Multi-cloud computing resource management method and system

Abstract

The present invention relates to the technical field of multi-cloud computing resource management, and more specifically, to a multi-cloud computing resource management method and system. The method comprises a resource monitoring module, a policy formulation module, and a dynamic adjustment module. The present invention monitors the usage status of computing resources of each cloud platform through the monitoring service of the cloud platform via the resource monitoring module. The policy formulation module prioritizes tasks according to the importance, timeliness, and cost-effectiveness of the tasks using the hierarchical analysis method. The dynamic adjustment module uses the computing power status indicator of the cloud computing resources as the input variable and the task priority value as the output variable. The dynamic adjustment module uses the fuzzy algorithm to dynamically adjust the priority according to the status of the computing power resources. The priority determined by the policy formulation module is dynamically adjusted according to the status of the computing power resources to ensure that the priority strategy can adapt to the status of the computing power resources and ensure the rationality of the allocation of computing power resources.

Description

Technical Field

[0001] The present invention relates to the technical field of multi-cloud computing resource management, and in particular to a multi-cloud computing resource management method and system. Background Art

[0002] The Multi-Cloud Management Platform is an innovative cloud computing management solution designed to help businesses and organizations efficiently integrate, manage, and optimize cloud computing resources across multiple cloud service providers (such as public and private clouds). Through a unified interface and intelligent management mechanisms, it breaks down barriers between cloud services, enabling coordinated resource allocation, cost control, security assurance, and convenient operations and maintenance across multi-cloud environments. This provides users with a one-stop multi-cloud management experience, significantly improving the flexibility and efficiency of cloud computing resource utilization.

[0003] At present, when allocating computing resources on a multi-cloud management platform, different tasks have different requirements for computing resources. If computing resources are simply distributed evenly, some unimportant or non-urgent tasks will occupy resources, causing important tasks to be delayed and reducing the utilization of computing resources. At the same time, when multiple tasks are running simultaneously, the status of computing resources will also change. In order to prioritize tasks according to their importance, timeliness, and cost-effectiveness, improve resource utilization, and dynamically adjust the priority of tasks according to the status of computing resources to ensure the rationality of computing resource allocation, we propose a multi-cloud computing resource management method and system. Summary of the Invention

[0004] The purpose of this invention is to solve the problem that the multi-cloud management platform cannot effectively allocate computing resources to tasks according to the importance of the tasks, thereby reducing the utilization rate of computing resources. In order to prioritize tasks according to their importance, timeliness and cost-effectiveness, improve resource utilization, and dynamically adjust the priority of tasks according to the status of computing resources, the rationality of resource allocation is ensured.

[0005] To achieve the above objectives, the present invention provides a multi-cloud computing resource management method, comprising the following steps:

[0006] S1. Use the cloud platform's monitoring service to monitor the usage status of computing resources on each cloud platform;

[0007] S2. Prioritize tasks based on their importance, timeliness, and cost-effectiveness using the analytic hierarchy process.

[0008] S3. Using the computing power status indicator of cloud computing resources as the input variable and the task priority value as the output variable, the fuzzy algorithm is used to dynamically adjust the priority according to the status of the computing power resources.

[0009] Preferably, the step S2 uses the analytic hierarchy process to prioritize tasks, and the steps are as follows:

[0010] S2.1.1. Construct a hierarchical model: Determine the priority level as the target level, the importance, timeliness, and cost-effectiveness of the task as the criterion level, and the tasks that need to be prioritized as the solution level;

[0011] S2.1.2. Construct judgment matrix: Use the scaling method to construct the judgment matrix of the criterion layer relative to the target layer and the judgment matrix of the solution layer relative to the criterion layer;

[0012] S2.1.3. Calculate the weight vector: Calculate the maximum eigenvalue of the judgment matrix and its corresponding eigenvector, normalize the eigenvector, and obtain the weight vector of each criterion in the criterion layer relative to the target layer;

[0013] S2.1.4. Consistency test: For each judgment matrix at the criterion layer and the solution layer, calculate the consistency index, find the average random consistency index according to the order of the judgment matrix, calculate the consistency ratio, and judge the judgment matrix.

[0014] Preferably, the S2.1.3 calculates the weight vector and normalizes the feature vector, wherein the normalization formula is:

[0015]

[0016] Among them, w i is the i-th component of the weight vector, i is the sequence number of the eigenvector, v i is the i-th vector in the eigenvector, n is the order of the eigenvector, j is the initial sequence number of the eigenvector, v j is the jth vector in the eigenvector.

[0017] Preferably, the consistency test in S2.1.4 calculates the consistency index using the formula:

[0018]

[0019] Among them, CI is the consistency index value, λ max is the maximum eigenvalue of the eigenvector, and n is the order of the eigenvector.

[0020] Preferably, when dividing priorities, S2 adopts a computing power resource allocation strategy that is based on priority and supplemented by queue algorithm scheduling. Within each priority queue, a first-come, first-served algorithm is adopted, and tasks obtain computing power resources in the order they enter the queue.

[0021] Preferably, the S3 dynamically adjusts the priority according to the status of computing resources, and the method steps are as follows:

[0022] S3.1.1. Define fuzzy sets and membership functions: Define fuzzy sets for input variables and use trapezoidal membership functions to find the membership values ​​of each fuzzy set.

[0023] S3.1.2. Build a fuzzy rule base: Based on business needs and resource management experience, formulate fuzzy rules, and refine and quantify them;

[0024] S3.1.3 Fuzzy reasoning: Using the Mamdani reasoning algorithm, based on the membership of the input resource status fuzzy variables and combined with fuzzy rules, the activation strength of the business priority fuzzy set is calculated to obtain the final business priority fuzzy result;

[0025] S3.1.4 Defuzzification: Defuzzify the fuzzy set using the centroid method and obtain a definite priority value by calculating the centroid of the fuzzy output.

[0026] Preferably, S3.1.1 defines fuzzy sets and membership functions, wherein the formula of the trapezoidal membership function is:

[0027]

[0028] Among them, μ(x) is the membership function value, x is the CPU usage, a is the lower limit, b is the end point of the rising interval, c is the starting point of the falling interval, and d is the upper limit.

[0029] Preferably, the fuzzy reasoning in S3.1.3 utilizes the Mamdani reasoning algorithm to determine the activation strength by taking the minimum value according to the logical connectives in the rules.

[0030] Preferably, after dynamically adjusting the priority, S3 establishes a conflict resolution mechanism based on resource conflicts and waiting time conflicts, and performs resource regulation on the priority strategy and queue scheduling strategy.

[0031] A second object of the present invention is to provide a multi-cloud computing resource management system, including any one of the multi-cloud computing resource management methods described above, including a resource monitoring module, a policy formulation module, and a dynamic adjustment module;

[0032] The resource monitoring module monitors the usage status of computing resources of each cloud platform through the monitoring service of the cloud platform;

[0033] The strategy formulation module prioritizes tasks using the analytic hierarchy process according to their importance, timeliness, and cost-effectiveness;

[0034] The dynamic adjustment module uses the computing power status indicator of the cloud computing resources as an input variable and the task priority value as an output variable, and uses a fuzzy algorithm to dynamically adjust the priority according to the status of the computing power resources.

[0035] Compared with the prior art, the present invention has the following beneficial effects:

[0036] 1. This multi-cloud computing resource management method and system uses a policy-making module to prioritize tasks based on their importance, timeliness, and cost-effectiveness using the analytic hierarchy process. A computing resource allocation strategy based on priority and supplemented by a queue algorithm scheduling algorithm is adopted. Computing resources are allocated preferentially to tasks of high importance, improving computing resource utilization. Furthermore, within the same priority level, tasks are assigned computing resources sequentially based on the order they enter the queue, supplemented by a queue algorithm. This accelerates the use of computing resources and ensures efficient computing resource utilization.

[0037] 2. The resource monitoring module uses the monitoring service of the cloud platform to monitor the usage status of the computing resources of each cloud platform. The dynamic adjustment module monitors the usage status of the computing resources of the cloud platform based on the resource monitoring module, takes the computing status indicator of cloud computing resources as the input variable, and takes the task priority value as the output variable. The fuzzy algorithm is used to dynamically adjust the priority determined by the policy formulation module according to the status of the computing resources to ensure that the priority strategy can adapt to the status of the computing resources and ensure the rationality of the allocation of computing resources. BRIEF DESCRIPTION OF THE DRAWINGS

[0038] Figure 1 A flowchart of the method of the present invention;

[0039] Figure 2 This is a specific flow chart of S2 of the present invention;

[0040] Figure 3 This is a specific flow chart of S3 of the present invention;

[0041] Figure 4 It is a system flow chart of the present invention.

[0042] The meaning of each number in the figure is:

[0043] 100. Resource monitoring module; 200. Policy formulation module; 300. Dynamic adjustment module. DETAILED DESCRIPTION

[0044] The following will clearly and completely describe the technical solutions in the embodiments of the present invention in conjunction with the accompanying drawings. Obviously, the described embodiments are only part of the embodiments of the present invention, not all of the embodiments. Based on the embodiments of the present invention, all other embodiments obtained by ordinary technicians in this field without making creative efforts are within the scope of protection of the present invention.

[0045] Currently, multi-cloud management platforms cannot effectively allocate computing resources to tasks based on their importance, which reduces the utilization of computing resources. In order to prioritize tasks based on their importance, timeliness, and cost-effectiveness, improve resource utilization, and dynamically adjust task priorities based on the status of computing resources, we need to ensure the rationality of resource allocation.

[0046] Therefore, the present invention proposes that the resource monitoring module monitors the usage status of the computing resources of each cloud platform through the monitoring service of the cloud platform, the strategy formulation module uses the hierarchical analysis method to prioritize tasks according to the importance, timeliness and cost-effectiveness of the tasks, and the dynamic adjustment module uses the computing status indicator of the cloud computing resources as the input variable and the task priority value as the output variable, and uses the fuzzy algorithm to dynamically adjust the priority according to the status of the computing resources.

[0047] Example 1 is as follows:

[0048] like Figure 1 As shown, one of the objectives of the present invention is to provide a multi-cloud computing resource management method, comprising the following steps:

[0049] S1. Use the cloud platform's monitoring service to monitor the usage status of computing resources on each cloud platform;

[0050] S2. Prioritize tasks based on their importance, timeliness, and cost-effectiveness using the analytic hierarchy process.

[0051] S3. Using the computing power status indicator of cloud computing resources as the input variable and the task priority value as the output variable, the fuzzy algorithm is used to dynamically adjust the priority according to the status of the computing power resources.

[0052] All major cloud computing platforms offer their own monitoring services. For example, Amazon AWS's CloudWatch is a powerful monitoring tool that can monitor the usage of various AWS resources. It can provide detailed metrics such as CPU usage, memory usage, network I / O, and disk I / O of EC2 instances (cloud servers).

[0053] Microsoft Azure's Monitor service is similar, covering monitoring of Azure virtual machines, storage accounts, and other resources. You can view detailed performance data for resources, including but not limited to processor time percentage and disk read / write bytes per second.

[0054] like Figure 2 As shown, S2 uses the hierarchical analysis method to prioritize tasks, and the steps are as follows:

[0055] S2.1.1. Construct a hierarchical model: Determine the priority level as the target level, the importance, timeliness, and cost-effectiveness of the task as the criterion level, and the tasks that need to be prioritized as the solution level;

[0056] S2.1.2. Construct judgment matrix: Use the scaling method to construct the judgment matrix of the criterion layer relative to the target layer and the judgment matrix of the solution layer relative to the criterion layer;

[0057] S2.1.3. Calculate the weight vector: Calculate the maximum eigenvalue of the judgment matrix and its corresponding eigenvector, normalize the eigenvector, and obtain the weight vector of each criterion in the criterion layer relative to the target layer;

[0058] S2.1.4. Consistency test: For each judgment matrix at the criterion level and the solution level, calculate the consistency index. Based on the order of the judgment matrix, find the average random consistency index, calculate the consistency ratio, and make a judgment on the judgment matrix.

[0059] The overall goal of prioritization is to determine the three main criteria: business importance, timeliness, and cost-effectiveness. Business importance can be further broken down into sub-criteria such as impact on core business and impact on customer satisfaction. Timeliness can include sub-criteria such as the urgency of task deadlines and the length of business cycles. Cost-effectiveness can cover sub-criteria such as resource input-output ratio and potential economic benefits. In other words, each business needs to be prioritized.

[0060] In the Analytic Hierarchy Process (AHP), a 1-9 scale is used to quantify the relative importance of two elements. The specific scale is as follows:

[0061] 1 means that the two elements are equally important;

[0062] 3 means that one element is slightly more important than the other;

[0063] 5 means that one element is significantly more important than the other.

[0064] 7 means that one element is more important than the other.

[0065] 9 means that one element is extremely more important than the other.

[0066] 2, 4, 6, and 8 represent the intermediate values ​​of the adjacent judgments. For example, 2 represents the degree between one element being slightly more important than the other and being equally important.

[0067] If task importance is considered slightly more important than timeliness, then the matrix element corresponding to task importance and timeliness is assigned a value of 3. If timeliness is considered significantly more important than cost-effectiveness, then a value of 7 is assigned, and so on. For each criterion, the relative importance of each task is compared. For example, under the task importance criterion, the impact of Task 1 and Task 2 on the core task is compared. If Task 1 has a much greater impact than Task 2, then a value of 7 is assigned. If the impact of Task 1 and Task 2 is the same, then a value of 1 is assigned.

[0068] Calculate the maximum eigenvalue of the judgment matrix and its corresponding eigenvector. For the above criterion layer judgment matrix, calculate the maximum eigenvalue and the corresponding eigenvector, normalize the eigenvector, and obtain the weight vector of each criterion in the criterion layer relative to the target layer.

[0069] In order to better normalize the eigenvector, S2.1.3 calculates the weight vector and normalizes the eigenvector. The normalization formula is:

[0070]

[0071] Among them, w i is the i-th component of the weight vector, i is the sequence number of the eigenvector, v i is the i-th vector in the eigenvector, n is the order of the eigenvector, j is the initial sequence number of the eigenvector, v j is the jth vector in the eigenvector.

[0072] For example, the judgment matrix of the criterion layer relative to the target layer is as follows:

[0073] Task Importance (B1) Timeliness (B2) Cost-effectiveness (B3) Task Importance (B1) 1 3 4 Timeliness (B2) 1 / 3 1 2 Cost-effectiveness (B3) 1 / 4 1 / 2 1

[0074] In this matrix, for example, when comparing task importance (B1) and timeliness (B2), task importance is considered to be "slightly more important" than timeliness, so it is assigned a value of 3. When comparing timeliness (B2) and cost-effectiveness (B3), timeliness is considered to be "slightly more important" than cost-effectiveness, so it is assigned a value of 2.

[0075] The judgment matrix of the scheme layer relative to the criteria layer is as follows:

[0076] Task Importance B1:

[0077]

[0078]

[0079] This means that in terms of business importance, Project A is "slightly more important" than Project B, with a value of 2, and Project A is "significantly more important" than Project C, with a value of 3;

[0080] Timeliness B2:

[0081] A B C A 1 1 / 2 1 / 3 B 2 1 1 / 2 C 3 2 1

[0082] In terms of timeliness, Project C is "clearly more important" than Project A and is assigned a value of 3; Project B is "slightly more important" than Project A and is assigned a value of 2;

[0083] Cost-effectiveness B3:

[0084] A B C A 1 3 1 / 2 B 1 / 3 1 1 / 3 C 2 3 1

[0085] In terms of cost-effectiveness, Project A is "clearly more important" than Project B and is assigned a value of 3, while Project C is "slightly more important" than Project A and is assigned a value of 2.

[0086] In order to better calculate the consistency index value of the feature vector, the formula for calculating the consistency index in S2.1.4 consistency test is as follows:

[0087]

[0088] Among them, CI is the consistency index value, λ max is the maximum eigenvalue of the eigenvector, and n is the order of the eigenvector.

[0089] Calculate the maximum eigenvalue λ of the criterion layer judgment matrix max , change λ max ≈3.039, n=3 is substituted into the formula of consistency index to obtain:

[0090] CI=(3.039-3) / (3-1)≈0.0195;

[0091] Find the average random consistency index RI and calculate the consistency ratio:

[0092] CR=CI / RI≈0.0336<0.1;

[0093] Therefore, the consistency of the judgment matrix is ​​acceptable. After calculating and normalizing the eigenvector, we obtain the weight vector of each criterion in the criterion layer relative to the target layer. Similarly, we calculate the weight vector of the solution layer under each criterion according to the same steps and perform a comprehensive priority calculation on it.

[0094] The weight vectors of the solution layer under each criterion are comprehensively calculated with the weight vectors of the criterion layer, and the businesses are sorted according to the size of the comprehensive priority, thereby completing the priority division.

[0095] To better implement a computing resource allocation strategy that prioritizes tasks and supplements them with queue-based scheduling, S2 prioritizes tasks and supplements them with queue-based scheduling. Within each priority queue, a first-come, first-served algorithm is used, and tasks receive computing resources in the order they enter the queue.

[0096] Different queues are divided according to the priority level of tasks. For example, priority 1 queue, priority 2 queue and priority 3 queue are created. Tasks are assigned to the corresponding queues according to their comprehensive priority. Tasks in high-priority queues are given priority to obtain computing resources.

[0097] Within each priority queue, a first-come, first-served algorithm is used. That is, tasks are assigned computing resources in the order they enter the queue. This algorithm is simple to understand and implement, and it ensures fairness when tasks arrive at relatively even times. For example, in a priority 2 queue, if task A enters the queue before task B, then when there is sufficient computing power, task A will be assigned computing resources first.

[0098] Schedule tasks in the queue based on the real-time availability of computing resources. For example, when new GPU resources become available, prioritize tasks from the GPU demand queue for allocation. Or, when a server cluster in a data center has a large amount of idle CPU resources, select tasks with high CPU resource requirements from each priority queue and assign them to that cluster. Resource availability information can be obtained in real time through the resource monitoring system and fed back to the queue scheduling system to make reasonable scheduling decisions.

[0099] Task enqueuing rules should be closely aligned with priority strategies. When a new task arrives, it is first placed in the corresponding priority queue based on the priority calculation. During this process, the accuracy and consistency of priorities must be ensured. For example, if a task's priority is adjusted due to business changes, it must be moved to the correct priority queue in a timely manner.

[0100] Priority is always the primary consideration during queue scheduling. Even when using a first-come, first-served algorithm within a queue, computing resources are allocated first when a high-priority task reaches the head of the queue. Furthermore, priority plays a crucial role when considering resource availability and other scheduling factors. For example, when scheduling tasks based on resource availability, if two tasks in different queues require the same resource, and the resource can only satisfy one task, the higher-priority task will be prioritized.

[0101] like Figure 3 As shown, S3 dynamically adjusts the priority based on the status of computing resources. The method steps are as follows:

[0102] S3.1.1. Define fuzzy sets and membership functions: Define fuzzy sets for input variables and use trapezoidal membership functions to find the membership values ​​of each fuzzy set.

[0103] S3.1.2. Build a fuzzy rule base: Based on business needs and resource management experience, formulate fuzzy rules, and refine and quantify them;

[0104] S3.1.3 Fuzzy reasoning: Using the Mamdani reasoning algorithm, based on the membership of the input resource status fuzzy variables and combined with fuzzy rules, the activation strength of the business priority fuzzy set is calculated to obtain the final business priority fuzzy result;

[0105] S3.1.4 Defuzzification: Defuzzify the fuzzy set using the centroid method and obtain a definite priority value by calculating the centroid of the fuzzy output.

[0106] For computing resource status, define fuzzy sets such as "resource tightness," "resource moderateness," and "resource abundance." For example, for CPU utilization, a utilization rate of 0-30% can be defined as "resource abundance," 30%-70% as "resource moderateness," and 70%-100% as "resource tightness." For each fuzzy set, a membership function needs to be defined to describe the degree to which an element belongs to the fuzzy set. For example, for the "resource tightness" fuzzy set, a trapezoidal membership function can be used. When the CPU utilization rate is greater than or equal to 70%, the membership degree begins to increase linearly from 0 to 1 (reaching 1 when the utilization rate is 100%).

[0107] In order to better determine the trapezoidal membership function, S3.1.1 defines fuzzy sets and membership functions, where the formula of the trapezoidal membership function is:

[0108]

[0109] Among them, μ(x) is the membership function value, x is the CPU usage, a is the lower limit, b is the end point of the rising interval, c is the starting point of the falling interval, and d is the upper limit.

[0110] This function is used to describe situations where a variable has a membership of 1 within a certain interval and gradually changes at both ends of the interval. For example, for a resource in a "high load" state, when CPU usage reaches a certain level (such as 70%), it is considered to have entered a high load state, and the membership begins to gradually increase from 0. After reaching a higher value (such as 90%), the membership remains at 1, and a trapezoidal membership function is used.

[0111] Define fuzzy sets of task priorities, such as "high priority," "medium priority," and "low priority." These fuzzy sets can be defined based on factors such as the importance and timeliness of the business. Similarly, define a membership function for each task priority fuzzy set. For example, the membership function for "high priority" tasks can be determined based on the criticality and time urgency of the business. For example, urgent and critical tasks to the company's core business have a membership of 1, while other tasks have values ​​between 0 and 1 depending on the situation.

[0112] The domain is the range of values ​​for a fuzzy variable. For resource status variables, the domain for CPU usage is [0, 100%], and for memory utilization, the domain is [0, 100%]. For business priority variables, the domain might be the interval [0, 1], where 0 represents the lowest priority and 1 represents the highest. By defining the domain, the range of values ​​for the fuzzy variable can be clearly defined, providing a foundation for subsequent fuzzy reasoning.

[0113] Fuzzy rules are developed based on business needs and resource management experience. For example, "If resources are tight and the business has a high demand for resources, then the business priority should be lowered"; "If resources are abundant and the business has a certain demand for resources, then the business priority can be appropriately increased." These rules reflect the intuitive relationship between resource status and business priority, while also taking into account the specific nature of the business's demand for resources.

[0114] For each rule, we further refine the description of resource status and business priority. For example, the description of "a business has high resource demand" can be quantified by the resource utilization rate of the business during normal operation. If a business's CPU utilization rate frequently exceeds 50% during normal operation, it is considered to have high CPU resource demand. This quantification makes fuzzy rules more operational and facilitates subsequent fuzzy reasoning.

[0115] Using the Mamdani inference algorithm, according to the membership degree of the input resource status fuzzy variables and combined with fuzzy rules, the activation intensity of the business priority fuzzy set is calculated to obtain the final business priority fuzzy result;

[0116] When specific resource status data is input, such as a CPU utilization rate of 80%, the previously defined membership function is used to calculate its membership in the "resource-constrained" fuzzy set (assuming it is 0.6). Furthermore, assuming the business's CPU demand is "high," Rule 1 indicates that the activation strength of the "low priority" business priority is 0.6. This calculation is repeated for all eligible rules to obtain the activation strength of each fuzzy set for the business priority.

[0117] In order to better determine the activation strength, S3.1.3 fuzzy reasoning uses the Mamdani reasoning algorithm to determine the activation strength based on the logical connectives in the rules by taking the minimum value;

[0118] The fuzzy output is calculated based on the activation strength. For example, using the maximum-minimum synthesis method, for the "high priority", "medium priority", and "low priority" fuzzy sets of business priorities, the activation strength of each fuzzy set is synthesized with the corresponding membership function to obtain a fuzzy output that represents the distribution of business priorities on each fuzzy set.

[0119] Convert clear input values ​​(such as specific resource status indicators such as CPU usage and memory occupancy) into membership of fuzzy sets. This is achieved through pre-defined membership functions. For example, for the input variable of CPU usage, we may define three fuzzy sets: "low load", "medium load" and "high load", and each fuzzy set has a corresponding membership function. If the actual CPU usage is 60%, the membership of the membership function calculation to the "medium load" fuzzy set may be 0.7, the membership to the "high load" fuzzy set may be 0.3, and the membership to the "low load" fuzzy set is 0;

[0120] Fuzzy rules are a key component of Mamdani reasoning. They are typically expressed in the form of "if...then..." and describe the relationship between input fuzzy variables and output fuzzy variables (such as task priority). For each fuzzy rule, its activation strength is calculated using the above method. Suppose there is another rule: "If CPU usage is 'medium load' and memory utilization is 'medium occupancy', then task priority is 'medium priority'." Its activation strength is calculated to be 0.5 (an assumed value). These activation strengths represent the degree to which the corresponding output fuzzy set (such as "low priority" and "medium priority" task priority fuzzy sets) is triggered.

[0121] The centroid method is used to defuzzify the fuzzy set and a definite priority value is obtained by calculating the centroid of the fuzzy output;

[0122] Assume that through fuzzy reasoning, it is determined that the business priority has a membership of 0.3 in the "high priority" fuzzy set, a membership of 0.5 in the "medium priority" fuzzy set, and a membership of 0.2 in the "low priority" fuzzy set. Using the center of gravity method, based on the definition of the business priority fuzzy set (e.g., "high priority" corresponds to the numerical interval [0.7, 1], "medium priority" corresponds to [0.4, 0.7], and "low priority" corresponds to [0, 0.4]), a specific priority value is calculated. For example, the calculation result may be a value between 0 and 1, which represents the business priority after dynamic adjustment based on the current resource status and business resource requirements. Based on this priority value, businesses are sorted and resources are allocated to achieve dynamic priority adjustment.

[0123] In order to continue resource regulation for priority policies and queue scheduling policies, S3 dynamically adjusts priorities and establishes a conflict resolution mechanism based on resource conflicts and waiting time conflicts to regulate resources for priority policies and queue scheduling policies.

[0124] When priority policies and queue scheduling policies conflict in resource allocation, for example, priority preemptive scheduling may cause low-priority tasks to be over-preempted, affecting their normal completion. In this case, a conflict resolution mechanism needs to be established. A resource preemption limit can be set, stipulating that high-priority tasks can only preempt a certain proportion (such as 50%) of the resources of low-priority tasks at most, to ensure that low-priority tasks can be completed within a certain time.

[0125] If a task waits too long in the queue due to its low priority, it may affect the overall efficiency of the business. You can set a maximum waiting time limit. When a low-priority task waits longer than this limit, its priority is appropriately increased or other strategies (such as allocating some idle resources to it) are adopted to ensure that it can be processed. This ensures that high-priority tasks are processed first while preventing low-priority tasks from waiting indefinitely.

[0126] The second object of the present invention is to provide a multi-cloud computing resource management system, including any one of the multi-cloud computing resource management methods described above, such as Figure 4 As shown, it includes a resource monitoring module 100, a policy formulation module 200 and a dynamic adjustment module 300;

[0127] The resource monitoring module 100 monitors the usage status of computing resources of each cloud platform through the monitoring service of the cloud platform;

[0128] The strategy formulation module 200 prioritizes tasks using the analytic hierarchy process according to their importance, timeliness, and cost-effectiveness;

[0129] The dynamic adjustment module 300 uses the computing power status indicator of the cloud computing resource as the input variable and the task priority value as the output variable, and uses a fuzzy algorithm to dynamically adjust the priority according to the status of the computing power resource.

[0130] In summary, the working principle of this solution is as follows:

[0131] In this multi-cloud computing resource management method and system, the policy formulation module 200 uses the hierarchical analysis method to prioritize tasks according to their importance, timeliness and cost-effectiveness, and adopts a computing power resource allocation strategy that is mainly based on priority and supplemented by queue algorithm scheduling. Computing power resources are allocated preferentially to tasks with high importance, thereby improving the utilization rate of computing power resources. At the same time, within the same priority level, with the queue algorithm as an aid, tasks obtain computing power resources in the order in which they enter the queue, thereby accelerating the use of computing power resources and ensuring the efficiency of computing power resource utilization. The resource monitoring module 100 uses the monitoring service of the cloud platform to monitor the usage status of the computing power resources of each cloud platform. The dynamic adjustment module 300 monitors the usage status of the computing power resources of the cloud platform according to the resource monitoring module 100, uses the computing power status indicator of the cloud computing resources as the input variable, and uses the task priority value as the output variable. It uses a fuzzy algorithm to dynamically adjust the priority determined by the policy formulation module 200 according to the status of the computing power resources, thereby ensuring that the priority strategy can adapt to the status of the computing power resources and ensure the rationality of computing power resource allocation.

[0132] 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 are merely preferred examples of the present invention and are not intended to limit the present invention. Various changes and improvements may be made to the present invention without departing from the spirit and scope of the present invention. Such changes and improvements fall within the scope of the present invention. The scope of protection claimed in the present invention is defined by the appended claims and their equivalents.

Claims

1. A multi-cloud computing resource management method, characterized by: The following steps are involved: S1. Use the cloud platform's monitoring service to monitor the usage status of computing resources on each cloud platform; S2. Prioritize tasks based on their importance, timeliness, and cost-effectiveness using the analytic hierarchy process. S3, using the computing power status indicator of cloud computing resources as the input variable and the task priority value as the output variable, dynamically adjust the priority according to the status of computing power resources using a fuzzy algorithm; S2 uses the hierarchical analysis method to prioritize tasks, and the steps are as follows: S2.1.

1. Construct a hierarchical model: Determine the priority level as the target level, the importance, timeliness, and cost-effectiveness of the task as the criterion level, and the tasks that need to be prioritized as the solution level; S2.1.

2. Construct judgment matrix: Use the scaling method to construct the judgment matrix of the criterion layer relative to the target layer and the judgment matrix of the solution layer relative to the criterion layer; S2.1.

3. Calculate the weight vector: Calculate the maximum eigenvalue of the judgment matrix and its corresponding eigenvector, normalize the eigenvector, and obtain the weight vector of each criterion in the criterion layer relative to the target layer; S2.1.

4. Consistency test: For each judgment matrix at the criterion level and the solution level, calculate the consistency index. Based on the order of the judgment matrix, find the average random consistency index, calculate the consistency ratio, and make a judgment on the judgment matrix. S3 dynamically adjusts the priority according to the status of computing resources, and the method and steps are as follows: S3.1.

1. Define fuzzy sets and membership functions: Define fuzzy sets for input variables and use trapezoidal membership functions to find the membership values ​​of each fuzzy set. S3.1.

2. Build a fuzzy rule base: Based on business needs and resource management experience, formulate fuzzy rules, and refine and quantify them; S3.1.3 Fuzzy reasoning: Using the Mamdani reasoning algorithm, based on the membership of the input resource status fuzzy variables and combined with fuzzy rules, the activation strength of the business priority fuzzy set is calculated to obtain the final business priority fuzzy result; S3.1.4 Defuzzification: Defuzzify the fuzzy set using the centroid method and obtain a definite priority value by calculating the centroid of the fuzzy output.

2. The multi-cloud computing resource management method according to claim 1, characterized in that: The step S2.1.3 calculates the weight vector and normalizes the feature vector, wherein the normalization formula is: ； in, is the weight vector A quantity, is the sequence number of the eigenvector, is the first feature vector vectors, is the order of the eigenvector, is the initial sequence number of the eigenvector, is the first feature vector vectors.

3. The multi-cloud computing resource management method according to claim 1, wherein: The formula for calculating the consistency index in S2.1.4 consistency test is: ； in, is the consistency index value, is the maximum eigenvalue of the eigenvector, is the order of the eigenvector.

4. The multi-cloud computing resource management method according to claim 1, wherein: When dividing priorities, S2 adopts a computing power resource allocation strategy that is based on priority and supplemented by queue algorithm scheduling. Within each priority queue, a first-come, first-served algorithm is adopted, and tasks obtain computing power resources in the order they enter the queue.

5. The multi-cloud computing resource management method according to claim 4, characterized in that: S3.1.1 defines fuzzy sets and membership functions, where the formula for the trapezoidal membership function is: ； in, is the membership function value, is the CPU usage, is the lower limit, is the end point of the ascending interval, is the starting point of the descending interval, As the upper limit.

6. The multi-cloud computing resource management method according to claim 1, wherein: The fuzzy reasoning in S3.1.3 utilizes the Mamdani reasoning algorithm and determines the activation strength by taking the minimum value according to the logical connectives in the rules.

7. The multi-cloud computing resource management method according to claim 1, wherein: After dynamically adjusting the priority, S3 establishes a conflict resolution mechanism based on resource conflicts and waiting time conflicts, and performs resource regulation on the priority strategy and queue scheduling strategy.

8. A multi-cloud computing resource management system, configured to implement the multi-cloud computing resource management method according to any one of claims 1 to 7, characterized in that: It includes a resource monitoring module (100), a policy formulation module (200) and a dynamic adjustment module (300); The resource monitoring module (100) monitors the usage status of computing resources of each cloud platform through the monitoring service of the cloud platform; The strategy formulation module (200) prioritizes tasks using the analytic hierarchy process according to their importance, timeliness, and cost-effectiveness; The dynamic adjustment module (300) uses the computing power status indicator of the cloud computing resources as an input variable and the task priority value as an output variable, and uses a fuzzy algorithm to dynamically adjust the priority according to the status of the computing power resources.

Images