CN112162862B - Simple calculation task allocation method in heterogeneous network - Google Patents
Simple calculation task allocation method in heterogeneous network Download PDFInfo
- Publication number
- CN112162862B CN112162862B CN202011069217.XA CN202011069217A CN112162862B CN 112162862 B CN112162862 B CN 112162862B CN 202011069217 A CN202011069217 A CN 202011069217A CN 112162862 B CN112162862 B CN 112162862B
- Authority
- CN
- China
- Prior art keywords
- computing
- layer
- allocated
- task
- resource
- 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
- 238000000034 method Methods 0.000 title claims abstract description 28
- 238000004891 communication Methods 0.000 claims description 16
- 238000005516 engineering process Methods 0.000 description 2
- 230000006978 adaptation Effects 0.000 description 1
- 230000009286 beneficial effect Effects 0.000 description 1
- 230000007547 defect Effects 0.000 description 1
- 239000003595 mist Substances 0.000 description 1
- 238000012986 modification Methods 0.000 description 1
- 230000004048 modification Effects 0.000 description 1
- 238000013468 resource allocation Methods 0.000 description 1
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
- G06F9/46—Multiprogramming arrangements
- G06F9/50—Allocation of resources, e.g. of the central processing unit [CPU]
- G06F9/5061—Partitioning or combining of resources
- G06F9/5066—Algorithms for mapping a plurality of inter-dependent sub-tasks onto a plurality of physical CPUs
-
- 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
- G16—INFORMATION AND COMMUNICATION TECHNOLOGY [ICT] SPECIALLY ADAPTED FOR SPECIFIC APPLICATION FIELDS
- G16Y—INFORMATION AND COMMUNICATION TECHNOLOGY SPECIALLY ADAPTED FOR THE INTERNET OF THINGS [IoT]
- G16Y20/00—Information sensed or collected by the things
- G16Y20/30—Information sensed or collected by the things relating to resources, e.g. consumed power
Abstract
A simple computing task allocation method in a heterogeneous network comprises the following steps: s1: after initializing the system, establishing a computing task set to be distributed; s2: firstly, sorting the computing resource layers according to the sequence from the near to the far from the user; s3: starting from the nearest computing resource layer, solving an optimal allocation problem for each computing resource layer in turn, determining a task set allocated for each layer, and removing the task set from the computing task set to be allocated; s4: and checking whether the to-be-allocated computing task set has remaining unallocated computing tasks, if yes, and is different from the to-be-allocated computing task set used in the current round S1, updating the computing task set, updating the number of computing resources of each layer, and repeating the step S1. If no unallocated computing task remains or the same as the computing task set to be allocated used in the present round S1, the allocation is ended. By the method, a simple and rapid calculation task distribution method can be obtained, and the overall performance of the network is improved.
Description
Technical Field
The invention belongs to the fields of heterogeneous networks, edge computing, internet of vehicles, wireless communication, communication systems, network resource allocation and the like, and particularly relates to a simple computing task allocation method in a heterogeneous network.
Background
In recent years, due to the rise of various intelligent technologies such as internet of vehicles, application scenes of communication and calculation by means of networks are more and more increased, and in order to adapt to such changes, networks are gradually developed to include heterogeneous networks with different levels, such as common heterogeneous networks, including a cloud center at a far end, a small cloud center slightly close to an end user, and a mist node nearest to the end user. The network layers with different communication performance and calculation performance form a heterogeneous network. In order to enable technology of driving 6G such as internet of vehicles and edge computing to develop smoothly, it is necessary to study allocation of computing tasks in heterogeneous networks. The patent provides a simple calculation task allocation method by considering the distance between each layer of calculation resources and users, the calculation capability of each layer and the difference of communication resources of each layer of calculation resources.
Disclosure of Invention
Aiming at the defects in the prior art, the invention provides a simple calculation task allocation method in a heterogeneous network, and aims to fill the gap of calculation task allocation in the heterogeneous network and further improve the performance of the heterogeneous network.
In order to achieve the above purpose, the present invention adopts the following technical scheme:
a simple calculation task allocation method in a heterogeneous network is characterized by comprising the following steps:
s1: after initializing the system, establishing a computing task set to be distributed;
s2: ordering the computing resource layers in order from near to far from the user;
s3: starting from the nearest computing resource layer, solving an optimal allocation problem for each computing resource layer in sequence, determining a computing task set allocated for each layer, and removing the computing task set from the computing task set to be allocated;
s4: checking whether the to-be-allocated computing task set has residual unallocated computing tasks, if yes, and is different from the initial to-be-allocated computing task set in the step S1 of the round, updating the to-be-allocated computing task set, updating the number of computing resources of each layer, and repeating the step S1; if no unallocated computing task remains or is the same as the initial computing task set to be allocated in step S1 in this round, allocation is ended.
In order to optimize the technical scheme, the specific measures adopted further comprise:
further, in step S1, system parameters are initialized to obtain a set of computing tasks a to be distributed, and each time a computing task a is completed i The benefit obtained by heterogeneous networks is p i I represents a calculation task number, a i E A; the first layer of heterogeneous network is user layer, the second layer is user access layer, the third layer is computing resource layer, the total communication resource and total computing resource of each computing resource layer are r respectively j And m j Wherein the subscript j=3, …, N denotes the number of the computing resource layer, N denotes the maximum number of the computing resource layer, and the communication resources and computing resources each computing task needs to consume each computing resource layer are respectivelyAnd->。
Further, in step S3, the calculation task allocation problem in the heterogeneous network is divided into a plurality of independent calculation task allocation problems, and according to the order of the step S2, the optimal allocation problem is solved for each calculation resource layer in turn;
for the third computing resource layer nearest to the user, i.e. j=3, the following problem is solved:
obtaining a computing task A distributed to third-layer computing resources through a poor search method 3 The method comprises the steps of carrying out a first treatment on the surface of the Updating a set of computing tasks to be allocated A-A 3 The method comprises the steps of carrying out a first treatment on the surface of the For the j=4, …, N computing resource layers, the following problem is solved:
obtaining a computing task A distributed to a j-th layer computing resource through a poor search method j The method comprises the steps of carrying out a first treatment on the surface of the Updating a set of computing tasks to be allocated
Wherein the binary variable x i，j Indicating to which layer each computing task is assigned, x i，j When=0, the calculation task a is represented i Not assigned to the j-th computing resource layer; when x is i，j When=1, the calculation task a is represented i Is allocated to the j-th computing resource layer; the computing tasks may be assigned to at most one computing resource layer.
Further, in step S4, the set of computing tasks is checkedIf there are any remaining unallocated computing tasks, if there are any remaining unallocated computing tasks and different from the computing task set to be allocated a used in the step S1 of this round, updating the computing task set to be allocated, updating the number of computing resources of each layer, and repeating the step S1; if no unallocated computing task remains or is the same as the computing task set a to be allocated used in step S1 in this round, allocation is ended.
The beneficial effects of the invention are as follows: and the computing tasks are simply distributed, so that the computing task distribution performance in the heterogeneous network is improved.
Drawings
Fig. 1 is a flow chart of a simple computing task allocation method in a heterogeneous network according to the present invention.
Detailed Description
The invention will now be described in further detail with reference to the accompanying drawings.
Assuming a heterogeneous network, the lowest first layer is a user layer, the second layer is a user access layer, the third layer to the fifth layer are all computing resource layers, are edge computing resource layers of the third layer respectively, and comprise individual computing resources such as small base stations, etc., a small cloud computing resource layer of the fourth layer, such as a unit or an operator, establishes a small cloud center, and a cloud computing resource layer of the fifth layer, such as a large cloud computing center established by a professional cloud computing operator. In the heterogeneous network, if the computing resources of the user cannot process the computing tasks in time, the user of the user layer needs to distribute the computing tasks to three computing resource layers for processing through the second layer user access layer, and the number set of the computing tasks to be distributed is assumed to be A. Since the allocation of computing resources involves communication resources and the allocation of computing resources, we will give definitions below, respectively. The total communication resource of the edge computing resource layer of the third layer is r 3 The total computation resource is m 3 The method comprises the steps of carrying out a first treatment on the surface of the The total communication resource of the fourth small cloud computing resource layer is r 4 The total computation resource is m 4 The method comprises the steps of carrying out a first treatment on the surface of the The total communication resource of the cloud computing resource layer of the fifth layer is r 5 The total computation resource is m 5 . Each computing task needsThe consumption of communication resources and computing resources of each layer is respectivelyAnd->Where subscript j=3, 4,5 denotes the number of the computing resource layer, i denotes the computing task number, a i E a denotes a computing task numbered i. Every time a computing task a is completed i The benefits that the heterogeneous network can obtain are p i . Assuming to which layer each task is assigned, a binary variable x i，j Representation, where x i，j When=0, the calculation task a is represented i Not assigned to the computing resource j-th layer; when x is i，j When=1, the calculation task a is represented i Is assigned to the j-th layer of computing resources. The computing tasks may be assigned to at most one computing resource layer.
Fig. 1 is a flowchart of a simple computing task allocation method in a heterogeneous network, and the specific steps are as follows:
firstly, initializing system parameters, firstly obtaining a number set A of calculation tasks to be distributed, and finishing one calculation task a each time i The benefits that the heterogeneous network can obtain are p i ，a i E A; total communication resource r of each computing resource layer j Sum total computing resource m j Wherein the subscript j=3, 4,5 denotes the number of the computing resource layer and each computing task needs to consume the communication resources and computing resources of each layer separately asAnd->Where subscript j=3, 4,5 denotes the number of the computing resource layer, i denotes the computing task number, a i ∈A。
Second, after initialization, the computing resource layers are ordered in order from near to far from the user.
Thirdly, dividing the calculation task allocation problem in the network into three independent calculation task allocation problems, and respectively solving the optimal allocation problem. According to the well-ordered sequence of the first step, aiming at the third computing resource layer, the following problems are solved:
by the poor search method, the computing task A distributed to the computing resources of the third layer can be obtained 3 . Updating a set of computing tasks to be allocated A-A 3 The establishment of the problems:
by the search method, the computing resources distributed to the fourth layer can be obtainedBusiness A 4 . Updating a set of computing tasks to be allocated A-A 3 -A 4 The establishment of the problems:
by the search method, the computing task A distributed to the fifth layer computing resource can be obtained 5 . Updating a set of computing tasks to be allocated A-A 3 -A 4 -A 5 。
Fourth step, checking the computing task set A-A 3 -A 4 -A 5 If there are any remaining unallocated computing tasks, and if they are different from the to-be-allocated computing task set used in the step S1 of this round, updating the to-be-allocated computing task set, updating the number of computing resources of each layer, and repeating the step S1. If no unallocated computing task remains or the same computing task set to be allocated as used in step S1 of the present round, the allocation is ended.
The above is only a preferred embodiment of the present invention, and the protection scope of the present invention is not limited to the above examples, and all technical solutions belonging to the concept of the present invention belong to the protection scope of the present invention. It should be noted that modifications and adaptations to the invention without departing from the principles thereof are intended to be within the scope of the invention as set forth in the following claims.
Claims (2)
1. A simple calculation task allocation method in a heterogeneous network is characterized by comprising the following steps:
s1: after initializing the system, establishing a computing task set to be distributed;
s2: ordering the computing resource layers in order from near to far from the user;
s3: starting from the nearest computing resource layer, solving an optimal allocation problem for each computing resource layer in sequence, determining a computing task set allocated for each layer, and removing the computing task set from the computing task set to be allocated;
s4: checking whether the to-be-allocated computing task set has residual unallocated computing tasks, if yes, and is different from the initial to-be-allocated computing task set in the step S1 of the round, updating the to-be-allocated computing task set, updating the number of computing resources of each layer, and repeating the step S1; if no unallocated computing task remains or is the same as the initial computing task set to be allocated in the step S1 of the round, ending allocation;
in step S1, system parameters are initialized to obtain a set A of computing tasks to be distributed, and each time a computing task a is completed i The benefit obtained by heterogeneous networks is p i I represents a calculation task number, a i E A; the first layer of heterogeneous network is user layer, the second layer is user access layer, the third layer is computing resource layer, the total communication resource and total computing resource of each computing resource layer are r respectively j And m j Wherein the subscript j=3, …, N represents the number of the computing resource layer, N represents the maximum number of the computing resource layer, and each computing task needs to consume the communication resource and the computing resource of each computing resource layer are respectivelyAnd->
In step S3, dividing the calculation task allocation problem in the heterogeneous network into a plurality of independent calculation task allocation problems, and sequentially solving the optimal allocation problem for each calculation resource layer according to the sequence arranged in step S2;
for the third computing resource layer nearest to the user, i.e. j=3, the following problem is solved:
obtaining a computing task A distributed to third-layer computing resources through a poor search method 3 The method comprises the steps of carrying out a first treatment on the surface of the Updating a set of computing tasks to be allocated A-A 3 ；
For the j=4, …, N computing resource layers, the following problem is solved:
obtaining a computing task A distributed to a j-th layer computing resource through a poor search method j The method comprises the steps of carrying out a first treatment on the surface of the Updating a set of computing tasks to be allocated
Wherein the binary variable x i,j Indicating to which layer each computing task is assigned, x i,j When=0, the calculation task a is represented i Not assigned to the j-th computing resource layer; when x is i,j When=1, the calculation task a is represented i Is allocated to the j-th computing resource layer; the computing tasks may be assigned to at most one computing resource layer.
2. The method for simple computing task allocation in a heterogeneous network of claim 1, wherein: in step S4, the computing task set is checkedIf there are any remaining unallocated computing tasks, if there are any remaining unallocated computing tasks and different from the computing task set to be allocated a used in the step S1 of this round, updating the computing task set to be allocated, updating the number of computing resources of each layer, and repeating the step S1; if no unallocated computing task remains or is the same as the computing task set a to be allocated used in step S1 in this round, allocation is ended.
Priority Applications (1)
| Application Number | Priority Date | Filing Date | Title |
|---|---|---|---|
| CN202011069217.XA CN112162862B (en) | 2020-09-30 | 2020-09-30 | Simple calculation task allocation method in heterogeneous network |
Applications Claiming Priority (1)
| Application Number | Priority Date | Filing Date | Title |
|---|---|---|---|
| CN202011069217.XA CN112162862B (en) | 2020-09-30 | 2020-09-30 | Simple calculation task allocation method in heterogeneous network |
Publications (2)
| Publication Number | Publication Date |
|---|---|
| CN112162862A CN112162862A (en) | 2021-01-01 |
| CN112162862B true CN112162862B (en) | 2024-01-19 |
Family
ID=73861051
Family Applications (1)
| Application Number | Title | Priority Date | Filing Date |
|---|---|---|---|
| CN202011069217.XA Active CN112162862B (en) | 2020-09-30 | 2020-09-30 | Simple calculation task allocation method in heterogeneous network |
Country Status (1)
| Country | Link |
|---|---|
| CN (1) | CN112162862B (en) |
Citations (7)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| EP2949166A1 (en) * | 2013-01-23 | 2015-12-02 | Telefonaktiebolaget L M Ericsson (publ) | Resource allocation in a radio communication network |
| CN108990159A (en) * | 2018-07-12 | 2018-12-11 | 东南大学 | Federated resource distribution method based on layering game in mobile edge calculations system |
| CN109413724A (en) * | 2018-10-11 | 2019-03-01 | 重庆邮电大学 | A kind of task unloading and Resource Allocation Formula based on MEC |
| CN110769059A (en) * | 2019-10-28 | 2020-02-07 | 中国矿业大学 | Collaborative service deployment and business distribution method for regional edge computing Internet of things |
| CN111258677A (en) * | 2020-01-16 | 2020-06-09 | 重庆邮电大学 | Task unloading method for heterogeneous network edge computing |
| CN111262944A (en) * | 2020-01-20 | 2020-06-09 | 北京大学 | Method and system for hierarchical task offloading in heterogeneous mobile edge computing network |
| CN111447619A (en) * | 2020-03-12 | 2020-07-24 | 重庆邮电大学 | Joint task unloading and resource allocation method in mobile edge computing network |
Family Cites Families (3)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| US8392926B2 (en) * | 2010-04-06 | 2013-03-05 | International Business Machines Corporation | Scheduling heterogeneous partitioned resources with sharing constraints |
| US20140280701A1 (en) * | 2013-03-14 | 2014-09-18 | Comcast Cable Communications, Llc | Distributed computing |
| US20170277568A1 (en) * | 2016-03-25 | 2017-09-28 | International Business Machines Corporation | Allocating resources among tasks under uncertainty |
-
2020
- 2020-09-30 CN CN202011069217.XA patent/CN112162862B/en active Active
Patent Citations (7)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| EP2949166A1 (en) * | 2013-01-23 | 2015-12-02 | Telefonaktiebolaget L M Ericsson (publ) | Resource allocation in a radio communication network |
| CN108990159A (en) * | 2018-07-12 | 2018-12-11 | 东南大学 | Federated resource distribution method based on layering game in mobile edge calculations system |
| CN109413724A (en) * | 2018-10-11 | 2019-03-01 | 重庆邮电大学 | A kind of task unloading and Resource Allocation Formula based on MEC |
| CN110769059A (en) * | 2019-10-28 | 2020-02-07 | 中国矿业大学 | Collaborative service deployment and business distribution method for regional edge computing Internet of things |
| CN111258677A (en) * | 2020-01-16 | 2020-06-09 | 重庆邮电大学 | Task unloading method for heterogeneous network edge computing |
| CN111262944A (en) * | 2020-01-20 | 2020-06-09 | 北京大学 | Method and system for hierarchical task offloading in heterogeneous mobile edge computing network |
| CN111447619A (en) * | 2020-03-12 | 2020-07-24 | 重庆邮电大学 | Joint task unloading and resource allocation method in mobile edge computing network |
Non-Patent Citations (1)
| Title |
|---|
| 车联网中基于移动边缘计算的内容感知分类卸载算法研究;赵海涛;朱银阳;丁仪;朱洪波;;电子与信息学报(第01期);全文 * |
Also Published As
| Publication number | Publication date |
|---|---|
| CN112162862A (en) | 2021-01-01 |
Similar Documents
| Publication | Publication Date | Title |
|---|---|---|
| CN110505644B (en) | User task unloading and resource allocation joint optimization method | |
| Wu et al. | An efficient offloading algorithm based on support vector machine for mobile edge computing in vehicular networks | |
| CN110109745A (en) | A kind of task cooperation on-line scheduling method for edge calculations environment | |
| CN111711666B (en) | Internet of vehicles cloud computing resource optimization method based on reinforcement learning | |
| CN110519370B (en) | Edge computing resource allocation method based on facility site selection problem | |
| CN104142860A (en) | Resource adjusting method and device of application service system | |
| CN110519090B (en) | Method and system for allocating accelerator cards of FPGA cloud platform and related components | |
| CN111182495B (en) | 5G internet of vehicles partial calculation unloading method | |
| CN111611076B (en) | Fair distribution method for mobile edge computing shared resources under task deployment constraint | |
| CN109495565B (en) | High-concurrency service request processing method and device based on distributed ubiquitous computing | |
| CN110167031B (en) | Resource allocation method, equipment and storage medium for centralized base station | |
| Kumar et al. | A K-means clustering based message forwarding model for Internet of Things (IoT) | |
| CN112162862B (en) | Simple calculation task allocation method in heterogeneous network | |
| CN109062683B (en) | Method, apparatus and computer readable storage medium for host resource allocation | |
| CN112181658B (en) | Calculation task allocation method for maximizing network benefits in heterogeneous network | |
| CN111626354B (en) | Clustering method applied to Internet of vehicles and based on task dependency | |
| CN107918676A (en) | The method for optimizing resources and database inquiry system of structuralized query | |
| CN109089323B (en) | Low-overhead industrial wireless sensor selection method | |
| CN110177383B (en) | Efficiency optimization method based on task scheduling and power allocation in mobile edge calculation | |
| CN105138391B (en) | The multitasking virtual machine distribution method of cloud system justice is distributed towards wide area | |
| Cui et al. | Intelligent task offloading algorithm for mobile edge computing in vehicular networks | |
| CN113595801B (en) | Edge cloud network server deployment method based on task traffic and timeliness | |
| CN112468547B (en) | Regional-based industrial edge computing task cloud collaborative unloading method | |
| CN113347277B (en) | Unloading distribution method based on task segmentation in edge calculation | |
| CN111049900B (en) | Internet of things flow calculation scheduling method and device and electronic equipment |
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 |