CN112559135A - QoS-based container cloud resource scheduling method - Google Patents
QoS-based container cloud resource scheduling method Download PDFInfo
- Publication number
- CN112559135A CN112559135A CN202011545634.7A CN202011545634A CN112559135A CN 112559135 A CN112559135 A CN 112559135A CN 202011545634 A CN202011545634 A CN 202011545634A CN 112559135 A CN112559135 A CN 112559135A
- Authority
- CN
- China
- Prior art keywords
- node
- resource
- container
- qos
- nodes
- 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.)
- Granted
Links
- 238000000034 method Methods 0.000 title claims abstract description 23
- 238000012216 screening Methods 0.000 claims abstract description 10
- 239000003016 pheromone Substances 0.000 claims description 10
- 241000257303 Hymenoptera Species 0.000 claims description 9
- 238000013468 resource allocation Methods 0.000 claims description 4
- 238000012546 transfer Methods 0.000 claims description 4
- 238000004364 calculation method Methods 0.000 claims description 3
- 238000013507 mapping Methods 0.000 claims description 3
- 238000013210 evaluation model Methods 0.000 claims description 2
- 230000007704 transition Effects 0.000 claims description 2
- 230000001174 ascending effect Effects 0.000 claims 1
- 239000011159 matrix material Substances 0.000 description 7
- 230000008569 process Effects 0.000 description 6
- 238000011161 development Methods 0.000 description 4
- 230000018109 developmental process Effects 0.000 description 4
- 238000010276 construction Methods 0.000 description 3
- 238000005516 engineering process Methods 0.000 description 3
- 238000010606 normalization Methods 0.000 description 3
- 238000005457 optimization Methods 0.000 description 3
- 238000012423 maintenance Methods 0.000 description 2
- 230000004044 response Effects 0.000 description 2
- 230000004075 alteration Effects 0.000 description 1
- 230000009286 beneficial effect Effects 0.000 description 1
- 238000004891 communication Methods 0.000 description 1
- 238000010586 diagram Methods 0.000 description 1
- 238000011156 evaluation Methods 0.000 description 1
- 230000010354 integration Effects 0.000 description 1
- 230000003993 interaction Effects 0.000 description 1
- 238000004519 manufacturing process Methods 0.000 description 1
- 230000007246 mechanism Effects 0.000 description 1
- 238000012986 modification Methods 0.000 description 1
- 230000004048 modification Effects 0.000 description 1
- 238000012544 monitoring process Methods 0.000 description 1
- 238000007781 pre-processing Methods 0.000 description 1
- 238000012545 processing Methods 0.000 description 1
- 230000011218 segmentation Effects 0.000 description 1
- 238000012163 sequencing technique Methods 0.000 description 1
- 230000003068 static effect Effects 0.000 description 1
- 238000006467 substitution reaction Methods 0.000 description 1
- 238000012360 testing method Methods 0.000 description 1
- 239000002699 waste material Substances 0.000 description 1
Images
Classifications
-
- G—PHYSICS
- G06—COMPUTING; CALCULATING OR COUNTING
- G06F—ELECTRIC DIGITAL DATA PROCESSING
- G06F9/00—Arrangements for program control, e.g. control units
- G06F9/06—Arrangements for program control, e.g. control units using stored programs, i.e. using an internal store of processing equipment to receive or retain programs
- G06F9/44—Arrangements for executing specific programs
- G06F9/455—Emulation; Interpretation; Software simulation, e.g. virtualisation or emulation of application or operating system execution engines
- G06F9/45533—Hypervisors; Virtual machine monitors
- G06F9/45558—Hypervisor-specific management and integration aspects
-
- G—PHYSICS
- G06—COMPUTING; CALCULATING OR COUNTING
- G06F—ELECTRIC DIGITAL DATA PROCESSING
- G06F9/00—Arrangements for program control, e.g. control units
- G06F9/06—Arrangements for program control, e.g. control units using stored programs, i.e. using an internal store of processing equipment to receive or retain programs
- G06F9/46—Multiprogramming arrangements
- G06F9/48—Program initiating; Program switching, e.g. by interrupt
- G06F9/4806—Task transfer initiation or dispatching
- G06F9/4843—Task transfer initiation or dispatching by program, e.g. task dispatcher, supervisor, operating system
- G06F9/4881—Scheduling strategies for dispatcher, e.g. round robin, multi-level priority queues
-
- G—PHYSICS
- G06—COMPUTING; CALCULATING OR COUNTING
- G06F—ELECTRIC DIGITAL DATA PROCESSING
- G06F9/00—Arrangements for program control, e.g. control units
- G06F9/06—Arrangements for program control, e.g. control units using stored programs, i.e. using an internal store of processing equipment to receive or retain programs
- G06F9/46—Multiprogramming arrangements
- G06F9/50—Allocation of resources, e.g. of the central processing unit [CPU]
- G06F9/5061—Partitioning or combining of resources
- G06F9/5072—Grid computing
-
- G—PHYSICS
- G06—COMPUTING; CALCULATING OR COUNTING
- G06F—ELECTRIC DIGITAL DATA PROCESSING
- G06F9/00—Arrangements for program control, e.g. control units
- G06F9/06—Arrangements for program control, e.g. control units using stored programs, i.e. using an internal store of processing equipment to receive or retain programs
- G06F9/46—Multiprogramming arrangements
- G06F9/50—Allocation of resources, e.g. of the central processing unit [CPU]
- G06F9/5061—Partitioning or combining of resources
- G06F9/5077—Logical partitioning of resources; Management or configuration of virtualized resources
-
- G—PHYSICS
- G06—COMPUTING; CALCULATING OR COUNTING
- G06N—COMPUTING ARRANGEMENTS BASED ON SPECIFIC COMPUTATIONAL MODELS
- G06N3/00—Computing arrangements based on biological models
- G06N3/004—Artificial life, i.e. computing arrangements simulating life
- G06N3/006—Artificial life, i.e. computing arrangements simulating life based on simulated virtual individual or collective life forms, e.g. social simulations or particle swarm optimisation [PSO]
-
- G—PHYSICS
- G06—COMPUTING; CALCULATING OR COUNTING
- G06F—ELECTRIC DIGITAL DATA PROCESSING
- G06F9/00—Arrangements for program control, e.g. control units
- G06F9/06—Arrangements for program control, e.g. control units using stored programs, i.e. using an internal store of processing equipment to receive or retain programs
- G06F9/44—Arrangements for executing specific programs
- G06F9/455—Emulation; Interpretation; Software simulation, e.g. virtualisation or emulation of application or operating system execution engines
- G06F9/45533—Hypervisors; Virtual machine monitors
- G06F9/45558—Hypervisor-specific management and integration aspects
- G06F2009/4557—Distribution of virtual machine instances; Migration and load balancing
-
- G—PHYSICS
- G06—COMPUTING; CALCULATING OR COUNTING
- G06F—ELECTRIC DIGITAL DATA PROCESSING
- G06F9/00—Arrangements for program control, e.g. control units
- G06F9/06—Arrangements for program control, e.g. control units using stored programs, i.e. using an internal store of processing equipment to receive or retain programs
- G06F9/44—Arrangements for executing specific programs
- G06F9/455—Emulation; Interpretation; Software simulation, e.g. virtualisation or emulation of application or operating system execution engines
- G06F9/45533—Hypervisors; Virtual machine monitors
- G06F9/45558—Hypervisor-specific management and integration aspects
- G06F2009/45595—Network integration; Enabling network access in virtual machine instances
Landscapes
- Engineering & Computer Science (AREA)
- Software Systems (AREA)
- Theoretical Computer Science (AREA)
- Physics & Mathematics (AREA)
- General Engineering & Computer Science (AREA)
- General Physics & Mathematics (AREA)
- Mathematical Physics (AREA)
- Life Sciences & Earth Sciences (AREA)
- Health & Medical Sciences (AREA)
- Artificial Intelligence (AREA)
- Biomedical Technology (AREA)
- Biophysics (AREA)
- Computational Linguistics (AREA)
- Data Mining & Analysis (AREA)
- Evolutionary Computation (AREA)
- General Health & Medical Sciences (AREA)
- Molecular Biology (AREA)
- Computing Systems (AREA)
- Management, Administration, Business Operations System, And Electronic Commerce (AREA)
Abstract
The invention belongs to the field of cloud computing, and particularly relates to a container cloud resource scheduling method based on QoS; the scheduling method comprises the steps of collecting resource node loads and screening out a candidate node set of container resource requests in the current period; according to the request of the container service level protocol in the current period and the candidate node set, a QoS model with multiple constraint conditions is constructed, and the QoS value of each resource node is calculated; improving the ant colony algorithm by taking the calculated QoS value as a guide factor, and calculating an optimal path by adopting the improved ant colony algorithm to be used as an optimal solution of resource scheduling; the invention can effectively reduce the error of node selection, thereby improving the resource utilization rate; SLA level agreements are considered, so that user experience is improved; based on a QoS model with multiple constraint conditions, an improved ant colony algorithm is used for selecting proper nodes to deploy, different containers can be dispatched to proper nodes, and the resource utilization rate is improved while the overall service quality is improved.
Description
Technical Field
The invention belongs to the field of cloud computing, and particularly relates to a container cloud resource scheduling method based on QoS.
Background
In recent years, the cloud computing field is developed vigorously, and particularly the appearance of container technology subverts the original virtualization technology, which exhibits good performance in terms of automatic configuration and resource scheduling. And because of the low start and stop overhead, containers are rapidly replacing virtual machines VMs in many cloud deployments.
The popularity of container technology, represented by Docker, has accelerated the development of agile development of operation and maintenance models. The Docker is used as a core mirror image, so that the Docker can be repeatedly used in development, test and production environments, and the delivery mode of the traditional software product is changed. The advantages of elastic expansion and high-availability deployment provided by the Docker container cloud platform effectively support the continuous integration and continuous deployment requirements of products, and greatly reduce the development, operation and maintenance cost.
The container cloud takes the container as a basic unit for resource segmentation and scheduling, encapsulates the whole software runtime environment, and provides a platform for developers and system administrators to construct, publish and run distributed applications. The container cloud resource scheduling mechanism plays a very important role in the cloud platform and is an indispensable component of the cloud platform. The resource dynamic scheduling is mainly used for dynamically managing load balancing, resource scheduling, resource monitoring and the like of the application container so as to ensure efficient resource utilization rate and service quality of the system. The current mainstream container cloud platform mainly has the following problems:
1. the resource utilization rate is low. With the increase of the number and the types of resources requested by users, effective utilization of cloud platform center resources is difficult to realize by a single optimization strategy and constraint. Today, the underlying architecture of a container cloud based cloud platform is still composed of a cluster of physical nodes, i.e. physical resources are discrete. Not only can the server easily run more processes at the same time, but also the demands of the containers on the resources are different. From the various images, the services provided by the containers are diverse, which results in a variety of resource requirements. If the service is scheduled according to the binning policy or the propagation policy, it will result in unsuccessful deployment of the service or waste of some resources. Therefore, an effective resource evaluation model is not established, and a static resource scheduling strategy causes the problem of low resource utilization rate of the cloud platform.
2. Quality of service issues. An important requirement of the cloud platform center for providing services to users is to provide reliable QoS guarantees for users, which may be defined according to Service-Level agreements (SLAs) describing characteristics such as minimum throughput, maximum response time, or delay provided by the deployment system. Therefore, while the cloud platform provides services for the application programs, it is also required to ensure service level agreement response requirements achieved under the maximum load, however, in the container cloud scheduling process, due to insufficient resources, part of container services may cause service interruption, delay and exception, thereby affecting user experience. There are problems in that the service quality is degraded and the SLA violation rate is increased.
In summary, the resource utilization and service quality problems under cloud computing are still more to be solved.
Disclosure of Invention
The invention aims to solve the problems of resource utilization rate, service quality and the like under a container cloud platform by constructing a model to filter candidate nodes and establishing a container scheduling strategy.
In order to achieve the purpose, the invention provides the following technical scheme:
a QoS-based container cloud resource scheduling method comprises the following steps:
s1, collecting resource node loads, and screening out a candidate node set of the container resource request in the current period;
s2, constructing a multi-constraint QoS model according to the request of the container service level protocol in the current period and the candidate node set, and calculating the QoS value of each resource node;
and S3, improving the ant colony algorithm by taking the calculated QoS value as a guide factor, and calculating an optimal path by adopting the improved ant colony algorithm to serve as an optimal solution of resource scheduling.
The invention has the beneficial effects that:
1) the invention monitors and collects the resource information of all the hosts, screens out the resource nodes with normal resource states based on the resource requests of the containers in the current period, and can effectively reduce the error of node selection, thereby improving the resource utilization rate.
2) The invention collects the requests of various service containers, considers the SLA level agreement, improves the user experience and improves the enterprise income. The invention is based on the QoS model of multiple constraint conditions, selects proper nodes to deploy by utilizing the improved ant colony algorithm, can dispatch different containers to proper nodes, improves the overall service quality and the resource utilization rate, does not need user intervention in the process, and is very friendly to users.
Drawings
In order to make the objects, technical solutions and advantages of the present invention more apparent, the present invention will be further described in detail with reference to the accompanying drawings, in which:
FIG. 1 is a general scheduling flow diagram of an embodiment of the present invention;
FIG. 2 is a flow chart of candidate node set screening according to an embodiment of the present invention;
FIG. 3 is a flow chart of QoS model construction according to an embodiment of the present invention;
fig. 4 is a flowchart of an optimization method using an improved ant colony algorithm according to an embodiment of the present invention.
Detailed Description
The technical solutions in the embodiments of the present invention will be clearly and completely described below with reference to the drawings in the embodiments of the present invention, and it is obvious that the described embodiments are only a part of the embodiments of the present invention, and not all of the embodiments. All other embodiments, which can be derived by a person skilled in the art from the embodiments given herein without making any creative effort, shall fall within the protection scope of the present invention.
The scheduling method mainly comprises the steps that a container deploys a resource request in each period, a node subset is selected according to resource node load evaluation, and a node set is selected according to the main flow resource requirement of the container set in the current period; constructing a QoS model according to the candidate node set and the container set of the current period; and improving the ant colony algorithm according to the output result of the QoS model, calculating the optimal solution of container scheduling according to the improved ant colony algorithm, and obtaining a container node deployment mapping set.
Fig. 1 is a flowchart of a QoS-based container cloud resource scheduling method in an embodiment of the present invention, and as shown in fig. 1, the method includes the following steps:
s1, collecting resource node loads, and screening out a candidate node set of the container resource request in the current period;
fig. 2 is a flowchart of a candidate node set screening process according to an embodiment of the present invention, and as shown in fig. 2, the candidate node set screening process includes:
s11, collecting host resource information, and acquiring the load condition of the node cluster;
in the embodiment of the present invention, a corresponding candidate node set needs to be selected according to the load conditions of all resource node sets and the current container resource request.
The resource node load is resource information of the host, including Id, mirror image size, CPU computing power, memory size and bandwidth size of the virtual machine, and the number of containers, etc., and assuming that these six types of resource information are taken as an example, each resource node is a resource nodejCan be expressed as Representing resource nodesjId of (2);representing resource nodesjMirror size of (d);representing resource nodesjThe CPU computing power of (1);representing resource nodesjThe memory size of (d);representing resource nodesjThe memory size of (d); representing resource nodesjIs/are as follows
S12, constructing a two-dimensional decision matrix according to the node load condition;
by using the relationship between the resource nodes and the resource types, under the above six types of resource information, a two-dimensional decision matrix with the size of n × 6 can be formed:
s13, normalizing and weighting the two-dimensional decision matrix;
because the non-dimensionalization of the quality of the target attribute is reflected only by the value, and in order to enable the target attribute influencing switching to be more normalized and more intuitive, the invention uses vector normalization to determine the normalization matrix R for subsequent data preprocessing, and the normalization processing is expressed as:
obtaining the weighting coefficient of each index according to the influence proportion of each index on the node performance, and constructing a normalized weighting decision matrix vkj=fk_j*wkI 1.. n, and k ∈ Rj(ii) a The weighted decision matrix is represented as:
s14, calculating the relative closeness of the nodes according to the weighting matrix;
respectively calculating an optimal solution distance and a worst solution distance by using an Euclidean distance formula; calculating bestj(nodejDistance from optimal solution) and worstj(nodejDistance from the worst solution).
Defining the relative closeness of the resource nodes based on the optimal solution distance and the worst solution distance, sequencing the relative closeness, and selecting a node subset; wherein the calculation formula of the relative closeness is expressed as:
RCj=bestj/(bestj+worstj)
wherein, RCjRepresents the jth nodejRelative closeness of; bestjRepresents the jth nodejEuclidean distance from optimal solution, worstjRepresents the jth nodejEuclidean distance to the worst solution.
And S15, acquiring a candidate node set according to the relative closeness.
In some embodiments, the present embodiment may deploy a data acquisition module to acquire request information of various container services, and record the request information as C ═ C1,c2,…,cmC for each request detailed informationi={ci_id,ci_mem,ci_cpu,ci_disk,ci_net,ci_SLA,ci_timeIs stored in a database. And selecting a node subset meeting the container resource request of the current period from the candidate node set and updating a tabu list in the ant colony algorithm.
S2, according to the current period container service level agreement SLA request, according to the candidate node set, a multi-constraint QoS model is constructed, and the QoS value of each resource node is calculated.
Fig. 3 is a flow chart of QoS model construction according to an embodiment of the present invention, and as shown in fig. 3, the QoS model construction process includes:
s21, calculating task execution cost, task execution time and effective availability of the tasks;
calculating the cost P required by executing the deployment container according to the candidate node set and the current period container resource request setijAs follows:
Pij=nodeij*p≤LP
wherein, PijDenotes the ith container ciAssigned virtual jth nodejThe execution cost of; p represents the cost (including the cost of the compute node (defined as p) required to perform the taskcost) And SLA breach cost (defined as p)SLAcost) Two-part composition); LP represents a set expense constraint.
Based on the node cost and the SLA default cost, calculating the user cost expenditure as follows:
indicating container ciDeployed at nodejUser cost expenditure ofRespectively show the execution containers ciMaximum and minimum required expense, nodeijp is the container disposed at the nodejOverhead including calculating node cost (defined as p)cost) And SLA breach cost (defined as p)SLAcost) Two parts are formed;
denoted as container ciDeployed at nodejIn a performance time of whereinRespectively represent execution ciMaximum and minimum completion time required, nodeij*tijFor deployment of containers at nodesjThe completion time of (c);
denoted as container ciDeployed at nodejEffective availability of whereinRespectively represent execution ciMaximum and minimum effective availability, nodeijU is container deployment at nodejEffective availability of (a);
s22, constructing a QoS model according to a weighting mode, and outputting a QoS value of the container at each node;
using user expenditureTask completion timeAnd is effective inProperty of useEstablishing a QoS model, and calculating QoS values of request containers respectively deployed at each node in the current period:
wherein the QoS isijRepresents the QoS value of the jth node under the ith container resource request; a represents a node expenditure influence factor; b represents a task completion time influence factor; c represents a deployment result effective availability impact factor.
And S3, improving the ant colony algorithm by taking the calculated QoS value as a guide factor, and calculating an optimal path by adopting the improved ant colony algorithm to serve as an optimal solution of resource scheduling.
Specifically, as shown in fig. 4, the step S3 specifically includes the following steps:
and the Qos value obtained by calculation is used as a guide factor of the ant colony algorithm, so that the transfer probability of the ant colony algorithm is improved, and the phenomenon that the convergence speed is too high and then the ant colony algorithm falls into local optimum is avoided. The node transition probability formula is as follows:
wherein,representing the probability of transferring the ith container deployment from the kth ant to the jth node at time t; tau isij(t) pheromones representing the ith container at the jth node at the tth time; etaij(t) represents the expected strength of the ith container selected by the jth node at time t; tb represents the taboo list of ants; α represents the relative importance of the pheromone; beta represents the relative importance of the desired intensity.
According to the invention, by using an improved ant colony algorithm, the optimal path can be found for the container deployment task in the whole period, namely, the optimal solution of resource allocation can be obtained, and the container is deployed to the designated node according to the optimal demodulation degree.
The calculating the optimal path by adopting the improved ant colony algorithm comprises the following steps:
s31, initializing basic parameters of the resource nodes and various parameters of the ant colony algorithm;
initializing various parameters of the ant colony algorithm according to basic parameters such as computing capacity, bandwidth and memory of the nodes, wherein the parameters comprise initialization of pheromones, initialization of initial prices of virtual nodes, initialization of iteration times, initialization of pheromone concentration and initialization of task execution time.
In addition, a tabu list may also be created for recording the path that an ant has taken.
S32, randomly deploying a plurality of ants at each starting node;
a plurality of ants are randomly deployed at each initial node, n containers to be deployed and m nodes can be set, corresponding parameter values can be set according to different QoS requirements of different tasks, and QoS values of the containers on the nodes are calculated according to a node transfer probability formula.
S33, calculating the transfer probability of each ant selecting the next adjacent node according to the QoS value of the resource node, and obtaining the optimal path of the current ant, namely the optimal resource allocation from the current period container resource request to the corresponding resource node; s34, updating pheromones of ants on the current path in a local updating mode, and adding the passed path nodes into a taboo list;
s35, repeatedly executing the step S32-the step S34 until all ants find the optimal path;
s36, updating pheromones on all paths in a global updating mode;
and S37, judging whether the maximum iteration times is reached, if not, returning to the step S32, otherwise, outputting a mapping set of container and node deployment.
The QoS value is used as a leading factor, and an optimal path is calculated by adopting an improved ant colony algorithm and is used as an optimal solution of resource allocation; the invention can dispatch different containers to proper nodes, is suitable for different container service requests, can realize the integral optimization of resource dispatching while ensuring the SLA and the QoS of a user, and effectively improves the resource utilization rate.
In the description of the present invention, it is to be understood that the terms "coaxial", "bottom", "one end", "top", "middle", "other end", "upper", "one side", "top", "inner", "outer", "front", "center", "both ends", and the like, indicate orientations or positional relationships based on those shown in the drawings, and are only for convenience of description and simplicity of description, and do not indicate or imply that the devices or elements referred to must have a particular orientation, be constructed and operated in a particular orientation, and thus, are not to be construed as limiting the present invention.
In the present invention, unless otherwise expressly stated or limited, the terms "mounted," "disposed," "connected," "fixed," "rotated," and the like are to be construed broadly, e.g., as meaning fixedly connected, detachably connected, or integrally formed; can be mechanically or electrically connected; the terms may be directly connected or indirectly connected through an intermediate, and may be communication between two elements or interaction relationship between two elements, unless otherwise specifically limited, and the specific meaning of the terms in the present invention will be understood by those skilled in the art according to specific situations.
Although embodiments of the present invention have been shown and described, it will be appreciated by those skilled in the art that changes, modifications, substitutions and alterations can be made in these embodiments without departing from the principles and spirit of the invention, the scope of which is defined in the appended claims and their equivalents.
Claims (6)
1. A scheduling method of container cloud resources based on QoS is characterized by comprising the following steps:
s1, collecting resource node loads, and screening out a candidate node set of the container resource request in the current period;
s2, constructing a multi-constraint QoS model according to the request of the container service level protocol in the current period and the candidate node set, and calculating the QoS value of each resource node;
and S3, improving the ant colony algorithm by taking the calculated QoS value as a guide factor, and calculating an optimal path by adopting the improved ant colony algorithm to serve as an optimal solution of resource scheduling.
2. The QoS-based container cloud resource scheduling method of claim 1, wherein the screening of the candidate node set of the container resource request in the current period comprises establishing a node resource evaluation model by using a good-bad solution distance method for decision relationships between nodes and different resource types; calculating the relative closeness of the nodes based on the optimal solution distance and the worst solution distance, and screening out an available node subset; and selecting a candidate node set which meets the container resource request of the current period from the node subset.
3. The QoS-based container cloud resource scheduling method according to claim 2, wherein the screening out available node subsets includes calculating relative closeness of the nodes based on the optimal solution distance and the worst solution distance, and sorting the nodes in ascending order according to the relative closeness, and selecting a plurality of nodes in the top ranking as available node subsets, wherein the calculation formula of the relative closeness is represented as:
RCj=bestj/(bestj+worstj)
wherein, RCjRepresenting the relative closeness of the jth node; bestjRepresenting Euclidean distance between the jth node and the optimal solution, worstjIndicating the euclidean distance of the jth node from the worst solution.
4. The QoS-based container cloud resource scheduling method of claim 1, wherein the multi-constraint QoS model is constructed by weighting task execution cost, task execution time and effective availability of tasks, and is represented as:
wherein the QoS isijIndicated in the ith container ciJ node under resource requestjA QoS value of (1); a represents a node expenditure influence factor; b represents a task completion time influence factor; c represents a deployment result effective availability impact factor;denotes the ith container ciDeployed at the j nodejThe execution cost of;denoted as the ith container ciDeployed at the j nodejThe execution time of (1);denotes the ith container ciDeployed at the j nodejIs effectively available.
5. The QoS-based scheduling method for container cloud resources according to claim 1, wherein the calculating an optimal path by using an improved ant colony algorithm includes:
step 1) initializing basic parameters of resource nodes and various parameters of an ant colony algorithm;
step 2) randomly deploying a plurality of ants at each starting node;
step 3) calculating the transfer probability of each ant selecting the next adjacent node according to the QoS value of the resource node to obtain the optimal path of the current ant, namely the optimal resource allocation from the current period container resource request to the corresponding resource node;
step 4) updating pheromones of ants on the current path in a local updating mode, and adding passed path nodes into a taboo list;
step 5) repeatedly executing the step 2) to the step 4) until all ants find the optimal path;
step 6) updating pheromones on all paths in a global updating mode;
and 7) judging whether the maximum iteration times are reached, if not, returning to the step 2), otherwise, outputting a mapping set of container and node deployment.
6. The QoS-based scheduling method for container cloud resources of claim 5, wherein the transition probability of the node comprises:
wherein the QoS isijRepresents the QoS value of the jth node under the ith container resource request; tau isij(t) a pheromone indicating that the ith container is at the jth node at the time t; etaij(t) represents the expected strength of the ith container selected by the jth node at time t; tb represents the taboo list of ants; α represents the relative importance of the pheromone; beta represents the relative importance of the desired intensity.
Priority Applications (1)
Application Number | Priority Date | Filing Date | Title |
---|---|---|---|
CN202011545634.7A CN112559135B (en) | 2020-12-24 | 2020-12-24 | Container cloud resource scheduling method based on QoS |
Applications Claiming Priority (1)
Application Number | Priority Date | Filing Date | Title |
---|---|---|---|
CN202011545634.7A CN112559135B (en) | 2020-12-24 | 2020-12-24 | Container cloud resource scheduling method based on QoS |
Publications (2)
Publication Number | Publication Date |
---|---|
CN112559135A true CN112559135A (en) | 2021-03-26 |
CN112559135B CN112559135B (en) | 2023-09-26 |
Family
ID=75030512
Family Applications (1)
Application Number | Title | Priority Date | Filing Date |
---|---|---|---|
CN202011545634.7A Active CN112559135B (en) | 2020-12-24 | 2020-12-24 | Container cloud resource scheduling method based on QoS |
Country Status (1)
Country | Link |
---|---|
CN (1) | CN112559135B (en) |
Cited By (4)
Publication number | Priority date | Publication date | Assignee | Title |
---|---|---|---|---|
CN113377495A (en) * | 2021-05-17 | 2021-09-10 | 杭州中港科技有限公司 | Method for optimizing docker cluster deployment based on heuristic ant colony algorithm |
CN114006784A (en) * | 2021-11-04 | 2022-02-01 | 国网湖南省电力有限公司 | Real-time interaction method and device for high-speed bus communication data |
CN114640598A (en) * | 2022-03-17 | 2022-06-17 | 重庆邮电大学 | Container placement method based on WOA algorithm under multi-tenant environment |
CN117076142A (en) * | 2023-10-17 | 2023-11-17 | 阿里云计算有限公司 | Multi-tenant resource pool configuration method and multi-tenant service system |
Citations (4)
Publication number | Priority date | Publication date | Assignee | Title |
---|---|---|---|---|
CN102932422A (en) * | 2012-09-29 | 2013-02-13 | 南京邮电大学 | Cloud environment task scheduling method based on improved ant colony algorithm |
CN103067524A (en) * | 2013-01-18 | 2013-04-24 | 浪潮电子信息产业股份有限公司 | Ant colony optimization computing resource distribution method based on cloud computing environment |
US20160292013A1 (en) * | 2012-12-10 | 2016-10-06 | Zte Corporation | Method and System for Scheduling Task in Cloud Computing |
CN111967643A (en) * | 2020-07-13 | 2020-11-20 | 北京工业大学 | Task scheduling method based on greedy self-adaptive ant colony algorithm |
-
2020
- 2020-12-24 CN CN202011545634.7A patent/CN112559135B/en active Active
Patent Citations (4)
Publication number | Priority date | Publication date | Assignee | Title |
---|---|---|---|---|
CN102932422A (en) * | 2012-09-29 | 2013-02-13 | 南京邮电大学 | Cloud environment task scheduling method based on improved ant colony algorithm |
US20160292013A1 (en) * | 2012-12-10 | 2016-10-06 | Zte Corporation | Method and System for Scheduling Task in Cloud Computing |
CN103067524A (en) * | 2013-01-18 | 2013-04-24 | 浪潮电子信息产业股份有限公司 | Ant colony optimization computing resource distribution method based on cloud computing environment |
CN111967643A (en) * | 2020-07-13 | 2020-11-20 | 北京工业大学 | Task scheduling method based on greedy self-adaptive ant colony algorithm |
Non-Patent Citations (3)
Title |
---|
ZHANG D.: "Container oriented job scheduling using linear programming model", 《INTERNATIONAL CONFERENCE ON INFORMATION MANAGEMENT. IEEE》 * |
李莉: "基于RBF-DE的改进蚁群算法和多QoS约束的云资源调度策略研究", 《软件导刊》 * |
王恩重: "基于改进蚁群优化算法的云计算调度方法", 《计算机与数字工程》 * |
Cited By (8)
Publication number | Priority date | Publication date | Assignee | Title |
---|---|---|---|---|
CN113377495A (en) * | 2021-05-17 | 2021-09-10 | 杭州中港科技有限公司 | Method for optimizing docker cluster deployment based on heuristic ant colony algorithm |
CN113377495B (en) * | 2021-05-17 | 2024-02-27 | 杭州中港科技有限公司 | Dock cluster deployment optimization method based on heuristic ant colony algorithm |
CN114006784A (en) * | 2021-11-04 | 2022-02-01 | 国网湖南省电力有限公司 | Real-time interaction method and device for high-speed bus communication data |
CN114006784B (en) * | 2021-11-04 | 2023-12-12 | 国网湖南省电力有限公司 | Real-time interaction method and device for high-speed bus communication data |
CN114640598A (en) * | 2022-03-17 | 2022-06-17 | 重庆邮电大学 | Container placement method based on WOA algorithm under multi-tenant environment |
CN114640598B (en) * | 2022-03-17 | 2023-09-29 | 重庆邮电大学 | Container placement method based on WOA algorithm in multi-tenant environment |
CN117076142A (en) * | 2023-10-17 | 2023-11-17 | 阿里云计算有限公司 | Multi-tenant resource pool configuration method and multi-tenant service system |
CN117076142B (en) * | 2023-10-17 | 2024-01-30 | 阿里云计算有限公司 | Multi-tenant resource pool configuration method and multi-tenant service system |
Also Published As
Publication number | Publication date |
---|---|
CN112559135B (en) | 2023-09-26 |
Similar Documents
Publication | Publication Date | Title |
---|---|---|
CN112559135B (en) | Container cloud resource scheduling method based on QoS | |
US10552221B2 (en) | Systems, apparatus and methods for managing resources in computer systems | |
US7174379B2 (en) | Managing server resources for hosted applications | |
Li et al. | SSLB: self-similarity-based load balancing for large-scale fog computing | |
Sandhu et al. | Scheduling of big data applications on distributed cloud based on QoS parameters | |
Shi et al. | Location-aware and budget-constrained service deployment for composite applications in multi-cloud environment | |
US7356592B2 (en) | Method and apparatus for web farm traffic control | |
Ding et al. | Kubernetes-oriented microservice placement with dynamic resource allocation | |
Attaoui et al. | Vnf and cnf placement in 5g: Recent advances and future trends | |
US20140074647A1 (en) | Methods and systems for recommending cloud configuration in a cloud service market place | |
CN110221920B (en) | Deployment method, device, storage medium and system | |
CN108897606B (en) | Self-adaptive scheduling method and system for virtual network resources of multi-tenant container cloud platform | |
US20230283656A1 (en) | Utilizing network analytics for service provisioning | |
US11042419B2 (en) | Cooperative scheduling method and system for computing resource and network resource of container cloud platform | |
Saravanan et al. | Priority based prediction mechanism for ranking providers in federated cloud architecture | |
Abdullah et al. | A reliable, TOPSIS-based multi-criteria, and hierarchical load balancing method for computational grid | |
Satpathy et al. | CoMap: An efficient virtual network re-mapping strategy based on coalitional matching theory | |
Al Muktadir et al. | Multi-target classification based automatic virtual resource allocation scheme | |
Garg et al. | Optimal virtual machine scheduling in virtualized cloud environment using VIKOR method | |
CN117707763A (en) | Hierarchical calculation scheduling method, system, equipment and storage medium | |
US20230108819A1 (en) | Automated processes and systems for managing and troubleshooting services in a distributed computing system | |
Alam et al. | Multi-objective interdependent VM placement model based on cloud reliability evaluation | |
WO2021090133A1 (en) | Achieving requested service availability | |
Meriam et al. | Multiple QoS priority based scheduling in cloud computing | |
CN118138589B (en) | Service cluster scheduling method, device, equipment and medium |
Legal Events
Date | Code | Title | Description |
---|---|---|---|
PB01 | Publication | ||
PB01 | Publication | ||
SE01 | Entry into force of request for substantive examination | ||
SE01 | Entry into force of request for substantive examination | ||
GR01 | Patent grant | ||
GR01 | Patent grant |