A cloud desktop scheduling method and system

Abstract

This invention application relates to the technical field of cloud desktop management, and specifically discloses a cloud desktop scheduling method and system. The method includes: collecting user behavior data, the actual usage of various resources, and system performance data; processing the user behavior data to obtain the viscosity of cloud desktop users, and processing the system performance data to obtain the cloud desktop system performance evaluation index. Combining the actual usage of various resources, comprehensively analyze to obtain the predicted usage of various resources at each time node; according to the predicted usage of various resources and the actual usage of various resources at each historical time node, comprehensively analyze to obtain the resource usage prediction accuracy index; evaluate the resource usage prediction result according to the resource usage prediction accuracy index. By evaluating the predicted usage at future time nodes, this invention application not only helps to improve the stability and security of the system, but also can optimize resource usage, enhance the user experience, and bring higher operational efficiency to enterprises.

Description

Technical Field

[0001] The present invention application relates to the technical field of cloud desktop management, and specifically provides a cloud desktop scheduling method and system. Background Art

[0002] Cloud desktop scheduling is a very important part in the field of cloud computing. With the development of artificial intelligence technology and cloud computing technology, providing more user-friendly cloud desktop services has become the norm. An efficient and user-friendly cloud desktop scheduling method is of great significance for improving user experience and enhancing market competitiveness.

[0003] For example, the invention patent with the publication number CN108769233B is a method for optimizing resource allocation based on desktop cloud, including the following steps: S1: Construct a laboratory resource optimization model based on the professional teaching desktop cloud D starting from professional teaching, the teacher T defined by the scope of the courses taught, and the student S who completes the semester course objectives; calculate the ideal number of desktop clouds, recalculate the minimum number of desktop clouds according to the limit of the number of professional teachers, and according to the determined number of desktop clouds D, try to fill up the physical laboratories with experimental teaching arrangements as much as possible.

[0004] For example, the invention patent with the publication number CN104253865B is a two-level management method for a hybrid desktop cloud service platform, including the following steps: Construct a hybrid desktop cloud data center; the server node sends a registration request to the central management node (Vmm-Server); the central management node receives and processes the registration request of the server node; the central management node uniformly receives user requests through the service interface layer; the central management node responds to user requests according to a two-level scheduling method; the central management node adopts a two-level migration method to maintain system load balance according to the current system state and the running state of virtual machines.

[0005] However, in the process of implementing the technical solution of the present invention in the embodiments of the present application, it is found that the above technologies have at least the following technical problems: Currently, cloud desktop scheduling methods pay more attention to improving resource utilization rate, but there may still be uneven distribution of resources during peak periods, and the personalized needs of users cannot be fully met. Summary of the Invention

[0006] In view of the deficiencies of the prior art, the present invention application provides a cloud desktop scheduling method and system, which can effectively solve the problems involved in the above background art.

[0007] To achieve the above object, the present invention application is realized through the following technical solutions: The first aspect of the present invention application provides a cloud desktop scheduling method, including: collecting user behavior data, the actual usage amounts of various resources, and system performance data.

[0008] Process user behavior data to obtain the viscosity of cloud desktop users, process system performance data to obtain the cloud desktop system performance evaluation index, and combine the actual usage amounts of various resources to comprehensively analyze and obtain the predicted usage amounts of various resources at each time node.

[0009] Perform time node division according to the current time node to obtain each historical time node and each future time node, and comprehensively analyze based on the predicted usage amounts and actual usage amounts of various resources at each historical time node to obtain the resource usage prediction accuracy index.

[0010] Evaluate the resource usage prediction results according to the resource usage prediction accuracy index. If the evaluation result is qualified, perform cloud desktop resource scheduling according to the predicted usage amounts of various resources at each future time node. If the evaluation result is unqualified, re-predict the resource usage amounts.

[0011] As a further method, the process of processing user behavior data to obtain the viscosity of cloud desktop users is as follows: The user behavior data includes the cumulative login times, cumulative login duration, and the number of users.

[0012] Extract from the cloud desktop database the impact factors for evaluating the viscosity of cloud desktop users corresponding to the preset cumulative login times and the impact factors for evaluating the viscosity of cloud desktop users corresponding to the cumulative login duration.

[0013] Comprehensively analyze based on the cumulative login times and cumulative login duration of each user at each time node in each monitoring period to obtain the viscosity of cloud desktop users at each time node in each monitoring period.

[0014] As a further method, the process of processing system performance data to obtain the cloud desktop system performance evaluation index is as follows: The system performance data includes the system response time and system throughput.

[0015] Extract from the cloud desktop database the impact factors for evaluating the cloud desktop system performance corresponding to the preset system response time and the impact factors for evaluating the cloud desktop system performance corresponding to the preset system throughput.

[0016] Comprehensively analyze based on the system response time and system throughput at each time node in each monitoring period to obtain the cloud desktop system performance evaluation index.

[0017] As a further method, the specific analysis process for comprehensively analyzing and obtaining the predicted usage amounts of various resources at each time node is as follows: Extract from the cloud desktop database the impact factors for evaluating the predicted usage amounts corresponding to the preset viscosity of cloud desktop users, the cloud desktop system performance evaluation index, and the actual usage amounts of various resources.

[0018] Based on the user viscosity, system performance evaluation index, and the actual usage of various resources, the predicted usage of various resources at each time node is obtained through comprehensive analysis.

[0019] As a further method, the resource usage prediction accuracy index is a quantitative indicator obtained by comparing and analyzing the predicted usage and actual usage of each resource at each time node, and is used to quantify the accuracy of resource usage prediction.

[0020] As a further method, the cloud desktop system performance evaluation index is a quantitative indicator obtained by analyzing the system response time and system throughput at each time node in each monitoring period, and is used to quantify the performance of the cloud desktop system.

[0021] As a further method, the evaluation of the cloud desktop scheduling method according to the resource usage prediction accuracy index is as follows: extract the resource usage prediction accuracy threshold in the cloud desktop database, compare the resource usage prediction accuracy index with the resource usage prediction accuracy threshold. If the resource usage prediction accuracy index is greater than or equal to the resource usage prediction accuracy threshold, the cloud desktop scheduling method is evaluated as qualified; if the resource usage prediction accuracy index is less than the resource usage prediction accuracy threshold, the cloud desktop scheduling method is evaluated as unqualified.

[0022] As a further method, the predicted usage of each resource at each time node has the following specific numerical expression:

[0023]

[0024] where y ik represents the predicted usage of the kth resource at the ith time node, x ijk represents the usage of the kth resource at the ith time node on the jth day, σ ik represents the resource prediction compensation parameter of the kth resource at the ith time node, ω1 represents the prediction usage evaluation influence factor corresponding to the set historical average usage, ω2 represents the prediction usage evaluation influence factor corresponding to the set resource prediction compensation parameter, i represents the number of time nodes, i = 1, 2, 3,..., n, n represents the total number of time nodes, j represents the number of monitoring periods, j = 1, 2, 3,..., m, m represents the total number of monitoring periods, k represents the number of resources, k = 1, 2, 3,..., h, h represents the total number of resources.

[0025] As a further method, the prediction accuracy index has the following specific numerical expression:

[0026]

[0027] where C represents the prediction accuracy index, e represents the natural constant, yik represents the predicted usage of the k-th resource at the i-th time node. represents the actual usage of the k-th resource at the i-th time node, Δy represents the set allowable deviation usage, i represents the number of time nodes, i = 1, 2, 3,..., n, n represents the total number of time nodes, k represents the number of resources, k = 1, 2, 3,..., h, and h represents the total number of resources.

[0028] The second aspect of the present invention application provides a cloud desktop scheduling method system, including: a cloud desktop data collection module, which is used to collect user behavior data, the actual usage of various resources, and system performance data. The user behavior data includes the cumulative login times, cumulative login duration, and system response time of the user; the system performance data includes system throughput and resource usage.

[0029] A cloud desktop predicted usage analysis module, which is used to process the user behavior data to obtain the cloud desktop user viscosity, process the system performance data to obtain the cloud desktop system performance evaluation index, and comprehensively analyze in combination with the actual usage of various resources to obtain the predicted usage of various resources at each time node.

[0030] A cloud desktop prediction accuracy analysis module, which is used to divide the time nodes according to the current time node to obtain each historical time node and each future time node, and comprehensively analyze according to the predicted usage of various resources and the actual usage of various resources at each historical time node to obtain the resource usage prediction accuracy index.

[0031] A cloud desktop scheduling method evaluation module, which is used to evaluate the resource usage prediction result according to the resource usage prediction accuracy index. If the evaluation result is qualified, cloud desktop resource scheduling is performed according to the predicted usage of various resources at each future time node. If the evaluation result is unqualified, the resource usage prediction is performed again.

[0032] A cloud desktop database, the cloud desktop data includes the cloud desktop user viscosity evaluation influence factor corresponding to the preset cumulative login times, the cloud desktop user viscosity evaluation influence factor corresponding to the cumulative login duration, the cloud desktop system performance evaluation influence factor corresponding to the preset system response time, the cloud desktop system performance evaluation influence factor corresponding to the preset system throughput, the resource usage, and the prediction usage evaluation influence factor corresponding to the resource prediction compensation parameter, and the resource usage prediction accuracy threshold.

[0033] Compared with the prior art, the embodiments of the present invention application have at least the following advantages or beneficial effects:

[0034] (1) By evaluating the user viscosity of the cloud desktop, this invention application can help formulate more targeted marketing strategies, improve user retention rate and satisfaction. Secondly, abnormal changes in user viscosity may indicate problems in the service, which helps to quickly diagnose and solve problems. At the same time, it can more accurately predict resource requirements and avoid cost waste caused by over-allocation.

[0035] (2) By evaluating the performance of the cloud desktop system, this invention application can more accurately predict resource requirements and avoid cost waste caused by over-allocation. At the same time, according to the changes in the performance evaluation index of the cloud desktop system, more personalized services and supports can be provided, such as providing additional support during high-load periods.

[0036] (3) By evaluating the predicted usage at future time nodes, this invention application not only helps to improve the stability and security of the system, but also optimizes resource usage, enhances the user experience, and brings higher operational efficiency to the enterprise. BRIEF DESCRIPTION OF THE DRAWINGS

[0037] The present invention application will be further described with reference to the accompanying drawings. However, the embodiments in the drawings do not constitute any limitation to the present invention application. For those of ordinary skill in the art, other drawings can also be obtained according to the following drawings without creative efforts.

[0038] Figure 1 It is a schematic flow diagram of the cloud desktop scheduling method of the present invention application.

[0039] Figure 2 It is a schematic diagram of the module connection of the cloud desktop system of the present invention application.

[0040] Figure 3 It is a schematic diagram of the functional relationship between the resource prediction correction parameter evaluation index and the cloud desktop user viscosity evaluation index involved in the present invention application. DETAILED DESCRIPTION OF THE EMBODIMENTS

[0041] Next, the technical solutions in the embodiments of the present invention application will be clearly and completely described in conjunction with the accompanying drawings in the embodiments of the present invention application. Obviously, the described embodiments are only a part of the embodiments of the present invention application, rather than all the embodiments. Based on the embodiments in the present invention application, all other embodiments obtained by those of ordinary skill in the art without creative efforts belong to the scope of protection of the present invention application.

[0042] Referring to Figure 1 as shown, the first aspect of the present invention application provides a cloud desktop scheduling method, including:

[0043] Collect user behavior data, the actual usage of various resources, and system performance data;

[0044] Process the user behavior data to obtain the viscosity of cloud desktop users, process the system performance data to obtain the performance evaluation index of the cloud desktop system, and combine the actual usage amounts of various resources to comprehensively analyze and obtain the predicted usage amounts of various resources at each time node;

[0045] Perform time node division according to the current time node to obtain each historical time node and each future time node, and comprehensively analyze and obtain the resource usage prediction accuracy index according to the predicted usage amounts and actual usage amounts of various resources at each historical time node;

[0046] Evaluate the resource usage prediction results according to the resource usage prediction accuracy index. If the evaluation result is qualified, perform cloud desktop resource scheduling according to the predicted usage amounts of various resources at each future time node. If the evaluation result is unqualified, re-predict the resource usage amounts.

[0047] It should be understood that the actual usage amounts of various resources in this embodiment include: CPU usage amount, memory usage amount, system disk usage amount, data disk usage amount, bandwidth usage amount, traffic usage amount, and GPU usage amount.

[0048] Specifically, processing the user behavior data to obtain the viscosity of cloud desktop users, the specific processing process is as follows: the user behavior data includes the cumulative login times, cumulative login duration, and the number of users.

[0049] The impact factors for evaluating the viscosity of cloud desktop users corresponding to the preset cumulative login times and the impact factors for evaluating the viscosity of cloud desktop users corresponding to the cumulative login duration can be extracted from the cloud desktop database.

[0050] According to the cumulative login times and cumulative login duration of each user at each time node in each monitoring period, comprehensively analyze and obtain the viscosity of cloud desktop users at each time node in each monitoring period.

[0051] In a specific embodiment, monitor the cumulative login times, cumulative login duration, and the number of users of users through the functions provided by the cloud desktop platform. Monitoring the cumulative login times and the number of users can understand the load conditions of the system at different time periods, so as to further allocate resources to achieve load balancing, and at the same time help predict future resource requirements, so as to make an expansion plan in advance to ensure that the system can handle the load during peak periods; monitoring the cumulative login duration helps to quickly discover performance anomalies and security vulnerabilities, so as to quickly locate and solve problems. Abnormally high login times or login duration may also be signs of security threats.

[0052] Specifically, the viscosity evaluation index of cloud desktop users, the specific numerical expression is:

[0053]

[0054] Among them, A ij represents the cloud desktop user viscosity evaluation index at the i-th time node in the j-th monitoring period. T ijf represents the cumulative login times of the f-th user at the i-th time node in the j-th monitoring period. T0 represents the critical cumulative login times. S ijf represents the cumulative login duration of the f-th user at the i-th time node in the j-th monitoring period. S0 represents the critical cumulative login duration. f0 represents the critical number of users. represents the influence factor of the cloud desktop user viscosity evaluation corresponding to the set cumulative login times. represents the influence factor of the cloud desktop user viscosity evaluation corresponding to the set cumulative login duration. represents the influence factor of the cloud desktop user viscosity evaluation corresponding to the set number of users. i represents the number of time nodes, i = 1, 2, 3,..., n, where n represents the total number of time nodes. j represents the number of monitoring periods, j = 1, 2, 3,..., m, where m represents the total number of monitoring periods. f represents the number of users, f = 1, 2, 3,..., z, where z represents the total number of users.

[0055] The algorithm of this embodiment combines the cumulative login times and cumulative login duration of users at a certain time node and the number of users at the current time node, and comprehensively analyzes to obtain the dependent variable. In this formula, the more the cumulative login times of each user, the longer the cumulative login duration, indicating that the user's dependence on the cloud desktop service is higher. At the same time, the increase in the number of users indicates that the cloud desktop service is more popular. Through comprehensive analysis, a more comprehensive cloud desktop user viscosity evaluation index can be obtained.

[0056] Table 1 Data example of cloud desktop user viscosity evaluation index

[0057]

[0058] As shown in Table 1, the cloud desktop user viscosity evaluation index is jointly determined by the cumulative login times, cumulative login duration, and the number of users. In a specific embodiment, z = 1, the critical cumulative login times is 10 times, the critical cumulative login duration is 1 hour, the critical number of users is 50, the influence factor of the cloud desktop user viscosity evaluation corresponding to the set cumulative login times is 0.3, the influence factor of the cloud desktop user viscosity evaluation corresponding to the set cumulative login duration is 0.4, and the influence factor of the cloud desktop user viscosity evaluation corresponding to the set number of users is 0.3.

[0059] This formula takes into account the cumulative login times, cumulative login durations, and the number of users for each user, and can provide more personalized services and support based on the user's behavior patterns. For example, it can offer higher-level technical support or customized services for high-frequency users. By standardizing the cumulative login times, cumulative login durations, and the number of users at different time nodes in different monitoring periods, it ensures that they are compared on the same scale, improving the fairness and comparability of the evaluation. At the same time, it can understand which time periods or user groups have a higher dependence on the cloud desktop service, so as to reasonably arrange resource allocation and optimize the user experience. By weighting the impacts of the cumulative login times, cumulative login durations, and the number of users, it reflects their relative importance in the evaluation index, and the weights of different factors can be adjusted according to different needs, making the model highly adaptable. It can be seen that the larger the cumulative login times, cumulative login durations, or the number of users, the larger the cloud desktop user viscosity evaluation index. By evaluating the cloud desktop user viscosity, it can help formulate more targeted marketing strategies, improve user retention rates and satisfaction. Secondly, abnormal changes in user viscosity may indicate problems in the service, which helps to quickly diagnose and solve problems. At the same time, it can more accurately predict resource requirements and avoid cost waste caused by over-allocation.

[0060] In a specific embodiment, the value ranges of the impact factors of the cumulative login times, cumulative login durations, and the number of users for each user corresponding to the cloud desktop user viscosity evaluation are between 0 and 1. By adjusting the values of the impact factors, the influence degrees of different factors on the final cloud desktop user viscosity evaluation index can be flexibly adjusted.

[0061] It should be understood that in this embodiment, based on the relationship between the cumulative login times, cumulative login durations, and the number of users in the historical data and the cloud desktop user viscosity evaluation index, a mapping set of the cumulative login times, cumulative login durations, and the number of users and the corresponding impact factors of the cloud desktop user viscosity evaluation is constructed. By inputting the real-time cumulative login times, cumulative login durations, and the number of users, the corresponding impact factors of the cloud desktop user viscosity evaluation are obtained from the mapping set.

[0062] In a specific embodiment, the cloud desktop user viscosity evaluation index is a quantitative index obtained by analyzing the cumulative login times, cumulative login durations, and the number of users, and is used to quantify the viscosity of cloud desktop users.

[0063] Specifically, the cloud desktop system performance evaluation index is obtained by processing the system performance data. The specific processing process is as follows: The system performance data includes system response time and system throughput.

[0064] The cloud desktop system performance evaluation impact factors corresponding to the preset system response time and the cloud desktop system performance evaluation impact factors corresponding to the preset system throughput can be extracted from the cloud desktop database.

[0065] Based on the system response time and system throughput at each time node in each monitoring period, the cloud desktop system performance evaluation index is comprehensively analyzed.

[0066] In a specific embodiment, throughput refers to the number of requests processed by the system per unit time, and response time refers to the time taken for the system to respond to a request, that is, from the moment a user initiates a request on the client to the moment the client receives the response returned from the server end, the time consumed throughout the process. The system response time and system throughput can be detected through the built-in performance monitoring function of the cloud desktop platform. By monitoring the system response time, it can be ensured that the cloud desktop can quickly respond to user operations, provide a smooth usage experience, reduce the user's waiting time, improve work efficiency and satisfaction. Monitoring the system throughput can help determine the system's load situation, achieve reasonable resource allocation, ensure that resources are available when needed, and abnormal response times and throughputs may indicate that the system is under attack or there are potential security vulnerabilities. Detection can help identify areas where security measures need to be strengthened.

[0067] Specifically, the cloud desktop system performance evaluation index, the specific numerical expression is:

[0068]

[0069] Among them, B ij represents the cloud desktop system performance evaluation index at the i-th time node in the j-th monitoring period, P ij represents the system response time at the i-th time node in the j-th monitoring period, P0 represents the set maximum allowable system response time, Q ij represents the system throughput at the i-th time node in the j-th monitoring period, Q0 represents the set maximum allowable system throughput, ρ1 represents the cloud desktop system performance evaluation impact factor corresponding to the set response time, ρ2 represents the cloud desktop system performance evaluation impact factor corresponding to the set throughput, i represents the number of time nodes, i = 1, 2, 3,..., n, n represents the total number of time nodes, j represents the number of monitoring periods, j = 1, 2, 3,..., m, m represents the total number of monitoring periods.

[0070] The algorithm of this embodiment combines the system response time and system throughput at each time node, and comprehensively analyzes to obtain the dependent variable. There is a direct correlation between the system response time and system throughput. When the system throughput increases, the system may need to process more requests, which may lead to a longer response time for a single request. Conversely, if the system response time is too long, the system may not be able to effectively process more requests, thus limiting the throughput. Comprehensive analysis can evaluate the system performance level at a specific time node within a specific monitoring period, and obtain a more comprehensive cloud desktop system performance evaluation index.

[0071] It should be noted that two key factors, namely the system response time and system throughput, are considered in this embodiment. It can help identify performance bottlenecks, quickly locate the causes of performance problems, and also identify periods of low resource utilization efficiency, thus saving costs. By standardizing the system response time and system throughput at different time nodes, ensuring that they are compared on the same scale, the fairness and comparability of the evaluation are improved. At the same time, the performance of the cloud desktop service at different time periods can be understood, so as to better allocate resources and achieve load balancing. By weighting the impacts of the system response time and system throughput, the relative importance of them in the evaluation index is reflected. The weights of different factors can be adjusted according to different requirements, making the model have good adaptability. It is not difficult to see that when the system response time is smaller and / or the system throughput is larger, the cloud desktop system performance evaluation index is larger. By evaluating the cloud desktop system performance, the resource requirements can be predicted more accurately, avoiding cost waste caused by over-allocation. At the same time, according to the change of the cloud desktop system performance evaluation index, more personalized services and supports can be provided, such as providing additional support during high-load periods.

[0072] In a specific embodiment, the value ranges of the cloud desktop system performance evaluation impact factors corresponding to the system response time and system throughput at each time node are both between 0 and 1. By adjusting the values of the impact factors, the influence degrees of different factors on the final cloud desktop system performance evaluation index can be flexibly adjusted.

[0073] It should be understood that in this embodiment, based on the relationship between the system response time and system throughput in historical data and the cloud desktop system performance evaluation index, a mapping set of the system response time and system throughput and the corresponding cloud desktop system performance evaluation impact factors is constructed. The real-time system response time and system throughput are input, and the corresponding cloud desktop system performance evaluation impact factors are obtained from the mapping set.

[0074] In a specific embodiment, the cloud desktop system performance evaluation index is a quantitative index obtained by analyzing the system response time and system throughput, and is used to quantify the cloud desktop system performance.

[0075] Specifically, the predicted usage amounts of various resources at each time node are obtained through comprehensive analysis. The specific analysis process is as follows: Extract the predicted usage amount evaluation impact factors corresponding to the preset cloud desktop user viscosity, cloud desktop system performance evaluation index, and the actual usage amounts of various resources from the cloud desktop database.

[0076] Based on the user viscosity, system performance evaluation index, and the actual usage amounts of various resources, the predicted usage amounts of various resources at each time node are obtained through comprehensive analysis.

[0077] Specifically, the resource prediction correction parameter evaluation index at each time node has the following specific numerical expression:

[0078]

[0079] where ε i represents the resource prediction correction parameter evaluation index at the i-th time node, A ij represents the cloud desktop user viscosity evaluation index at the i-th time node in the j-th monitoring period, B ij represents the cloud desktop system performance evaluation index at the i-th time node in the j-th monitoring period, θ1 represents the resource prediction correction parameter evaluation impact factor corresponding to the set user viscosity, θ2 represents the resource prediction correction parameter evaluation impact factor corresponding to the set system performance evaluation index, i represents the number of time nodes, i = 1, 2, 3,..., n, n represents the total number of time nodes, j represents the number of monitoring periods, j = 1, 2, 3,..., m, and m represents the total number of monitoring periods.

[0080] The algorithm of this embodiment combines the cloud desktop user viscosity evaluation index and the cloud desktop system performance evaluation index at a certain time node, and through comprehensive analysis, the dependent variable is obtained. If the system performance is good, the user viscosity is usually also high, because good performance helps to improve the user experience, thereby increasing the user's dependence on the service, indicating that more resources are needed to maintain the service quality. Comprehensive analysis can more comprehensively evaluate the resource requirements and adjust the resource prediction accordingly.

[0081] As Figure 3 shown, in a specific embodiment, m = 1, θ1 = 0.5, and θ2 = 0.3. When B ij = 0.1, the functional relationship between the resource prediction correction parameter evaluation index and the cloud desktop user viscosity evaluation index is as shown by curve a; when B ij = 0.5, the functional relationship between the resource prediction correction parameter evaluation index and the cloud desktop user viscosity evaluation index is as shown by curve b; when B ij = 1, the functional relationship between the resource prediction correction parameter evaluation index and the cloud desktop user viscosity evaluation index is as shown by curve c.

[0082] It should be noted that in this embodiment, two key factors are comprehensively considered, namely the cloud desktop user viscosity evaluation index and the cloud desktop system performance evaluation index, which can more accurately predict future resource requirements. According to the changing trends of these indicators, resource allocation can be dynamically adjusted to ensure that resources are available when needed. By summing and averaging the cloud desktop user viscosity and cloud desktop system performance evaluation indexes for different monitoring periods, it is beneficial to accurately allocate the resource requirements for future time nodes based on the cloud desktop user viscosity and cloud desktop system performance evaluation indexes at different time nodes, achieve load balancing, and improve the user experience. By weighting the impacts of the cloud desktop user viscosity and cloud desktop system performance, the relative importance of them in the evaluation index is reflected, and the weights of different factors can be adjusted according to different requirements, making the model have good adaptability. When the cloud desktop user viscosity evaluation index is larger and / or the cloud desktop system performance evaluation index is larger, the resource prediction correction parameter evaluation index is larger. By evaluating the resource prediction correction parameter, the influence degree of the cloud desktop user viscosity evaluation index and the cloud desktop system performance evaluation index on the resource prediction usage amount can be quantified, which helps the management make more informed decisions, such as increasing or decreasing resources in a timely manner.

[0083] In a specific embodiment, the value ranges of the resource prediction correction parameter evaluation impact factors corresponding to the cloud desktop user viscosity evaluation index and the cloud desktop system performance evaluation index at each time node are all between 0 and 1. By adjusting the values of the impact factors, the influence degrees of different factors on the final resource prediction correction parameter evaluation index can be flexibly adjusted.

[0084] It should be understood that in this embodiment, based on the relationship between the cloud desktop user viscosity evaluation index and the cloud desktop system performance evaluation index in the historical data and the resource prediction correction parameter evaluation index, a mapping set of the cloud desktop user viscosity evaluation index and the cloud desktop system performance evaluation index and the corresponding resource prediction correction parameter evaluation impact factors is constructed. By inputting the real-time cloud desktop user viscosity evaluation index and the cloud desktop system performance evaluation index, the corresponding resource prediction correction parameter evaluation impact factors can be obtained from the mapping set.

[0085] In a specific embodiment, the resource prediction correction parameter evaluation index is a quantitative index obtained by analyzing the cloud desktop user viscosity evaluation index and the cloud desktop system performance evaluation index, and is used to quantify the resource prediction correction parameter.

[0086] Specifically, the predicted usage amount of each resource at each time node has the following specific numerical expression:

[0087]

[0088] where y ik represents the predicted usage amount of the kth resource at the ith time node, and xijk represents the usage amount of the k-th resource at the i-th time node on the j-th day, σ ik represents the resource prediction compensation parameter of the k-th resource at the i-th time node, ω1 represents the prediction usage evaluation influence factor corresponding to the set historical average usage amount, ω2 represents the prediction usage evaluation influence factor corresponding to the set resource prediction compensation parameter, i represents the number of time nodes, i = 1, 2, 3,..., n, n represents the total number of time nodes, j represents the number of monitoring periods, j = 1, 2, 3,..., m, m represents the total number of monitoring periods, k represents the number of resources, k = 1, 2, 3,..., h, h represents the total number of resources.

[0089] The algorithm of this embodiment combines the predicted usage amount of resources and the resource prediction compensation parameter at historical time nodes, and comprehensively analyzes to obtain the dependent variable. If there is a large deviation between the historical average usage amount and the actual usage amount, the resource prediction compensation parameter can be used to adjust the predicted value to make it closer to the actual usage situation to cope with uncertainties and changes. The comprehensive analysis can more accurately predict the resource usage amount and perform resource scheduling accordingly.

[0090] It should be noted that in this embodiment, the resource prediction compensation parameter corresponding to the resource prediction correction parameter evaluation index at different time nodes is extracted from the cloud desktop dataset, and the resource prediction compensation parameter can ensure being on the same order of magnitude as the resource usage amount.

[0091] It should be noted that in this embodiment, two key factors, namely the resource usage amount at historical time nodes and the resource prediction compensation parameter, are comprehensively considered, and the demand for each time node and each type of resource can be predicted more accurately. By summing and averaging the resource usage amounts at historical time nodes of different monitoring periods, the user's behavior pattern can be further understood, and more personalized services can be provided accordingly. By weighting the influences of the resource usage amount at historical time nodes and the resource prediction compensation parameter, their relative importance in the evaluation index is reflected, and the weights of different factors can be adjusted according to different needs, making the model have good adaptability. It is not difficult to see that when the resource usage amount at the historical time node is larger and / or the resource prediction compensation parameter is larger, the predicted usage amount at the future time node is larger. By evaluating the predicted usage amount at the future time node, the influence degree of the resource usage amount at the historical time node and the resource prediction compensation parameter on the predicted usage amount at the future time node can be quantified, which not only helps to improve the stability and security of the system, but also can optimize the resource usage, enhance the user experience, and bring higher operational efficiency to the enterprise.

[0092] In a specific embodiment, the value ranges of the resource usage at historical time nodes and the influence factor of the predicted resource usage at future time nodes corresponding to the resource prediction compensation parameter are both between 0 and 1. By adjusting the value of the influence factor, the influence degree of different factors on the predicted resource usage at the final future time node can be flexibly adjusted.

[0093] It should be understood that in this embodiment, based on the relationship between the resource usage at historical time nodes and the resource prediction compensation parameter in historical data and the predicted resource usage at future time nodes, a mapping set of the resource usage at historical time nodes and the resource prediction compensation parameter and the corresponding influence factor of the predicted resource usage at future time nodes is constructed. The real-time resource usage at historical time nodes and the resource prediction compensation parameter are input, and the corresponding influence factor of the predicted resource usage at future time nodes is obtained from the mapping set.

[0094] Specifically, the resource usage prediction accuracy index is a quantitative index obtained by comparing and analyzing the predicted usage and the actual usage of each resource at each time node, and is used to quantify the accuracy of the resource usage prediction.

[0095] Furthermore, the specific numerical expression of the resource usage prediction accuracy index is:

[0096]

[0097] where C represents the prediction accuracy index, e represents the natural constant, y ik represents the predicted usage of the kth resource at the ith time node, represents the actual usage of the kth resource at the ith time node, Δy represents the set allowable deviation usage, i represents the number of time nodes, i = 1, 2, 3,..., n, n represents the total number of time nodes, k represents the number of resources, k = 1, 2, 3,..., h, and h represents the total number of resources.

[0098] It should be explained that in this embodiment, it is not difficult to see that the closer the predicted usage and the actual usage of each resource at each time node are, the larger the resource usage prediction accuracy index is. By evaluating the resource usage prediction accuracy index, the accuracy of the cloud desktop resource usage prediction can be effectively improved, so as to provide better services for enterprise and individual users, while reducing costs and improving efficiency.

[0099] Specifically, the cloud desktop scheduling method is evaluated according to the resource usage prediction accuracy index. The specific evaluation process is as follows: Extract the resource usage prediction accuracy threshold from the cloud desktop database, compare the resource usage prediction accuracy index with the resource usage prediction accuracy threshold. If the resource usage prediction accuracy index is greater than or equal to the resource usage prediction accuracy threshold, the cloud desktop scheduling method is evaluated as qualified; if the resource usage prediction accuracy index is less than the resource usage prediction accuracy threshold, the cloud desktop scheduling method is evaluated as unqualified.

[0100] Refer to Figure 2 As shown, the second aspect of the present invention provides a cloud desktop scheduling system, including:

[0101] A cloud desktop data collection module, used to collect user behavior data, the actual usage of various resources, and system performance data. The user behavior data includes the cumulative login times, cumulative login duration, and system response time of the user; the system performance data includes system throughput and resource usage;

[0102] A cloud desktop predicted usage analysis module, used to process the user behavior data to obtain the cloud desktop user viscosity, process the system performance data to obtain the cloud desktop system performance evaluation index, and comprehensively analyze the predicted usage of various resources at each time node in combination with the actual usage of various resources;

[0103] A cloud desktop prediction accuracy analysis module, used to divide time nodes according to the current time node to obtain each historical time node and each future time node, and comprehensively analyze the resource usage prediction accuracy index according to the predicted usage and actual usage of various resources at each historical time node;

[0104] A cloud desktop scheduling method evaluation module, used to evaluate the resource usage prediction result according to the resource usage prediction accuracy index. If the evaluation result is qualified, cloud desktop resource scheduling is performed according to the predicted usage of various resources at each future time node. If the evaluation result is unqualified, resource usage prediction is performed again;

[0105] In a specific embodiment, when the evaluation result of the resource usage prediction result is qualified, cloud desktop resource scheduling is performed according to the predicted usage of various resources at each future time node. For example, through the analysis of historical data, it is found that 9:00 to 11:00 am every day is the peak user login period, and at this time, the CPU and memory usage rates increase significantly. Then, according to the prediction result, the resource allocation is adjusted in advance, such as increasing the number of CPUs and the memory capacity, to meet the requirements during the peak period.

[0106] A cloud desktop database is used to store cloud desktop data, which includes cloud desktop user viscosity evaluation influencing factors corresponding to preset cumulative login times and cloud desktop user viscosity evaluation influencing factors corresponding to cumulative login durations, cloud desktop system performance evaluation influencing factors corresponding to preset system response times and cloud desktop system performance evaluation influencing factors corresponding to preset system throughput, prediction usage evaluation influencing factors corresponding to resource usage amounts and resource prediction compensation parameters, and resource usage amount prediction accuracy thresholds. The data in the cloud desktop database can also be obtained by collecting multiple cloud desktop experiment data.

[0107] The above content is only an example and explanation of the structure of the present invention application. Those skilled in the art of this technology can make various modifications or supplements to the described specific embodiments or use similar methods for substitution, as long as they do not deviate from the structure of the invention or exceed the scope defined by the present invention application, they should all fall within the protection scope of the present invention application.

Claims

1. A cloud desktop scheduling method, characterized in that, Including: Collecting user behavior data, the actual usage of various resources, and system performance data; Processing the user behavior data to obtain the viscosity of cloud desktop users, and processing the system performance data to obtain the cloud desktop system performance evaluation index. According to the user viscosity and the cloud desktop system performance evaluation index, the resource prediction correction parameter evaluation index at each time node is obtained. The specific numerical expression is: where εi represents the resource prediction correction parameter evaluation index at the i-th time node, Aij represents the cloud desktop user viscosity evaluation index at the i-th time node in the j-th monitoring period, Bij represents the cloud desktop system performance evaluation index at the i-th time node in the j-th monitoring period, θ1 represents the resource prediction correction parameter evaluation influence factor corresponding to the set user viscosity, θ2 represents the resource prediction correction parameter evaluation influence factor corresponding to the set system performance evaluation index, i represents the number of time nodes, i = 1, 2, 3,..., n, n represents the total number of time nodes, j represents the number of monitoring periods, j = 1, 2, 3,..., m, and m represents the total number of monitoring periods; Extracting the resource prediction compensation parameters corresponding to the resource prediction correction parameter evaluation index at different time nodes from the cloud desktop dataset, combining with the actual usage of various resources, and comprehensively analyzing to obtain the predicted usage of various resources at each time node; dividing the time nodes according to the current time node to obtain each historical time node and each future time node, and comprehensively analyzing based on the predicted usage of various resources and the actual usage of various resources at each historical time node to obtain the resource usage prediction accuracy index; evaluating the resource usage prediction result according to the resource usage prediction accuracy index. If the evaluation result is qualified, perform cloud desktop resource scheduling according to the predicted usage of various resources at each future time node. If the evaluation result is unqualified, re-predict the resource usage.

2. The cloud desktop scheduling method according to claim 1, wherein: The process of processing the user behavior data to obtain the viscosity of cloud desktop users is as follows: The user behavior data includes the cumulative login times, the cumulative login duration, and the number of users; Extracting the cloud desktop user viscosity evaluation influence factor corresponding to the preset cumulative login times and the cloud desktop user viscosity evaluation influence factor corresponding to the cumulative login duration from the cloud desktop database; comprehensively analyzing based on the cumulative login times and the cumulative login duration of each user at each time node in each monitoring period to obtain the cloud desktop user viscosity at each time node in each monitoring period.

3. The cloud desktop scheduling method according to claim 1, wherein: The process of processing the system performance data to obtain the cloud desktop system performance evaluation index is as follows: The system performance data includes the system response time and the system throughput; extracting the cloud desktop system performance evaluation influence factor corresponding to the preset system response time and the cloud desktop system performance evaluation influence factor corresponding to the preset system throughput from the cloud desktop database; Comprehensively analyzing based on the system response time and the system throughput at each time node in each monitoring period to obtain the cloud desktop system performance evaluation index.

4. The cloud desktop scheduling method according to claim 2, wherein: The comprehensive analysis obtains the predicted usage amounts of various resources at each time node. The specific analysis process is as follows: Extract the predicted usage amount evaluation impact factors corresponding to the preset cloud desktop user viscosity, cloud desktop system performance evaluation index, and the actual usage amounts of various resources from the cloud desktop database; Based on the user viscosity, system performance evaluation index, and the actual usage amounts of various resources, comprehensively analyze to obtain the predicted usage amounts of various resources at each time node.

5. The cloud desktop scheduling method according to claim 1, wherein: The resource usage amount prediction accuracy index is a quantitative index obtained by comparing and analyzing the predicted usage amounts and actual usage amounts of each resource at each time node, and is used to quantify the accuracy of resource usage amount prediction.

6. The cloud desktop scheduling method according to claim 1, wherein: The cloud desktop system performance evaluation index is a quantitative index obtained by analyzing the system response time and system throughput at each time node in each monitoring period, and is used to quantify the performance of the cloud desktop system.

7. The cloud desktop scheduling method according to claim 1, characterized in that: The evaluation of the cloud desktop scheduling method according to the resource usage amount prediction accuracy index. The specific evaluation process is as follows: Extract the resource usage amount prediction accuracy threshold in the cloud desktop database, compare the resource usage amount prediction accuracy index with the resource usage amount prediction accuracy threshold. If the resource usage amount prediction accuracy index is greater than or equal to the resource usage amount prediction accuracy threshold, the cloud desktop scheduling method is evaluated as qualified; if the resource usage amount prediction accuracy index is less than the resource usage amount prediction accuracy threshold, the cloud desktop scheduling method is evaluated as unqualified.

8. The cloud desktop scheduling method according to claim 1, wherein: The predicted usage amounts of various resources at each time node, the specific numerical expression is: Among them, yik represents the predicted usage amount of the kth resource at the ith time node, xijk represents the usage amount of the kth resource at the ith time node on the jth day, σik represents the resource prediction compensation parameter of the kth resource at the ith time node, ω1 represents the predicted usage amount evaluation impact factor corresponding to the set historical average usage amount, ω2 represents the predicted usage amount evaluation impact factor corresponding to the set resource prediction compensation parameter, i represents the number of time nodes, i = 1, 2, 3,..., n, n represents the total number of time nodes, j represents the number of monitoring periods, j = 1, 2, 3,..., m, m represents the total number of monitoring periods, k represents the number of resources, k = 1, 2, 3,..., h, h represents the total number of resources.

9. The cloud desktop scheduling method according to claim 1, characterized in that: The prediction accuracy index, the specific numerical expression is: Among them, C represents the prediction accuracy index, e represents the natural constant, yik represents the predicted usage of the k-th resource at the i-th time node, represents the actual usage of the k-th resource at the i-th time node, Δy represents the set allowable deviation usage, i represents the number of time nodes, i = 1, 2, 3,..., n, n represents the total number of time nodes, k represents the number of resources, k = 1, 2, 3,..., h, h represents the total number of resources.

10. A system using the cloud desktop scheduling method according to any one of claims 1-9, characterized in that: Including: The cloud desktop data collection module is used to collect user behavior data, the actual usage amounts of various resources, and system performance data. The user behavior data includes the cumulative login times, cumulative login durations, and system response times of users; The system performance data includes system throughput and resource usage amounts; The cloud desktop predicted usage amount analysis module is used to process the user behavior data to obtain the cloud desktop user viscosity, process the system performance data to obtain the cloud desktop system performance evaluation index, and obtain the resource prediction correction parameter evaluation index at each time node according to the user viscosity and system performance evaluation index. The specific numerical expression is: Among them, εi represents the resource prediction correction parameter evaluation index at the i-th time node, Aij represents the cloud desktop user viscosity evaluation index at the i-th time node in the j-th monitoring period, Bij represents the cloud desktop system performance evaluation index at the i-th time node in the j-th monitoring period, θ1 represents the resource prediction correction parameter evaluation influence factor corresponding to the set user viscosity, θ2 represents the resource prediction correction parameter evaluation influence factor corresponding to the set system performance evaluation index, i represents the number of time nodes, i = 1, 2, 3,..., n, n represents the total number of time nodes, j represents the number of monitoring periods, j = 1, 2, 3,..., m, and m represents the total number of monitoring periods; Extract the resource prediction compensation parameters corresponding to the resource prediction correction parameter evaluation index at different time nodes from the cloud desktop dataset, and combine with the actual usage of various resources to comprehensively analyze and obtain the predicted usage of various resources at each time node; the cloud desktop prediction accuracy analysis module is used to divide the time nodes according to the current time node to obtain each historical time node and each future time node, and comprehensively analyze and obtain the resource usage prediction accuracy index according to the predicted usage and the actual usage of various resources at each historical time node; the cloud desktop scheduling method evaluation module is used to evaluate the resource usage prediction result according to the resource usage prediction accuracy index. If the evaluation result is qualified, the cloud desktop resource scheduling is performed according to the predicted usage of various resources at each future time node. If the evaluation result is unqualified, the resource usage prediction is performed again; the cloud desktop database is used to store cloud desktop data, and the cloud desktop data includes the cloud desktop user viscosity evaluation influence factor corresponding to the preset cumulative login times and the cloud desktop user viscosity evaluation influence factor corresponding to the cumulative login duration, the cloud desktop system performance evaluation influence factor corresponding to the preset system response time and the cloud desktop system performance evaluation influence factor corresponding to the preset system throughput, the prediction usage evaluation influence factor corresponding to the resource usage and the resource prediction compensation parameter, and the resource usage prediction accuracy threshold.

Images