Mobile phone cloud computing power lease scheduling method for virtual computer

Abstract

The invention discloses a mobile phone cloud computing power lease scheduling method for a virtual computer, and relates to the technical field of resource scheduling, and the method comprises the steps: based on the historical load data of construction hardware of all cloud computing power lines, analyzing the performance change trend of the historical load data of the construction hardware, and evaluating the dynamic load index of each cloud computing power line; acquiring historical cloud computing power user lease data, analyzing the computing power overhead demand of the user lease data, and constructing a user computing power lease preference portrait; for regression analysis, predicting a to-be-executed lease task demand of a unit time node; and according to the dynamic load index of each cloud computing power line and the to-be-executed lease task demand of the unit time node, constructing a cloud computing power resource scheduling model to maximize the utilization of the computing power resources of the cloud computing power lines, and generating a dynamic cloud computing power lease scheduling task. The method has the advantages that the user experience and the resource utilization rate are improved.

Description

Technical Field

[0001] The present invention relates to the technical field of resource scheduling, and in particular to a mobile phone cloud computing power leasing scheduling method for a virtual computer. Background Art

[0002] Mobile cloud computing power leasing and scheduling of virtual computers refers to the process of renting mobile cloud computing power as resources to users in need through virtualization technology in a cloud computing environment, and dynamically allocating and managing these computing resources based on the actual needs of users, the availability of cloud computing resources, and scheduling strategies.

[0003] The existing virtual computer mobile cloud computing power rental scheduling is relatively complete in scheduling and allocating user task requirements when the line status is good. However, since user needs are usually more concentrated, the actual resource scheduling cannot meet user task requirements. When the cloud computing power line is congested, it is very easy for users to go offline to perform tasks. Summary of the invention

[0004] In order to solve the above technical problems, a mobile phone cloud computing power leasing and scheduling method for virtual computers is provided. This technical solution solves the problem that when the line status of the above-mentioned existing virtual computer mobile phone cloud computing power leasing and scheduling is good, the scheduling and allocation of user task requirements is relatively complete, but because user needs are usually more concentrated, the actual resource scheduling cannot meet the user task requirements. When the cloud computing power line is congested, it is very easy to cause the user to be offline when performing tasks.

[0005] In order to achieve the above purpose, the technical solution adopted by the present invention is: A mobile phone cloud computing power leasing scheduling method for a virtual computer includes: Based on the historical load data of the hardware of all cloud computing power lines, analyze the performance change trend of the historical load data of the hardware and evaluate the dynamic load indicators of each cloud computing power line; Obtain historical cloud computing power user rental data, analyze the computing power expenditure requirements of user rental data, and build a user computing power rental preference profile; Carry out regression analysis to predict the demand for rental tasks to be executed at a unit time node; According to the dynamic load indicators of each cloud computing power line and the demand for rental tasks to be executed per unit time node, a cloud computing power resource scheduling model is constructed to maximize the utilization of the computing power resources of the cloud computing power line and generate dynamic cloud computing power leasing scheduling tasks.

[0006] Preferably, based on the historical load data of the hardware of all cloud computing power lines, the performance change trend of the historical load data of the hardware is analyzed, and the dynamic load indicators of each cloud computing power line are evaluated, specifically including: Based on the historical load data of the construction hardware of all cloud computing power lines, the data is processed smoothly according to the difference method, and divided by unit time to form the historical load time series data of the construction hardware of all cloud computing power lines; According to the historical load time series data of the hardware of all cloud computing power lines, the basic characteristic data of the historical load of the hardware of each cloud computing power line is marked with the unit time as the observation window and the historical load data of the hardware as the observation variable; the basic characteristic data includes: average load, maximum load value and minimum load value; Using wavelet transform, extract the load cycle characteristic data from the historical load time series data of the hardware of each cloud computing power line; Combine the historical load basic characteristic data of the hardware of each cloud computing power line with the historical load period characteristic data of the hardware of each cloud computing power line into a cloud computing power line load characteristic original data set; Based on ARIMA autoregressive integrated moving average, a cloud computing power line dynamic load prediction model is constructed; Substitute the original data set of cloud computing power line load characteristics into the dynamic load prediction model of computing power lines, take the load characteristic data of each cloud computing power line at a unit time node as input, and take the load label data of each cloud computing power line at a future unit time node as output, and obtain the dynamic load index of each cloud computing power line; The cloud computing power line dynamic load prediction model is specifically as follows: ; In the formula, is the dynamic load index of the t-th unit time node of the k-th cloud computing power circuit, is the kth cloud computing power circuit Load characteristic data of nodes with unit time lag, is a constant term, is the ith lagged autoregressive coefficient, is the jth sliding average coefficient, For the The error term of the sliding average node per unit time, is the error term of the t-th unit time, p is the total number of autoregressive orders, and q is the total number of moving average orders.

[0007] Preferably, obtaining historical cloud computing power user rental data, analyzing the computing power expenditure requirements of user rental data, and building a user computing power rental preference profile specifically includes: Based on the historical cloud computing power user rental data, normalization is performed and the cloud computing power rental action events of the user unit time nodes are marked to construct a cloud computing power rental action event dataset of historical users; PCA principal component analysis is used to reduce the dimension of the cloud computing power rental action event dataset of historical users; According to several dimensions associated with cloud computing power, an initial user computing power leasing preference profile is established; the several dimensions associated with cloud computing power include: computing power leasing time, computing power leasing configuration, computing power request scenario Using the Euclidean distance formula, we calculated the average distance between the historical user's cloud computing power rental action event data set and several dimensions in the initial user's computing power rental preference portrait, and performed initial clustering of the cloud computing power rental action event data; For the initial clustering of cloud computing power leasing action event data, the distance between each cluster and other clusters is used to iteratively merge clusters according to the average connection method to obtain a user computing power leasing preference profile; The user's computing power leasing preference profile is specifically as follows: ; In the formula, For the A user's computing power leasing preference profile, for The initial cluster of cloud computing power leasing action event data and The average distance between the initial clusters of cloud computing power leasing action event data, for The first The cloud computing power leasing action events of historical users and The first The Euclidean distance between the cloud computing power leasing action events of historical users, for and The initial cluster of cloud computing power leasing action event data and The average connection distance between the initial clusters of cloud computing power leasing action event data.

[0008] Preferably, for performing regression analysis, predicting the demand for to-be-executed leasing tasks at a unit time node specifically includes: Based on SVR support vector regression, a user rental task prediction model is constructed; According to the preference values ​​of each associated dimension of the user's computing power leasing preference portrait, linear mapping is performed on the associated dimension preference values ​​to obtain the associated dimension preference feature vector of the user's computing power leasing preference portrait; According to the user leasing task prediction model, the associated dimension preference feature vector of the user computing power leasing preference portrait is used as the feature data input to train the associated dimension preference feature vector to minimize the error of the leasing task demand, determine the optimal hyperplane in the feature space, and predict the demand for the leasing task to be executed at the unit time node as the output; The user rental task prediction model is specifically: ; In the formula, is the first time node of the prediction unit The first user's computing power leasing preference profile leasing tasks to be performed, is the positive space constraint Lagrange multiplier corresponding to the V-th dimension preference eigenvector, is the negative space constraint Lagrange multiplier corresponding to the V-th dimension preference eigenvector, For the The Vth dimension preference feature vector of the user's computing power leasing preference portrait, is the kernel function and b is the bias.

[0009] Preferably, according to the dynamic load index of each cloud computing power line and the demand for the to-be-executed leasing task per unit time node, a cloud computing power resource scheduling model is constructed to maximize the use of the computing power resources of the cloud computing power line, and the generation of dynamic cloud computing power leasing scheduling tasks specifically includes: Determine the cloud computing power expenditure corresponding to the requirements of all pending leasing tasks per time node; Based on random forest, we build a decision tree for the executable leasing tasks of each cloud computing line according to the cloud computing resource redundancy corresponding to the dynamic load index of each cloud computing line at a unit time node, and connect them in series to form a cloud computing resource scheduling model. The cloud computing power overhead corresponding to all pending leasing task demands per unit time node is substituted into the cloud computing power resource scheduling model, and the cloud computing power resource redundancy information gain corresponding to the dynamic load index of each pending leasing task demand corresponding to the cloud computing power line is divided into lines with the largest information gain to generate dynamic cloud computing power leasing scheduling tasks.

[0010] Compared with the prior art, the present invention has the following beneficial effects: The present invention proposes a cloud computing power leasing scheduling scheme for mobile phones used in virtual computers. Based on the hardware historical load data of cloud computing power lines and user leasing data, the system uses performance trend analysis and user preference profile construction, and uses time series regression analysis to predict future leasing task requirements, thereby building a cloud computing power resource scheduling model to achieve efficient use of computing power resources and smooth task scheduling. The beneficial effects are: improving user experience and resource utilization. BRIEF DESCRIPTION OF THE DRAWINGS

[0011] Figure 1 It is a flow chart of a method for leasing and scheduling mobile cloud computing power for virtual computers; Figure 2 A flow chart of the method for evaluating the dynamic load indicators of each cloud computing power line; Figure 3 A flowchart for building a user computing power leasing preference profile method; Figure 4 A flow chart of a method for predicting the demand for rental tasks to be executed at a unit time node; Figure 5 A flow chart of the method for generating dynamic cloud computing power leasing scheduling tasks. DETAILED DESCRIPTION

[0012] The following description is used to disclose the present invention so that those skilled in the art can implement the present invention. The preferred embodiments described below are only examples, and those skilled in the art may think of other obvious variations.

[0013] Reference Figure 1 As shown, a method for leasing and scheduling mobile cloud computing power for virtual computers includes: Based on the historical load data of the hardware of all cloud computing power lines, analyze the performance change trend of the historical load data of the hardware and evaluate the dynamic load indicators of each cloud computing power line; Obtain historical cloud computing power user rental data, analyze the computing power expenditure requirements of user rental data, and build a user computing power rental preference profile; Carry out regression analysis to predict the demand for rental tasks to be executed at a unit time node; According to the dynamic load indicators of each cloud computing power line and the demand for rental tasks to be executed per unit time node, a cloud computing power resource scheduling model is constructed to maximize the utilization of the computing power resources of the cloud computing power line and generate dynamic cloud computing power leasing scheduling tasks.

[0014] It should be noted that the mobile cloud computing power leasing of the virtual computer in this solution refers to the local mobile phone leasing the computing power resources of the cloud virtual computer to realize local remote play.

[0015] The implementation principle of this solution is based on the hardware historical load data and user rental data of the cloud computing power line, through performance trend analysis and user preference portrait construction, using time series regression analysis to predict future rental task demand, and then build a cloud computing power resource scheduling model to achieve efficient use of computing power resources and smooth task scheduling. The beneficial effect is: improving user experience and resource utilization.

[0016] Reference Figure 2 As shown in the figure, based on the historical load data of the hardware of all cloud computing power lines, the performance change trend of the historical load data of the hardware is analyzed, and the dynamic load indicators of each cloud computing power line are evaluated, including: Based on the historical load data of the construction hardware of all cloud computing power lines, the data is processed smoothly according to the difference method, and divided by unit time to form the historical load time series data of the construction hardware of all cloud computing power lines; According to the historical load time series data of the hardware of all cloud computing power lines, the basic characteristic data of the historical load of the hardware of each cloud computing power line is marked with the unit time as the observation window and the historical load data of the hardware as the observation variable; the basic characteristic data includes: average load, maximum load value and minimum load value; Using wavelet transform, extract the load cycle characteristic data from the historical load time series data of the hardware of each cloud computing power line; Combine the historical load basic characteristic data of the hardware of each cloud computing power line with the historical load period characteristic data of the hardware of each cloud computing power line into a cloud computing power line load characteristic original data set; Based on ARIMA autoregressive integrated moving average, a cloud computing power line dynamic load prediction model is constructed; Substitute the original data set of cloud computing power line load characteristics into the dynamic load prediction model of computing power lines, take the load characteristic data of each cloud computing power line at a unit time node as input, and take the load label data of each cloud computing power line at a future unit time node as output, and obtain the dynamic load index of each cloud computing power line; The cloud computing power line dynamic load prediction model is specifically as follows: ; In the formula, is the dynamic load index of the t-th unit time node of the k-th cloud computing power circuit, is the kth cloud computing power circuit Load characteristic data of nodes with unit time lag, is a constant term, is the ith lagged autoregressive coefficient, is the jth sliding average coefficient, For the The error term of the sliding average node per unit time, is the error term of the t-th unit time, p is the total number of autoregressive orders, and q is the total number of moving average orders.

[0017] It is understandable that since the cloud computing power of the virtual computer needs to rely on the public network for transfer when connecting to the mobile phone, and it is easy to be disconnected or delayed when the load state of the connection line is high, it will cause a large fluctuation in the number of real-time online game users renting the line, but it has little impact on local stand-alone games. Therefore, by analyzing the dynamic load indicators of each cloud computing power line, it is possible to provide planning objects for subsequent mobile phone cloud computing power lines; Reference Figure 3 As shown in the figure, obtaining historical cloud computing power user rental data, analyzing the computing power expenditure requirements of user rental data, and building a user computing power rental preference profile specifically includes: Based on the historical cloud computing power user rental data, normalization is performed and the cloud computing power rental action events of the user unit time nodes are marked to construct a cloud computing power rental action event dataset of historical users; PCA principal component analysis is used to reduce the dimension of the cloud computing power rental action event dataset of historical users; According to several dimensions associated with cloud computing power, an initial user computing power leasing preference profile is established; the several dimensions associated with cloud computing power include: computing power leasing time, computing power leasing configuration, computing power request scenario Using the Euclidean distance formula, we calculated the average distance between the historical user's cloud computing power rental action event data set and several dimensions in the initial user's computing power rental preference portrait, and performed initial clustering of the cloud computing power rental action event data; For the initial clustering of cloud computing power leasing action event data, the distance between each cluster and other clusters is used to iteratively merge clusters according to the average connection method to obtain a user computing power leasing preference profile; The user's computing power leasing preference profile is specifically as follows: ; In the formula, for The first user's computing power leasing preference profile, for The initial cluster of cloud computing power leasing action event data and The average distance between the initial clusters of cloud computing power leasing action event data, for The first The cloud computing power leasing action events of historical users and The first The Euclidean distance between the cloud computing power leasing action events of historical users, for and The initial cluster of cloud computing power leasing action event data and The average connection distance between the initial clusters of cloud computing power leasing action event data.

[0018] It is understandable that the purpose of clustering analysis based on historical cloud computing power user rental data and constructing a user computing power rental preference portrait is to seek user behavior habits for subsequent line screening and matching. For example: based on the analysis of historical cloud computing power user rental data, the user attributes are as follows: 1. User groups with high computing power and high latency sensitivity, 2. User groups with low computing power and low latency sensitivity, 3. Users with medium computing power requirements but low latency requirements, and the corresponding labels are: competitive players, light online game players, and stand-alone strategy players.

[0019] Reference Figure 4 As shown, for regression analysis, the forecast of the rental task demand to be executed per unit time node specifically includes: Based on SVR support vector regression, a user rental task prediction model is constructed; According to the preference values ​​of each associated dimension of the user's computing power leasing preference portrait, linear mapping is performed on the associated dimension preference values ​​to obtain the associated dimension preference feature vector of the user's computing power leasing preference portrait; According to the user leasing task prediction model, the associated dimension preference feature vector of the user computing power leasing preference portrait is used as the feature data input to train the associated dimension preference feature vector to minimize the error of the leasing task demand, determine the optimal hyperplane in the feature space, and predict the demand for the leasing task to be executed at the unit time node as the output; The user rental task prediction model is specifically: ; In the formula, is the first time node of the prediction unit The first user's computing power leasing preference profile leasing tasks to be performed, is the positive space constraint Lagrange multiplier corresponding to the V-th dimension preference eigenvector, is the negative space constraint Lagrange multiplier corresponding to the V-th dimension preference eigenvector, For the The Vth dimension preference feature vector of the user's computing power leasing preference portrait, is the kernel function and b is the bias.

[0020] It is understandable that by using the SVR support vector regression technology, combined with the associated dimension preference feature vector of the user's computing power leasing preference portrait, the optimal hyperplane in the feature space is determined by minimizing the prediction error through the training model, so as to accurately predict the demand for leasing tasks to be executed at a unit time node. Its beneficial effect is that it can improve the accuracy of the prediction and provide decision support for the reasonable scheduling and resource allocation of leasing tasks.

[0021] Reference Figure 5 As shown in the figure, according to the dynamic load indicators of each cloud computing power line and the requirements of the rental tasks to be executed per unit time node, a cloud computing power resource scheduling model is constructed to maximize the use of the computing power resources of the cloud computing power line. The dynamic cloud computing power rental scheduling tasks generated specifically include: Determine the cloud computing power expenditure corresponding to the requirements of all pending leasing tasks per time node; Based on random forest, we build a decision tree for the executable leasing tasks of each cloud computing line according to the cloud computing resource redundancy corresponding to the dynamic load index of each cloud computing line at a unit time node, and connect them in series to form a cloud computing resource scheduling model. The cloud computing power overhead corresponding to all pending leasing task demands per unit time node is substituted into the cloud computing power resource scheduling model, and the cloud computing power resource redundancy information gain corresponding to the dynamic load index of each pending leasing task demand corresponding to the cloud computing power line is divided into lines with the largest information gain to generate dynamic cloud computing power leasing scheduling tasks.

[0022] The above shows and describes the basic principles, main features and advantages of the present invention. Those skilled in the art should understand that the present invention is not limited to the above embodiments. The above embodiments and descriptions only describe the principles of the present invention. The present invention may be subject to various changes and improvements without departing from the spirit and scope of the present invention. These changes and improvements fall within the scope of the present invention. The scope of protection claimed by the present invention is defined by the attached claims and their equivalents.

Claims

1. A method for leasing and scheduling mobile cloud computing power for virtual computers, characterized in that: include: Based on the historical load data of the hardware of all cloud computing power lines, analyze the performance change trend of the historical load data of the hardware and evaluate the dynamic load indicators of each cloud computing power line; Obtain historical cloud computing power user rental data, analyze the computing power expenditure requirements of user rental data, and build a user computing power rental preference profile; Carry out regression analysis to predict the demand for rental tasks to be executed at a unit time node; According to the dynamic load indicators of each cloud computing power line and the demand for rental tasks to be executed per unit time node, a cloud computing power resource scheduling model is constructed to maximize the utilization of the computing power resources of the cloud computing power line and generate dynamic cloud computing power leasing scheduling tasks.

2. According to the method for scheduling mobile phone cloud computing power leasing for virtual computers in claim 1, it is characterized in that: Based on the historical load data of the hardware of all cloud computing lines, the performance change trend of the historical load data of the hardware is analyzed, and the dynamic load indicators of each cloud computing line are evaluated, including: Based on the historical load data of the construction hardware of all cloud computing power lines, the data is processed smoothly according to the difference method, and divided by unit time to form the historical load time series data of the construction hardware of all cloud computing power lines; According to the historical load time series data of the hardware of all cloud computing power lines, the basic characteristic data of the historical load of the hardware of each cloud computing power line is marked with the unit time as the observation window and the historical load data of the hardware as the observation variable; the basic characteristic data includes: average load, maximum load value and minimum load value; Using wavelet transform, extract the load cycle characteristic data from the historical load time series data of the hardware of each cloud computing power line; Combine the historical load basic characteristic data of the hardware of each cloud computing power line with the historical load period characteristic data of the hardware of each cloud computing power line into a cloud computing power line load characteristic original data set; Based on ARIMA autoregressive integrated moving average, a cloud computing power line dynamic load prediction model is constructed; The original data set of cloud computing power line load characteristics is substituted into the dynamic load prediction model of the computing power line. The load characteristic data of each cloud computing power line at a unit time node is used as input, and the load label data of each cloud computing power line at a future unit time node is used as output to obtain the dynamic load index of each cloud computing power line.

3. A method for leasing and scheduling mobile cloud computing power for virtual computers according to claim 2, characterized in that: The cloud computing power line dynamic load prediction model is specifically as follows: ； In the formula, is the dynamic load index of the t-th unit time node of the k-th cloud computing power circuit, is the kth cloud computing power circuit Load characteristic data of nodes with unit time lag, is a constant term, is the ith lagged autoregressive coefficient, For the The sliding average coefficient, For the The error term of the sliding average node per unit time, For the The error term per unit time, p is the total number of autoregressive orders, and q is the total number of sliding average orders.

4. A method for leasing and scheduling mobile cloud computing power for virtual computers according to claim 3, characterized in that: Obtain historical cloud computing power user rental data, analyze the computing power expenditure requirements of user rental data, and build a user computing power rental preference profile, including: Based on the historical cloud computing power user rental data, normalization is performed and the cloud computing power rental action events of the user unit time nodes are marked to construct a cloud computing power rental action event dataset of historical users; PCA principal component analysis is used to reduce the dimension of the cloud computing power rental action event dataset of historical users; According to several dimensions associated with cloud computing power, an initial user computing power leasing preference profile is established; the several dimensions associated with cloud computing power include: computing power leasing time, computing power leasing configuration, computing power request scenario Using the Euclidean distance formula, we calculated the average distance between the historical user's cloud computing power rental action event data set and several dimensions in the initial user's computing power rental preference portrait, and performed initial clustering of the cloud computing power rental action event data; For the initial clustering of cloud computing power leasing action event data, the distance between each cluster and other clusters is used to iteratively merge clusters according to the average connection method to obtain a profile of user computing power leasing preferences.

5. A method for leasing and scheduling mobile cloud computing power for virtual computers according to claim 4, characterized in that: The user computing power leasing preference profile is specifically as follows: ； In the formula, For the A user's computing power leasing preference profile, for The initial cluster of cloud computing power leasing action event data and The average distance between the initial clusters of cloud computing power leasing action event data, for The first in the initial cluster of cloud computing power leasing action event data The cloud computing power leasing action events of historical users and The first The Euclidean distance between the cloud computing power leasing action events of historical users, for and The initial cluster of cloud computing power leasing action event data and The average connection distance between the initial clusters of cloud computing power leasing action event data.

6. A method for leasing and scheduling mobile cloud computing power for virtual computers according to claim 5, characterized in that: For regression analysis, the forecast of the rental task demand to be executed per unit time node specifically includes: Based on SVR support vector regression, a user rental task prediction model is constructed; According to the preference values ​​of each associated dimension of the user's computing power leasing preference portrait, linear mapping is performed on the associated dimension preference values ​​to obtain the associated dimension preference feature vector of the user's computing power leasing preference portrait; According to the user rental task prediction model, the associated dimension preference feature vector of the user's computing power rental preference portrait is used as the feature data input to train the associated dimension preference feature vector to minimize the error of the rental task demand, determine the optimal hyperplane in the feature space, and predict the demand for to-be-executed rental tasks at a unit time node as the output.

7. A method for leasing and scheduling mobile cloud computing power for virtual computers according to claim 6, characterized in that: The user rental task prediction model is specifically: ； In the formula, is the first time node of the prediction unit The first user's computing power leasing preference profile leasing tasks to be performed, For the The positive-interval-constrained Lagrange multiplier corresponding to the dimensional preference eigenvector, For the The negative space constraint Lagrange multiplier corresponding to the dimensional preference eigenvector, For the The first user's computing power leasing preference profile dimensional preference feature vector, is the kernel function, For bias.

8. A method for leasing and scheduling mobile cloud computing power for virtual computers according to claim 7, characterized in that: According to the dynamic load indicators of each cloud computing power line and the requirements of the rental tasks to be executed per unit time node, a cloud computing power resource scheduling model is constructed to maximize the use of the computing power resources of the cloud computing power line. The dynamic cloud computing power rental scheduling tasks are generated, including: Determine the cloud computing power expenditure corresponding to the requirements of all pending leasing tasks per time node; Based on random forest, a decision tree for executing leasing tasks on each cloud computing line is constructed according to the cloud computing resource redundancy corresponding to the dynamic load index of each cloud computing line at a unit time node, and the decision trees are connected in series to form a cloud computing resource scheduling model. The cloud computing power overhead corresponding to all pending leasing task demands per unit time node is substituted into the cloud computing power resource scheduling model, and the cloud computing power resource redundancy information gain corresponding to the dynamic load index of each pending leasing task demand corresponding to the cloud computing power line is divided into lines with the largest information gain to generate dynamic cloud computing power leasing scheduling tasks.

Images