AU2017100412A4 - Cloud task scheduling algorithm based on user satisfaction - Google Patents
Cloud task scheduling algorithm based on user satisfaction Download PDFInfo
- Publication number
- AU2017100412A4 AU2017100412A4 AU2017100412A AU2017100412A AU2017100412A4 AU 2017100412 A4 AU2017100412 A4 AU 2017100412A4 AU 2017100412 A AU2017100412 A AU 2017100412A AU 2017100412 A AU2017100412 A AU 2017100412A AU 2017100412 A4 AU2017100412 A4 AU 2017100412A4
- Authority
- AU
- Australia
- Prior art keywords
- task
- user
- cloud
- virtual machine
- costs
- Prior art date
- Legal status (The legal status is an assumption and is not a legal conclusion. Google has not performed a legal analysis and makes no representation as to the accuracy of the status listed.)
- Expired
Links
Landscapes
- Management, Administration, Business Operations System, And Electronic Commerce (AREA)
Abstract
Abstract A cloud task scheduling algorithm based on user satisfaction, the algorithm mainly comprising several stages including normalizing virtual machine and cloud task parameters; calculating Euclidean distance; selecting resources; updating Euclidean distance; calculating user satisfaction of a task; and calculating the resource usage costs of a single cloud task and the total costs of a system after execution of all tasks. The algorithm set forth in the present invention distributes tasks to the most suitable resources from the perspective of the user, thus better satisfying user requirements for various aspects including CPU, completion time, and bandwidth, and simultaneously effectively reducing the costs of resource usage by the user. In cloud computing, in which users are concerned with whether the costs paid reasonably match the quality of service obtained, user requirements are highly satisfied. Compared to the prior art, the present invention provides an effective strategy for users to acquire the best quality of service.
Description
CLOUD TASK SCHEDULING ALGORITHM BASED ON USER SATISFACTION
[0001] The present application is a divisional application from International Patent Application No. PCT/CN2015/089512 filed on 14 September 2015, the entire disclosure of which is incorporated herein by reference.
TECHNICAL FIELD
[0002] The present invention relates to a cloud task scheduling algorithm. BACKGROUND
[0003] Cloud computing is a comprehensive development of parallel computing, distributed computing and grid computing, which is a commercial computing model, can distribute tasks that need to be completed by high-performance computers to resource pools of a large amount of cheap computing mechanisms and make various application system acquire computing capability, storage space and information service as required. However, while implementing these services, it needs to consider one question, that is, different users have different demands to the usage of cloud computing resources, such as CPU, memory, completion time, bandwidth, usage fee and so on, and how to make the user obtain better quality of service with an effective policy. The cloud task scheduling algorithm is one of the approaches to solve the above problems.
[0004] The traditional task scheduling algorithm pays attention to the efficiency of the server, such as the task scheduling method taking the optimal completion time as the target, although it has better completion efficiency, it may cause the utilization of the resources with powerful computing capability to be high and make the system load unbalanced; the load balancing algorithm can provide an effective method to expand the bandwidth of the network devices and servers, increase the throughput, strengthen the network data processing capability, improve network flexibility and availability, but the traditional task scheduling algorithm ignores the quality of service demand of user tasks and cannot perform on-demand allocation of resources.
[0005] The discussion of the background to the invention included herein including reference to documents, acts, materials, devices, articles and the like is included to explain the context of the present invention. This is not to be taken as an admission or a suggestion that any of the material referred to was published, known or part of the common general knowledge in Australia or in any other country as at the priority date of any of the claims.
SUMMARY
[0006] Many classic scheduling algorithms are formed during the researches of the cloud task scheduling technology, which, from the perspective of cloud resource providers, consider parameters such as optimal completion time, lowest power consumption, node load balancing, resource availability and reliability, system utilization and so on, while the algorithm proposed in the present invention, from the perspective of the user, considers task completion time, costs, matching degree of costs and quality of service, user satisfaction of resource usage and so on and at the same time considers the load balancing of the system [0007] Cloud computing uses virtualization technology to encapsulate the underlying physical resources in the form of virtual machine and make the virtual machine execute the task of the user. The scheduling problem is to map the task of the user and the resources under the principle of certain optimization targets, and cloud computing simplifies the matching of task and resources and make the resources required by the task to be embodied in the form of one virtual machine, and thus the search of resources is translated into the search of a certain virtual machine.
[0008] According to an aspect of the present invention, there is provided a cloud task scheduling algorithm based on user satisfaction, comprising the following steps: step 1, normalizing resource parameters the performance parameters of a task and a virtual machine are all normalized to interval [0, 1], let the set Xq = {Xq, ... , Xtj}j be the number of performance parameters, be the set of the same kind of performance parameters of the virtual machine, the normalization value thereof is:
(5) where i the number of tasks, j is the number of performance parameters, curXjj is the current performance value, minXij is the minimum value of the same performance parameter set, and lnaxXy is the maximum value of the same performance parameter set; step 2, calculating Euclidean distance the parameter vector of the virtual machine after parameter normalization is X= {Xi, X2, X3}, the parameter vector of the cloud task is Υ={Υι, Y2, Y3}; considering three performance parameters of CPU, memory and bandwidth, a weight vector W= {Wi, W2, W3} is obtained according to the type of the cloud task, then the calculation formula of the Euclidean distance is :
(6) where Xj represents the normalized parameter value of the jth resource in the ith virtual machine; Yj represents the expected value of the jth kind of resource by the task; and Wj represents the weight of the jth kind of resource; step 3, selecting resources each task selects a virtual machine with the minimum Euclidean distance to execute the task, a method of controlling an idle virtual machine is used to perform load balancing, each virtual machine maintains one Euclidean distance table, when a certain task is successfully allocated to a certain virtual machine for execution, the Euclidean distance table needs to be updated to increase the Euclidean distance between a certain kind of resources and the virtual machine, and the update formula is:
(7) step 4, calculating user satislaction after the task is completed, considering the completion situation of each task, including the completion time of the task and the user satislaction of each task and the comprehensive satislaction of all tasks; and the user satislaction of a single task is:
(8) where s; is the user satislaction of task i; Wj is the weight of the jth performance parameter; actj is the actual consumption of the ith performance parameter by the task; and expj is the user expected value of the ith performance by the cloud task; when ¢) *=* isd 5, it is deemed that is highly satisfied with the resource allocation of cloud task i; when b<;si: ¢. l.? ft is deemed that the user is relatively satisfied with the resource allocation of cloud task i; when |sj|> 1, it is deemed that the user is unsatisfied with the resource allocation of cloud task i; and when the value of |si| is very big, it is deemed that the user is very unsatisfied with the resource allocation of cloud task i; the comprehensive user satislaction of all cloud task is:
(9) where Sj is the user satislaction of the ith task; and t is the number of all cloud tasks; step 5, calculating the costs after each task is executed, the costs of executing the task are calculated; and the virtual machine charges the resources according to the unit, and all costs cost; of task consumption are:
(10) where Pj is the number of resources, and C is the unit resource cost; after all tasks are executed, the total costs of the system are:
(10 where cosh is the costs of the ith task; and t is the number of all cloud tasks.
[0009] In order to realize the scheduling algorithm, the present invention first describes the cloud task, virtual machine and task classification.
[0010] · The virtual machine is expressed with a septuple; [0011]
O) [0012] The septuple respectively represents the ID of the virtual machine, the number of CPUs, the memory, the bandwidth and the unit prices of the CPU, memory and bandwidth.
[0013] · The cloud task is expressed with an eightuple: [0014]
(2) [0015] The eightuple respectively represents the ID of the cloud task, the type, the task size, the expected number of CPUs, the expected memory, the expected bandwidth, the user satisfaction of the task and the costs of task execution.
[0016] · Cloud task type: the present invention mainly considers the following QoS parameters: [0017] a) completion time: for a cloud task with real-time performance demand, it needs to be completed within a short time as much as possible, and the corresponding two resources thereof are CPU and execution speed.
[0018] b) bandwidth: when the cloud task has high requirements to communication bandwidth, such as multimedia stream requirements, it requires to preferentially consider the bandwidth requirements.
[0019] c) memory: when the cloud task has high requirements to the memory, it requires to preferentially consider the memory requirements.
[0020] With respect to different cloud task requirements, the user satisfaction is measured according to different QoS parameters, and for this end, the present invention designs a weight problem, which represents the value recognition of different resources by the cloud platform, and a weight vector is used to adjust and select the performance ratio parameter of the virtual machine resource so as to better improve the user satisfaction of resource usage. For example, for a cloud task sensitive to real-time performance or time, it is desired to complete the task with the minimum completion time, and thus resources with powerful computing capability are needed, so the CPU is assigned a large weight. Let the weight vector of the ith kind of task be expressed as: [0021]
(3) [0022] where eii, eii, and ei3 respectively correspond to the weights of CPU, memory, and bandwidth, and [0023]
[0024] The concept of the cloud task scheduling algorithm based on user satisfaction is as follows: for a pile of given cloud tasks, selecting a cloud task with the highest priority at present in the system, normalizing the parameters thereof, calculating Euclidean distance of this normalized cloud task and all virtual machines in the system (the parameters of all virtual machines have been normalized in advance), assigning different weights to different performance parameters according to the type of the cloud task and the value recognition of each parameter by the system, and binding the current cloud task to the virtual machine with the minimum Euclidean distance value. In order to ensure the complete time of all tasks while balancing the load of the system, when a virtual machine is bound with a cloud task, the Euclidean distance list thereof is updated, and the possibility that the next cloud task is allocated to the same virtual machine is lowered. After the execution of the current task is completed, the user satisfaction and resource usage costs thereof are calculated, and after the execution of all tasks are completed, the comprehensive satisfaction of all cloud tasks and the total costs of the system are calculated.
[0025] The technical solution to be protected by the present invention is expressed as follows.
[0026] A cloud task scheduling algorithm based on user satisfaction, comprising the following steps.
[0027] Step 1, normalizing resource parameters [0028] the performance parameters of a task and a virtual machine are all normalized to interval [0, 1], let the set Xy={Xij, ..., Xtj}j be the number of performance parameters, be the set of the same kind of performance parameters of the virtual machine, the normalization value thereof is: [0029]
(5) [0030] where i the number of tasks, j is the number of performance parameters, curXy is the current performance value, minXy is the minimum value of the same performance parameter set, and maxXij is the maximum value of the same performance parameter set; [0031 ] Step 2, calculating Euclidean distance [0032] the parameter vector of the virtual machine after parameter normalization is Χ={Χι, X2, X3}, the parameter vector of the cloud task is Υ={Υι, Y2, Y3}. Considering three performance parameters of CPU, memory and bandwidth, a weight vector W= {Wl, W2, W3} is obtained according to the type of the cloud task. Then the calculation formula of the Euclidean distance is: [0033]
[0034] where Xj represents the normalized parameter value of the jth resource in the ith virtual machine; Yj represents the expected value of the jth kind of resource by the task; and Wj represents the weight of the jth kind of resource.
[0035] Step 3, selecting resources [0036] each task selects a virtual machine with the minimum Euclidean distance to execute the task, a method of controlling an idle virtual machine is used to perform load balancing, each virtual machine maintains one Euclidean distance table, when a certain task is successfully allocated to a certain virtual machine for execution, the Euclidean distance table needs to be updated to increase the Euclidean distance between a certain kind of resources and the virtual machine, and the update formula is: [0037]
(7) [0038] Step 4, calculating user satisfaction [0039] after the task is completed, considering the completion situation of each task, including the completion time of the task and the user satislaction of each task and the comprehensive satislaction of all tasks is: The user satislaction of a single task is: [0040]
[0041] where Sj is the user satisfaction of task i; Wj is the weight of the jth performance parameter; actj is the actual consumption of the ith performance parameter by the task; and expj is the user expected value of the ith performance by the cloud task.
[0042] when 0 Sv ls<' ^°·5, it is deemed that is highly satisfied with the resource allocation of cloud task i; when 0· 5<!s(t =¾ 1, it is deemed that the user is relatively satisfied with the resource allocation of cloud task i; when |si| > 1, it is deemed that the user is unsatisfied with the resource allocation of cloud task i; and when the value of |Sj| is very big, it is deemed that the user is very unsatisfied with the resource allocation of cloud task i [0043] The comprehensive user satisfaction of all cloud task is: [0044]
[0045] where s; is the user satisfaction of the ith task; and t is the number of all cloud tasks. In the cloud computing system, the smaller the value of S, the higher the satisfaction of all users of the system to the service provided by the cloud computing service provider.
[0046] Step 5, calculating the costs [0047] after each task is executed, the costs of executing the task are calculated. The virtual machine charges the resources according to the unit, and all costs costj of task consumption are: [0048]
(K)) [0049] where Pj is the number of resources, and C is the unit resource cost.
[0050] after all tasks are executed, the total costs of the system are: [0051]
[0052] where costj is the costs of the ith task; and t is the number of all cloud tasks. In the cloud computing system, the smaller the value of C, the lower the costs for the system to execute all cloud tasks.
[0053] The algorithm set forth in the present invention distributes tasks to the most suitable resources from the perspective of the user, thus better satisfying user requirements for various aspects including CPU, completion time, and bandwidth, and simultaneously effectively reducing the costs of resource usage by the user. In cloud computing, in which users are concerned with whether the costs paid reasonably match the quality of service obtained, user requirements are highly satisfied. Compared to the prior art, the present invention provides an effective strategy for users to acquire the best quality of service.
BRIEF DESCRIPTION OF THE DRAWINGS
[0054] Fig. 1 is a flowchart of a cloud task scheduling algorithm based on user satisfactioa [0055] Fig. 2 is a simulation result of a cloud task scheduling algorithm based on user satisfaction.
[0056] Fig. 3 is a simulation result of the optimal completion time scheduling algorithm [0057] Fig. 4 is the comparison of task completion time.
[0058] Fig. 5 is the comparison of task user satisfaction.
[0059] Fig. 6 of the comparison of task execution cost.
DETAILED DESCRIPTION
[0060] In cloud computing, users are concerned with whether the costs paid reasonably match the quality of service obtained rather than the performance of the system, and in the consideration of making the user demand obtain higher satis faction, the present invention proposes a cloud task scheduling algorithm based on user satisfaction. The algorithm distributes tasks to the most suitable resources from the perspective of the user, thus better satisfying user requirements for various aspects including CPU, completion time, and bandwidth, and simultaneously effectively reducing the costs of resource usage by the user. At last, the present invention uses CloudSim platform to simulate the algorithm and compares the algorithm and the currently commonly used optimal completion time scheduling algorithm to verily the effectiveness of the algorithm in respect of user satisfaction and resource usage cost.
[0061] The present invention will be described further in conjunction with the algorithm flowcharts of the accompanying drawings hereinafter.
[0062] Fig. 1 is an algorithm flowchart of the present inventioa As shown in Fig. 1, the algorithm mainly comprises several stages including normalizing virtual machine and cloud task parameters; calculating Euclidean distance; selecting resources; updating Euclidean distance; calculating user satisfaction of a task; and calculating the resource usage costs of a single cloud task and the total costs of a system after execution of all tasks.
[0063] Step 1, normalizing resource parameters. In order to calculate the Euclidean distance more conveniently, in the present invention, the performance paramters of a task and a virtual machine are all normalized to interval [0, 1], let the set X;j = {Xjj, .. . , XtJ}j be the number of performance parameters, be the set of the same kind of performance parameters of the virtual machine, the normalization value thereof is: [0064] GXij = (curXij-nrinXij)/(maxXij-minXij) (5) [0065] where i the number of tasks, j is the number of performance parameters, curXij is the current performance value, minXy is the minimum value of the same performance parameter set, and maxXy is the maximum value of the same performance parameter set; [0066] Step 2, calculating Euclidean distance. The parameter vector of the virtual machine after parameter normalization is Χ={Χι, X2, X3}, the parameter vector of the cloud task is Υ={Υι, Y2, Y3}. The present invention mainly consideres three performance parameters of CPU, memory and bandwidth, a weight vector W = {Wl, W2, W3} is obtained according to the type of the cloud task. Then the calculation formula of the Euclidean distance is: [0067]
(6) [0068] where Xj represents the normalized parameter value of the jth resource in the ith virtual machine; Yj represents the expected value of the jth kind of resource by the task; and Wj represents the weight of the jth kind of resource.
[0069] The smaller the Euclidean distance between the task and the virtual machine, the better the user satisfaction that can be obtained by the task selecting this virtual machine, and at the same time, the better the value recognition demand of different resources by the cloud computing providers can be satisfied.
[0070] Step 3, selecting resources. Each task selects a virtual machine with the minimum Euclidean distance to execute the task, but considering the load balancing problem of the system, avoiding that all tasks are allocated to a powerful virtual machine simultaneously and in order to satisfy the optimization of task completion time, a method of controlling an idle virtual machine is used to perform load balancing, each virtual machine maintains one Euclidean distance table, when a certain task is successfully allocated to a certain virtual machine for execution, the Euclidean distance table needs to be updated to increase the Euclidean distance between a certain kind of resources and the virtual machine, and the update formula is: [0071] V ™ MfU/n), n is the number of virtual machines (7) [0072] The resource selection process is as follows: [0073] l.Fori=ltom [0074] 2. Select VM by parameter of tj to VlS/fi; (all tasks with the same performance fonn a vector) [0075] 3. For i=l to t [0076] 4. Forj = lto3 [0077] 5. Compute GXij (parameter normalization); [0078] 6. For i= 1 to t [0079] 7. Calculating the Euclidean distance Dj between the task and the virtual machine; [0080] 8. Select min Dj; [0081] 9. Bind t; to VM which has the min Dj; [0082] 10. End; [0083] Step 4, calculating user satislaction. After the task is completed, consider the completion situation of each task. It includes the completion time of the task and the user satisfaction of each task and the comprehensive satisfaction of all tasks. The user satislaction of a single task is: [0084]
^ [0085] where Sj is the user satisfaction of task i; Wj is the weight of the jth performance parameter; actj is the actual consumption of the ith performance parameter by the task; and expj is the user expected value of the ith performance by the cloud task.
[0086] when 0 js, j A 0. 3, it is deemed that is highly satisfied with the resource allocation of cloud task i; when 0. 5<;sJ A-1, it is deemed that the user is relatively satisfied with the resource allocation of cloud task i; when |sj|>l, it is deemed that the user is unsatisfied with the resource allocation of cloud task i; and when the value of |sj| is very big, it is deemed that the user is very unsatisfied with the resource allocation of cloud task i.
[0087] The comprehensive user satislaction of all cloud task is: [0088]
^ [0089] where Sj is the user satislaction of the ith task; and t is the number of all cloud tasks. In the cloud computing system, the smaller the value of S, the higher the satisfaction of all users of the system to the service provided by the cloud computing service provider.
[0090] Step 5, calculating the costs. After each task is executed, the costs of executing the task need to be calculated. The virtual machine charges the resources according to the unit, and thus all costs cost; of task consumption are: [0091]
U0) [0092] where Pj is the number of resources, and C is the unit resource cost.
[0093] After all tasks are executed, the total costs of the system are: [0094]
[0095] where cosh is the costs of the ith task; and t is the number of all cloud tasks. In the cloud computing system, the smaller the value of C, the lower the costs for the system to execute all cloud tasks.
[0096] Step 6, algorithm simulation. The cloud environment simulated in the present invention consists of 5 virtual machine nodes, a resource proxy is established on the node, and 10 simulated user tasks are established. Mainly the following aspects need to be observed in simulation: the completion time of all cloud tasks, the user satisfaction of a single cloud task, the comprehensive satisfaction of all tasks, the execution costs of a single task, and the costs for the system to execute all cloud tasks, and the unit prices of the resources in the simulation are all 1 (which can be set autonomously during practical use). Fig. 2 is a simulation result of a cloud task scheduling algorithm based on user satisfaction. Fig. 3 is a simulation result of the optimal completion time scheduling algorithm [0097] It can be seen from Fig. 4 that in the optimal completion time algorithm, the finally completed task is task 3, the total completion time is 334. 62ms, and in the cloud task scheduling algorithm based on user satisfaction, the last completed task is task 7 and the total completion time is 389. 92ms. The scheduling method in the present invention is inferior to the classic optimal time scheduling algorithm in terms of completion time but close.
[0095] It can be seen from Fig. 5 that the satisfaction and total user satisfaction of most tasks in the cloud task scheduling algorithm based on user satisfaction are superior to the optimal completion time scheduling algorithm. This result embodies the effectiveness of the algorithm designed by the present invention.
[0098] It can be seen from Fig. 6 that the execution costs of most tasks in the cloud task scheduling algorithm based on user satisfaction are lower than the optimal completion time scheduling algorithm, and the total system costs of the cloud task scheduling algorithm based on user satisfaction is 25587 units and the total system costs of the optimal completion time scheduling algorithm is 30432 units. This result shows that the cloud task scheduling algorithm based on user satisfaction is advantageous in terms of saving cost.
[0099] It is analyzed from the above simulation result that compared to the optimal completion time scheduling algorithm, the cloud task scheduling algorithm based on user satisfaction can better satisfy different user demands, improve user satisfaction and can effectively save execution costs while ensuring good task completion time.
[00100] The innovative points of the present invention are as follows.
[00101] 1) the cloud task scheduling algorithm is designed from the perspective of user satisfaction to cloud computing resources.
[00102] 2) the scheduling algorithm can better satisfy different user demands and can obtain better user satisfaction and comprehensive system satisfaction and can effectively save the execution costs of the system by means of a dynamic task allocation policy while ensuring the condition of task completion time.
[00103] Where the terms "comprise", "comprises", "comprised" or "comprising" are used in this specification (including the claims) they are to be interpreted as specifying the presence of the stated features, integers, steps or components, but not precluding the presence of one or more other features, integers, steps or components, or group thereof
Claims (2)
- The claims defining the invention are as follows:
- 1. A cloud task scheduling algorithm based on user satisfaction, comprising the following steps: step 1, normalizing resource parameters the performance parameters of a task and a virtual machine are all normalized to interval [0, 1], let the set Xy = {Xij, ... , Xtj}j be the number of performance parameters, be the set of the same kind of performance parameters of the virtual machine, the normalization value thereof is:(5) where i the number of tasks, j is the number of performance parameters, curXy is the current performance value, minXy is the minimum value of the same performance parameter set, and maxXy is the maximum value of the same performance parameter set; step 2, calculating Euclidean distance the parameter vector of the virtual machine after parameter normalization is X= {Xi, X2, X3}, the parameter vector of the cloud task is Y= {Y1, Y2, Y3}; considering three performance parameters of CPU, memory and bandwidth, a weight vector W= {Wi, W2, W3} is obtained according to the type of the cloud task, then the calculation formula of the Euclidean distance is :«>) where Xj represents the normalized parameter value of the jth resource in the ith virtual machine; Yj represents the expected value of the jth kind of resource by the task; and Wj represents the weight of the jth kind of resource; step 3, selecting resources each task selects a virtual machine with the minimum Euclidean distance to execute the task, a method of controlling an idle virtual machine is used to perform load balancing, each virtual machine maintains one Euclidean distance table, when a certain task is successfully allocated to a certain virtual machine for execution, the Euclidean distance table needs to be updated to increase the Euclidean distance between a certain kind of resources and the virtual machine, and the update formula is: Di'=Dj(l+l/n), n is the number of virtual machines (7) step 4, calculating user satisiaction after the task is completed, considering the completion situation of each task, including the completion time of the task and the user satisiaction of each task and the comprehensive satisiaction of all tasks; and the user satisiaction of a single task is:(8) where s; is the user satisiaction of task i; Wj is the weight of the jth performance parameter; actj is the actual consumption of the ith performance parameter by the task; and expj is the user expected value of the ith performance by the cloud task; when 0 < iiji ^0. 5, it is deemed that is highly satisfied with the resource allocation of cloud task i; when iis s; *·, it is deemed that the user is relatively satisfied with the resource allocation of cloud task i; when |si|>l, it is deemed that the user is unsatisfied with the resource allocation of cloud task i; and when the value of |si| is very big, it is deemed that the user is very unsatisfied with the resource allocation of cloud task i; the comprehensive user satisfaction of all cloud task is:(9) where Sj is the user satisiaction of the ith task; and t is the number of all cloud tasks; step 5, calculating the costs after each task is executed, the costs of executing the task are calculated; and the virtual machine charges the resources according to the unit, and all costs costj of task consumption are:(10) where Pi is the number of resources, and C is the unit resource cost; after all tasks are executed, the total costs of the system are:00 where cost; is the costs of the ith task; and t is the number of all cloud tasks.
Priority Applications (1)
| Application Number | Priority Date | Filing Date | Title |
|---|---|---|---|
| AU2017100412A AU2017100412A4 (en) | 2014-09-23 | 2017-04-10 | Cloud task scheduling algorithm based on user satisfaction |
Applications Claiming Priority (3)
| Application Number | Priority Date | Filing Date | Title |
|---|---|---|---|
| CN201410491004.4 | 2014-09-23 | ||
| PCT/CN2015/089512 WO2016045515A1 (en) | 2014-09-23 | 2015-09-14 | Cloud task scheduling algorithm based on user satisfaction |
| AU2017100412A AU2017100412A4 (en) | 2014-09-23 | 2017-04-10 | Cloud task scheduling algorithm based on user satisfaction |
Related Parent Applications (1)
| Application Number | Title | Priority Date | Filing Date |
|---|---|---|---|
| PCT/CN2015/089512 Division WO2016045515A1 (en) | 2014-09-23 | 2015-09-14 | Cloud task scheduling algorithm based on user satisfaction |
Publications (1)
| Publication Number | Publication Date |
|---|---|
| AU2017100412A4 true AU2017100412A4 (en) | 2017-05-18 |
Family
ID=58700175
Family Applications (1)
| Application Number | Title | Priority Date | Filing Date |
|---|---|---|---|
| AU2017100412A Expired AU2017100412A4 (en) | 2014-09-23 | 2017-04-10 | Cloud task scheduling algorithm based on user satisfaction |
Country Status (1)
| Country | Link |
|---|---|
| AU (1) | AU2017100412A4 (en) |
Cited By (2)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN111932106A (en) * | 2020-08-05 | 2020-11-13 | 山东科技大学 | Effective and practical cloud manufacturing task and service resource matching method |
| CN113220431A (en) * | 2021-04-29 | 2021-08-06 | 西安易联趣网络科技有限责任公司 | Cross-cloud distributed data task scheduling method, device and storage medium |
-
2017
- 2017-04-10 AU AU2017100412A patent/AU2017100412A4/en not_active Expired
Cited By (4)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN111932106A (en) * | 2020-08-05 | 2020-11-13 | 山东科技大学 | Effective and practical cloud manufacturing task and service resource matching method |
| CN111932106B (en) * | 2020-08-05 | 2022-06-28 | 山东科技大学 | Effective and practical cloud manufacturing task and service resource matching method |
| CN113220431A (en) * | 2021-04-29 | 2021-08-06 | 西安易联趣网络科技有限责任公司 | Cross-cloud distributed data task scheduling method, device and storage medium |
| CN113220431B (en) * | 2021-04-29 | 2023-11-03 | 西安易联趣网络科技有限责任公司 | Cross-cloud distributed data task scheduling method, device and storage medium |
Similar Documents
| Publication | Publication Date | Title |
|---|---|---|
| Priya et al. | Resource scheduling algorithm with load balancing for cloud service provisioning | |
| Xu et al. | A survey on load balancing algorithms for virtual machines placement in cloud computing | |
| Mao et al. | Max–min task scheduling algorithm for load balance in cloud computing | |
| WO2016045515A1 (en) | Cloud task scheduling algorithm based on user satisfaction | |
| CN107291536B (en) | Application task flow scheduling method in cloud computing environment | |
| Liu et al. | A survey on virtual machine scheduling in cloud computing | |
| Rejiba et al. | Custom scheduling in Kubernetes: A survey on common problems and solution approaches | |
| Lagwal et al. | Load balancing in cloud computing using genetic algorithm | |
| CN105260230A (en) | Resource scheduling method for data center virtual machine based on segmented service level agreement | |
| CN104881322A (en) | Method and device for dispatching cluster resource based on packing model | |
| Singh et al. | Survey on various load balancing techniques in cloud computing | |
| Sharma et al. | An improved task allocation strategy in cloud using modified k-means clustering technique | |
| Zhou et al. | Strategy optimization of resource scheduling based on cluster rendering | |
| AU2017100412A4 (en) | Cloud task scheduling algorithm based on user satisfaction | |
| Kumbhare et al. | Exploiting application dynamism and cloud elasticity for continuous dataflows | |
| CN111159859B (en) | Cloud container cluster deployment method and system | |
| Ge et al. | Cloud computing task scheduling strategy based on improved differential evolution algorithm | |
| de Souza Toniolli et al. | Resource allocation for multiple workflows in cloud-fog computing systems | |
| CN106502790A (en) | A kind of task distribution optimization method based on data distribution | |
| Tamilarasu et al. | Quality of service aware improved coati optimization algorithm for efficient task scheduling in cloud computing environment | |
| CN107070965A (en) | A kind of Multi-workflow resource provision method virtualized under container resource | |
| Jiang et al. | A cloud-agnostic framework to enable cost-aware scheduling of applications in a multi-cloud environment | |
| Jayswal | Efficient task allocation for cloud using bat algorithm | |
| CN109298932A (en) | Resource regulating method, scheduler and system based on OpenFlow | |
| Goswami et al. | Deadline stringency based job scheduling in computational grid environment |
Legal Events
| Date | Code | Title | Description |
|---|---|---|---|
| FGI | Letters patent sealed or granted (innovation patent) | ||
| MK22 | Patent ceased section 143a(d), or expired - non payment of renewal fee or expiry |