CN106357796A - Optimal service allocation algorithm for mobile applications under mobile cloud computing - Google Patents
Optimal service allocation algorithm for mobile applications under mobile cloud computing Download PDFInfo
- Publication number
- CN106357796A CN106357796A CN201610890478.5A CN201610890478A CN106357796A CN 106357796 A CN106357796 A CN 106357796A CN 201610890478 A CN201610890478 A CN 201610890478A CN 106357796 A CN106357796 A CN 106357796A
- Authority
- CN
- China
- Prior art keywords
- service
- mobile
- cloud
- cost
- represent
- Prior art date
- Legal status (The legal status is an assumption and is not a legal conclusion. Google has not performed a legal analysis and makes no representation as to the accuracy of the status listed.)
- Pending
Links
Classifications
-
- H—ELECTRICITY
- H04—ELECTRIC COMMUNICATION TECHNIQUE
- H04L—TRANSMISSION OF DIGITAL INFORMATION, e.g. TELEGRAPHIC COMMUNICATION
- H04L67/00—Network arrangements or protocols for supporting network services or applications
- H04L67/01—Protocols
- H04L67/10—Protocols in which an application is distributed across nodes in the network
- H04L67/104—Peer-to-peer [P2P] networks
- H04L67/1074—Peer-to-peer [P2P] networks for supporting data block transmission mechanisms
-
- H—ELECTRICITY
- H04—ELECTRIC COMMUNICATION TECHNIQUE
- H04L—TRANSMISSION OF DIGITAL INFORMATION, e.g. TELEGRAPHIC COMMUNICATION
- H04L67/00—Network arrangements or protocols for supporting network services or applications
- H04L67/01—Protocols
- H04L67/10—Protocols in which an application is distributed across nodes in the network
Landscapes
- Engineering & Computer Science (AREA)
- Computer Networks & Wireless Communication (AREA)
- Signal Processing (AREA)
- Mobile Radio Communication Systems (AREA)
Abstract
The invention relates to an optimal service allocation algorithm for mobile applications under mobile cloud computing; the optimal service allocation algorithm can simulate the service and a usage mode of a mobile user according to the mobility of the user. Modeling is firstly performed on mobile cloud service, the mobile user and the mobile applications, and is then performed on the service quality of the mobile applications, and the optimal service allocation algorithm based on mobile awareness in a cloud environment is finally provided. In cloud resource allocation, the optimal service allocation algorithm improves Qos level, reduces delay and power, also has better robustness for error/uncertainty when being used for predicting location-time workflow of the mobile user, and is better in expansibility.
Description
Technical field
The present invention relates to mobile cloud computing, scheduling of resource field is and in particular to move the optimum of Mobile solution under cloud computing
Service allocation algorithm.
Background technology
With people, the demand of abundant Mobile solution is risen rapidly, need new platform and framework to process continuous increasing
The requirement to extensibility and qos level for many mobile subscriber groups.Mobile cloud computing platform is by using under distributed cloud environment
The resource constraint to overcome mobile device and network for the available resources.Target is deficient from resource calculating data intensive task
Weary type mobile device is transferred on cloud node.Ensure that one of Main Bottleneck of mobile qos level is exactly wirelessly connecing of transmission network
Water flowing is put down.The Mobile solution that another key issue is abundant often requires that higher storage and disposal ability although equipment skill
Art achieves progress, but the resource of mobile host (energy, storage and process) is still limited.
Resources Management in mobile cloud computing is current study hotspot, in succession has numerous researcheres that this problem is entered
Go research, had method to be directed to mobile subscriber and propose a kind of intelligent network access strategy, to meet application demand；Somebody proposes
A kind of security service Access Model, is cloud user kernel safety (cs) service and the service of common safety (ns) provides and supports, is giving
Under the conditions of determining state (such as active user) and application resource consumption, (i.e. cloud income deducts to realize system revenus maximization
Surplus value after resource use cost).However, the mobility of user be ensure mcc platform application qos level bring new
Challenge.When quantity and the speed raising of mobile subscriber, the time delay of Mobile solution increases, reliability decrease.When the user is mobile.
Physical distance between the cloud resource of user and original distribution changes, and leads to extra time delay.Similarly, when user moves rapidly,
Wi-fi network, due to lacking effective transfer mechanism, leads to message dropping quantity to rise.In other words, the mobility of user is asked
Topic is without properly settling, it will lead to suboptimum esource impact to select, the performance of the final application reducing qos.Side of the present invention
A kind of optimal service allocation algorithm of method Mobile solution on the basis of existing research work it is proposed that under mobile cloud computing, intelligence
Which local cloud and public cloud can be selected to be used for task and shift.
Content of the invention
Being directed to user mobility problem leads to suboptimum esource impact to select, thus reducing the deficiency of qos application performance, this
Invention provides a kind of optimal service allocation algorithm of Mobile solution under mobile cloud computing.
In order to solve the above problems, the present invention is achieved by the following technical solutions:
The present invention, using double-deck cloud framework, proposes a kind of new framework and Mobile solution is modeled as a kind of space -- time work
Flow, it is particular in that the abstract model of this paper can be simulated the service of mobile subscriber and be made according to the mobility of user
Use pattern.
By using this concept, under considering the qos Multiple factors such as power, cost and time delay, shifting will be run on
Task-set in dynamic client and double-deck cloud framework carries out optimal Decomposition.
Step 1: mobile cloud service, mobile subscriber and Mobile solution are modeled；
Step 2: the service quality modeling to Mobile solution；
Step 3: the optimal service allocation algorithm based on mobile awareness under a kind of cloud environment of proposition, that is, solving model
Algorithm.
The invention has the beneficial effects as follows:
In cloud resource allocation, improve qos level, reduce time delay and power, in prediction mobile subscriber place -- the time
In the face of mistake/uncertainty also has preferable robustness during workflow, autgmentability is preferable simultaneously.
Specific embodiment
In order to solve the problems, such as user mobility lead to suboptimum esource impact select, thus reducing the problem of qos application performance,
Its specific implementation step is as follows:
Step 1: mobile cloud service, mobile subscriber and Mobile solution are modeled, its concrete modeling process is as follows:
Mobile solution model includes three basic models, is that mobile cloud service, mobile subscriber, Mobile solution (are ascended the throne respectively
Put time service stream).
(1) mobile cloud service model is set up
Assume to use s1..., ssTo represent cloud service, then the set of all services of local cloud and the offer of public cloud provider
(cs) can be described as:
Total in local cloud service, the mobile client request of limited quantity can only be received.A kind of function defined in this method
Cap (lc), this function can return the mobile client maximum quantity that can service based on local cloud lc.
(2) mobile subscriber's model is set up
Use u1..., ukTo represent mobile subscriber's set, then user ukThe all set of services being had on their device
(such as decoder, image editor etc.) is expressed as:
(3) Mobile solution (i.e. position time service stream) model is set up
Using l1..., lmCome representation space position, using t1..., tnCome express time interval.Part 2 dimension spaces/area
Domain, mobile host and cloud resource are just located in this region.Known 2 dimension region r2, location drawing l is represented by:
Distribute a vector to the center of position, be expressed asMobile subscriber ukTrack be expressed as form and be:
{(τ1, lk) ..., (τn, lm) string tuple, wherein (τi, lj) represent that mobile subscriber is located at ljPlace and persistent period are τi.
Represent mobile subscriber ukThis position or near spend its most of the time, computational methods are as follows:
The Mobile solution of broad sense can be modeled as workflow ω being made up of logical sum exact procedure, and each step is referred to as letter
Number.Workflow, from starting to start at function, terminates the function in # workflow at end function and can combine by different mode.seq
Pattern shows that function executes successively, and and pattern representative function parallel running, and xor representative function is had ready conditions operation, loop pattern
Representative function circular flow.For each function f in workflow ωi, define xfiFor:
Mobile solution defined above work stream concept is combined with user trajectory, so as to mobile subscriber and its rail
Requested service in mark is modeled, and the position based on mobile subscriber and time are indexed the one group of workflow structure worked out
Become.Method for expressing is:
Wherein ukRepresent k-th mobile subscriber,Expression position is ln, the persistent period be tnUser's request work
Stream.
Step 2: the service quality modeling to Mobile solution, its concrete modeling process is as follows:
Various mobile cloud (mcc) application has multiple service quality demand, represents the different aspect of user satisfaction, main
Time delay to be used, power consumption and cost isoparametric formulations.Mobility is that these qos factors provide new content, because they depend on
In customer location and request time.This is because the feature of communication link with customer location and service time difference and not
With.This so influence whether time delay, power consumption and cost and the qos servicing.Service time delay represents that service is requested and (sets from movement
Standby or high in the clouds) to service be terminated between time interval.If the service being currently in use on cloud, also need to consider network delay
The energy that when power consumption of service represents execution service, mobile device consumes.If service operation is on cloud, power consumption includes network
Connect and the power overhead that leads to of the data transfer related to this service.Finally, cost of serving represents and executes clothes in public cloud
The actual cost that during business, terminal use undertakes.Modeling process adopts normalized.
(1) normalization cost definition
Ltw-qos is the qos sum of diverse location and time Consumer's Experience.Calculate the effectiveness of mobile subscriber using ltw,
The qos index to each parameter is asked to be normalized, the next step of normalization process is to be expanded in workflow ω.With
When, without loss of generality, this method cost is normalized (can extend to power consumption and time delay):
Set γ represents all feasible solutions or implement plan, and he can be defined asP represent cost it is assumed that
max p(xfi) represent fiService maximum cost, min p (xfi) represent fiService minimum cost.S is serviced to each
∈xfi, normalization can be defined as:
S ∈ xf is serviced to eachi, total normalization qos level is defined as
Wherein pow represents power consumption, and delay represents time delay；| | s | | is higher on the whole, and qos performance is higher.
(2) the normalization cost of workflow
WithWithRepresent after selecting service the most expensive and generally the least expensive respectively, the totle drilling cost of service in workflow, then:
(3) the normalization cost of space time workflow
WithWithRepresent the totle drilling cost that after selecting service the most expensive and generally the least expensive, ltw services respectively, then empty
Between the normalization cost of time service stream be defined as:
(4) the globality modeling of system
Ltw and qos provides the performance to analyze mobile cloud Mobile solution for the formal framework.In the method, mainly
Consider is the benefit of mobile subscriber, defines following mobile subscriber's justice utility index and carrys out the overall performance to system and carries out
Modeling:
This function can return to the meansigma methodss of the cost, power consumption and time delay minimum saving of mobile subscriber as effectiveness.Pass through
In conjunction with utility function and system restriction, present invention definition service allocation optimization problems model is as follows:
max f
Step 3: the optimal service allocation algorithm based on mobile awareness under a kind of cloud environment of proposition, that is, solving model
Algorithm, its specific algorithm process is as follows:
Model above is solved, in the present invention, devises the efficient heuritic approach of resource allocation under a kind of layering cloud environment,
Simulated annealing method being used as the core methed of its services selection and refinement, and devise modified strategy makes it be more suitable for moving
The double-deck cloud framework of dynamic application.After known cloud service set and the set of the user with corresponding ltw (position -- time service stream),
Algorithm calculates each user u firstkThe center of mobilityThen using service functionReturn
Reuse family activity centreThe service list of neighbouring and achievable ltw meet the constraint condition, pseudo-code of the algorithm is as follows:
ukLtw, s: services set db, f: utility function, c: constrained vector, maxiter: the following of simulated annealing
Ring number of times
begin
(1) calculate
(2)
(3)util0=computef(candidates),
(4) for i=1tomaxiterDo,
(5)
(6)util1=computef(candidates),
(7) δ=util1-util0,
(8) if δ ＞ 0,
(9)util1=util0,
(10) else,
(11) as exp (maxiterDuring) >=u [0,1], util0=util1/ * u [0,1] expression uniformly distributed function */
(12)end if
(13)end for
(14) return candidats, util0
end
The service in candidate service set during beginning withDistance in threshold value d=dthIn the range of.According to candidate collection
Generate four sorted lists, be ranked up according to normalization cost, power consumption, time delay and total qos level from high to low.Then algorithm
Service is randomly choosed from these lists；Random selection is estimated, to meet input constraint.If meeting input constraint,
Then return list.Otherwise, repeat said process after increasing detection range.
Assume that directory service database includes the qos information after servicing normalization.
ukLtw,ukMobile location centre Chinese, constant dth: threshold distance, constant dr: the increment of distance, constant
It: maximum cycle
begin
(1) i=0
(2)while(i<it)
Start
(3) d=dth+i*dr
(4)
(5) if candidatesIncluding all services being required, then according to the cost after normalization, power, time delay
With total qos, by descending order, four different listss are sorted
(6) randomly choose from three service lists
(7) check whether meet the constraint condition
(8) meet, return services set
(9) otherwise
(10) i=i+1
(11) search radius are extended to d=dth+i*dr
end while
end.
Claims (4)
1. move the optimal service allocation algorithm of Mobile solution under cloud computing, the present invention relates to mobile cloud computing, scheduling of resource neck
Domain, and in particular to moving the optimal service allocation algorithm of Mobile solution under cloud computing, is characterized in that, comprises the steps:
The present invention, using double-deck cloud framework, proposes a kind of new framework and Mobile solution is modeled as a kind of space -- time service
Stream, it is particular in that the abstract model of this paper can simulate service and the use of mobile subscriber according to the mobility of user
Pattern
By using this concept, under considering the qos Multiple factors such as power, cost and time delay, mobile objective running on
Task-set on family end and double-deck cloud framework carries out optimal Decomposition
Step 1: mobile cloud service, mobile subscriber and Mobile solution are modeled；
Step 2: the service quality modeling to Mobile solution；
Step 3: the optimal service allocation algorithm based on mobile awareness under a kind of cloud environment is proposed, that is, the calculation of solving model
Method.
2. under the mobile cloud computing according to claim 1 Mobile solution optimal service allocation algorithm, it is characterized in that, with
Concrete calculating process in upper described step 1 is as follows:
Step 1: mobile cloud service, mobile subscriber and Mobile solution are modeled, its concrete modeling process is as follows:
Mobile solution model includes three basic models, is mobile cloud service, mobile subscriber, Mobile solution (i.e. position respectively
Time service stream)
(1) mobile cloud service model is set up
Assume to useTo represent cloud service, then the set of all services of local cloud and the offer of public cloud providerCan be described as:
Total in local cloud service, the mobile client request of limited quantity can only be received, a kind of function cap defined in this method
(lc), this function can return the mobile client maximum quantity that can service based on local cloud lc
(2) mobile subscriber's model is set up
WithTo represent mobile subscriber's set, then userThe all set of services being had on their device
(such as decoder, image editor etc.) is expressed as:
(3) Mobile solution (i.e. position time service stream) model is set up
UseCome representation space position, useCome express time interval, part 2 dimension spaces/area
Domain, mobile host and cloud resource are just located in this region it is known that 2 tie up regionsLocation drawing l is represented by:
Distribute a vector to the center of position, be expressed as, mobile subscriberTrack be expressed as form and be:String tuple, whereinRepresent that mobile subscriber is located atThe place and persistent period is
Represent mobile subscriberThis position or near spend its most of the time, computational methods are as follows:
The Mobile solution of broad sense can be modeled as the workflow being made up of logical sum exact procedure, each step is referred to as function, work
Flow from starting to start at function, terminate the function in # workflow at end function and can combine by different mode, seq pattern
Show that function executes successively, and and pattern representative function parallel running, xor representative function is had ready conditions operation, loop pattern represents
Function loops run, for workflowIn each function, definitionFor:
Mobile solution defined above work stream concept is combined with user trajectory, so that in mobile subscriber and its track
Requested service be modeled, one group of workflow that the position based on mobile subscriber and time are indexed working out is constituted, table
Show that method is:
WhereinRepresent k-th mobile subscriber,Represent that position is, the persistent period beUser's request work
Stream.
3. under the mobile cloud computing according to claim 1 Mobile solution optimal service allocation algorithm, it is characterized in that, with
Concrete calculating process in upper described step 2 is as follows:
Step 2: the service quality modeling to Mobile solution, its concrete modeling process is as follows:
Various mobile cloud (mcc) application has multiple service quality demand, represents the different aspect of user satisfaction, main use
Time delay, power consumption and cost isoparametric formulations, mobility is that these qos factors provide new content, because they depend on using
Family position and request time, this is because the feature of communication link is different with the difference of customer location and service time, this
And then influence whether time delay, power consumption and cost and the qos servicing, service time delay represent service requested (from mobile device or
High in the clouds) to service be terminated between time interval, if the service being currently in use on cloud, also need consideration network delay service
Power consumption represent execution service when mobile device consume energy, if service operation is on cloud, power consumption includes network connection
And the power overhead that the data transfer related to this service leads to, finally, when cost of serving represents execution service in public cloud
The actual cost that terminal use undertakes, modeling process adopts normalized
(1) normalization cost definition
Ltw-qos is the qos sum of diverse location and time Consumer's Experience, calculates the effectiveness of mobile subscriber using ltw it is desirable to right
The qos index of each parameter is normalized, and the next step of normalization process is to be expanded to workflowIn, meanwhile, no
Lose general, this method cost is normalized (can extend to power consumption and time delay):
SetRepresent all feasible solutions or implement plan, he can be defined as, p represent cost it is assumed that
RepresentService maximum cost,RepresentService minimum cost, to each service,
Normalization can be defined as:
To each service, total normalization qos level is defined as
Wherein pow represents power consumption, and delay represents time delay；On the wholeHigher, qos performance is higher
(2) the normalization cost of workflow
WithWithRepresent after selecting service the most expensive and generally the least expensive respectively, the totle drilling cost of service in workflow, then:
(3) the normalization cost of space time workflow
WithWithRepresent the totle drilling cost that after selecting service the most expensive and generally the least expensive, ltw services, then space respectively
The normalization cost of time service stream is defined as:
(4) the globality modeling of system
Ltw and qos provides the performance to analyze mobile cloud Mobile solution for the formal framework, in the method, main consideration
Be mobile subscriber benefit, define following mobile subscriber's justice utility index and the overall performance of system is built
Mould:
This function can return to the meansigma methodss of the cost, power consumption and time delay minimum saving of mobile subscriber as effectiveness, by combining
Utility function and system restriction, present invention definition service allocation optimization problems model is as follows:
Using the mobile subscriber's quantity of local cloud service,.
4. under the mobile cloud computing according to claim 1 Mobile solution optimal service allocation algorithm, it is characterized in that, with
Concrete calculating process in upper described step 3 is as follows:
Step 3: the optimal service allocation algorithm based on mobile awareness under a kind of cloud environment is proposed, that is, the calculation of solving model
Method, its specific algorithm process is as follows
Model above is solved, devises the efficient heuritic approach of resource allocation under a kind of layering cloud environment in the present invention, use
Simulated annealing method as its services selection with the core methed that refines, and devise modified strategy make its be more suitable for mobile should
Double-deck cloud framework it is known that cloud service set and carry corresponding ltw(position -- time service stream) user's set after, algorithm
Calculate each user firstThe center of mobilityThen using service function
Return to User Activity centerThe service list of neighbouring and achievable ltw meet the constraint condition, pseudo-code of the algorithm is as follows:
:Ltw, s: services set db, f: utility function, c: constrained vector,: simulated annealing
Cycle-index
begin
(1) calculate
(2),
(3),
(4),
(5),
(6),
(7),
(8),
(9),
(10) else,
(11) whenWhen,Represent uniformly distributed function
(12) end if
(13) end for
(14) return
end
The service in candidate service set during beginning withDistance in threshold valueIn the range of, according to Candidate Set symphysis
Become four sorted lists, be ranked up according to normalization cost, power consumption, time delay and total qos level from high to low, then algorithm from
Service is randomly choosed in these lists；Random selection is estimated, to meet input constraint, if meeting input constraint,
Return list, otherwise, after increasing detection range, repeat said process
Assume that directory service database includes the qos information after servicing normalization
:::Mobile location centre Chinese, constant: threshold distance, constant: the increasing of distance
Amount, constant it: maximum cycle
begin
(1) i=0
(2) while(i < it)
Start
(3)
(4)Existed according to ltwRelated service is searched in the range of surrounding d
(5) ifIncluding all services being required, then according to the cost after normalization, power, time delay and total
Four different listss are sorted by qos by descending order
(6) randomly choose from three service lists
(7) check whether meet the constraint condition
(8) meet, return services set
(9) otherwise
(10) i=i+1
(11) search radius are extended to
end while
end.
Priority Applications (1)
| Application Number | Priority Date | Filing Date | Title |
|---|---|---|---|
| CN201610890478.5A CN106357796A (en) | 2016-10-12 | 2016-10-12 | Optimal service allocation algorithm for mobile applications under mobile cloud computing |
Applications Claiming Priority (1)
| Application Number | Priority Date | Filing Date | Title |
|---|---|---|---|
| CN201610890478.5A CN106357796A (en) | 2016-10-12 | 2016-10-12 | Optimal service allocation algorithm for mobile applications under mobile cloud computing |
Publications (1)
| Publication Number | Publication Date |
|---|---|
| CN106357796A true CN106357796A (en) | 2017-01-25 |
Family
ID=57866368
Family Applications (1)
| Application Number | Title | Priority Date | Filing Date |
|---|---|---|---|
| CN201610890478.5A Pending CN106357796A (en) | 2016-10-12 | 2016-10-12 | Optimal service allocation algorithm for mobile applications under mobile cloud computing |
Country Status (1)
| Country | Link |
|---|---|
| CN (1) | CN106357796A (en) |
Cited By (8)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN107256001A (en) * | 2017-05-27 | 2017-10-17 | 四川用联信息技术有限公司 | The improved algorithm for weighing manufacturing process multivariate quality ability |
| CN107256002A (en) * | 2017-05-27 | 2017-10-17 | 四川用联信息技术有限公司 | The algorithm of new measurement manufacturing process multivariate quality ability |
| CN108696596A (en) * | 2018-05-29 | 2018-10-23 | 南京财经大学 | The resource provider method of Services Composition problem in cloud integrated wireless-fiber hybrid access network network |
| CN109496321A (en) * | 2017-07-10 | 2019-03-19 | 欧洲阿菲尼帝科技有限责任公司 | For estimating the technology of the expection performance in task distribution system |
| CN109660623A (en) * | 2018-12-25 | 2019-04-19 | 广东浪潮大数据研究有限公司 | A kind of distribution method, device and the computer readable storage medium of cloud service resource |
| CN110301128A (en) * | 2017-03-02 | 2019-10-01 | 华为技术有限公司 | Resource management data center cloud framework based on study |
| CN110650544A (en) * | 2019-01-21 | 2020-01-03 | 周晓菲 | Network service operation control method |
| CN110650032A (en) * | 2018-06-27 | 2020-01-03 | 复旦大学 | Method for constructing QoS-based application optimization deployment scheme in multi-cloud environment |
Citations (1)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN103944766A (en) * | 2014-04-30 | 2014-07-23 | 浙江大学 | Method for selecting service having QoS incidence relation |
-
2016
- 2016-10-12 CN CN201610890478.5A patent/CN106357796A/en active Pending
Patent Citations (1)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN103944766A (en) * | 2014-04-30 | 2014-07-23 | 浙江大学 | Method for selecting service having QoS incidence relation |
Non-Patent Citations (1)
| Title |
|---|
| 黄会群: "双层云环境下面向移动应用的最优服务分配算法", 《计算机应用研究》 * |
Cited By (8)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN110301128A (en) * | 2017-03-02 | 2019-10-01 | 华为技术有限公司 | Resource management data center cloud framework based on study |
| CN107256001A (en) * | 2017-05-27 | 2017-10-17 | 四川用联信息技术有限公司 | The improved algorithm for weighing manufacturing process multivariate quality ability |
| CN107256002A (en) * | 2017-05-27 | 2017-10-17 | 四川用联信息技术有限公司 | The algorithm of new measurement manufacturing process multivariate quality ability |
| CN109496321A (en) * | 2017-07-10 | 2019-03-19 | 欧洲阿菲尼帝科技有限责任公司 | For estimating the technology of the expection performance in task distribution system |
| CN108696596A (en) * | 2018-05-29 | 2018-10-23 | 南京财经大学 | The resource provider method of Services Composition problem in cloud integrated wireless-fiber hybrid access network network |
| CN110650032A (en) * | 2018-06-27 | 2020-01-03 | 复旦大学 | Method for constructing QoS-based application optimization deployment scheme in multi-cloud environment |
| CN109660623A (en) * | 2018-12-25 | 2019-04-19 | 广东浪潮大数据研究有限公司 | A kind of distribution method, device and the computer readable storage medium of cloud service resource |
| CN110650544A (en) * | 2019-01-21 | 2020-01-03 | 周晓菲 | Network service operation control method |
Similar Documents
| Publication | Publication Date | Title |
|---|---|---|
| CN106357796A (en) | Optimal service allocation algorithm for mobile applications under mobile cloud computing | |
| CN103294521B (en) | A kind of method reducing data center's traffic load and energy consumption | |
| Wang et al. | An effective edge-intelligent service placement technology for 5G-and-beyond industrial IoT | |
| CN110519783B (en) | 5G network slice resource allocation method based on reinforcement learning | |
| CN103916438B (en) | Cloud testing environment scheduling method and system based on load forecast | |
| CN105049326A (en) | Social content caching method in edge network area | |
| Di et al. | Collaborative smartphone sensing using overlapping coalition formation games | |
| CN104679595A (en) | Application-oriented dynamic resource allocation method for IaaS (Infrastructure As A Service) layer | |
| CN104754053A (en) | Distributed software-defined network and method of dynamically controlling controllers therein | |
| Li et al. | Deployment of edge servers in 5G cellular networks | |
| CN108632077A (en) | A kind of power business data transmission modeling procedure and transmission channel determine method | |
| Li et al. | DQN-enabled content caching and quantum ant colony-based computation offloading in MEC | |
| Zhao et al. | Mobility management with transferable reinforcement learning trajectory prediction | |
| Wang et al. | Reinforcement learning-based optimization for mobile edge computing scheduling game | |
| CN107835130A (en) | A kind of flow allocation method and device | |
| Li et al. | Task computation offloading for multi-access edge computing via attention communication deep reinforcement learning | |
| Zhao et al. | Socialized learning for smart cities: cognitive paradigm, methodology, and solution | |
| CN113014649B (en) | Cloud Internet of things load balancing method, device and equipment based on deep learning | |
| Zhu et al. | Cognitive analytics of social media services for edge resource pre-allocation in industrial manufacturing | |
| CN106413057A (en) | Wireless access network energy consumption optimizing method based on SDWN (Software Defined Wireless Networking) framework | |
| Wang et al. | A dynamic channel-borrowing approach with fuzzy logic control in distributed cellular networks | |
| Jiang et al. | A Task Offloading Method with Edge for 5G‐Envisioned Cyber‐Physical‐Social Systems | |
| AlQerm et al. | I-HARF: Intelligent and hierarchical framework for adaptive resource facilitation in edge-IoT systems | |
| Wu et al. | Optimal storage allocation for delay sensitivity data in electric vehicle network | |
| Guo et al. | Multi-level federated learning mechanism with reinforcement learning optimizing in smart city |
Legal Events
| Date | Code | Title | Description |
|---|---|---|---|
| C06 | Publication | ||
| PB01 | Publication | ||
| SE01 | Entry into force of request for substantive examination | ||
| SE01 | Entry into force of request for substantive examination | ||
| WD01 | Invention patent application deemed withdrawn after publication | ||
| WD01 | Invention patent application deemed withdrawn after publication |
Application publication date: 20170125 |