CN111245717A - Cloud service route distribution method and device - Google Patents
Cloud service route distribution method and device Download PDFInfo
- Publication number
- CN111245717A CN111245717A CN201811449156.2A CN201811449156A CN111245717A CN 111245717 A CN111245717 A CN 111245717A CN 201811449156 A CN201811449156 A CN 201811449156A CN 111245717 A CN111245717 A CN 111245717A
- Authority
- CN
- China
- Prior art keywords
- service
- task
- predicted
- value
- income value
- 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.)
- Pending
Links
Images
Classifications
-
- H—ELECTRICITY
- H04—ELECTRIC COMMUNICATION TECHNIQUE
- H04L—TRANSMISSION OF DIGITAL INFORMATION, e.g. TELEGRAPHIC COMMUNICATION
- H04L45/00—Routing or path finding of packets in data switching networks
- H04L45/12—Shortest path evaluation
- H04L45/123—Evaluation of link metrics
-
- H—ELECTRICITY
- H04—ELECTRIC COMMUNICATION TECHNIQUE
- H04L—TRANSMISSION OF DIGITAL INFORMATION, e.g. TELEGRAPHIC COMMUNICATION
- H04L67/00—Network arrangements or protocols for supporting network services or applications
- H04L67/01—Protocols
- H04L67/10—Protocols in which an application is distributed across nodes in the network
Landscapes
- Engineering & Computer Science (AREA)
- Computer Networks & Wireless Communication (AREA)
- Signal Processing (AREA)
- Management, Administration, Business Operations System, And Electronic Commerce (AREA)
Abstract
The embodiment of the invention provides a cloud service route distribution method and a cloud service route distribution device, wherein the method comprises the steps of obtaining a predicted service income value of a single subtask in each service instance completion target task set, wherein the predicted service income value is obtained according to a trend prediction method; and performing task routing distribution according to the prediction service income value through an ant algorithm to obtain an optimal task routing path of the target task set. According to the service income value corresponding to the service instance, the service income value when the task is executed next time is predicted, and the optimal solution of the next service route distribution is obtained according to the predicted service income value, so that the processing efficiency of the whole task is improved, and the utilization rate of server resources is improved.
Description
Technical Field
The embodiment of the invention relates to the technical field of cloud computing, in particular to a cloud service route distribution method and device.
Background
In a cloud computing system, along with the development of system access flow and industrial business, the development of a software architecture is promoted, so that the daily average access amount reaches over ten million levels, meanwhile, a business task is also developed from single-flow single-business to multi-flow fusion-business, and as the distribution principle of the business task directly influences the service quality of cloud computing, the service routing in the cloud computing needs to be reasonably distributed.
The existing support core system is based on a flow computing architecture, uses a service scheduling center to manage the access capacity of a cluster in real time, and performs access scheduling on service resources. The service dispatching center core component is a service registration center and a service load balancing module. And the application carries out vertical and horizontal splitting according to the service and function clustering, each split module is used as a service provider to provide capacity in an interface service mode, and the service is registered in a service registration center. The service registration center publishes the registered service information to the service user who subscribes to the service, and calls the corresponding service for the service user according to the load balancing strategy.
However, in the prior art, when tasks are allocated, the servers are allocated by adopting polling strategies, random strategies, smaller concurrency service or response time ratios and other manners, so that when the service tasks are processed, the processing efficiency of the whole task is reduced, and the resource utilization rate of the servers is lower.
Disclosure of Invention
Aiming at the problems in the prior art, the embodiment of the invention provides a cloud service route distribution method and device.
In a first aspect, an embodiment of the present invention provides a cloud service route allocation method, including:
obtaining a predicted service income value of a single subtask in each service instance completion target task set, wherein the predicted service income value is obtained according to a trend prediction method;
and performing task routing distribution according to the prediction service income value through an ant algorithm to obtain an optimal task routing path of the target task set.
In a second aspect, an embodiment of the present invention provides a cloud service route distribution device, including:
the processing module is used for acquiring a predicted service income value of each service instance for completing a single subtask in the target task set, and the predicted service income value is obtained according to a trend prediction method;
and the task routing distribution module is used for carrying out task routing distribution according to the prediction service income value through an ant algorithm to obtain an optimal task routing path of the target task set.
In a third aspect, an embodiment of the present invention provides an electronic device, which includes a memory, a processor, and a computer program stored in the memory and executable on the processor, and the processor implements the steps of the method provided in the first aspect when executing the program.
In a fourth aspect, an embodiment of the present invention provides a non-transitory computer readable storage medium, on which a computer program is stored, which when executed by a processor, implements the steps of the method as provided in the first aspect.
According to the cloud service route allocation method and device provided by the embodiment of the invention, the service income value when the task is executed next time is predicted according to the service income value corresponding to the service instance, and the optimal solution of the next service route allocation is obtained according to the predicted service income value, so that the processing efficiency of the whole task is improved, and the utilization rate of server resources is improved.
Drawings
In order to more clearly illustrate the embodiments of the present invention or the technical solutions in the prior art, the drawings used in the description of the embodiments or the prior art will be briefly described below, and it is obvious that the drawings in the following description are some embodiments of the present invention, and those skilled in the art can also obtain other drawings according to the drawings without creative efforts.
Fig. 1 is a schematic flow chart of a cloud service route allocation method according to an embodiment of the present invention;
fig. 2 is a schematic diagram of a service route allocation policy provided in an embodiment of the present invention;
fig. 3 is a schematic structural diagram of a cloud service route distribution device according to an embodiment of the present invention;
fig. 4 is a schematic structural diagram of an electronic device according to an embodiment of the present invention.
Detailed Description
In order to make the objects, technical solutions and advantages of the embodiments of the present invention clearer, 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 some, but not all, embodiments of the present invention. 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.
After the current cloud service is deployed in a container cloud, when the processing efficiency is reduced, the load balancer can only detect the service survival state to control the service route, and an effective strategy is not adopted to control the service route. In addition, when the supporting core system is deployed, in consideration of application continuity, disaster recovery deployment is generally performed on the service system, and common disaster recovery includes database remote disaster recovery deployment, service multi-cluster, service remote deployment, automatic service expansion and capacity and the like. Therefore, when the service provider and the service consumer are in different places, cross-machine routing of the service occurs, and network delay of the service is increased.
Fig. 1 is a schematic flow diagram of a cloud service route allocation method according to an embodiment of the present invention, and as shown in fig. 1, an embodiment of the present invention provides a cloud service route allocation method, including:
and 102, distributing task routes according to the predicted service income value through an ant algorithm to obtain an optimal task route path of the target task set.
In the embodiment of the invention, after receiving the task request of the target task set, a service instance list for processing the target task set is obtained first. And acquiring a corresponding service instance list from the service registration center according to the task type of the target task set, wherein the service instance list comprises service instance information, service specification information, service directory information and service position information. And selecting the service instances which can be used for the target task set according to the target task set and by combining the related information in the service instance list. Then, through step 101, a predicted service profit value of each service instance for completing a single subtask in the target task set is obtained, in the embodiment of the present invention, a combination of factors such as task execution time and network communication cost in the service instance is converted into a service profit value, and a trend prediction method is adopted to predict the service profit value of the next task according to the historical service profit value. And finally, performing task routing distribution according to the predicted service income value through an ant algorithm to obtain an optimal task routing path of the target task set in step 102.
According to the cloud service route allocation method provided by the embodiment of the invention, the service income value when the task is executed next time is predicted according to the service income value corresponding to the service instance, and the optimal solution of the next service route allocation is obtained according to the predicted service income value, so that the processing efficiency of the whole task is improved, and the utilization rate of server resources is improved.
On the basis of the foregoing embodiment, the obtaining a predicted service revenue value of each service instance for completing a single subtask in the target task set includes:
obtaining a historical service income value of each service instance, wherein the historical service income value comprises historical task execution time and historical network communication cost;
and predicting the historical task execution time and the historical network communication cost of each service instance by a trend prediction method to obtain a predicted service profit value of each service instance for completing a single subtask in the target task set.
In the embodiment of the present invention, a service revenue value corresponding to each service instance in a service instance list is first obtained, and time required for the service instance to execute a historical task, that is, historical task execution time, and communication cost between a corresponding service route and the service instance, that is, historical network communication cost are recorded in the service revenue value, so that a formula of the service revenue value can be obtained according to the task execution time and the network communication cost:
the service profit value is 1/(execution time + communication cost);
when the service profit value of a service instance is larger, the visibility of the service instance processing task is larger. In the embodiment of the invention, a trend prediction method is adopted according to task execution time and network communication cost generated when a service instance K processes a task each time and stored in a service instance list, so as to obtain a prediction service income value required when the service task is distributed at this time, and an income value prediction model formula based on the trend prediction method is as follows:
yt+k＝αt+bt×k；
wherein, atRepresenting the intercept of the predicted line, αt＝2m(1) t-m(2) 2；btWhich represents the slope of the predicted line or lines,
n represents the average length of each movement, and t represents the number of processing tasks, namely the number of task processing periods; m is(1) tIndicates the t-th periodAnd the moving average length is a moving average of n, i.e. one
qiExpressed as the service income value of the ith time, t is more than or equal to 2 n-2; m is(2) 2Expressed as the quadratic moving average of period t and moving average length n, i.e.
m(1) iExpressed as the ith moving average value, t is more than or equal to 2 n-2; k denotes the trend prediction period number, yt+kRepresenting the predicted service revenue value for period t + k. Taking n as an example of 5, the quadratic moving average is calculated, as shown in table 1:
TABLE 1
As shown in table 1, the service instance K has not yet been allocated with the processing task of the 13 th stage, and therefore, the service profit value prediction needs to be performed on the task of the 13 th stage. Reference is made to table 1 for m at service instance 12(1) t＝21.12，m(2) 222.00, the intercept of the corresponding predicted line:
αt＝2m(1) t-m(2) 2＝2*21.12-22.00＝20.24；
slope of the predicted line:
the predicted service revenue value for phase 13 can thus be obtained:
yt+k＝20.24+(-0.44)*1＝19.8。
and continuously predicting the predicted service income values of other service instances through an income value prediction model based on a trend prediction method, and according to a maximum income formula:
wherein the content of the first and second substances,
xij∈{0,1},i∈{1,2,…,m},j∈{1,2,…n}，qijrepresents the service profit value allocated to the ith service instance for executing the jth task, i.e. the predicted service profit value, x, obtained by the profit value prediction model based on the trend prediction methodijAs decision variables, xij0 means that the ith service instance is not scheduled to perform the jth task, xij1 indicates that the ith service instance is scheduled to perform the jth task. Fig. 2 is a schematic diagram of a service route allocation policy provided by an embodiment of the present invention, as shown in fig. 2, TjRepresenting a target task set, j is less than or equal to n, AiAnd the service instance is used for processing the target task set, i is less than or equal to m, P represents an initial node before the task is distributed, and P' represents a node at which the task is distributed. Initial node P and task node TjThere is an edge between and the cost constant is 0, the task node TjAnd service instance node AiThere is an edge in between and the edge cost is AiTreatment TjWeight of, service instance node AiThere is an edge with the task node and the cost constant is 0. Therefore, the service route allocation method is as follows: find a route from P node to P' node and pass through all TjShortest path of a node. Referring to fig. 2, if the shortest path to be solved passes through all n T nodes, it also passes through m a nodes. Because the edge from the T node to the A node has the weight value of the profit value qij(length of path), but the weight from node a to node T is 0. Therefore, all edges passing through the node A from the node T represent the edges of task allocation, namely the matrix X is obtained, and therefore the optimal task routing path of the target task set is obtained.
According to the embodiment of the invention, the historical service income value of the service instance is considered, the income value of the current service route is predicted through a trend prediction method, and the optimal solution of service route distribution is obtained according to the predicted income value, so that the overall efficiency of service processing is improved, and the utilization rate of server resources is improved.
On the basis of the above embodiment, the obtaining an optimal task routing path of the target task set by performing task routing allocation according to the predicted service revenue value through an ant algorithm includes:
enabling ants to carry out iterative search in a routing path between each subtask and each service instance according to a transition probability formula;
and if the iteration times or the operation time meets the preset conditions, selecting an ant search path with the maximum accumulated predicted service income value in the iteration process as an optimal task routing path so as to distribute service routes to the target task set.
In the embodiment of the invention, the optimal task routing path is obtained through a routing distribution algorithm based on an ant algorithm. The ant algorithm is used as a probability algorithm for searching for an optimized path in a graph, inspiration of the probability algorithm is derived from the behavior of ants in the process of finding the path in the process of searching for food, an independent search solution of each ant in a candidate solution space is obtained by simulating the ant colony cooperation process of a plurality of ants, and a certain amount of information is left on the found solution. Wherein, the better the performance of the solution represents that the larger the pheromone left on the ant, the larger the probability that the solution with larger pheromone is selected.
Further, in this embodiment of the present invention, the performing, by using an ant algorithm, task route allocation according to the predicted service revenue value to obtain an optimal task route path of the target task set further includes:
and updating the pheromone in the ant search path for the next service route distribution.
In the embodiment of the present invention, at time t +1, ant k selects the edge with the maximum probability of being connected to the ith node on the ith node for transfer, and then the path selection method for transferring node i to node j is implemented, that is, the transfer probability formula is:
wherein, Jk(i) Represents the node set allowed to be selected next step of the ant k, and J is required to be illustratedk(i) There are 2 cases: 1) when an ant goes from a T node to an A node, Jk(i)＝{A1,A2,...Am}-AtabukList of AtabukExpressed as a tabu table recording the class a node set through which ant k just passed; 2) when an ant goes from node A to node T, Jk(i)＝{T1,T2,...Tn}-AtabukList of AtabukRepresented as a tabu table recording the set of T-type nodes that ant k just passed through, i.e. recording the previous transfer path that ant passed through into the tabu table during each iteration ηijIn the embodiment of the present invention, η is a heuristic factor representing the expected degree of ants from the current inode to the next inode jijExpressed as a service revenue value, α is an information elicitor which represents the relative importance of the residual pheromone of the ant colony in the movement process, β is an expected heuristic factor which represents the relative importance of the expected value, and tauij(t) represents the pheromone remaining on the connection line of the paths (i, j) at time t, and at the initial time, the pheromones on the respective paths are equal, and τ is setij(0) As the time goes on, the pheromone volatilizes, while as ants iterate, the pheromone increases. Thus, at time t +1, pheromone τijThe update formula of (t) is:
τij(t+1)＝ρτij(t)+Δτij(t)；
wherein, Δ τijRepresents the total increment of pheromones from the node i to the node j of the iteration, delta tauk ijRepresents the current iteration of the kth antIncrement of pheromone on the edge from the node i to the node j, rho represents the remaining degree of pheromone track after volatilization on a certain path, Q is a normal number, and LkAnd (4) representing the total benefit value of the path taken by the kth ant in the current round trip.
In the embodiment of the present invention, the ant algorithm is used to perform iterative processing on the service instance list and the predicted service revenue value, so as to obtain the optimal task routing path of the target task set, and with reference to fig. 2, the specific steps are as follows:
s1, initializing a Kth ant triggering position P;
s2, ant selects corresponding edge to T according to path selection methodj；
S3, selecting corresponding edge from T according to the path selection methodjTo AiThen corresponds to xijAccumulating the obtained profit values at the same time as 1;
s4, selecting corresponding edge from A according to the path selection methodiTo Tj+1Then corresponds to xij+1Accumulating the obtained profit value at the same time, wherein the obtained profit value is 0;
s5, selecting corresponding edge from T according to the path selection methodj+1To Ai+1Then corresponds to xi+1j+1Accumulating the obtained profit values at the same time as 1;
s6, continuing to execute the step S2 to the step S5 to allow the ants to continuously crawl on the way;
s7, when the ant reaches the node A and does not reach the path of the node T, the ant selects the path of the node P' to finish crawling;
s8, calculating the total benefit value of ants through the path, according to the pheromone tauij(t) updating pheromones on the ant search path by the updating formula, and obtaining a path X which is the optimal task routing path and is passed by the ant under the maximum total benefit value according to the maximum benefit formula;
s9, if the preset iteration number is not reached or the operation time does not exceed the maximum limit, go to step S1.
According to the embodiment of the invention, the historical service income value of the service instance is considered, the service route income value of the time is predicted through a trend prediction method, the ant algorithm is adopted to distribute the task route according to the service income value, the service instance with lower network communication cost is selected, the overall efficiency of service processing is improved, the probability of cross-machine room service is further reduced, and the network consumption increased by remote service access is reduced.
On the basis of the above embodiment, after performing task routing distribution according to the predicted service revenue value by using an ant algorithm to obtain an optimal task routing path of the target task set, the method includes:
acquiring task execution time and network communication cost of each target service instance on the optimal task routing path;
and updating the service income value of each target service instance according to the task execution time and the network communication cost so as to be used for the next trend prediction method.
In the embodiment of the invention, after the target service instance on the optimal task routing path completes the task, the service income value of the target service instance is updated according to the task execution time and the network communication cost of the task completed this time, and the updated information is stored in the target service instance for service routing distribution of the next task.
The embodiment of the invention improves the service route distribution efficiency by updating the service income value of the service instance each time, so that the service route distribution is more reasonable.
On the basis of the foregoing embodiments, before the obtaining a predicted service revenue value of each service instance for completing a single subtask in the target task set, the method further includes:
acquiring a target task set, wherein the target task set comprises a plurality of subtasks;
and generating a service list according to the task information of each subtask, wherein the service list comprises a plurality of service instances.
In the embodiment of the invention, before service route allocation is carried out, a task set to be route allocated submitted by a user, namely a target task set, is obtained, and a service instance set which can be used for processing subtasks, namely a service list, is selected according to task information carried by different subtasks in the target task set.
The embodiment of the invention improves the efficiency of subsequent service route distribution by preprocessing the target task set to be processed.
Fig. 3 is a schematic structural diagram of a cloud service route distribution device according to an embodiment of the present invention, and as shown in fig. 3, an embodiment of the present invention provides a cloud service route distribution device, including: a processing 301 task route allocation module 302, wherein the processing module 301 is configured to obtain a predicted service profit value of a single subtask in each service instance completion target task set, and the predicted service profit value is obtained according to a trend prediction method; the task route allocation module 302 is configured to perform task route allocation according to the predicted service revenue value through an ant algorithm to obtain an optimal task route path of the target task set.
According to the cloud service route distribution device provided by the embodiment of the invention, the service income value when the task is executed next time is predicted according to the service income value corresponding to the service instance, and the optimal solution of the next service route distribution is obtained according to the predicted service income value, so that the processing efficiency of the whole task is improved, and the utilization rate of server resources is improved.
On the basis of the above embodiment, the processing module 301 includes: the system comprises a profit value acquisition unit and a profit value prediction unit, wherein the profit value acquisition unit is used for acquiring a historical service profit value of each service instance, and the historical service profit value comprises historical task execution time and historical network communication cost; and the profit value prediction unit is used for predicting the historical task execution time and the historical network communication cost of each service instance by a trend prediction method to obtain a predicted service profit value of each service instance for completing a single subtask in the target task set.
On the basis of the above embodiment, the task route distribution module 302 includes: the path searching unit is used for enabling ants to carry out iterative search in the routing path between each subtask and each service instance according to a transition probability formula; and if the iteration times or the operation time meets the preset conditions, selecting an ant search path with the maximum accumulated predicted service income value in the iteration process as an optimal task routing path so as to distribute service routes to the target task set.
On the basis of the above embodiment, the apparatus further includes: the system comprises an acquisition module and an updating module, wherein the acquisition module is used for acquiring the task execution time and the network communication cost of each target service instance on the optimal task routing path; and the updating module is used for updating the service income value of each target service instance according to the task execution time and the network communication cost so as to be used for the next trend prediction method.
The apparatus provided in the embodiment of the present invention is used for executing the above method embodiments, and for details of the process and the details, reference is made to the above embodiments, which are not described herein again.
Fig. 4 is a schematic structural diagram of an electronic device according to an embodiment of the present invention, and as shown in fig. 4, the electronic device may include: a processor (processor)401, a communication Interface (communication Interface)402, a memory (memory)403 and a communication bus 404, wherein the processor 401, the communication Interface 402 and the memory 403 complete communication with each other through the communication bus 404. Processor 401 may call logic instructions in memory 403 to perform the following method: obtaining a predicted service income value of a single subtask in each service instance completion target task set, wherein the predicted service income value is obtained according to a trend prediction method; and performing task routing distribution according to the prediction service income value through an ant algorithm to obtain an optimal task routing path of the target task set.
In addition, the logic instructions in the memory 403 may be implemented in the form of software functional units and stored in a computer readable storage medium when the software functional units are sold or used as independent products. Based on such understanding, the technical solution of the present invention may be embodied in the form of a software product, which is stored in a storage medium and includes instructions for causing a computer device (which may be a personal computer, a server, or a network device) to execute all or part of the steps of the method according to the embodiments of the present invention. And the aforementioned storage medium includes: a U-disk, a removable hard disk, a Read-Only Memory (ROM), a Random Access Memory (RAM), a magnetic disk or an optical disk, and other various media capable of storing program codes.
An embodiment of the present invention discloses a computer program product, which includes a computer program stored on a non-transitory computer readable storage medium, the computer program including program instructions, when the program instructions are executed by a computer, the computer can execute the methods provided by the above method embodiments, for example, the method includes: obtaining a predicted service income value of a single subtask in each service instance completion target task set, wherein the predicted service income value is obtained according to a trend prediction method; and performing task routing distribution according to the prediction service income value through an ant algorithm to obtain an optimal task routing path of the target task set.
An embodiment of the present invention provides a non-transitory computer-readable storage medium, where the non-transitory computer-readable storage medium stores a server instruction, and the server instruction causes a computer to execute the cloud service route allocation method provided in the foregoing embodiment, where the method includes: obtaining a predicted service income value of a single subtask in each service instance completion target task set, wherein the predicted service income value is obtained according to a trend prediction method; and performing task routing distribution according to the prediction service income value through an ant algorithm to obtain an optimal task routing path of the target task set.
Finally, it should be noted that: the above examples are only intended to illustrate the technical solution of the present invention, but not to limit it; although the present invention has been described in detail with reference to the foregoing embodiments, it will be understood by those of ordinary skill in the art that: the technical solutions described in the foregoing embodiments may still be modified, or some technical features may be equivalently replaced; and such modifications or substitutions do not depart from the spirit and scope of the corresponding technical solutions of the embodiments of the present invention.
Claims (10)
1. A cloud service route distribution method is characterized by comprising the following steps:
obtaining a predicted service income value of a single subtask in each service instance completion target task set, wherein the predicted service income value is obtained according to a trend prediction method;
and performing task routing distribution according to the prediction service income value through an ant algorithm to obtain an optimal task routing path of the target task set.
2. The method of claim 1, wherein obtaining a predicted service revenue value for each service instance to complete a single subtask in the target task set comprises:
obtaining a historical service income value of each service instance, wherein the historical service income value comprises historical task execution time and historical network communication cost;
and predicting the historical task execution time and the historical network communication cost of each service instance by a trend prediction method to obtain a predicted service profit value of each service instance for completing a single subtask in the target task set.
3. The method as claimed in claim 2, wherein the obtaining the optimal task routing path of the target task set by performing task routing distribution according to the predicted service profit value through an ant algorithm comprises:
enabling ants to carry out iterative search in a routing path between each subtask and each service instance according to a transition probability formula;
and if the iteration times or the operation time meets the preset conditions, selecting an ant search path with the maximum accumulated predicted service income value in the iteration process as an optimal task routing path so as to distribute service routes to the target task set.
4. The method as claimed in claim 3, wherein the task routing distribution is performed according to the predicted service profit value by using an ant algorithm to obtain an optimal task routing path of the target task set, further comprising:
and updating the pheromone in the ant search path for the next service route distribution.
5. The method as claimed in claim 4, wherein after the task routing distribution is performed according to the predicted service profit value through an ant algorithm to obtain an optimal task routing path of the target task set, the method comprises:
acquiring task execution time and network communication cost of each target service instance on the optimal task routing path;
and updating the service income value of each target service instance according to the task execution time and the network communication cost so as to be used for the next trend prediction method.
6. The method according to any one of claims 1-5, wherein before said obtaining a predicted service revenue value for each service instance to complete a single subtask in the target set of tasks, the method further comprises:
acquiring a target task set, wherein the target task set comprises a plurality of subtasks;
and generating a service list according to the task information of each subtask, wherein the service list comprises a plurality of service instances.
7. A cloud service route distribution device, comprising:
the processing module is used for acquiring a predicted service income value of each service instance for completing a single subtask in the target task set, and the predicted service income value is obtained according to a trend prediction method;
and the task routing distribution module is used for carrying out task routing distribution according to the prediction service income value through an ant algorithm to obtain an optimal task routing path of the target task set.
8. The apparatus of claim 7, wherein the processing module comprises:
the income value acquiring unit is used for acquiring a historical service income value of each service instance, and the historical service income value comprises historical task execution time and historical network communication cost;
and the profit value prediction unit is used for predicting the historical task execution time and the historical network communication cost of each service instance by a trend prediction method to obtain a predicted service profit value of each service instance for completing a single subtask in the target task set.
9. An electronic device comprising a memory, a processor and a computer program stored on the memory and executable on the processor, characterized in that the steps of the method according to any of claims 1 to 6 are implemented when the processor executes the program.
10. A non-transitory computer-readable storage medium, on which a computer program is stored, which, when being executed by a processor, carries out the steps of the method according to any one of claims 1 to 6.
Priority Applications (1)
| Application Number | Priority Date | Filing Date | Title |
|---|---|---|---|
| CN201811449156.2A CN111245717A (en) | 2018-11-28 | 2018-11-28 | Cloud service route distribution method and device |
Applications Claiming Priority (1)
| Application Number | Priority Date | Filing Date | Title |
|---|---|---|---|
| CN201811449156.2A CN111245717A (en) | 2018-11-28 | 2018-11-28 | Cloud service route distribution method and device |
Publications (1)
| Publication Number | Publication Date |
|---|---|
| CN111245717A true CN111245717A (en) | 2020-06-05 |
Family
ID=70876248
Family Applications (1)
| Application Number | Title | Priority Date | Filing Date |
|---|---|---|---|
| CN201811449156.2A Pending CN111245717A (en) | 2018-11-28 | 2018-11-28 | Cloud service route distribution method and device |
Country Status (1)
| Country | Link |
|---|---|
| CN (1) | CN111245717A (en) |
Citations (4)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| 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 |
| CN103970609A (en) * | 2014-04-24 | 2014-08-06 | 南京信息工程大学 | Cloud data center task scheduling method based on improved ant colony algorithm |
| CN106055395A (en) * | 2016-05-18 | 2016-10-26 | 中南大学 | Method for constraining workflow scheduling in cloud environment based on ant colony optimization algorithm through deadline |
| CN106951059A (en) * | 2017-03-28 | 2017-07-14 | 中国石油大学(华东) | Based on DVS and the cloud data center power-economizing method for improving ant group algorithm |
-
2018
- 2018-11-28 CN CN201811449156.2A patent/CN111245717A/en active Pending
Patent Citations (4)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| 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 |
| CN103970609A (en) * | 2014-04-24 | 2014-08-06 | 南京信息工程大学 | Cloud data center task scheduling method based on improved ant colony algorithm |
| CN106055395A (en) * | 2016-05-18 | 2016-10-26 | 中南大学 | Method for constraining workflow scheduling in cloud environment based on ant colony optimization algorithm through deadline |
| CN106951059A (en) * | 2017-03-28 | 2017-07-14 | 中国石油大学(华东) | Based on DVS and the cloud data center power-economizing method for improving ant group algorithm |
Non-Patent Citations (4)
| Title |
|---|
| 文志强，等: ""基于蚁群算法的多Agent任务分配方法"", 《湖南工业大学学报》 * |
| 王海涛，等: ""云计算环境中任务调度策略"", 《信息通信技术》 * |
| 王胜男: ""基于蚁群算法及时间序列预测模型的云计算资源调度策略"", 《中国优秀硕士学位论文全文数据库信息科技辑》 * |
| 王霞军: ""一种高效云计算资源管理平台的设计与实现"", 《中国优秀硕士学位论文全文数据库信息科技辑》 * |
Similar Documents
| Publication | Publication Date | Title |
|---|---|---|
| Ge et al. | GA-based task scheduler for the cloud computing systems | |
| US10200457B2 (en) | Selective distribution of machine-learned models | |
| US10474504B2 (en) | Distributed node intra-group task scheduling method and system | |
| CN109814997B (en) | Distributed autonomous balanced artificial intelligence task scheduling method and system | |
| US10887202B2 (en) | Pre-starting services based on traversal of a directed graph during execution of an application | |
| CN109788046B (en) | Multi-strategy edge computing resource scheduling method based on improved bee colony algorithm | |
| CN110712206B (en) | Multitask allocation method, multitask allocation device, multitask allocation equipment and storage medium of intelligent robot | |
| US8843929B1 (en) | Scheduling in computer clusters | |
| CN103530182A (en) | Working scheduling method and device | |
| Durgadevi et al. | Resource allocation in cloud computing using SFLA and cuckoo search hybridization | |
| CN107273211A (en) | Data processing method based on virtual machine under a kind of cloud computing environment | |
| CN111143036A (en) | Virtual machine resource scheduling method based on reinforcement learning | |
| CN115022311B (en) | Method and device for selecting micro-service container instance | |
| Deniziak et al. | Cost optimization of real-time cloud applications using developmental genetic programming | |
| Nalini et al. | Reinforced ant colony optimization for fault tolerant task allocation in cloud environments | |
| CN111913800B (en) | Resource allocation method for optimizing cost of micro-service in cloud based on L-ACO | |
| CN109767094B (en) | Smart cloud manufacturing task scheduling device | |
| CN111245717A (en) | Cloud service route distribution method and device | |
| CN116932198A (en) | Resource scheduling method, device, electronic equipment and readable storage medium | |
| CN111813525B (en) | Heterogeneous system workflow scheduling method | |
| Vinothini et al. | Meta-heuristic firefly approach to multi-servers load balancing with independent and dependent server availability consideration | |
| CN111324444B (en) | Cloud computing task scheduling method and device | |
| Kant et al. | An ACO approach to job scheduling in grid environment | |
| Ignaciuk et al. | Application of continuous genetic algorithms for optimization of logistic networks governed by order-up-to inventory policy | |
| Azari et al. | Service composition with knowledge of quality in the cloud environment using the cuckoo optimization and artificial bee colony algorithms |
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 | ||
| RJ01 | Rejection of invention patent application after publication | ||
| RJ01 | Rejection of invention patent application after publication |
Application publication date: 20200605 |