CN109905859A - A kind of efficient edge computation migration method for car networking application - Google Patents
A kind of efficient edge computation migration method for car networking application Download PDFInfo
- Publication number
- CN109905859A CN109905859A CN201910031387.XA CN201910031387A CN109905859A CN 109905859 A CN109905859 A CN 109905859A CN 201910031387 A CN201910031387 A CN 201910031387A CN 109905859 A CN109905859 A CN 109905859A
- Authority
- CN
- China
- Prior art keywords
- node
- vehicle
- indicate
- car networking
- task
- 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
Classifications
-
- Y—GENERAL TAGGING OF NEW TECHNOLOGICAL DEVELOPMENTS; GENERAL TAGGING OF CROSS-SECTIONAL TECHNOLOGIES SPANNING OVER SEVERAL SECTIONS OF THE IPC; TECHNICAL SUBJECTS COVERED BY FORMER USPC CROSS-REFERENCE ART COLLECTIONS [XRACs] AND DIGESTS
- Y02—TECHNOLOGIES OR APPLICATIONS FOR MITIGATION OR ADAPTATION AGAINST CLIMATE CHANGE
- Y02D—CLIMATE CHANGE MITIGATION TECHNOLOGIES IN INFORMATION AND COMMUNICATION TECHNOLOGIES [ICT], I.E. INFORMATION AND COMMUNICATION TECHNOLOGIES AIMING AT THE REDUCTION OF THEIR OWN ENERGY USE
- Y02D30/00—Reducing energy consumption in communication networks
- Y02D30/70—Reducing energy consumption in communication networks in wireless communication networks
Abstract
The present invention provides a kind of efficient edge computation migration methods for car networking application, comprising the following steps: S1, the application demand for obtaining the migration task that the current location information of vehicle and vehicle generate in car networking;S2, obtain car networking in it is all while calculate node location information and while node computing resource situation;S3, the application demand at a distance from node and migrating task is calculated with side according to vehicle, filters out ineligible side and calculates node;S4, calculate each migration strategy needed for time and energy consumption;S5, optimal computation migration strategy is obtained by simple additive weight and multi-standard decision making algorithm.The method of the present invention reduces the energy consumption that side calculates node to the full extent, improves the utilization rate that side calculates node after the requirement of the computing capability and computing relay that meet calculating task.
Description
Technical field
The present invention relates to a kind of efficient edge calculations moving methods, belong to mobile edge calculations technical field.
Background technique
Extensive concern with the continuous development and people of transport service to traffic safety, car networking (Internet of
Vehicles, IoV) it has gradually developed.One of main application as Internet of Things, car networking be better achieved vehicle it
Between, the information exchange between people and vehicle, between vehicle and roadside unit (Roadside Unit, RSU), substantially increase traffic peace
Entirely.Continuous with car networking is popularized, and the application based on this is also being continuously increased, especially many to prolong to computing capability, response
Application more demanding late, at present much using proposed demand considerably beyond the calculation processing energy of vehicle itself
Power.
When mobile cloud computing is introduced into the environment of car networking, vehicle can migrate calculating task to long-distance cloud and put down
Platform executes, and is equivalent to the computing resource for having expanded vehicle, meets the computing capability requirement of calculating task, still, vehicle is meter
Calculation task by wide area network (Wide Area Network, WAN) migrate it is more to the time needed for long-range cloud platform, meet not
The low time delay requirement of calculating task.
Mobile edge calculations have well solved the long-range longer problem of cloud platform calculation delay.RSU and server composition
Side calculate equipment (Edge Computing Device, ECD) be a kind of small-sized cloud, it is typically deployed near vehicle, provides
The cloud service of enhancing, thus vehicle calculating task move on ECD execute can greatly reduce time delay, improve the service of user
Experience.But the resource of ECD is limited, and the energy consumption that calculating node execution computation migration task in side generates is also more.Cause
How this is efficiently the emphasis of contemporary scientific research using the resource of ECD.In specific operation, optionally calculating cannot be appointed
Business moves to be executed on ECD, it is necessary to the reasonable distribution of ECD resource could be not only realized in a kind of reasonable computation migration method, but also
Meet the needs of calculating task low time delay, while reducing the energy consumption that side calculates node to the full extent.
Currently, many scientific research personnel are dedicated to designing utilization rate of the efficient computation migration mechanism to improve cloudlet, for example,
M.Wang et al. is in " Toward Mobility Support for Information-Centric IoV in Smart
Consider that mist, which is calculated (Fog Computing), to be introduced into IoV environment in City Using Fog Computing ", according to not
Same service features design a dynamic service support mechanism;Y.Cao et al. is in " QoE-based node selection
It proposes and is based in strategy for edge computing enabled Internet-of-Vehicles (EC-IoV) "
The concept for the car networking (edge computing enabled Internet-of-Vehicles, EC-IoV) that side calculates utilizes
Online vehicles devise one based on user experience quality (Quality of as edge calculations platform
Experience, QoE) node selection strategy, to select optimal side to calculate node for user.But in current car networking
Computation migration technology research almost without consider ECD energy consumption problem, when migration strategy is able to satisfy calculating task
When prolonging demand, the energy consumption of ECD is also very important.
Summary of the invention
For the feelings for only taking into account delay requirement in current car networking computation migration technology and not accounting for ECD energy consumption problem
Condition, the invention proposes a kind of efficient edge computation migration methods for car networking application, for more and more car networkings
Using can propose a kind of computation migration strategy in real time according to the information of vehicle and ECD, both can satisfy vehicle calculation delay
With the demand in energy consumption, while the car networking service experience of user can be enhanced.
In order to solve the above technical problems, present invention employs following technological means:
A kind of efficient edge computation migration method for car networking application, specifically includes the following steps:
S1, the application demand for obtaining the migration task that the current location information of vehicle and vehicle generate in car networking;
S2, obtain car networking in it is all while calculate node location information and it is each while node computing resource situation;
S3, the application demand at a distance from node and migrating task is calculated with side according to vehicle, filtered out ineligible
Side calculates node;
S4, vehicle calculating task is matched one by one with qualified side node, is calculated needed for each migration strategy
Time and energy consumption;
S5, optimal computation migration strategy is obtained by simple additive weight and multi-standard decision making algorithm.
Further, the concrete operations of step S1 are as follows:
It include M vehicle, the m vehicle c in S11, car networking region AmIn the coordinate cp at i momentm,iIt is as follows:
cpm,i=(cpxm,i,cpym,i) (1)
Wherein, cpxm,iIndicate i moment vehicle cmAbscissa positions in region a, cpym,iIndicate i moment vehicle cm?
Ordinate position in the A of region, m=1,2 ..., M.
S12, the m vehicle cmThe calculating task of generation is tm=(twm,trm,tw'm), wherein twmIndicate calculating task tm
Task amount, trmIt indicates to execute tmRequired resource, tw'mIt indicates to execute the data volume for terminating to return.
Further, N number of side is set in the A of car networking region in step S2 and calculates node, side calculates the expression formula of node
It is as follows:
en=(epxn,epyn,eqn,ern) (2)
Wherein, enIndicate that n-th of side calculates node, n=1,2 ..., N, epxnIndicate enAbscissa position in region a
It sets, epynIndicate enOrdinate position in region a, eqnIndicate enTotal capacity, ernIndicate enIdling-resource.
Further, trm、eqnAnd ernAll use the form calculus of virtual machine quantity.
Further, the concrete operations of step S3 are as follows:
S31, all sides of comparison calculate the idling-resource of node and execute the size of vehicle required by task resource, work as trm>
ern, vehicle cmCalculating task tmThe side cannot be moved to and calculate node.
S32, vehicle c is calculatedmNode e is calculated to sidenDistance:
S33, as dis (cm,en) < ρ, ρ enSphere of action, vehicle cmCalculating task tmSide meter cannot be moved to
Calculate node, and cannot move to this while the node side opposite with vehicle heading while node on.
Further, the concrete operations of step S4 are as follows:
S41, the qualified target side of selection one calculate a target carriage in node and destination node sphere of action
?.
S42, vehicle c is calculatedmCalculating task tmIt is transferred to target vehicle cnTime Ttm, target vehicle cnTmMigration
Node e is calculated to target sidenTime Tom、enExecute the time Te of calculating taskmAnd enCalculated result is fed back to cmTime
Tfm, specific formula is as follows:
Wherein, v indicates the transmission rate between vehicle, λm,nIndicate calculating task from cmIt is transferred to cnThe vehicle passed through
Number, v ' expression vehicle and side calculate the transmission rate between node, and p indicates the computing capability of each virtual machine.
Overall delay T needed for S43, computation migration strategy:
S44, side calculating node e is calculatednBasic energy consumption Ebn, idle energy consumption EinWith occupancy energy consumption Eun:
Ebn=Tsn·Pα (9)
Wherein, TsnIndicate enServer runing time, PαIndicate that side calculates node enThe power of server, Bm,nTable
Show calculating task tmWhether in enUpper execution, PβIndicate enThe power of upper unappropriated resource, PγIndicate enThe resource of upper occupancy
Power.
S45, side calculating node e is calculatednTotal energy consumption E:
Further, the concrete operations of step S5 are as follows:
S51, pass through simple additive weight and multi-standard decision making algorithm, the overall delay and total energy consumption point of each computation migration strategy
It is not normalized are as follows:
Wherein, TmaxAnd TminRespectively indicate maximum time delay and the smallest time delay caused by computation migration, EmaxAnd Emin
Respectively indicate maximum energy consumption and the smallest energy consumption caused by computation migration.
S52, the value of utility for calculating each migration strategy obtain the maximum computation migration strategy of value of utility:
UV=V (T) ωT+V(E)·ωE(ωT+ωE=1) (15)
Wherein, ωTIndicate the weight of V (T), ωERespectively indicate the weight of V (E).
Using following advantage can be obtained after the above technological means:
The invention proposes a kind of efficient edge computation migration methods for car networking application, obtain vehicle in car networking
The information that node is calculated with side filters out ineligible side according to computation migration task application resource requirement and calculates node,
Then according to satisfactory node plan migration strategy, the energy consumption of time needed for calculating each migration strategy and generation,
Optimal computation migration strategy is finally selected according to SAW and MCDM.The considerations of the method for the present invention, calculating was moved to vehicle driving situation
The transmission between vehicle and vehicle and vehicle and side are applied during moving and calculates migrating technology between node, it is ensured that calculating task can be with
Normal migration, improves the efficiency of transition process;Meanwhile the computation migration strategy of this method is with specific information of vehicles and side meter
It calculates the information of node and dynamically changes, so that the result of computation migration is more objective credible.Compared with traditional calculations moving method, this
Inventive method comprehensively considers the energy consumption for executing delay and the generation of calculating task, in the computing capability and calculating for meeting calculating task
After the requirement of delay, the energy consumption that side calculates node is reduced to the full extent, meets the theme of green calculating, and make rational planning for
The migration of calculating task, the utilization efficiency for making side calculate node maximize.
Detailed description of the invention
Fig. 1 is a kind of step flow chart of the efficient edge computation migration method for car networking application of the present invention.
Fig. 2 is a kind of car networking instance graph of the efficient edge computation migration method for car networking application of the present invention.
Specific embodiment
Technical solution of the present invention is described further with reference to the accompanying drawing:
A kind of efficient edge computation migration method for car networking application, as shown in Figure 1, specifically includes the following steps:
S1, the application demand for obtaining the migration task that the current location information of vehicle and vehicle generate in car networking;Tool
Gymnastics is made as follows:
S11, assume that shared M vehicle driving on a road, indicates the road area using x-y coordinate system, define
Car networking region A=(x, y) | and 0≤x≤X, 0≤y≤Y }, C={ c1,c2,…,cMIndicate vehicle set, cmIndicate region
The m vehicle in A, cmIn the coordinate cp at i momentm,iAre as follows:
cpm,i=(cpxm,i,cpym,i) (16)
Wherein, cpxm,iIndicate i moment vehicle cmAbscissa positions in region a, cpym,iIndicate i moment vehicle cm?
Ordinate position in the A of region, m=1,2 ..., M.
S12, each car can generate the calculating task needed to be implemented, therefore share in this car networking environment
M calculating task generates, and calculating task can be expressed as set T={ t1,t2,…,tM, wherein tmIndicate what the m vehicle generated
Calculating task.
The m vehicle cmThe calculating task of generation can be expressed as tm=(twm,trm,tw'm), wherein twmIt indicates to calculate and appoint
Be engaged in tmTask amount, trmIt indicates to execute tmRequired resource, tw'mIt indicates to execute the data volume for terminating to return.In present invention side
In method, resource required for calculating task is to execute the quantity of the occupied virtual machine instance of calculating task.
S2, obtain car networking in it is all while calculate node location information and it is each while node computing resource situation;?
The N number of side of setting calculates node, E={ e in the A of car networking region1,e2,…,eN, the expression formula that side calculates node is as follows:
en=(epxn,epyn,eqn,ern) (17)
Wherein, enIndicate that n-th of side calculates node, n=1,2 ..., N, epxnIndicate enAbscissa position in region a
It sets, epynIndicate enOrdinate position in region a, eqnIndicate enTotal capacity, ernIndicate enIdling-resource.
In the methods of the invention, side calculates the idling-resource of node and total capacity is given in the form of virtual machine quantity
Out, the physical resource that side calculates node is equally divided into several virtual machines, calculates node progress when calculating task moves to side
When execution, corresponding virtual machine is instantiated.
S3, the application demand at a distance from node and migrating task is calculated with side according to vehicle, filtered out ineligible
Side calculates node;Concrete operations are as follows:
S31, all sides of comparison calculate the idling-resource of node and execute the size of vehicle required by task resource, when side calculates
Computing resource, i.e. tr needed for the idling-resource of node is less than calculating taskm> ernWhen, vehicle cmCalculating task tmIt cannot move
It moves on to the side and calculates node.
S32, vehicle c is calculatedmNode e is calculated to sidenDistance:
S33, side calculate node with a sphere of action ρ, referred to as effective links, as dis (cm,en) < ρ, then cmIn en
Effective links, cmIt can be its calculating task tmDirectly migrate to enUpper execution, but in actual conditions, due to cmIt is travelling,
If calculating task is moved to enOn, work as enT is executedmCalculated result is returned to cmWhen, cmIt may be not in enIt is effective
In section, in order to avoid this kind of situation, vehicle cmCalculating task tmThe side cannot be moved to and calculate node, cmIt can only
The calculating task t generatedmIt moves on vehicle heading and in enSide later calculates node and goes to execute.
S4, vehicle calculating task is matched one by one with qualified side node, is calculated needed for each migration strategy
Time and energy consumption;Concrete operations are as follows:
S41, the qualified target side of selection one calculate a target carriage in node and destination node sphere of action
?;The transition process of calculating task includes two parts: first is that cmBy the transmission mode between vehicle and vehicle tmIt is transmitted to target carriage
Process;Second is that target vehicle migrates calculating task to target side the process for calculating node.
S42, calculating task tmTime delay include vehicle cmCalculating task tmIt is transferred to target vehicle cnTime Ttm, mesh
Mark vehicle cnTmIt moves to target side and calculates node enTime Tom、enExecute the time Te of calculating taskmAnd enIt is tied calculating
Fruit feeds back to cmTime Tfm。
Calculate Ttm、Tom、TemAnd TfmFormula it is as follows:
Wherein, v indicates the transmission rate between vehicle, λm,nIndicate calculating task from cmIt is transferred to cnThe vehicle passed through
Number, v ' expression vehicle and side calculate the transmission rate between node, and p indicates the computing capability of each virtual machine.
Overall delay T needed for S43, computation migration strategy:
S44, side calculate node enEnergy consumption mainly include basic energy consumption Ebn, idle energy consumption EinWith occupancy energy consumption Eun.Side
Calculate the energy consumption of node and the running time T s of its servernIt is related, TsnCalculation expression is as follows:
Wherein Bm,nIndicate calculating task tmWhether in enUpper execution, Bm,nExpression formula are as follows:
Calculate Ebn、EinAnd EunFormula it is as follows:
Ebn=Tsn·Pα (26)
Wherein, PαIndicate that side calculates node enThe power of server, PβIndicate enThe power of upper unappropriated resource, Pγ
Indicate enThe power of the resource of upper occupancy.
S45, side calculating node e is calculatednTotal energy consumption E:
S5, optimal computation migration strategy is obtained by simple additive weight and multi-standard decision making algorithm;Concrete operations are as follows:
S51, for computation migration technology, the lower generated time delay and energy consumption the better.According to simple additive weight
With multi-standard decision making algorithm, the overall delay and total energy consumption of each computation migration strategy are passive standard, can be returned respectively
One turns to:
Wherein, TmaxAnd TminRespectively indicate maximum time delay and the smallest time delay caused by computation migration, EmaxAnd Emin
Respectively indicate maximum energy consumption and the smallest energy consumption caused by computation migration.
S52, the value of utility for calculating each migration strategy obtain the maximum computation migration strategy of value of utility:
UV=V (T) ωT+V(E)·ωE(ωT+ωE=1) (32)
Wherein, ωTIndicate the weight of V (T), ωERespectively indicate the weight of V (E).
A specific embodiment is set forth below, the method for the present invention is explained further, as shown in Fig. 2, by car networking
One section of one road is used as survey region, and 4 sides are provided in region and calculate node, E={ e1,e2,e3,e4, Ge Gebian
The effective coverage for calculating node is as shown in phantom in Figure 1, and 11 vehicles are shared in region and are travelled in region, C={ c1,c2,
c3,...,c11}.The relevant information that side calculates node is as shown in table 1:
Table 1
Side calculates node | e1/e2/e3/e4 |
Virtual machine quantity (total capacity eqn) | 10 |
The computing capability (p) of each virtual machine | 2000MHz |
In this embodiment, vehicle c2, c5And c7Calculating task t is generated respectively2, t5And t7, the letter of each calculating task
Breath is as shown in table 2:
Table 2
Calculating task | t2 | t5 | t7 |
Need virtual machine quantity | 3 | 4 | 3 |
Task amount (Kb) | 300 | 500 | 400 |
It feeds back task amount (Kb) | 400 | 300 | 500 |
The judgment criteria of step S3 according to the method for the present invention, task t2E can be moved to2、e3And e4It executes;t5It can migrate
To e3And e4It executes;t7E can only be moved to4It executes;In addition, according to Tables 1 and 2 it is found that side calculates node e2、e3And e4It is all shared
10 idle virtual machine resources, task t2、t5And t7Required resources of virtual machine is respectively 3,4,3, therefore migrates in above-mentioned 6
Path is all feasible.
When calculating task is transmitted between vehicle, to guarantee efficiency of transmission, have strictly to the relative position of vehicle
Requirement, transmission of the calculating task between adjacent closer vehicle is only considered in the present embodiment, for example, task t2It moves to
e3It executes, c2It cannot be directly t2It is transferred to c7Or c8, and must passage path c2→c4→c6→c8Realize t2Transmission, pass through c8?
t2It migrates to e3It executes.
In step s 4, calculating task is moved to the time To that target side calculates node by target vehiclem, side node execute
The time Te of calculating taskmThe time Tf that calculated result is feedbacked with side nodemBe it is certain, not with execute the task
Side calculate the difference of node and change, but vehicle number of the calculating task in the transmission time and transmission path between vehicle
It measures related.Parameters value involved in step S4 is as shown in table 3:
Table 3
Parameter | Value |
Transmission rate v between vehicle | 1Gbps |
Vehicle and side calculate the transmission rate v' between node | 600Mbps |
Calculate node server power Pα | 300W |
The power P of unoccupied virtual machineβ | 30W |
The power P of occupied virtual machineγ | 50W |
With migration path c2→c4→c6→c8→e3For, transmission time Tt of the calculating task between vehicle2:
It successively calculates the corresponding time delay of 6 migration paths and energy consumption, calculated result is as shown in table 4:
Table 4
According to the available 6 computation migration strategies of migration path in 6 in table 4, each move is calculated according to formula (32)
The value of utility of strategy is moved, as shown in table 5:
Table 5
According to the data in table 5 it is found that the value of utility highest of computation migration strategy 2, the Optimal calculation of this specific embodiment
Migration strategy are as follows: by calculating task t2Move to e2It executes, calculating task t5And t7Move to e4It executes.
Embodiments of the present invention are explained in detail above in conjunction with attached drawing, but the invention is not limited to above-mentioned
Embodiment within the knowledge of a person skilled in the art can also be before not departing from present inventive concept
It puts and makes a variety of changes.
Claims (7)
1. a kind of efficient edge computation migration method for car networking application, which comprises the following steps:
S1, the application demand for obtaining the migration task that the current location information of vehicle and vehicle generate in car networking;
S2, obtain car networking in it is all while calculate node location information and it is each while node computing resource situation;
S3, the application demand at a distance from node and migrating task is calculated with side according to vehicle, filters out ineligible side meter
Calculate node;
S4, vehicle calculating task is matched one by one with qualified side node, the time needed for calculating each migration strategy
And energy consumption;
S5, optimal computation migration strategy is obtained by simple additive weight and multi-standard decision making algorithm.
2. a kind of efficient edge computation migration method for car networking application according to claim 1, which is characterized in that
The concrete operations of step S1 are as follows:
It include M vehicle, the m vehicle c in S11, car networking region AmIn the coordinate cp at i momentm,iIt is as follows:
cpm,i=(cpxm,i,cpym,i)
Wherein, cpxm,iIndicate i moment vehicle cmAbscissa positions in region a, cpym,iIndicate i moment vehicle cmIn region A
In ordinate position, m=1,2 ..., M;
S12, the m vehicle cmThe calculating task of generation is tm=(twm,trm,tw'm), wherein twmIndicate calculating task tmTask
Amount, trmIt indicates to execute tmRequired resource, tw'mIt indicates to execute the data volume for terminating to return.
3. a kind of efficient edge computation migration method for car networking application according to claim 1, which is characterized in that
N number of side is set in the A of car networking region in step S2 and calculates node, the expression formula that side calculates node is as follows:
en=(epxn,epyn,eqn,ern)
Wherein, enIndicate that n-th of side calculates node, n=1,2 ..., N, epxnIndicate enAbscissa positions in region a, epyn
Indicate enOrdinate position in region a, eqnIndicate enTotal capacity, ernIndicate enIdling-resource.
4. according to a kind of described in any item efficient edge computation migration methods for car networking application of Claims 2 or 3,
It is characterized in that, trm、eqnAnd ernAll use the form calculus of virtual machine quantity.
5. a kind of efficient edge computation migration method for car networking application according to claim 1, which is characterized in that
The concrete operations of step S3 are as follows:
S31, all sides of comparison calculate the idling-resource of node and execute the size of vehicle required by task resource, work as trm> ern, vehicle
CmCalculating task tmThe side cannot be moved to and calculate node;
S32, vehicle c is calculatedmNode e is calculated to sidenDistance:
Wherein, vehicle cmIt is cp in the coordinate at current timem,i=(cpxm,i,cpym,i), side calculates node enCoordinate be en=
(epxn,epyn);
S33, as dis (cm,en) < ρ, ρ enSphere of action, vehicle cmCalculating task tmThe side cannot be moved to and calculate knot
Point, and cannot move to this while the node side opposite with vehicle heading while node on.
6. a kind of efficient edge computation migration method for car networking application according to claim 1, which is characterized in that
The concrete operations of step S4 are as follows:
S41, the qualified target side of selection one calculate a target vehicle in node and destination node sphere of action;
S42, vehicle c is calculatedmCalculating task tmIt is transferred to target vehicle cnTime Ttm, target vehicle cnTmMove to mesh
It marks side and calculates node enTime Tom、enExecute the time Te of calculating taskmAnd enCalculated result is fed back to cmTime Tfm,
Specific formula is as follows:
Wherein, twmIndicate tmTask amount, v indicate vehicle between transmission rate, λm,nIndicate calculating task from cmIt is transferred to cn
The vehicle number passed through, v ' expression vehicle and side calculate the transmission rate between node, trmIt indicates to execute tmRequired resource,
P indicates the computing capability of each virtual machine, tw'mIt indicates to execute the data volume for terminating to return;
Overall delay T needed for S43, computation migration strategy:
Wherein, M vehicle, m=1,2 ..., M are shared in car networking;
S44, side calculating node e is calculatednBasic energy consumption Ebn, idle energy consumption EinWith occupancy energy consumption Eun:
Ebn=Tsn·Pα
Wherein, TsnIndicate enServer runing time, PαIndicate that side calculates node enThe power of server, eqnIndicate en's
Total capacity, Bm,nIndicate calculating task tmWhether in enUpper execution, PβIndicate enThe power of upper unappropriated resource, PγIndicate en
The power of the resource of upper occupancy;
S45, side calculating node e is calculatednTotal energy consumption E:
Wherein, N number of side is shared in car networking calculates node, n=1,2 ..., N.
7. a kind of efficient edge computation migration method for car networking application according to claim 6, which is characterized in that
The concrete operations of step S5 are as follows:
S51, by simple additive weight and multi-standard decision making algorithm, the overall delay and total energy consumption of each computation migration strategy respectively by
It is normalized to:
Wherein, TmaxAnd TminRespectively indicate maximum time delay and the smallest time delay caused by computation migration, EmaxAnd EminRespectively
Indicate maximum energy consumption and the smallest energy consumption caused by computation migration;
S52, the value of utility for calculating each migration strategy obtain the maximum computation migration strategy of value of utility:
UV=V (T) ωT+V(E)·ωE(ωT+ωE=1)
Wherein, ωTIndicate the weight of V (T), ωERespectively indicate the weight of V (E).
Priority Applications (1)
Application Number | Priority Date | Filing Date | Title |
---|---|---|---|
CN201910031387.XA CN109905859B (en) | 2019-01-14 | 2019-01-14 | Efficient edge computing migration method for Internet of vehicles application |
Applications Claiming Priority (1)
Application Number | Priority Date | Filing Date | Title |
---|---|---|---|
CN201910031387.XA CN109905859B (en) | 2019-01-14 | 2019-01-14 | Efficient edge computing migration method for Internet of vehicles application |
Publications (2)
Publication Number | Publication Date |
---|---|
CN109905859A true CN109905859A (en) | 2019-06-18 |
CN109905859B CN109905859B (en) | 2021-09-28 |
Family
ID=66943781
Family Applications (1)
Application Number | Title | Priority Date | Filing Date |
---|---|---|---|
CN201910031387.XA Active CN109905859B (en) | 2019-01-14 | 2019-01-14 | Efficient edge computing migration method for Internet of vehicles application |
Country Status (1)
Country | Link |
---|---|
CN (1) | CN109905859B (en) |
Cited By (5)
Publication number | Priority date | Publication date | Assignee | Title |
---|---|---|---|---|
CN111338760A (en) * | 2020-02-27 | 2020-06-26 | 长沙市源本信息科技有限公司 | Service instance cross-node scaling method and device for edge computing |
CN111614745A (en) * | 2020-05-18 | 2020-09-01 | 安徽中科美络信息技术有限公司 | Vehicle task data scheduling method based on edge calculation |
CN115002155A (en) * | 2022-05-25 | 2022-09-02 | 安徽江淮汽车集团股份有限公司 | Time delay optimization-based road side unit service migration method |
CN115100898A (en) * | 2022-05-31 | 2022-09-23 | 东南大学 | Cooperative computing task unloading method for urban intelligent parking management system |
US11803413B2 (en) | 2020-12-03 | 2023-10-31 | International Business Machines Corporation | Migrating complex legacy applications |
Citations (10)
Publication number | Priority date | Publication date | Assignee | Title |
---|---|---|---|---|
US20050273668A1 (en) * | 2004-05-20 | 2005-12-08 | Richard Manning | Dynamic and distributed managed edge computing (MEC) framework |
WO2015171800A1 (en) * | 2014-05-09 | 2015-11-12 | Amazon Technologies, Inc. | Migration of applications between an enterprise-based network and a multi-tenant network |
EP2976860A1 (en) * | 2013-03-20 | 2016-01-27 | Wolting Holding B.V. | Compiler for and method for software defined networks |
WO2016188438A1 (en) * | 2015-05-27 | 2016-12-01 | International Business Machines Corporation | Updating networks with migration information for a virtual machine |
CN106844051A (en) * | 2017-01-19 | 2017-06-13 | 河海大学 | The loading commissions migration algorithm of optimised power consumption in a kind of edge calculations environment |
CN107317700A (en) * | 2017-06-09 | 2017-11-03 | 湖北理工学院 | Vehicle-mounted edge calculations node selects system and method |
CN108632813A (en) * | 2018-05-21 | 2018-10-09 | 北京邮电大学 | The motion management method and system of mobile edge calculations |
CN108810849A (en) * | 2018-06-19 | 2018-11-13 | 广东工业大学 | A kind of moving method, device and the unmanned plane of unmanned plane calculating task |
CN108845885A (en) * | 2018-07-04 | 2018-11-20 | 济南浪潮高新科技投资发展有限公司 | A kind of edge calculations method for managing resource towards automatic Pilot |
CN109005538A (en) * | 2018-07-27 | 2018-12-14 | 安徽大学 | Towards the message authentication method between automatic driving vehicle and more mobile edge calculations servers |
-
2019
- 2019-01-14 CN CN201910031387.XA patent/CN109905859B/en active Active
Patent Citations (10)
Publication number | Priority date | Publication date | Assignee | Title |
---|---|---|---|---|
US20050273668A1 (en) * | 2004-05-20 | 2005-12-08 | Richard Manning | Dynamic and distributed managed edge computing (MEC) framework |
EP2976860A1 (en) * | 2013-03-20 | 2016-01-27 | Wolting Holding B.V. | Compiler for and method for software defined networks |
WO2015171800A1 (en) * | 2014-05-09 | 2015-11-12 | Amazon Technologies, Inc. | Migration of applications between an enterprise-based network and a multi-tenant network |
WO2016188438A1 (en) * | 2015-05-27 | 2016-12-01 | International Business Machines Corporation | Updating networks with migration information for a virtual machine |
CN106844051A (en) * | 2017-01-19 | 2017-06-13 | 河海大学 | The loading commissions migration algorithm of optimised power consumption in a kind of edge calculations environment |
CN107317700A (en) * | 2017-06-09 | 2017-11-03 | 湖北理工学院 | Vehicle-mounted edge calculations node selects system and method |
CN108632813A (en) * | 2018-05-21 | 2018-10-09 | 北京邮电大学 | The motion management method and system of mobile edge calculations |
CN108810849A (en) * | 2018-06-19 | 2018-11-13 | 广东工业大学 | A kind of moving method, device and the unmanned plane of unmanned plane calculating task |
CN108845885A (en) * | 2018-07-04 | 2018-11-20 | 济南浪潮高新科技投资发展有限公司 | A kind of edge calculations method for managing resource towards automatic Pilot |
CN109005538A (en) * | 2018-07-27 | 2018-12-14 | 安徽大学 | Towards the message authentication method between automatic driving vehicle and more mobile edge calculations servers |
Non-Patent Citations (3)
Title |
---|
DAN ZHAO 等: "A service migration strategy based on multiple attribute decision in mobile edge computing", 《 2017 IEEE 17TH INTERNATIONAL CONFERENCE ON COMMUNICATION TECHNOLOGY (ICCT)》 * |
伏舒存 等: "移动边缘环境下面向工作流管理的计算迁移方法", 《计算机应用》 * |
郭俊: "移动边缘环境下面向工作流管理的计算迁移方法", 《中国优秀硕士学位论文全文数据库 信息科技辑》 * |
Cited By (9)
Publication number | Priority date | Publication date | Assignee | Title |
---|---|---|---|---|
CN111338760A (en) * | 2020-02-27 | 2020-06-26 | 长沙市源本信息科技有限公司 | Service instance cross-node scaling method and device for edge computing |
CN111338760B (en) * | 2020-02-27 | 2023-04-25 | 长沙市源本信息科技有限公司 | Service instance cross-node telescoping method and device for edge computing |
CN111614745A (en) * | 2020-05-18 | 2020-09-01 | 安徽中科美络信息技术有限公司 | Vehicle task data scheduling method based on edge calculation |
CN111614745B (en) * | 2020-05-18 | 2022-04-26 | 安徽中科美络信息技术有限公司 | Vehicle task data scheduling method based on edge calculation |
US11803413B2 (en) | 2020-12-03 | 2023-10-31 | International Business Machines Corporation | Migrating complex legacy applications |
CN115002155A (en) * | 2022-05-25 | 2022-09-02 | 安徽江淮汽车集团股份有限公司 | Time delay optimization-based road side unit service migration method |
CN115002155B (en) * | 2022-05-25 | 2023-02-21 | 安徽江淮汽车集团股份有限公司 | Time delay optimization-based road side unit service migration method |
CN115100898A (en) * | 2022-05-31 | 2022-09-23 | 东南大学 | Cooperative computing task unloading method for urban intelligent parking management system |
CN115100898B (en) * | 2022-05-31 | 2023-09-12 | 东南大学 | Collaborative computing task unloading method of urban intelligent parking management system |
Also Published As
Publication number | Publication date |
---|---|
CN109905859B (en) | 2021-09-28 |
Similar Documents
Publication | Publication Date | Title |
---|---|---|
CN109905859A (en) | A kind of efficient edge computation migration method for car networking application | |
Christofa et al. | Arterial traffic signal optimization: A person-based approach | |
CN102664814B (en) | Grey-prediction-based adaptive dynamic resource allocation method for virtual network | |
CN104683488B (en) | Streaming computing system and its dispatching method and device | |
CN107330547A (en) | A kind of city bus dynamic dispatching optimization method and system | |
CN105656771B (en) | A kind of service path determines methods, devices and systems | |
CN110445855B (en) | SDN-based design method for vehicle networking distributed fog computing system structure | |
CN107040479A (en) | A kind of method and apparatus of cloud computing resources regulation | |
CN105610715B (en) | A kind of cloud data center multi-dummy machine migration scheduling method of planning based on SDN | |
Li et al. | Optimal zone design for feeder transit services | |
CN105574665A (en) | Flight time resource configuration and optimization method suitable for airline hubs | |
CN103856548B (en) | Dynamic resource scheduling method and dynamic resource scheduling device | |
CN108877253A (en) | A kind of public transportation lane resource dynamic sharing method and system based on Internet of Things | |
CN112712247A (en) | Method and system for making operation scheme for cross-line operation | |
CN101859100A (en) | Improved particle swarm optimization method based on streamline production scheduling of fuzzy due date | |
CN109325671A (en) | A kind of online method for allocating tasks of space-time crowdsourcing and system | |
CN104935628A (en) | Method of migrating a plurality of associated virtual machines among a plurality of data centers | |
CN106954232A (en) | A kind of resource allocation methods of time delay optimization | |
CN108616553A (en) | Cloud computing resource pool carries out the method and device of scheduling of resource | |
CN104392298A (en) | Production scheduling method adopting particle swarm algorithm | |
CN107483355A (en) | The online scene low bandwidth overhead flow scheduling scheme at data-oriented center | |
CN104994149A (en) | Cloud video service oriented resource provision method | |
CN115983187A (en) | Multi-strategy-based layer distribution method considering bus deviation | |
CN103617083A (en) | Storage scheduling method and system, job scheduling method and system and management node | |
CN108768857A (en) | A kind of virtual flow-line retransmission method, apparatus and system |
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 | ||
TR01 | Transfer of patent right | ||
TR01 | Transfer of patent right |
Effective date of registration: 20221221 Address after: 201203 zone a, floor 3, building 5, No. 888, Bibo Road, pilot Free Trade Zone, Pudong New Area, Shanghai Patentee after: SHANGHAI CHANGXING SOFTWARE Co.,Ltd. Patentee after: Shanghai Changxing Information Technology Co.,Ltd. Address before: No.219, ningliu Road, Jiangbei new district, Nanjing, Jiangsu Province, 210032 Patentee before: Nanjing University of Information Science and Technology |