CN114024894B - Dynamic calculation method and system in software-defined heaven-earth integrated network - Google Patents
Dynamic calculation method and system in software-defined heaven-earth integrated network Download PDFInfo
- Publication number
- CN114024894B CN114024894B CN202111295319.8A CN202111295319A CN114024894B CN 114024894 B CN114024894 B CN 114024894B CN 202111295319 A CN202111295319 A CN 202111295319A CN 114024894 B CN114024894 B CN 114024894B
- Authority
- CN
- China
- Prior art keywords
- subtask
- task
- subtasks
- heaven
- network
- 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.)
- Active
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
- H04L45/125—Shortest path evaluation based on throughput or bandwidth
-
- 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]
- G06F9/5005—Allocation of resources, e.g. of the central processing unit [CPU] to service a request
- G06F9/5027—Allocation of resources, e.g. of the central processing unit [CPU] to service a request the resource being a machine, e.g. CPUs, Servers, Terminals
-
- 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
Abstract
The invention provides a dynamic calculation method and a system in a software-defined heaven-earth integrated network, comprising the following steps: splitting an initial task to be processed to generate a plurality of subtasks; constructing a subtask dependency relationship graph according to the execution dependency relationship among the subtasks, and quantifying the subtask resource overhead and the task execution time; uploading the subtask description and the subtask dependency graph to a control plane; the control plane adopts a calculation planning algorithm to plan the transmission path of the data and the deployment position of each subtask according to the network state, the subtask description and the subtask dependency graph; and according to the transmission path planning result, a routing table is issued to the data plane, and a plurality of subtasks are uploaded to corresponding nodes according to the subtask deployment strategy. The invention distributes data processing on the transmission path, fully utilizes node computing resources, realizes simultaneous transmission and calculation, obviously reduces transmission cost and saves limited transmission resources in an heaven-earth integrated network.
Description
Technical Field
The invention relates to the field of data processing, in particular to a dynamic calculation method and a system in a software-defined heaven-earth integrated network.
Background
The space-earth integrated information network refers to a space-time integrated network composed of various satellite systems (communication, remote sensing, navigation systems and the like) positioned in high orbit, medium orbit and low orbit, a stratosphere network (composed of airplanes, high-altitude balloons, unmanned aerial vehicles and the like) and a ground network (Internet, mobile communication network: 2G/3G/4G, mobile self-organizing network, wiFi and the like), and aims to realize global random access, free interconnection communication and cross-network seamless switching of air, space, earth and sea (mobile) entities and meet the requirements of timely communication and information service of human beings at any time and any place.
The software-defined heaven-earth integration network refers to an heaven-earth integration network managed using a logically centralized control plane on the basis of the heaven-earth integration network. The state of the heaven-earth integrated network is maintained by the controller, and the network is dynamically managed according to the state.
The existing software-defined heaven-earth integration network lacks a set of data processing framework based on dynamic transmission and calculation. Specifically, existing data processing first transfers raw data to a designated data analysis center and then processes it. This introduces higher transmission costs and results in more serious transmission resource waste.
In the method, in the heaven-earth integrated network, node information of each network transmission device is reported to a lower controller, and then the lower controller is summarized and reported to an upper controller, each layer controller obtains network detailed information in own jurisdiction, when network management is carried out, each controller is responsible for all services in own jurisdiction, when the services cross-domain, the service nodes are initially covered by a complete controller for management, and related control strategies obtained from a manager or the upper controller are utilized for calculation, and the obtained result is issued, so that the management mode of the heaven-earth integrated information system requiring mixing is satisfied, namely, each terminal group and each autonomous domain still have a certain degree of independent management capability on the basis of unified terminal management.
In literature (Wenrui Ma, oscar sandval, jonathan Beltran, deng Pan and Niki pissinou aware placement of interdependent NFV middleboxes, ieee info com 2017), a task deployment strategy based on a task dependency graph is proposed for a static network. The strategy assumes that each subtask has the same task overhead, all the subtasks are ordered according to the input-output ratio from small to large, and then task deployment is carried out in a greedy manner by combining task dependency. The assumption that the method has the same task overhead for all subtasks is not applicable to a real network environment, and meanwhile, the method does not combine with a strategy for considering the planning of a transmission path, so that only suboptimal strategies can be finally obtained.
The literature (Sevil Mehraghdam, matthias Keller, holger karl. Specifying and placing chains of virtual network functions, ieee CloudNet 2014) proposes a greedy strategy-based joint routing and task planning strategy, which also sorts the subtasks according to the task input-output ratio in priority, traverses all schemes in a combined optimization mode, and finally calculates the optimal transmission path and optimal task deployment strategy of the sequence. The strategy also assumes that the subtask overhead is the same and does not take into account the dynamics of the topology and is therefore also not applicable to dynamic world-wide integrated networks.
Disclosure of Invention
Aiming at the defects in the prior art, the invention aims to provide a dynamic calculation method and a system in a software-defined heaven-earth integrated network.
The invention provides a dynamic calculation method in a software-defined heaven-earth integrated network, which comprises the following steps:
step S1: splitting an initial task to be processed to generate a plurality of independently deployable subtasks;
step S2: constructing a subtask dependency relationship graph according to the execution dependency relationship among the subtasks, and quantifying the subtask resource overhead, the subtask input-output ratio and the task execution time;
step S3: uploading a subtask description and a subtask dependency graph to a control plane, wherein the subtask description is the computing resource overhead of the subtask and the transmission data quantity which can be reduced by the subtask;
step S4: the control plane adopts a calculation planning algorithm to plan the transmission path of the data and the deployment position of each subtask according to the network state, the subtask description and the subtask dependency graph;
step S5: and according to the transmission path planning result, a routing table is issued to the data plane, and a plurality of subtasks are uploaded to corresponding nodes according to the subtask deployment strategy.
Preferably, the splitting the initial task to be processed in step S1 includes: splitting the original codes of the initial tasks according to code logic, generating a plurality of code segments, and adding codes required for input or output before and after each code segment to enable each code segment to be deployed independently, wherein each code segment capable of being deployed independently is a subtask.
Preferably, the execution dependency relationship between the subtasks in the step S2 is: data dependencies exist between subtasks.
Preferably, the subtask dependency graph in step S2 is: a directed acyclic graph constructed according to execution dependency of the subtasks; wherein nodes in the directed acyclic graph represent subtasks, and directed edges represent dependencies between subtasks.
Preferably, the network state in the step S4 is: the available computing resources at each time instant for each node in the network, the remaining bandwidth at each time instant for each link in the network.
Preferably, the algorithm of the transmission rule in step S4 includes the following steps:
step S4.1: calculating bottleneck resources of the heaven-earth integrated network in the task execution process;
step S4.2: calculating the average transmission hop count between each pair of nodes in the task execution process of the heaven-earth integrated network;
step S4.3: sequencing the subtasks according to the execution dependency relationship and the task execution benefits to obtain a task execution sequence;
step S4.4: combining the network topology graph and the subtask dependency graph to construct a task-topology graph;
step S4.5: calculating a shortest path from the virtual source node to the virtual destination node on the task-topology graph;
step S4.6: and (5) converting the shortest path in the step S4.5 into a transmission path of final data and a subtask deployment strategy.
Preferably, the step S4.3 comprises the following sub-steps:
step S4.3.1: dividing an original subtask dependency graph into a plurality of disjoint task groups in an iterative mode;
step S4.3.2: the tasks are ordered based on group numbers, task dependencies, or task execution benefits.
Preferably, the task execution benefit maximum group in step S4.3.1 is a task group formed by a certain subtask and all the dependent predecessor tasks, the execution benefit of the task group is a ratio of the total data size of all the subtasks in the group to the total computing resource requirement, and the task group with the execution benefit maximum is the task execution benefit maximum group.
Preferably, the step S4.4 includes the following sub-steps:
step S4.4.1: constructing a virtual source node and a virtual destination node;
step S4.4.2: and cross-mapping the nodes and subtasks in the heaven-earth integrated network topology, and constructing links of the task-topology graph according to resource constraint and transmission overhead.
The invention provides a dynamic communication system in a software-defined heaven-earth integrated network, which comprises the following modules:
task segmentation module: splitting an initial task to be processed to generate a plurality of independently deployable subtasks;
the task analysis module: constructing a subtask dependency relationship graph according to the execution dependency relationship among the subtasks, and quantifying the subtask resource overhead, the subtask input-output ratio and the task execution time;
and a task uploading module: uploading a subtask description and a subtask dependency graph to a control plane, wherein the subtask description is the computing resource overhead of the subtask and the transmission data quantity which can be reduced by the subtask;
and the transmission and calculation planning module is used for: according to the network state of the control plane, the subtask description and the subtask dependency graph, adopting a calculation planning algorithm to plan a data transmission path and the deployment position of each subtask;
the task deployment module: and according to the transmission path planning result, a routing table is issued to the data plane, and a plurality of subtasks are uploaded to corresponding nodes according to the subtask deployment strategy.
Compared with the prior art, the invention has the following beneficial effects:
1. the invention distributes data processing on the transmission path, fully utilizes node computing resources, reduces transmission overhead and saves limited transmission resources in the network;
2. the invention can reduce the network load and improve the network capacity as only the data processing result is required to be transmitted;
3. under the condition of meeting the resource constraint and the task dependency relationship, the invention searches the optimal transmission path and the deployment position of the subtask, thereby realizing the minimization of the transmission cost.
Drawings
Other features, objects and advantages of the present invention will become more apparent upon reading of the detailed description of non-limiting embodiments, given with reference to the accompanying drawings in which:
FIG. 1 is a flow chart of a dynamic calculation method in a software-defined heaven and earth integration network according to an embodiment of the invention;
fig. 2 is a schematic diagram of a method for calculating an average hop count of an heaven-earth integrated network according to an embodiment of the present invention;
FIG. 3 is a schematic diagram of a subtask partitioning method based on a maximum set of task execution benefits in an embodiment of the present invention;
FIG. 4 is a schematic diagram of a method for sorting sub-tasks according to an embodiment of the present invention;
FIG. 5 is a block diagram of a dynamic computing system of a software defined heaven and earth integration network in accordance with an embodiment of the present invention.
Detailed Description
The present invention will be described in detail with reference to specific examples. The following examples will assist those skilled in the art in further understanding the present invention, but are not intended to limit the invention in any way. It should be noted that variations and modifications could be made by those skilled in the art without departing from the inventive concept. These are all within the scope of the present invention.
The invention discloses a dynamic calculation method in a software-defined heaven-earth integrated network, which comprises the following steps with reference to fig. 1:
step S1: splitting an initial task to be processed to generate a plurality of subtasks which can be deployed independently. When a user deploys a complex initial task in a software-defined heaven-earth integrated network, the initial task is firstly compiled into an intermediate language locally, then the original code of the initial task is split into a plurality of code segments according to code logic at the level of source codes, the intermediate language or binary machine codes, and codes required for input and output are added before and after the split code segments, so that each code segment can be deployed independently, and the code segments which can be deployed independently are subtasks.
Step S2: according to sonAnd constructing a subtask dependency relationship graph according to the execution dependency relationship among the tasks, and quantifying subtask resource overhead, a subtask input-output ratio and task execution time in a local side writing mode. The execution dependency relationship refers to a data dependency relationship existing between subtasks, that is, the input of one subtask is the output of another subtask. The specific operation of constructing the subtask dependency graph is as follows: directed acyclic graph constructed according to execution dependency relationship of subtasks, each node t in the graph m Representing a subtask, directed edge e (t m ,t n ) Representing subtask t n Dependent subtask t m . Subtask dependency graph denoted R (T, E), where T, E is subtask set and edge set, respectively, T m E T represents a subtask, directed edge e (T m ,t n ) E refers to subtask t n Dependent subtask t m . And the local side writing mode generates test data according to fixed data distribution, locally executes the subtasks and records the average task cost, the average input-output ratio and the average task execution time of the execution subtasks.
Step S3: and uploading a subtask description and a subtask dependency graph to a control plane, wherein the subtask description refers to the computing resource overhead of each subtask and the reducible transmission data quantity of each subtask, and the reducible transmission data quantity of the subtask is equal to the input data quantity of the subtask multiplied by (1-input-output ratio of the subtask).
Step S4: the control plane adopts a calculation planning algorithm to plan the transmission path of the data and the deployment position of each subtask according to the network state, the subtask description and the subtask dependency graph; the network state of the control plane refers to the available computing resources of each node in the network at each moment, and the remaining bandwidth of each link in the network at each moment.
The execution of the pass planning algorithm comprises the following steps:
step S4.1: and calculating bottleneck resources of the heaven-earth integrated network in the task execution process. The method comprises the following steps: node v in a network i Bottleneck computing resource is
Where T is the task execution time, i represents the number of the node, T is the time of day,
for node v at time t i Is a function of the remaining computing resources of the computer. Node v in a network i To node v j Bottleneck transmission resource is->
Wherein->
For node v at time t i To node v j Is allocated to the remaining transmission resources of the mobile station.
Step S4.2: and calculating the average transmission hop count between each pair of nodes in the task execution process of the heaven-earth integrated network. The specific method comprises the following steps: according to the satellite motion law, calculating the topology of the world integration network at each moment, and nodes v in the network i To node v j Average hop count of (a) is
Wherein->
For node v at time t i To node v j Is a number of hops. As shown in fig. 2, the topology of the world integration network changes twice during the task execution, and the link e (v d ,v 1 ) And link e (v 1 ,v des ) The number of hops is 3 in the 2 nd and 3 rd time windows, so the average number of hops for these two links is (1+1+3)/3=1.67 hops.
Step S4.3: sequencing the subtasks according to the execution dependency relationship and the task execution benefits to obtain a task execution sequence; where task execution benefit refers to the ratio of the amount of data that a subtask can reduce to the subtask computational resource overhead. The method comprises the following specific steps:
step S4.3.1: and dividing the original subtask dependency graph into a plurality of disjoint task groups in an iterative mode. The specific process is as follows: firstly, defining a certain subtask and all dependent preamble tasks as a task group, defining the execution gain of the task group as the ratio of the total reduced data quantity of all subtasks in the group to the total calculation resource requirement, and defining the task execution gain maximum group as the task group with the execution gain maximum.
Each time iteration, the maximum Group of execution benefits is found out from the subtask dependency graph in an iteration mode, the Group of subtasks are removed from the subtask dependency graph until the subtask dependency graph is empty, and the maximum Group of execution benefits found out from the ith iteration is a Group i The maximum group has a group number i.
As shown in FIG. 3, the subtask dependency graph is partitioned into three disjoint task groups, where in the first iteration, subtask t 1 To t 3 The execution benefit of the formed task group is maximum; in the second iteration, subtask t 4 And t 5 Make up the task execution maximum group, while in the third iteration, subtask t 6 To t 8 The execution benefit maximum group is composed.
Step S4.3.2: sorting tasks based on group numbers, task dependency relationships or task execution benefits, wherein the sorting rules are as follows: subtask t m Arranged in subtasks t n Previously if and only if subtask t m The group number of the group is smaller than the group number of the group of the subtask; or the existence of a sub-task dependency graph represented by t n To t m Is a path of (2); or t m The task execution benefit is less than t n Is a task execution benefit of (1).
As shown in FIG. 4, group 1 The subtasks in (a) are all arranged in a Group 2 And Group 3 Before the subtask of (2), due to subtask t 3 Dependent on t 1 And t 2 ，t 3 Arranged at t 1 And t 2 Later, simultaneous subtask t 1 Execution yield ratio t 2 High, thus t 1 Arranged at t 2 Front.
Step S4.4: and combining the network topology graph and the subtask dependency graph to construct a task-topology graph. The method comprises the following specific steps:
step S4.4.1: constructing virtual source nodes
And virtual destination node->
Wherein M is the number of subtasks;
step S4.4.2: and cross-mapping the nodes and subtasks in the heaven-earth integrated network topology, and constructing links of the task-topology graph according to resource constraint and transmission overhead. For each link e (v i ,v j ) Creating a set of links in a task-topology graph
When the task is executed in sequence, subtask t m To subtask t n Is greater than node v i When computing resources in bottleneck, or subtask t 1 To subtask t n The remaining data after execution exceeds link e (v i ,v j ) When the bottleneck of the task-topology graph transmits resources, the link in the task-topology graph is used for transmitting the resources
Weight setting of (2) is +' infinity. Otherwise, link +_in task-topology>
Is set as the weight of subtask t 1 To subtask t n The remaining data after execution is multiplied by e (v i ,v j ) Average hop count of (a).
Step S4.5: computing virtual source nodes on task-topology graph
To virtual destination node->
Is the shortest path of (a);
step S4.6: and (5) converting the shortest path in the step S4.5 into a transmission path of final data and a subtask deployment strategy. The specific method comprises the following steps: if it is
For one of the shortest paths described in step 3.4, link e9v i ,v j ) Is a link on a data transmission path, and is subtask t m To subtask t n Is deployed at node v i And (3) upper part.
Step S5: and according to a transmission path planning result, a control plane issues a routing table to a data plane, and a plurality of subtasks are uploaded to corresponding nodes according to a subtask deployment strategy.
Referring to fig. 5, the present invention introduces a dynamic computing system in a software-defined heaven-earth integration network, which includes the following modules:
task segmentation module: splitting an initial task to be processed to generate a plurality of independently deployable subtasks;
the task analysis module: constructing a subtask dependency relationship graph according to the execution dependency relationship among the subtasks, and quantifying the subtask resource overhead, the subtask input-output ratio and the task execution time;
and a task uploading module: uploading a subtask description and a subtask dependency graph to a control plane, wherein the subtask description is the computing resource overhead of the subtask and the transmission data quantity which can be reduced by the subtask;
and the transmission and calculation planning module is used for: according to the network state of the control plane, the subtask description and the subtask dependency graph, adopting a calculation planning algorithm to plan a data transmission path and the deployment position of each subtask;
the task deployment module: and according to the transmission path planning result, a routing table is issued to the data plane, and a plurality of subtasks are uploaded to corresponding nodes according to the subtask deployment strategy.
Those skilled in the art will appreciate that the invention provides a system and its individual devices, modules, units, etc. that can be implemented entirely by logic programming of method steps, in addition to being implemented as pure computer readable program code, in the form of logic gates, switches, application specific integrated circuits, programmable logic controllers, embedded microcontrollers, etc. Therefore, the system and various devices, modules and units thereof provided by the invention can be regarded as a hardware component, and the devices, modules and units for realizing various functions included in the system can also be regarded as structures in the hardware component; means, modules, and units for implementing the various functions may also be considered as either software modules for implementing the methods or structures within hardware components.
The foregoing describes specific embodiments of the present invention. It is to be understood that the invention is not limited to the particular embodiments described above, and that various changes or modifications may be made by those skilled in the art within the scope of the appended claims without affecting the spirit of the invention. The embodiments of the present application and features in the embodiments may be combined with each other arbitrarily without conflict.
Claims (9)
1. The dynamic calculation method in the software-defined heaven and earth integrated network is characterized by comprising the following steps of:
step S1: splitting an initial task to be processed to generate a plurality of independently deployable subtasks;
step S2: constructing a subtask dependency relationship graph according to the execution dependency relationship among the subtasks, and quantifying the subtask resource overhead, the subtask input-output ratio and the task execution time;
step S3: uploading a subtask description and a subtask dependency graph to a control plane, wherein the subtask description is the computing resource overhead of the subtask and the transmission data quantity which can be reduced by the subtask;
step S4: the control plane adopts a calculation planning algorithm to plan the transmission path of the data and the deployment position of each subtask according to the network state, the subtask description and the subtask dependency graph;
step S5: according to the transmission path planning result, a routing table is issued to a data plane, and a plurality of subtasks are uploaded to corresponding nodes according to a subtask deployment strategy;
the transfer algorithm in the step S4 includes the following steps:
step S4.1: calculating bottleneck resources of the heaven-earth integrated network in the task execution process;
step S4.2: calculating the average transmission hop count between each pair of nodes in the task execution process of the heaven-earth integrated network;
step S4.3: sequencing the subtasks according to the execution dependency relationship and the task execution benefits to obtain a task execution sequence;
step S4.4: combining the network topology graph and the subtask dependency graph to construct a task-topology graph;
step S4.5: calculating a shortest path from the virtual source node to the virtual destination node on the task-topology graph;
step S4.6: and (5) converting the shortest path in the step S4.5 into a transmission path of final data and a subtask deployment strategy.
2. The method for dynamically calculating in a software-defined heaven and earth integration network according to claim 1, wherein: the splitting the initial task to be processed in the step S1 includes: splitting the original codes of the initial tasks according to code logic, generating a plurality of code segments, and adding codes required for input or output before and after each code segment to enable each code segment to be deployed independently, wherein each code segment capable of being deployed independently is a subtask.
3. The method for dynamically calculating in a software-defined heaven and earth integration network according to claim 1, wherein: the execution dependency relationship between the subtasks in the step S2 is as follows: data dependencies exist between subtasks.
4. The method for dynamically calculating in a software-defined heaven and earth integration network according to claim 1, wherein: the subtask dependency graph in the step S2 is as follows: a directed acyclic graph constructed according to execution dependency of the subtasks; wherein nodes in the directed acyclic graph represent subtasks, and directed edges represent dependencies between subtasks.
5. The method for dynamically calculating in a software-defined heaven and earth integration network according to claim 1, wherein: the network state in the step S4 is: the available computing resources at each time instant for each node in the network, the remaining bandwidth at each time instant for each link in the network.
6. The method for dynamically calculating in a software-defined heaven and earth integration network according to claim 1, wherein: said step S4.3 comprises the sub-steps of:
step S4.3.1: dividing an original subtask dependency graph into a plurality of disjoint task groups in an iterative mode;
step S4.3.2: the tasks are ordered based on group numbers, task dependencies, or task execution benefits.
7. The method for dynamically calculating in a software-defined heaven and earth integration network according to claim 6, wherein: the task execution benefit maximum group in step S4.3.1 is a task group formed by a certain subtask and all the dependent preceding tasks, the execution benefit of the task group is a ratio of the total data volume of all the subtasks in the group to the total computing resource requirement, and the task group with the execution benefit maximum is the task execution benefit maximum group.
8. The method for dynamically calculating in a software-defined heaven and earth integration network according to claim 1, wherein: said step S4.4 comprises the sub-steps of:
step S4.4.1: constructing a virtual source node and a virtual destination node;
step S4.4.2: and cross-mapping the nodes and subtasks in the heaven-earth integrated network topology, and constructing links of the task-topology graph according to resource constraint and transmission overhead.
9. A dynamic communication system in a software-defined heaven and earth integrated network, comprising the following modules:
task segmentation module: splitting an initial task to be processed to generate a plurality of independently deployable subtasks;
the task analysis module: constructing a subtask dependency relationship graph according to the execution dependency relationship among the subtasks, and quantifying the subtask resource overhead, the subtask input-output ratio and the task execution time;
and a task uploading module: uploading a subtask description and a subtask dependency graph to a control plane, wherein the subtask description is the computing resource overhead of the subtask and the transmission data quantity which can be reduced by the subtask;
and the transmission and calculation planning module is used for: according to the network state of the control plane, the subtask description and the subtask dependency graph, adopting a calculation planning algorithm to plan a data transmission path and the deployment position of each subtask;
the task deployment module: according to the transmission path planning result, a routing table is issued to a data plane, and a plurality of subtasks are uploaded to corresponding nodes according to a subtask deployment strategy;
the pass rule algorithm comprises the following steps:
step S4.1: calculating bottleneck resources of the heaven-earth integrated network in the task execution process;
step S4.2: calculating the average transmission hop count between each pair of nodes in the task execution process of the heaven-earth integrated network;
step S4.3: sequencing the subtasks according to the execution dependency relationship and the task execution benefits to obtain a task execution sequence;
step S4.4: combining the network topology graph and the subtask dependency graph to construct a task-topology graph;
step S4.5: calculating a shortest path from the virtual source node to the virtual destination node on the task-topology graph;
step S4.6: and (5) converting the shortest path in the step S4.5 into a transmission path of final data and a subtask deployment strategy.
Priority Applications (1)
| Application Number | Priority Date | Filing Date | Title |
|---|---|---|---|
| CN202111295319.8A CN114024894B (en) | 2021-11-03 | 2021-11-03 | Dynamic calculation method and system in software-defined heaven-earth integrated network |
Applications Claiming Priority (1)
| Application Number | Priority Date | Filing Date | Title |
|---|---|---|---|
| CN202111295319.8A CN114024894B (en) | 2021-11-03 | 2021-11-03 | Dynamic calculation method and system in software-defined heaven-earth integrated network |
Publications (2)
| Publication Number | Publication Date |
|---|---|
| CN114024894A CN114024894A (en) | 2022-02-08 |
| CN114024894B true CN114024894B (en) | 2023-04-25 |
Family
ID=80060400
Family Applications (1)
| Application Number | Title | Priority Date | Filing Date |
|---|---|---|---|
| CN202111295319.8A Active CN114024894B (en) | 2021-11-03 | 2021-11-03 | Dynamic calculation method and system in software-defined heaven-earth integrated network |
Country Status (1)
| Country | Link |
|---|---|
| CN (1) | CN114024894B (en) |
Families Citing this family (1)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN116389284B (en) * | 2023-03-17 | 2023-11-07 | 南通大学 | Dependency graph-based transmission cost optimization method in distributed quantum computing |
Citations (2)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN108600019A (en) * | 2018-04-28 | 2018-09-28 | 电子科技大学 | a kind of network service function chain mapping method |
| WO2020181761A1 (en) * | 2019-03-11 | 2020-09-17 | 江苏君英天达人工智能研究院有限公司 | Sdn enhanced path allocation device and method employing bin-packing technique |
Family Cites Families (3)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN107025205B (en) * | 2016-01-30 | 2021-06-22 | 华为技术有限公司 | Method and equipment for training model in distributed system |
| CN108124294B (en) * | 2016-11-30 | 2019-08-30 | 华中科技大学 | A kind of method for routing under identical recursive calculation constraint |
| CN113542371B (en) * | 2021-06-29 | 2022-05-17 | 西南大学 | Resource scheduling method and system based on edge gateway |
-
2021
- 2021-11-03 CN CN202111295319.8A patent/CN114024894B/en active Active
Patent Citations (2)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN108600019A (en) * | 2018-04-28 | 2018-09-28 | 电子科技大学 | a kind of network service function chain mapping method |
| WO2020181761A1 (en) * | 2019-03-11 | 2020-09-17 | 江苏君英天达人工智能研究院有限公司 | Sdn enhanced path allocation device and method employing bin-packing technique |
Also Published As
| Publication number | Publication date |
|---|---|
| CN114024894A (en) | 2022-02-08 |
Similar Documents
| Publication | Publication Date | Title |
|---|---|---|
| CN109714219B (en) | Virtual network function rapid mapping method based on satellite network | |
| Zhou et al. | An air-ground integration approach for mobile edge computing in IoT | |
| Wang et al. | A dynamic resource scheduling scheme in edge computing satellite networks | |
| Faraci et al. | Design of a 5G network slice extension with MEC UAVs managed with reinforcement learning | |
| Gao et al. | Virtual network function placement in satellite edge computing with a potential game approach | |
| CN109257091B (en) | Global load balancing satellite-ground cooperative network networking device and method | |
| Cheng et al. | 6G service-oriented space-air-ground integrated network: A survey | |
| CN107682068B (en) | Task-driven reconfigurable spatial information network resource management architecture and method | |
| CN111174805A (en) | Distributed centralized automatic driving system | |
| CN109005108B (en) | Space network route planning method and system | |
| CN111447005B (en) | Link planning method and device for software defined satellite network | |
| CN113346944A (en) | Time delay minimization calculation task unloading method and system in air-space-ground integrated network | |
| Guo et al. | Service coordination in the space-air-ground integrated network | |
| Li et al. | Jointly optimized request dispatching and service placement for MEC in LEO network | |
| CN109947574A (en) | A kind of vehicle big data calculating discharging method based on mist network | |
| Wang et al. | Fuzzy-CNN based multi-task routing for integrated satellite-terrestrial networks | |
| CN114024894B (en) | Dynamic calculation method and system in software-defined heaven-earth integrated network | |
| CN106603143A (en) | Space station test platform and controller thereof | |
| Wang et al. | Radio resource allocation for bidirectional offloading in space-air-ground integrated vehicular network | |
| CN106452555A (en) | Multi-path optimization algorithm planning method based on medium and low earth orbit satellite network | |
| Tang et al. | Slicing-based software-defined mobile edge computing in the air | |
| CN112422319B (en) | Simulation system and method of space-based information port system | |
| Gao et al. | Dynamic resource management for neighbor-based VNF placement in decentralized satellite networks | |
| Kim et al. | Satellite network slice planning: Architecture, performance analysis, and open issues | |
| CN117118497A (en) | Controller and gateway joint deployment method suitable for satellite-ground integrated network |
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 |