day in the next week can be predicted, and the computing power allocation of the cloud platform can be adjusted according to the prediction results.
[0059] like Figure 4 As shown, in one embodiment, a computing power analysis system 400 based on big data is provided. The computing power analysis system 400 based on big data includes: an acquisition module 401, a first analysis module 402, a second analysis module 403 and an output module 404.
[0060] The acquisition module 401 is used to obtain the current computing request of the cloud platform, and to obtain the expected computing request of the cloud platform within the next preset time based on big data analysis; the cloud platform includes multiple servers, each of which has multiple virtual machines for executing computing requests, and a computing power sharing pool for sharing the remaining computing power is established between the multiple servers.
[0061] The first analysis module 402 is used to obtain the computing resource usage information of each of the established virtual machines and the computing power sharing pool at the current moment, and calculate the first computing power value of the virtual machine and the second computing power value of the computing power sharing pool respectively according to the computing resource usage information; and calculate the completion time of each of the virtual machines and the computing power sharing pool for the allocated computing request according to the allocation of the current computing request, the first computing power value and the second computing power value, and calculate the first expected computing power value to be released by each of the virtual machines within a preset time period according to the completion time;
[0062] The second analysis module 403 is used to calculate the newly created virtual machine for executing the expected computing request and adjust the computing resources allocated to the computing power sharing pool according to the expected computing request, the first expected computing power value and the computing power automatic expansion mechanism; calculate the second expected computing power value of the computing power sharing pool based on the adjusted computing resources; and calculate the third expected computing power value of the newly added virtual machine based on the number of the newly added virtual machines and the allocated computing resources;
[0063] The output module 404 is used to calculate the current computing power of the cloud platform based on the first computing power value and the second computing power value, and to calculate the expected computing power value of the cloud platform based on the first expected computing power value, the second expected computing power value and the third expected computing power value.
[0064] In the above embodiment, the method of calculating the newly created virtual machine for executing the expected computing request and adjusting the computing resources allocated to the computing power sharing pool according to the expected computing request, the first expected computing power value and the computing power automatic expansion mechanism includes the steps of:
[0065] Allocating the expected computing request to two or more servers according to an allocation mechanism;
[0066] The server calculates the computing power required to execute the allocated computing request, and generates the number of newly added virtual machines and the allocated computing resources according to the difference between the required computing power and the first expected computing power value, wherein the number of newly added virtual machines is proportional to the difference;
[0067] The server calculates the allocated computing resources occupied by the established virtual machines and the newly added virtual machines, and adjusts the computing resources allocated to the computing power sharing pool by each server according to the ratio of the allocated computing resources to the total computing resources of the server, and the computing resources reallocated to the computing power sharing pool are inversely proportional to the ratio.
[0068] And in the above embodiment, the expected computing requests of the cloud platform within the next preset time are obtained based on big data analysis, including the steps of: collecting computing resource usage data in the past period of time from the monitoring data of the cloud platform; cleaning and processing the collected computing resource usage data, removing duplicate data, filling missing values and processing outliers; extracting features related to the expected computing requests from the cleaned and processed computing resource usage data; establishing an ARIMA model and using the processed standard sample data for training and optimization; using the ARIMA model to predict the expected computing requests of the cloud platform within the next preset time.
[0069] Furthermore, in the above embodiment, when the ratio of the allocated computing resources to the total computing resources of the server is greater than a preset threshold, the server no longer allocates computing resources to the computing power sharing pool.
[0070] In the above-mentioned embodiment of the computing power analysis system based on big data, the explanation and description of each feature, as well as the explanation and description of the working principle and effect of the entire solution all follow the relevant description in the embodiment of the computing power analysis method based on big data, and will not be repeated here.
[0071] Finally, it should be noted that although the above embodiments have been described in the specification and drawings of this application, this does not limit the scope of patent protection of this application. All technical solutions generated by replacing or modifying equivalent structures or equivalent processes based on the essential concept of this application using the contents recorded in the specification and drawings of this application, as well as directly or indirectly implementing the technical solutions of the above embodiments in other related technical fields, are included in the scope of patent protection of this application.
Claims
1. A computing power analysis method based on big data, It is characterized in that The following steps are involved: Obtaining the current computing request of the cloud platform, and obtaining the expected computing request of the cloud platform within the next preset time according to big data analysis; the cloud platform includes multiple servers, each of which has multiple virtual machines for executing computing requests, and a computing power sharing pool for sharing the remaining computing power is established between the multiple servers; Obtain computing resource usage information of each of the established virtual machines and the computing power sharing pool at the current moment, and respectively calculate a first computing power value of the virtual machine and a second computing power value of the computing power sharing pool according to the computing resource usage information; and calculate, according to the allocation of the current computing request, the first computing power value, and the second computing power value, the completion time of each of the virtual machines and the computing power sharing pool for the allocated computing request, and calculate, according to the completion time, a first expected computing power value to be released by each of the virtual machines within a preset time period; According to the expected computing request, the first expected computing power value and the computing power automatic expansion mechanism, calculate the newly created virtual machine for executing the expected computing request and adjust the computing resources allocated to the computing power sharing pool; calculate the second expected computing power value of the computing power sharing pool based on the adjusted computing resources; and calculate the third expected computing power value of the newly added virtual machine based on the number of the newly added virtual machines and the allocated computing resources; The current computing power of the cloud platform is calculated based on the first computing power value and the second computing power value, and the expected computing power value of the cloud platform is calculated based on the first expected computing power value, the second expected computing power value, and the third expected computing power value; The method of calculating, according to the expected computing request, the first expected computing power value, and the computing power automatic expansion mechanism, a newly created virtual machine for executing the expected computing request by the server and adjusting the computing resources allocated to the computing power sharing pool comprises the following steps: Allocating the expected computing request to two or more servers according to an allocation mechanism; The server calculates the computing power required to execute the allocated computing request, and generates the number of newly added virtual machines and the allocated computing resources according to the difference between the required computing power and the first expected computing power value, wherein the number of newly added virtual machines is proportional to the difference; The server calculates the allocated computing resources occupied by the established virtual machines and the newly added virtual machines, and adjusts the computing resources allocated to the computing power sharing pool by each server according to the ratio of the allocated computing resources to the total computing resources of the server, and the computing resources reallocated to the computing power sharing pool are inversely proportional to the ratio.
2. According to the computing power analysis method based on big data according to claim 1, It is characterized in that The step of obtaining the expected computing request of the cloud platform within the next preset time according to the big data analysis includes the following steps: Collect computing resource usage data from the cloud platform's monitoring data over a period of time; Clean and process the collected computing resource usage data to remove duplicate data, fill in missing values, and handle outliers; extracting features related to expected computing requests from the cleaned and processed computing resource usage data; Establish an ARIMA model and use the processed standard sample data for training and optimization; The ARIMA model is used to predict the expected computing requests of the cloud platform within the next preset time.
3. According to the computing power analysis method based on big data according to claim 1, It is characterized in that When the ratio of the allocated computing resources to the total computing resources of the server is greater than a preset threshold, the server no longer allocates computing resources to the computing power sharing pool.
4. According to the big data-based computing power analysis method of claim 1, It is characterized in that When the computing power required by the computing request allocated by the server reaches the safety ratio of the first computing power value, the server calls computing resources from the computing power sharing pool according to the signed computing power sharing smart contract.
5. A computing power analysis system based on big data, It is characterized in that include: An acquisition module is used to acquire the current computing request of the cloud platform, and to obtain the expected computing request of the cloud platform within the next preset time according to big data analysis; the cloud platform includes a plurality of servers, each of which has a plurality of virtual machines for executing computing requests, and a computing power sharing pool for sharing the remaining computing power is established between the plurality of servers; A first analysis module is used to obtain computing resource usage information of each of the established virtual machines and the computing power sharing pool at the current moment, and calculate a first computing power value of the virtual machine and a second computing power value of the computing power sharing pool according to the computing resource usage information; and calculate a completion time of each of the virtual machines and the computing power sharing pool for the allocated computing request according to the allocation of the current computing request, the first computing power value and the second computing power value, and calculate a first expected computing power value to be released by each of the virtual machines within a preset time period according to the completion time; A second analysis module is used to calculate, according to the expected computing request, the first expected computing power value and the computing power automatic expansion mechanism, the newly created virtual machine of the server for executing the expected computing request and the computing resources allocated to the computing power sharing pool; calculate the second expected computing power value of the computing power sharing pool based on the adjusted computing resources; and calculate the third expected computing power value of the newly added virtual machine based on the number of the newly added virtual machines and the allocated computing resources; an output module, configured to calculate the current computing power of the cloud platform based on the first computing power value and the second computing power value, and to calculate the expected computing power value of the cloud platform based on the first expected computing power value, the second expected computing power value, and the third expected computing power value; The method of calculating, according to the expected computing request, the first expected computing power value, and the computing power automatic expansion mechanism, a newly created virtual machine for executing the expected computing request by the server and adjusting the computing resources allocated to the computing power sharing pool comprises the following steps: Allocating the expected computing request to two or more servers according to an allocation mechanism; The server calculates the computing power required to execute the allocated computing request, and generates the number of newly added virtual machines and the allocated computing resources according to the difference between the required computing power and the first expected computing power value, wherein the number of newly added virtual machines is proportional to the difference; The server calculates the allocated computing resources occupied by the established virtual machines and the newly added virtual machines, and adjusts the computing resources allocated to the computing power sharing pool by each server according to the ratio of the allocated computing resources to the total computing resources of the server, and the computing resources reallocated to the computing power sharing pool are inversely proportional to the ratio.
6. According to the big data-based computing power analysis system of claim 5, It is characterized in that The step of obtaining the expected computing request of the cloud platform within the next preset time according to the big data analysis includes the following steps: Collect computing resource usage data from the cloud platform's monitoring data over a period of time; Clean and process the collected computing resource usage data to remove duplicate data, fill in missing values, and handle outliers; extracting features related to expected computing requests from the cleaned and processed computing resource usage data; Establish an ARIMA model and use the processed standard sample data for training and optimization; The ARIMA model is used to predict the expected computing requests of the cloud platform within the next preset time.
7. The computing power analysis system based on big data according to claim 5, It is characterized in that When the ratio of the allocated computing resources to the total computing resources of the server is greater than a preset threshold, the server no longer allocates computing resources to the computing power sharing pool.
Citation Information
Patent Citations
Techniques to dynamically allocate resources for local service chains of configurable computing resources
CN107003905A
Research and development resource cloud platform and resource sharing method
CN110138855A
Dynamic sharing and intelligent distribution method for cloud manufacturing resources for intelligent manufacturing
CN111812982A
Computing power matching method and device and management platform
CN114880106A
Virtual-machine dynamic allocation system and server
US20170155721A1
