CN110287024A - The dispatching method of multi-service oriented device multi-user in a kind of industrial intelligent edge calculations - Google Patents
The dispatching method of multi-service oriented device multi-user in a kind of industrial intelligent edge calculations Download PDFInfo
- Publication number
- CN110287024A CN110287024A CN201910506190.7A CN201910506190A CN110287024A CN 110287024 A CN110287024 A CN 110287024A CN 201910506190 A CN201910506190 A CN 201910506190A CN 110287024 A CN110287024 A CN 110287024A
- Authority
- CN
- China
- Prior art keywords
- user
- server
- task
- calculating
- algorithm
- Prior art date
- Legal status (The legal status is an assumption and is not a legal conclusion. Google has not performed a legal analysis and makes no representation as to the accuracy of the status listed.)
- Granted
Links
- 238000000034 method Methods 0.000 title claims abstract description 39
- 238000004364 calculation method Methods 0.000 title claims abstract description 24
- 230000005540 biological transmission Effects 0.000 claims abstract description 19
- 238000007599 discharging Methods 0.000 claims abstract description 18
- 238000006243 chemical reaction Methods 0.000 claims description 4
- 230000003111 delayed effect Effects 0.000 claims description 3
- 230000009467 reduction Effects 0.000 claims description 3
- 230000007246 mechanism Effects 0.000 description 6
- 238000010586 diagram Methods 0.000 description 4
- 230000008859 change Effects 0.000 description 2
- 230000004075 alteration Effects 0.000 description 1
- 230000002146 bilateral effect Effects 0.000 description 1
- 230000007547 defect Effects 0.000 description 1
- 238000001514 detection method Methods 0.000 description 1
- 238000010191 image analysis Methods 0.000 description 1
- 210000003715 limbic system Anatomy 0.000 description 1
- 238000004519 manufacturing process Methods 0.000 description 1
- 230000004048 modification Effects 0.000 description 1
- 238000012986 modification Methods 0.000 description 1
- 230000008447 perception Effects 0.000 description 1
- 230000008569 process 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
- G06F9/48—Program initiating; Program switching, e.g. by interrupt
- G06F9/4806—Task transfer initiation or dispatching
- G06F9/4843—Task transfer initiation or dispatching by program, e.g. task dispatcher, supervisor, operating system
- G06F9/4881—Scheduling strategies for dispatcher, e.g. round robin, multi-level priority queues
-
- G—PHYSICS
- G06—COMPUTING; CALCULATING OR COUNTING
- G06F—ELECTRIC DIGITAL DATA PROCESSING
- G06F9/00—Arrangements for program control, e.g. control units
- G06F9/06—Arrangements for program control, e.g. control units using stored programs, i.e. using an internal store of processing equipment to receive or retain programs
- G06F9/46—Multiprogramming arrangements
- G06F9/50—Allocation of resources, e.g. of the central processing unit [CPU]
- G06F9/5061—Partitioning or combining of resources
- G06F9/5072—Grid computing
-
- G—PHYSICS
- G06—COMPUTING; CALCULATING OR COUNTING
- G06F—ELECTRIC DIGITAL DATA PROCESSING
- G06F2209/00—Indexing scheme relating to G06F9/00
- G06F2209/50—Indexing scheme relating to G06F9/50
- G06F2209/509—Offload
Landscapes
- Engineering & Computer Science (AREA)
- Software Systems (AREA)
- Theoretical Computer Science (AREA)
- Physics & Mathematics (AREA)
- General Engineering & Computer Science (AREA)
- General Physics & Mathematics (AREA)
- Mathematical Physics (AREA)
- Computer And Data Communications (AREA)
- Management, Administration, Business Operations System, And Electronic Commerce (AREA)
Abstract
The invention discloses the dispatching methods of multi-service oriented device multi-user in industrial intelligent edge calculations a kind of, comprising steps of the maximum server of S1, user terminal selection transmission rate, which is sent, calculates unloading request;S2, server selection scheduling algorithm are scheduled receiving for task, and the information for the task that accepts or rejects is sent to user;If receiving, S4 is thened follow the steps, if refusal, thens follow the steps S3;S3, user reduce itself according to server scheduling table and calculate discharging quantity, and issue repeatedly to server and calculate unloading request, and until calculating, unloading request is received by server or user stops autonomously request;S4, server are collected to user calculates unloading expense.Dispatching method multi-service oriented device multi-user application of the invention, and being unloaded for task can meet delay requirement.The method for scheduling task not only meets individual subscriber rationality and quotation authenticity, but also under the limitation of server computing resource, the Income Maximum for calculating time longest and server obtains for saving user.
Description
Technical field
The present invention relates to edge calculations technical field, dispatching method in specially a kind of edge calculations is especially industrial
The dispatching method of multi-service oriented device multi-user in intelligent edge calculations.
Background technique
Industrial Internet of Things (IIoT) is subset of the Internet of Things (IoT) in industrial application, its utilization is so that a large amount of work
Industry equipment (user) can monitor jointly with analytical industry big data, to improve the quality of production and efficiency of enterprise.So
And user is due to the limitation of its computing capability, can not handle the more demanding task of some calculated performances, such as failure predication,
Image analysis etc..It is then faced in addition, transferring data to the data center with powerful calculating ability due to causing over long distances
Time delay problems of too and personal secrets problem, be not particularly suited for IIoT environment.Therefore, industrial intelligent edge calculations will have
Mobile edge calculations (MEC) server disposition of higher computational power provides receipts in the network edge close to user for user
The calculating unloading service taken.Due to MEC server own resources are limited and it is most of provided by third party, with user it
Between transmission rate it is different, it is therefore desirable to design reasonable dispatching method make MEC server offer meet user service
The calculating of quality (QoS) unloads.
In the prior art, Sun Wen et al. is proposed a kind of based on bilateral towards the mobile edge calculations of industrial Internet of Things
The resource allocation methods of auction, however it does not consider that the transmission rate between MEC server and different user is brought
Influence.Zhang Cheng et al. devises a kind of unloading based on density towards the internet of things equipment in mobile limbic system
Strategy, but it assumes that MEC server can receive all tasks for being uploaded to it, but since MEC server computing resource has
Limit, this hypothesis are difficult to meet.Li Longjiang et al. reached towards vehicle mobile edge calculations network design task and
The calculating Unloading Model of Load-aware, that takes into account the factors such as the distance between user and server and server load, but simultaneously
Not designing reasonable incentive mechanism makes server be ready to provide calculating unloading.Zhang Tian et al. is towards edge calculations
In calculating unloading problem propose a kind of syndicate policy model, it is contemplated that server load and selfishness problem, but not
Consider the application scenarios of multiple servers.Therefore these methods are all not applied for facing multiple users multiserver, and server is certainly
The resource-constrained application scenarios with selfishness of body.
In the application of industrial intelligent edge calculations, most scenes are all complex, generally all take comprising multiple MEC
Business device and large-scale consumer, due to distance and bandwidth etc., the transmission rate of these servers to user is different, needs to use
Family selects suitable MEC server to obtain and calculates unloading service.The computing resource of MEC server is limited, therefore can not protect
Meet the unloading demand of all request tasks while demonstrate,proving QoS.
Further, since MEC server is usually provided by third party, there is selfishness, be unwilling actively to provide to calculate to unload
It carries.If user does not provide reasonable calculating expense, server provides refusal to calculating unloading, industrial intelligent edge calculations frame
Frame will be unable to operate normally.
Therefore, existing dispatching method has following defects that
The first, the dispatching method of multi-service oriented device multi-user does not consider that specific user appoints different server unloading
The performance of business is distinguished.
The second, the limited bring limitation of itself computing resource of MEC server is not considered, cannot be wanted meeting user QoS
Receive all tasks in the case of asking.
Third does not consider that MEC server is provided by third party, has selfishness, needing to design reasonable incentive mechanism makes
It obtains it and calculating unloading service is provided.
4th, the authenticity for not considering customer quote needs to design reasonable mechanism and it is made to submit true quotation.
In consideration of it, how to consider the calculating unloading that different server provides under the application scenarios of multiserver multi-user
The performance of service is distinguished, and the QoS requirement of user how is met under the limitation of MEC server computing resource, and how to design conjunction
The incentive mechanism of reason makes MEC server be ready to provide calculating unloading service, while considering that the authenticity of customer quote mentions it
True quotation is handed over, the above becomes those skilled in the art's urgent problem to be solved.
Summary of the invention
The purpose of the present invention is in view of the drawbacks of the prior art, provide in a kind of industrial intelligent edge calculations towards more
The dispatching method of server multi-user.This method makes MEC server provide the calculating unloading service for meeting its QoS for user,
And the Income Maximum that server is obtained, while user reduces the calculating time in the case where meeting its personal financing.With
In solving the problems such as dispatching method practicability in the prior art is low, stability is poor.
In order to achieve the goal above, the invention adopts the following technical scheme:
The dispatching method of multi-service oriented device multi-user in a kind of industrial intelligent edge calculations, comprising steps of
S1, the maximum server of user terminal selection transmission rate, which are sent, calculates unloading request;
S2, server selection scheduling algorithm are scheduled receiving for task, and send to user and accept or reject task
Information;If receiving, S4 is thened follow the steps, if refusal, thens follow the steps S3;
S3, user reduce itself according to server scheduling table and calculate discharging quantity, and issue repeatedly to server and calculate unloading
Request, until calculating, unloading request is received by server or user stops autonomously request;
S4, server are collected to user calculates unloading expense.
Further, the transmission rate are as follows:
Wherein, i is user, and j is server, wjFor server transmission bandwidth, powiFor subscriber signal power, disijFor
The distance between user and server, decay are the attenuation constant that signal power is generated by distance, nijFor channel noise power.
Further, the calculating unloading request are as follows:
[oi,di,bi,ui]
Wherein, oiFor the calculating discharging quantity that task needs, diFor the maximum delay for completing task, biMeeting it for user
Server is paid in the case where personal financing for calculating the quotation of unloading, uiFor the number of user;
The initial value for calculating discharging quantity is all calculation amounts of the task;It is described calculate unloading quotation be less than
User unloads the price of saved calculating time bring income by calculating:
Wherein, eiFor the income of user, ciFor the computing capability of user itself, k is the conversion pass of unit time and currency
System, is determined by upper layer application demand.
Further, the specific steps of the selection scheduling algorithm are as follows:
S21, server determine that sends the number of users threshold value T for calculating unloading request;
S22, server predict active user's quantity, use monovalent maximum calculated if predicted quantity is greater than T
Otherwise method uses total price maximum algorithm.
Further, the predicted quantity are as follows:
A=α time+ β usershort+γ·userlong
Wherein, time indicates current slot number of users situation, usershortFor t before current time pieceshortWhen a
Between piece number of users average value, userlongFor t before current time piecelongThe number of users average value of a timeslice,
tshort< tlong, α, β, γ are weight coefficient.
Further, the specific steps of the dispatching algorithm are as follows:
(1) server deletes having completed in dispatch list for task, and by the d of current calculating tasknIt is revised as
WhereinFor job end time, dnFor task maximum time delay;
(2) by task existing in server delay dispatching as far as possible;
(3) if dispatching algorithm is total price maximum algorithm, server is by all receiving for tasks according to biFrom big to small
It is ranked up;If dispatching algorithm is the maximum algorithm of unit price, server by all receiving for tasks according toFrom greatly to
It is small to be ranked up, wherein cjFor the computing capability of server;
(4) having sorted for task is from left to right successively discharged into dispatch list and delay dispatching as far as possible, if at this time this
Business can be discharged into dispatch list, then send the information that receives an assignment to user, otherwise send refusal mission bit stream to user;
(5) for each received task ta, remove it in all tasks at current time, then hold again
Row step (2)-(4) dispatching algorithm, the task t being rejected until onerReceived at this time.If dispatching algorithm is total price
Maximum algorithm, then paFor br;If dispatching algorithm is the maximum algorithm of unit price, paFor br·cj·oa/or.If without trIt is connect
By then paFor ba.Wherein, paFor task expense.
Further, the dispatch list are as follows:
Wherein, n is task,For job start time, pnFor task expense, unFor the Customs Assigned Number of the task.
Further, the reduction calculates discharging quantity and issues calculating unloading request to server repeatedly are as follows:
User is according to the dispatch list of selected server, by the end time in dispatch list in diTask before is according to dnAs far as possible
It places in advance, by remaining task according to dnPlacement is delayed as far as possible, is then constantly reduced discharging quantity according to suitable step-length and to take
Business device can dispatch the task, until user's price paid is less than 0 or server is in diIt is fully loaded with before;
The suitable step-length are as follows:
Wherein m is the interior maximum times for allowing user to submit unloading request of a timeslice that server determines.
The present invention provides the dispatching method of multi-service oriented device multi-user in industrial intelligent edge calculations a kind of, can make
The Income Maximum of server, and under conditions of guaranteeing user QoS reduce user calculating discharge time;The present invention passes through meter
User is calculated at a distance from server and transmission rate selects optimal service device, it is ensured that the QoS of user;It sends and calculates in user
During unloading request, user can submit the maximum delay requirement of task, guarantee that server provides the clothes for meeting its QoS
Business;Two kinds of dispatching algorithms have also been devised in the present invention, and it is mostly different with few two kinds of prediction number of users to respectively correspond prediction number of users
Used task scheduling algorithm under scene, ensure that the Income Maximum of server;In addition, the present invention, which devises, both meets use
Family personal financing, and guarantee the incentive mechanism of quotation authenticity, it ensure that the reasonability of dispatching method.
Detailed description of the invention
Fig. 1 is the flow diagram of dispatching method of the present invention;
Fig. 2 is multiserver multi-user scene schematic diagram of the present invention.
Fig. 3, Fig. 4, Fig. 5, Fig. 6, Fig. 7, Fig. 8 are the dispatch list schematic diagrames when present invention executes different scheduler tasks.
Specific embodiment
Illustrate embodiments of the present invention below by way of specific specific example, those skilled in the art can be by this explanation
Other advantages and efficacy of the present invention can be easily understood for content disclosed by book.The present invention can also pass through in addition different tools
Body embodiment is embodied or practiced, and the various details in this specification can also not had based on different viewpoints and application
Various modifications or alterations are carried out under spirit of the invention.It should be noted that in the absence of conflict, following embodiment
And the feature in embodiment can be combined with each other.
It should be noted that illustrating the basic structure that only the invention is illustrated in a schematic way provided in following embodiment
Think, only shown in schema then with related component in the present invention rather than component count, shape and size when according to actual implementation
Draw, when actual implementation kenel, quantity and the ratio of each component can arbitrarily change for one kind, and its assembly layout kenel
It may also be increasingly complex.
In order to achieve the above objects and other related objects, the present invention is provided in a kind of industrial intelligent edge calculations towards more
The dispatching method of server multi-user.This method makes MEC server provide the calculating unloading service for meeting its QoS for user,
And the Income Maximum that server is obtained, while user reduces the calculating time in the case where meeting its personal financing.
Due to forming calculating unloading service network by the multiple servers of multiple users in existing industrial Internet of Things application
The case where it is relatively conventional.For example, various industrial equipments pass through various sensor collections apparatus parameter setting information, product matter
Detection information etc. is measured, its own computing capability is limited, needs to provide calculating unloading service by MEC server.Therefore, this hair
Bright to be based primarily upon multiserver multi-user application, i.e. user selects most suitable server to carry out calculating unloading, and server is simultaneously
The task unloading demand information that multiple users submit can be received.
The present invention will be further explained below with reference to the attached drawings and specific examples, but not as the limitation of the invention.
As shown in Figure 1, the present embodiment proposes the tune of multi-service oriented device multi-user in industrial intelligent edge calculations a kind of
Degree method, comprising:
S1, the maximum server of user terminal selection transmission rate, which are sent, calculates unloading request;
Specifically, the specific steps of transmission rate maximum service device are selected described in step S1 are as follows:
S11, user terminal, which are listed, to be the server list of its service;
S12, calculate each server between user at a distance from;
S13, link rate between each server and user is calculated based on the distance;
S14, the selection maximum server of link rate.
Specifically, the server between user at a distance from are as follows:
Wherein, i is user, and j is server, (xi,yi,zi)、(xj,yj,zj) respectively indicate the position of user and server
Coordinate.
Specifically, the link rate between the server and user are as follows:
Wherein, i is user, and j is server, wjFor server transmission bandwidth, powiFor subscriber signal power, disijFor
The distance between user and server, decay are the attenuation constant that signal power is generated by distance, nijFor channel noise power.
Specifically, the calculating unloading request are as follows:
[oi,di,bi,ui]
Wherein, oiFor the calculating discharging quantity that task needs, diFor the maximum delay for completing task, biMeeting it for user
Server is paid in the case where personal financing for calculating the quotation of unloading, uiFor the number of user.
Specifically, the initial value for calculating discharging quantity is all calculation amounts of the task.
Specifically, the quotation for calculating unloading is the calculating time band saved by calculating unloading less than user
The price for the income come:
Wherein, eiFor the income of user, ciFor the computing capability of user itself, k is the conversion pass of unit time and currency
System, is determined by upper layer application demand.
S2, server selection scheduling algorithm are scheduled receiving for task, and send to user and accept or reject task
Information;If receiving, S4 is thened follow the steps, if refusal, thens follow the steps S3;
Specifically, the specific steps of selection scheduling algorithm described in step S2 are as follows:
S21, server determine that sends the number of users threshold value T for calculating unloading request;
S22, server predict active user's quantity, use monovalent maximum calculated if predicted quantity is greater than T
Otherwise method uses total price maximum algorithm.
Specifically, the predicted quantity are as follows:
A=α time+ β usershort+γ·userlong
Wherein, time indicates current slot number of users situation, usershortFor t before current time pieceshortWhen a
Between piece number of users average value, userlongFor t before current time piecelongThe number of users average value of a timeslice,
tshort< tlong, α, β, γ are weight coefficient.
Specifically, the specific steps of the dispatching algorithm are as follows:
(1) server deletes having completed in dispatch list for task, and by the d of current calculating tasknIt is revised as
WhereinFor job end time, dnFor task maximum time delay.
(2) by task existing in server delay dispatching as far as possible.
(3) if dispatching algorithm is total price maximum algorithm, server is by all receiving for tasks according to biFrom big to small
It is ranked up;If dispatching algorithm is the maximum algorithm of unit price, server by all receiving for tasks according toFrom greatly to
It is small to be ranked up, wherein cjFor the computing capability of server.
(4) having sorted for task is from left to right successively discharged into dispatch list and delay dispatching as far as possible, if at this time this
Business can be discharged into dispatch list, then send the information that receives an assignment to user, otherwise send refusal mission bit stream to user.
(5) for each received task ta, remove it in all tasks at current time, then hold again
Row step (2)-(4) dispatching algorithm, the task t being rejected until onerReceived at this time.If dispatching algorithm is total price
Maximum algorithm, then paFor br;If dispatching algorithm is the maximum algorithm of unit price, paFor br·cj·oa/or.If without trIt is connect
By then paFor ba.Wherein, paFor task expense.
S3, user reduce itself according to server scheduling table and calculate discharging quantity, and issue repeatedly to server and calculate unloading
Request, until calculating, unloading request is received by server or user stops autonomously request;
Specifically, dispatch list described in step S3 are as follows:
Wherein, n is task,For job start time, pnFor task expense, unFor the Customs Assigned Number of the task.
Specifically, reduction described in step S3 calculates discharging quantity and issues calculating unloading request to server repeatedly are as follows:
User is according to the dispatch list of selected server, by the end time in dispatch list in diTask before is according to dnAs far as possible
It places in advance, by remaining task according to dnPlacement is delayed as far as possible, is then constantly reduced discharging quantity according to suitable step-length and to take
Business device can dispatch the task, until user's price paid is less than 0 or server is in diIt is fully loaded with before;
Specifically, the suitable step-length are as follows:
Wherein m is the interior maximum times for allowing user to submit unloading request of a timeslice that server determines.
S4, server are collected to user calculates unloading expense.
Multiserver multi-user's task schematic diagram of a scenario as shown in connection with fig. 2, to the industrial intelligent edge meter in the present invention
The time delay perception dispatching method that multi-service oriented device multi-user applies in calculation is illustrated.
Assuming that having 4 MEC servers, respectively s in scene0、s1、s2、s3, coordinate be respectively (1,1,0), (2,2,
0), (3,3,0), (1,1,1), transmission bandwidth wjIt is 1.There are 4 users, respectively u0、u1、 u2、u3, coordinate is respectively
(1,0,0), (0,1,0), (0,0,1), (0,0,0), signal power powiIt is 10.If channel noise power nijIt is 1,
Attenuation constant decay is 0.1.
In current time piece, 4 need to submit to server with there is a calculating unloading task per family.Since privacy is pacified
Full problem, what 4 users listed can be s for the server list of its service0、s1、s2.User calculates and all clothes in list
The distance of business device: dis00=1, dis01=2.24, dis02=3.61, dis10=1, dis11=2.24, dis12=3.61,
dis20=1.73, dis21=3, dis22=4.36, dis30=1.41, dis31=2.83, dis32=4.24.Following user
Calculate the transmission rate with Servers-all in list: c00=1, c01=1.69, c02=2.2, c10=1, c11=1.69, c12
=2.2, c20=1.45, c21=2, c22=2.42, c30=1.27, c31=1.94, c32=2.39.It is calculated according to above, service
Device s0It is maximum with the transmission rate of 4 users, thus 4 with select per family by calculate unloading request be sent to server s0。
User u0、u1、u2、u3Computing capability be respectively as follows: c0=5, c1=5, c2=1, c3=2.The meter of current time piece
It calculates discharging quantity and is respectively as follows: o0=1000, o1=3000, o2=1000, o3=2000.The corresponding completion maximum delay difference of task
Are as follows: d0=20, d1=60, d2=50, d3=60.The conversion relation k=1 of unit time and currency.Therefore, user pays clothes
The calculating of business device unloads expense are as follows: b0=170, b1=530, b2=940, b3=200.
By information above it is found that user u0、u1、u2、u3The calculating of submission, which unloads, to be requested to be respectively as follows: [1000,20,170,
0]、[3000,60,530,1]、[1000,50,940,2]、[2000,60,200,3]。
The number of users threshold value that the transmission of server current setting calculates unloading request is 3, current slot number of users
Situation is flat peak: time=0, usershort=3, userlong=5, weight coefficient be respectively as follows: α=0.1, β=0.5, γ=
0.4.Therefore predicted quantity A=3.5, the maximum dispatching algorithm of server selection unit price.
The computing capability c of serverj=100, and task not to be calculated.Server calculates the unit price of each task,
Respectively 17,17.67,94,10.Therefore, it will be obtained after task ranking: [1000,50,940,2], [3000,60,530,1],
[1000,20,170,0]、[2000,60,200,3]。
First task is first dispatched first, which can be discharged into dispatch list, therefore receive the task, as far as possible by it
It is discharged on the right side of toward dispatch list, as shown in figure 3, dispatch list at this time are as follows:
{[40,50,50,940,2]}。
Next second task of scheduling, which can be discharged into dispatch list, therefore receive the task, as far as possible by it
It is discharged on the right side of toward dispatch list, as shown in figure 4, dispatch list at this time are as follows:
{[10,40,40,530,1],[40,50,50,940,2]}。
Next scheduling third task, which can be discharged into dispatch list, therefore receive the task, as far as possible by it
It is discharged on the right side of toward dispatch list, as shown in figure 5, dispatch list at this time are as follows:
{[0,10,20,170,0],[10,40,40,530,1],[40,50,50,940,2]}。
Next the 4th task of scheduling, which can not be discharged into dispatch list, therefore refuse the task.
First received task [1000,50,940,2] is removed from task list, scheduling is executed again and calculates
Method, task list at this time are as follows: [3000,60,530,1], [1000,20,170,0], [2000,60,200,3].
First task is dispatched first, which can be discharged into dispatch list, which is times that scheduling for the first time receives
It is discharged into toward dispatch list right side, as shown in fig. 6, dispatch list at this time by business as far as possible are as follows:
{[30,60,60,530,1]}。
Next second task of scheduling, the task can be discharged into dispatch list, which is that scheduling receives for the first time
It is discharged into toward dispatch list right side, as shown in fig. 7, dispatch list at this time by task as far as possible are as follows:
{[10,20,20,170,0],[30,60,60,530,1]}。
Next scheduling third task, the task can be discharged into dispatch list, which is that scheduling is refused for the first time
Task, therefore the expense of task [1000,50,940,2] is revised as the valence calculated with the unit price of task [2000,60,200,3]
The price-setting process of lattice 100, task [1000,50,940,2] terminates.
Second task and third task are fixed a price according to identical pricing method, obtain task [3000,60,
530,1] price is 300, and the price of task [1000,20,170,0] is 170.
So far, all task prices finish, dispatch list at this time are as follows:
{[0,10,20,170,0],[10,40,40,300,1],[40,50,50,100,2]}
Task [2000,60,200,3] the owning user u being rejected3According to the dispatch list of server and submission is allowed to unload
Maximum times 2 times of request are carried, discharging quantity to 1000, quotation is reduced and adjusts to 100, with task [1000,60,100,3] submission
To server.
Server is scheduled the task, and task can be discharged into dispatch list, therefore receives the task, as far as possible by it
It is discharged on the right side of toward dispatch list, as shown in figure 8, dispatch list at this time are as follows:
{[0,10,20,170,0],[10,40,40,300,1],[40,50,50,100,2],[50,60,100,3]}。
Server fixes a price to task [1000,60,100,3], and obtaining price is 100, dispatch list at this time are as follows:
{[0,10,20,170,0],[10,40,40,300,1],[40,50,50,100,2],[50,60,100,3]}
Server is to user u0、u1、u2、u3It collects and calculates unloading expense, respectively 170,300,100,100.
So far, which does not have user to submit task, finishing scheduling.
To sum up, the present invention provides a kind of time delay sense of multi-service oriented device multi-user application in industrial intelligent edge calculations
Know dispatching method, the Income Maximum of server can be made, and reduces the calculating unloading of user under conditions of guaranteeing user QoS
Time;The present invention passes through calculating user at a distance from server and transmission rate selects optimal service device, it is ensured that user's
QoS;During user sends and calculates unloading request, user can submit the maximum delay requirement of task, guarantee server
The service for meeting its QoS is provided;Two kinds of dispatching algorithms have also been devised in the present invention, respectively correspond prediction number of users mostly and predict
The few different situations of number of users, ensure that the Income Maximum of server;In addition, the present invention, which devises, both meets individual subscriber
Rationality, and guarantee the incentive mechanism of quotation authenticity, it ensure that the reasonability of dispatching method.
Those of ordinary skill in the art will appreciate that all or part of the steps in the various methods of above-described embodiment is can
It is completed with instructing relevant hardware by program, which can be stored in a computer readable storage medium, storage
Medium may include: ROM, RAM, disk or CD etc..
Note that the above is only a better embodiment of the present invention and the applied technical principle.Those skilled in the art can manage
Solution, the invention is not limited to the specific embodiments described herein, is able to carry out various apparent changes for a person skilled in the art
Change, readjust and substitutes without departing from protection scope of the present invention.Therefore, although by above embodiments to the present invention
It is described in further detail, but the present invention is not limited to the above embodiments only, the case where not departing from present inventive concept
Under, it can also include more other equivalent embodiments, and the scope of the invention is determined by the scope of the appended claims.
Claims (9)
1. the dispatching method of multi-service oriented device multi-user in a kind of industrial intelligent edge calculations, which is characterized in that comprising steps of
S1, the maximum server of user terminal selection transmission rate, which are sent, calculates unloading request;
S2, server selection scheduling algorithm are scheduled receiving for task, and the letter for the task that accepts or rejects is sent to user
Breath;If receiving, S4 is thened follow the steps, if refusal, thens follow the steps S3;
S3, user reduce itself according to server scheduling table and calculate discharging quantity, and issue repeatedly to server and calculate unloading request,
Until calculating, unloading request is received by server or user stops autonomously request;
S4, server are collected to user calculates unloading expense.
2. dispatching method according to claim 1, which is characterized in that the transmission rate are as follows:
Wherein, i is user, and j is server, wjFor server transmission bandwidth, powiFor subscriber signal power, disijFor user with
The distance between server, decay are the attenuation constant that signal power is generated by distance, nijFor channel noise power.
3. dispatching method according to claim 1, which is characterized in that the calculating unloading request are as follows:
[oi,di,bi,ui]
Wherein, oiFor the calculating discharging quantity that task needs, diFor the maximum delay for completing task, biMeeting its people for user
Server is paid in the case where rationality for calculating the quotation of unloading, uiFor the number of user;It is described to calculate the first of discharging quantity
Initial value is all calculation amounts of the task;The quotation for calculating unloading is the calculating saved by calculating unloading less than user
Time and bring income price:
Wherein, eiFor the income of user, ciFor the computing capability of user itself, k is the conversion relation of unit time and currency, by
Upper layer application demand determines.
4. dispatching method according to claim 1, which is characterized in that the specific steps of the selection scheduling algorithm are as follows:
S21, server determine that sends the number of users threshold value T for calculating unloading request;
S22, server predict active user's quantity, monovalent maximum algorithm are used if predicted quantity is greater than T, otherwise
Use total price maximum algorithm.
5. the specific steps of selection scheduling algorithm according to claim 4, which is characterized in that the predicted quantity are as follows:
A=α time+ β usershort+γ·userlong
Wherein, time indicates current slot number of users situation, usershortFor t before current time pieceshortA timeslice
Number of users average value, userlongFor t before current time piecelongThe number of users average value of a timeslice, tshort< tlong,
α, β, γ are weight coefficient.
6. dispatching method according to claim 4, which is characterized in that the specific steps of the dispatching algorithm are as follows:
(1) server deletes having completed in dispatch list for task, and by the d of current calculating tasknIt is revised asWhereinFor job end time, dnFor task maximum time delay;
(2) by task existing in server delay dispatching as far as possible;
(3) if dispatching algorithm is total price maximum algorithm, server is by all receiving for tasks according to biIt is arranged from big to small
Sequence;If dispatching algorithm is the maximum algorithm of unit price, server by all receiving for tasks according toIt carries out from big to small
It sorts, wherein cjFor the computing capability of server;
(4) having sorted for task is from left to right successively discharged into dispatch list and delay dispatching as far as possible, if the task energy at this time
It is discharged into dispatch list, then sends the information that receives an assignment to user, otherwise sends refusal mission bit stream to user;
(5) for each received task ta, remove it in all tasks at current time, then re-execute the steps
(2)-(4) dispatching algorithm, the task t being rejected until onerReceived at this time, if dispatching algorithm is total price maximum calculated
Method, then paFor br;If dispatching algorithm is the maximum algorithm of unit price, paFor br·cj·oa/or;If without trReceived, then pa
For ba;Wherein, paFor task expense.
7. dispatching algorithm according to claim 6, which is characterized in that the dispatch list are as follows:
Wherein, n is task,For job start time, pnFor task expense, unFor the Customs Assigned Number of the task.
8. dispatching method according to claim 1, which is characterized in that the reduction calculates discharging quantity, and repeatedly to service
Device, which issues, calculates unloading request are as follows: user is according to the dispatch list of selected server, by the end time in dispatch list in diBefore
Task is according to dnIt places in advance as far as possible, by remaining task according to dnPlacement is delayed as far as possible, is then constantly reduced according to suitable step-length
Discharging quantity allows server to dispatch the task, until user's price paid is less than 0 or server is in diIt is fully loaded with before.
9. calculating unloading request according to claim 8, which is characterized in that the suitable step-length are as follows:
Wherein m is the interior maximum times for allowing user to submit unloading request of a timeslice that server determines.
Priority Applications (1)
Application Number | Priority Date | Filing Date | Title |
---|---|---|---|
CN201910506190.7A CN110287024B (en) | 2019-06-12 | 2019-06-12 | Multi-server and multi-user oriented scheduling method in industrial intelligent edge computing |
Applications Claiming Priority (1)
Application Number | Priority Date | Filing Date | Title |
---|---|---|---|
CN201910506190.7A CN110287024B (en) | 2019-06-12 | 2019-06-12 | Multi-server and multi-user oriented scheduling method in industrial intelligent edge computing |
Publications (2)
Publication Number | Publication Date |
---|---|
CN110287024A true CN110287024A (en) | 2019-09-27 |
CN110287024B CN110287024B (en) | 2021-09-28 |
Family
ID=68004062
Family Applications (1)
Application Number | Title | Priority Date | Filing Date |
---|---|---|---|
CN201910506190.7A Active CN110287024B (en) | 2019-06-12 | 2019-06-12 | Multi-server and multi-user oriented scheduling method in industrial intelligent edge computing |
Country Status (1)
Country | Link |
---|---|
CN (1) | CN110287024B (en) |
Cited By (4)
Publication number | Priority date | Publication date | Assignee | Title |
---|---|---|---|---|
CN110928599A (en) * | 2019-11-06 | 2020-03-27 | 浙江理工大学 | Task unloading method and system based on data flow in edge computing network |
CN111107153A (en) * | 2019-12-23 | 2020-05-05 | 国网冀北电力有限公司唐山供电公司 | MEC pricing unloading method based on D2D communication in power Internet of things |
CN112306696A (en) * | 2020-11-26 | 2021-02-02 | 湖南大学 | Energy-saving and efficient method and system for unloading edge computing tasks |
CN113282348A (en) * | 2021-05-26 | 2021-08-20 | 浙江理工大学 | Edge calculation task unloading system and method based on block chain |
Citations (4)
Publication number | Priority date | Publication date | Assignee | Title |
---|---|---|---|---|
US20180183855A1 (en) * | 2016-12-28 | 2018-06-28 | Intel Corporation | Application computation offloading for mobile edge computing |
CN108920279A (en) * | 2018-07-13 | 2018-11-30 | 哈尔滨工业大学 | A kind of mobile edge calculations task discharging method under multi-user scene |
CN108964817A (en) * | 2018-08-20 | 2018-12-07 | 重庆邮电大学 | A kind of unloading of heterogeneous network combined calculation and resource allocation methods |
CN109756912A (en) * | 2019-03-25 | 2019-05-14 | 重庆邮电大学 | A kind of multiple base stations united task unloading of multi-user and resource allocation methods |
-
2019
- 2019-06-12 CN CN201910506190.7A patent/CN110287024B/en active Active
Patent Citations (4)
Publication number | Priority date | Publication date | Assignee | Title |
---|---|---|---|---|
US20180183855A1 (en) * | 2016-12-28 | 2018-06-28 | Intel Corporation | Application computation offloading for mobile edge computing |
CN108920279A (en) * | 2018-07-13 | 2018-11-30 | 哈尔滨工业大学 | A kind of mobile edge calculations task discharging method under multi-user scene |
CN108964817A (en) * | 2018-08-20 | 2018-12-07 | 重庆邮电大学 | A kind of unloading of heterogeneous network combined calculation and resource allocation methods |
CN109756912A (en) * | 2019-03-25 | 2019-05-14 | 重庆邮电大学 | A kind of multiple base stations united task unloading of multi-user and resource allocation methods |
Non-Patent Citations (1)
Title |
---|
X.TAO ET.AL: "Preformance guaranteed computation offloading for moblie-edge cloud computing", 《IEEE WIRELESS COMMUN》 * |
Cited By (7)
Publication number | Priority date | Publication date | Assignee | Title |
---|---|---|---|---|
CN110928599A (en) * | 2019-11-06 | 2020-03-27 | 浙江理工大学 | Task unloading method and system based on data flow in edge computing network |
CN110928599B (en) * | 2019-11-06 | 2023-04-18 | 浙江理工大学 | Task unloading method and system based on data flow in edge computing network |
CN111107153A (en) * | 2019-12-23 | 2020-05-05 | 国网冀北电力有限公司唐山供电公司 | MEC pricing unloading method based on D2D communication in power Internet of things |
CN111107153B (en) * | 2019-12-23 | 2022-02-18 | 国网冀北电力有限公司唐山供电公司 | MEC pricing unloading method based on D2D communication in power Internet of things |
CN112306696A (en) * | 2020-11-26 | 2021-02-02 | 湖南大学 | Energy-saving and efficient method and system for unloading edge computing tasks |
CN112306696B (en) * | 2020-11-26 | 2023-05-26 | 湖南大学 | Energy-saving and efficient edge computing task unloading method and system |
CN113282348A (en) * | 2021-05-26 | 2021-08-20 | 浙江理工大学 | Edge calculation task unloading system and method based on block chain |
Also Published As
Publication number | Publication date |
---|---|
CN110287024B (en) | 2021-09-28 |
Similar Documents
Publication | Publication Date | Title |
---|---|---|
CN110287024A (en) | The dispatching method of multi-service oriented device multi-user in a kind of industrial intelligent edge calculations | |
CN110109745B (en) | Task collaborative online scheduling method for edge computing environment | |
CN109656703B (en) | Method for assisting vehicle task unloading through mobile edge calculation | |
CN111427679B (en) | Computing task scheduling method, system and device for edge computing | |
CN111107506B (en) | Network resource safety sharing method based on block chain and auction game | |
CN110825520B (en) | Cluster extremely-fast elastic telescoping method for realizing efficient resource utilization | |
CN106922002A (en) | A kind of network section virtual resource allocation method based on internal auction mechanism | |
CN104219167B (en) | Network resource scheduling method and server | |
CN110888687B (en) | Mobile edge computing task unloading optimal contract design method based on contract design | |
CN111614754B (en) | Fog-calculation-oriented cost-efficiency optimized dynamic self-adaptive task scheduling method | |
Mekala et al. | A DRL-based service offloading approach using DAG for edge computational orchestration | |
CN111711962B (en) | Cooperative scheduling method for subtasks of mobile edge computing system | |
CN107370799B (en) | A kind of online computation migration method of multi-user mixing high energy efficiency in mobile cloud environment | |
Yolken et al. | Game based capacity allocation for utility computing environments | |
CN110149401B (en) | Method and system for optimizing edge calculation task | |
CN111176840A (en) | Distributed task allocation optimization method and device, storage medium and electronic device | |
CN113641417B (en) | Vehicle security task unloading method based on branch-and-bound method | |
CN109005211B (en) | Micro-cloud deployment and user task scheduling method in wireless metropolitan area network environment | |
CN111611076B (en) | Fair distribution method for mobile edge computing shared resources under task deployment constraint | |
CN113961264A (en) | Intelligent unloading algorithm and system for video monitoring cloud edge coordination | |
CN110012507B (en) | Internet of vehicles resource allocation method and system with priority of user experience | |
CN114615705B (en) | Single-user resource allocation strategy method based on 5G network | |
CN114143317B (en) | Cross-cloud-layer mobile edge calculation-oriented multi-priority calculation unloading strategy optimization method | |
CN115016861A (en) | MEC task unloading strategy with task retry and optimization method | |
CN109343940A (en) | Multimedia Task method for optimizing scheduling in a kind of cloud platform |
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 |