CN109660623A - A kind of distribution method, device and the computer readable storage medium of cloud service resource - Google Patents
A kind of distribution method, device and the computer readable storage medium of cloud service resource Download PDFInfo
- Publication number
- CN109660623A CN109660623A CN201811595260.2A CN201811595260A CN109660623A CN 109660623 A CN109660623 A CN 109660623A CN 201811595260 A CN201811595260 A CN 201811595260A CN 109660623 A CN109660623 A CN 109660623A
- Authority
- CN
- China
- Prior art keywords
- server
- service
- tenant
- function
- unit
- 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
- 238000000034 method Methods 0.000 title claims abstract description 36
- 238000009826 distribution Methods 0.000 title claims abstract description 18
- 238000003860 storage Methods 0.000 title claims abstract description 13
- 230000035945 sensitivity Effects 0.000 claims abstract description 37
- 238000004422 calculation algorithm Methods 0.000 claims abstract description 24
- 230000006870 function Effects 0.000 claims description 105
- 238000004590 computer program Methods 0.000 claims description 11
- 238000005457 optimization Methods 0.000 abstract description 7
- 239000002355 dual-layer Substances 0.000 abstract description 4
- 230000008859 change Effects 0.000 description 6
- 238000010586 diagram Methods 0.000 description 6
- 230000008569 process Effects 0.000 description 3
- 238000004364 calculation method Methods 0.000 description 2
- 230000003247 decreasing effect Effects 0.000 description 2
- 238000011156 evaluation Methods 0.000 description 2
- 230000006872 improvement Effects 0.000 description 2
- 230000004048 modification Effects 0.000 description 2
- 238000012986 modification Methods 0.000 description 2
- 241000208340 Araliaceae Species 0.000 description 1
- 235000005035 Panax pseudoginseng ssp. pseudoginseng Nutrition 0.000 description 1
- 235000003140 Panax quinquefolius Nutrition 0.000 description 1
- 230000007423 decrease Effects 0.000 description 1
- 238000009795 derivation Methods 0.000 description 1
- 238000013461 design Methods 0.000 description 1
- 235000008434 ginseng Nutrition 0.000 description 1
- 239000000203 mixture Substances 0.000 description 1
- 238000002360 preparation method Methods 0.000 description 1
- 230000000750 progressive effect Effects 0.000 description 1
- 230000009467 reduction Effects 0.000 description 1
- 238000011160 research Methods 0.000 description 1
- 238000013468 resource allocation Methods 0.000 description 1
- 230000004044 response Effects 0.000 description 1
- 238000012360 testing method Methods 0.000 description 1
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
- H04L67/50—Network services
- H04L67/60—Scheduling or organising the servicing of application requests, e.g. requests for application data transmissions using the analysis and optimisation of the required network resources
- H04L67/61—Scheduling or organising the servicing of application requests, e.g. requests for application data transmissions using the analysis and optimisation of the required network resources taking into account QoS or priority requirements
-
- 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)
- Management, Administration, Business Operations System, And Electronic Commerce (AREA)
Abstract
The embodiment of the invention discloses distribution method, device and the computer readable storage medium of a kind of cloud service resource, obtains service-quality-sensitive coefficient and service monovalent sensitivity coefficient；According to service-quality-sensitive coefficient, monovalent sensitivity coefficient, each server unit price and each tenant data flow are serviced, establishes service quality utility function；According to the standard price of each server, each server unit price and each tenant data flow, server loss function is established；Service quality utility function is maximized and server loss function is minimized as objective function.By dynamic coordinate searching algorithm, the optimal solution of objective function can be determined；Wherein, optimal solution includes the value of each server unit price and the value of each tenant data flow, the two dual-layer optimization problems of effective solution under the premise of ensureing the service quality of each tenant reduce the loss in price of server.
Description
Technical field
The present invention relates to cloud service technical fields, more particularly to distribution method, device and the meter of a kind of cloud service resource
Calculation machine readable storage medium storing program for executing.
Background technique
The topic and technology that cloud computing in recent years is popular as one, obtain the very big concern of IT and scientific research circle, are claimed
Mode is calculated for follow-on mainstream.Currently, cloud computing gradually march toward it is practical, many enterprises by oneself application deployment beyond the clouds
It is calculated.In order to reach reduction application load, the method for reducing cloud service cost is exactly multi-tenant mode.
Server cluster needs to meet the service quality of each tenant when providing cloud service resource allocation for each tenant
(QualityofService, QoS).Furthermore the server in cluster is in the service of offer, need according to provided service come
Collect corresponding expense.To attract tenant using its service, server can provide corresponding price rebate, correspondingly, can also lead
Server is caused loss in price caused by discount occur.Lack comprehensive consideration service quality and server loss in price in the prior art
Technical solution, cause server fee charged setting it is unreasonable, to cause higher server loss in price.
As it can be seen that reducing the loss in price of server how under the premise of ensureing the service quality of each tenant, being this field
Technical staff's urgent problem to be solved.
Summary of the invention
The purpose of the embodiment of the present invention is that providing a kind of distribution method of cloud service resource, device and computer-readable storage
Medium can reduce the loss in price of server under the premise of ensureing the service quality of each tenant.
In order to solve the above technical problems, the embodiment of the present invention provides a kind of distribution method of cloud service resource, comprising:
It obtains service-quality-sensitive coefficient and services monovalent sensitivity coefficient；
According to the service-quality-sensitive coefficient, the monovalent sensitivity coefficient of the service, each server unit price and each tenant's number
According to flow, service quality utility function is established；
According to the standard price of each server, each server unit price and each tenant data flow, service is established
Device loss function；
The service quality utility function is maximized and the server loss function minimizes and is used as objective function；
Using dynamic coordinate searching algorithm, the optimal solution of the objective function is determined；Wherein, the optimal solution includes each
The value of the value of server unit price and each tenant data flow.
Optionally, described according to the service-quality-sensitive coefficient, the monovalent sensitivity coefficient of the service, each server unit price
With each tenant data flow, establishing service quality utility function includes:
Service quality utility function SF is established using logarithmic function, formula is as follows,
Wherein, aikIndicate i-th of tenant to the service-quality-sensitive coefficient of kth platform server, bikIndicate i-th of tenant
To the service unit price sensitivity coefficient of kth platform server, cikIndicate the unit price of kth platform server, fijkIndicate kth platform server to
I-th of tenant provides the data flow of jth class resource, and I indicates the total number of tenant, and J indicates the total number of types of cloud service resource, K table
Show server total number.
Optionally, described according to the standard price of each server, each server unit price and each tenant data stream
Amount, establishing server loss function includes:
According to the following formula, server loss function H (c) is established,
Wherein, ckIndicate the standard price of kth platform server.
Optionally, dynamic coordinate searching algorithm is utilized described, determines also to wrap after the optimal solution of the objective function
It includes:
Show the optimal solution.
The embodiment of the invention also provides a kind of distributors of cloud service resource, including acquiring unit, the first foundation list
Member, second establish unit, as unit and determination unit；
The acquiring unit, for obtaining service-quality-sensitive coefficient and servicing monovalent sensitivity coefficient；
The first establishing unit, for according to the service-quality-sensitive coefficient, the monovalent sensitivity coefficient of the service, respectively
Server unit price and each tenant data flow, establish service quality utility function；
Described second establishes unit, for monovalent and each described according to the standard price of each server, each server
Tenant data flow establishes server loss function；
It is described be used as unit, for by the service quality utility function maximize and the server loss function most
It is small to be turned to objective function；
The determination unit determines the optimal solution of the objective function for utilizing dynamic coordinate searching algorithm；Its
In, the optimal solution includes the value of each server unit price and the value of each tenant data flow.
Optionally, the first establishing unit is specifically used for establishing service quality utility function SF using logarithmic function,
Formula is as follows,
Wherein, aikIndicate i-th of tenant to the service-quality-sensitive coefficient of kth platform server, bikIndicate i-th of tenant
To the service unit price sensitivity coefficient of kth platform server, cikIndicate the unit price of kth platform server, fijkIndicate kth platform server to
I-th of tenant provides the data flow of jth class resource, and I indicates the total number of tenant, and J indicates the total number of types of cloud service resource, K table
Show server total number.
Optionally, described second establish unit be specifically used for according to the following formula, establish server loss function H (c),
Wherein, ckIndicate the standard price of kth platform server.
Optionally, also packet display unit；
The display unit determines the optimal of the objective function for utilizing dynamic coordinate searching algorithm described
After solution, the optimal solution is shown.
The embodiment of the invention also provides a kind of distributors of cloud service resource, comprising:
Memory, for storing computer program；
Processor, the step of for executing the computer program to realize the distribution method such as above-mentioned cloud service resource.
The embodiment of the invention also provides a kind of computer readable storage medium, deposited on the computer readable storage medium
Computer program is contained, the step of the distribution method such as above-mentioned cloud service resource is realized when the computer program is executed by processor
Suddenly.
Service-quality-sensitive coefficient is obtained it can be seen from above-mentioned technical proposal and services monovalent sensitivity coefficient；According to clothes
Business mass-sensitive coefficient services monovalent sensitivity coefficient, each server unit price and each tenant data flow, establishes service quality effectiveness
Function；According to the standard price of each server, each server unit price and each tenant data flow, server loss function is established；
It include each server unit price and each two class of tenant data flow in service quality utility function and server loss function
Variable.In order to guarantee the service quality of each tenant, and the loss in price of server is reduced, in the technical scheme by Service Quality
Dose-effect uses function maximization and server loss function is minimized as objective function.Since each server is mentioned for tenant
When for service, need to change unit price according to cloud service stock number used in last time tenant, so that the price of itself is damaged
It loses and minimizes, form a loop iteration process.By dynamic coordinate searching algorithm, the optimal of objective function can be determined
Solution；Wherein, optimal solution includes the value of each server unit price and the value of each tenant data flow, effective solution the two
Dual-layer optimization problem reduces the loss in price of server under the premise of ensureing the service quality of each tenant.
Detailed description of the invention
In order to illustrate the embodiments of the present invention more clearly, attached drawing needed in the embodiment will be done simply below
It introduces, it should be apparent that, drawings in the following description are only some embodiments of the invention, for ordinary skill people
For member, without creative efforts, it is also possible to obtain other drawings based on these drawings.
Fig. 1 is a kind of flow chart of the distribution method of cloud service resource provided in an embodiment of the present invention；
Fig. 2 a is that a kind of same tenant provided in an embodiment of the present invention damages in different tenant data flow Cluster devices
Lose the variation schematic diagram of function；
Fig. 2 b is a kind of same tenant service quality effectiveness under different tenant data flows provided in an embodiment of the present invention
The variation schematic diagram of function；
Fig. 3 is a kind of structural schematic diagram of the distributor of cloud service resource provided in an embodiment of the present invention；
Fig. 4 is a kind of hardware structural diagram of the distributor of cloud service resource provided in an embodiment of the present invention.
Specific embodiment
Following will be combined with the drawings in the embodiments of the present invention, and technical solution in the embodiment of the present invention carries out clear, complete
Site preparation description, it is clear that described embodiments are only a part of the embodiments of the present invention, rather than whole embodiments.Based on this
Embodiment in invention, those of ordinary skill in the art are without making creative work, obtained every other
Embodiment belongs to the scope of the present invention.
In order to enable those skilled in the art to better understand the solution of the present invention, with reference to the accompanying drawings and detailed description
The present invention is described in further detail.
Next, a kind of distribution method of cloud service resource provided by the embodiment of the present invention is discussed in detail.Fig. 1 is this hair
A kind of flow chart of the distribution method for cloud service resource that bright embodiment provides, this method comprises:
S101: obtaining service-quality-sensitive coefficient and services monovalent sensitivity coefficient.
Service-quality-sensitive coefficient is for indicating tenant to the evaluation index of service quality provided by the server.Service is single
The evaluation index for the service fee that valence sensitivity coefficient is used to indicate that tenant collects server.
S102: according to service-quality-sensitive coefficient, monovalent sensitivity coefficient, each server unit price and each tenant data stream are serviced
Amount, establishes service quality utility function.
Since each server is when providing service for tenant, the cloud service stock number according to used in last time tenant is needed
Change unit price, therefore, each server unit price belongs to Variable Factors.
The data traffic of each tenant is for indicating tenant to stock number needed for each server.When the unit price of each server
After determination, tenant can select corresponding server to provide cloud service resource for it according to the resource requirement total amount of itself.
In embodiments of the present invention, it is assumed that there are I (I ∈ Z+) tenant, server number present in cluster is K (K
∈Z+).The cloud service resource type that server needed for each tenant provides is different, can be divided into J class (J ∈ Z altogether+).I-th of rent
The data flow length of jth class cloud service resource needed for family is fij, therefore the corresponding number of cloud service resource needed for i-th of tenant
It is according to flow
Cloud service resource needed for each tenant can be provided by multiple servers in cluster.It is specific to meet
Following formula,
Wherein, fijkIndicate that kth platform server provides the data flow of jth class resource to i-th of tenant.When tenant does not need
When obtaining cloud service from kth platform server, then fijk=0.
In embodiments of the present invention, tenant can be portrayed by utility function to cloud service resource provided by the server
Satisfaction.Further, since tenant needs to pay corresponding expense when using the service of server, therefore tenant can also be expired
Meaning degree has an impact.In summary two aspect, in embodiments of the present invention can be by service-quality-sensitive coefficient and service unit price
Parameter value of the sensitivity coefficient as building service quality utility function.
In the concrete realization, can be by logarithmic function as utility function, and combine influence of the tenant to price paid
Tenant is portrayed to the satisfaction of cloud service resource, the formula of the service quality utility function SF of foundation is as follows,
Wherein, aikIndicate i-th of tenant to the service-quality-sensitive coefficient of kth platform server, bikIndicate i-th of tenant
To the service unit price sensitivity coefficient of kth platform server, cikIndicate the unit price of kth platform server, fijkIndicate kth platform server to
I-th of tenant provides the data flow of jth class resource, and I indicates the total number of tenant, and J indicates the total number of types of cloud service resource, K table
Show server total number.
S103: according to the standard price of each server, each server unit price and each tenant data flow, server damage is established
Lose function.
When tenant is before using service provided by the server, server side can attract tenant by way of discounting
Use, thereby resulted in the loss in price of server in cluster.
In the concrete realization, server loss function H (c) can be established according to the following formula,
Wherein, ckIndicate the standard price of kth platform server, 0≤cik≤ck。
S104: service quality utility function is maximized and server loss function is minimized as objective function.
It in embodiments of the present invention, can be by service quality effectiveness letter in order to effectively guarantee the service quality of each tenant
It is max SF that number, which maximizes,.Meanwhile in order to reduce the loss in price of each server, can be by server loss function minimum
min H(c)。
S105: dynamic coordinate searching algorithm is utilized, determines the optimal solution of objective function.
Wherein, optimal solution includes the value of each server unit price and the value of each tenant data flow.
When known to the unit price of each server, service quality utility function maximization problems is a convex optimization problem, can be led to
KKT condition is crossed to be solved, it is specific as shown in formula (4) and (5),
Wherein, λ is the undetermined coefficient of each constraint condition.
In conjunction with formula (4) and (5) it is found that the corresponding data flow f of cloud service resource needed for tenantijkIt can be by monovalent cikAnd λ
It is indicated, it is specific as shown in formula (6),
fijk=max { fijk(λ,cik),0}(6)；
In addition, after the data flow needed for tenant determines the bound of λ can be acquired according to formula (4), i.e., by formula (6)
Substituting into formula (4) can be obtained the bound of λ, specific as shown in formula (7),
After the bound of λ determines, formula (6) and formula (7) are substituted into formula (1), the available equation about λ,
It can be in the hope of the occurrence of λ, to further acquire f according to dichotomyijkValue.
Since the solution procedure is the derivation carried out under the conditions of the unit price for setting each server is known, thereby determine that out
FijkIt is by cikRepresented form.
Based on this, the optimal solution for solving objective function, which essentially consists in, solves c in server loss function minimization problemik's
Value.Due to 0≤cik≤ck, therefore, it is necessary to acquired in this section meet server loss function minimum optimal solution ask
Obtain cikValue.
Dynamic coordinate searching algorithm is a kind of algorithm that can solve higher-dimension bound constrained optimization problem.It is directed to server damage
Function minimization problem is lost, the server number as present in cluster is numerous.Therefore, it is minimum to be directed to server loss function
Change problem can be solved using dynamic coordinate searching algorithm, and specific solution procedure is as follows:
The input value of dynamic coordinate searching algorithm includes problem input valueI, J, K, λ, algorithm input
Value: nini,Nmax, m；Output valve: locally optimal solution c*。
1. inputting initial valueCalculate the value of L.
2. using c*The minimum value currently found is represented, n=n is enabledini, Cn=Ini.
3. working as n < NmaxWhen, execute operations described below step.
4. according to Bn={ (c, H (c)): c ∈ CnOne suitable response surface model s of selectionn(c)。
5. determining probability φ (n).
6. generating testing site by following steps
(1) suitable point is selected to be disturbed；
(2) a series of point of random generation；
(3) point being randomly generated is substituted into formula (3).
7. from ΩnIn be chosen so as to obtain sn(c) the point c that the point of minimum value is added as next iteration is obtainedn+1。
8. calculating the solution of server loss function minimum according to formula (4)-(7).
9. if H (cn+1) < H (c*), then c*=cn+1。
10. designing Cn+1=Cn∪cn+1, and make n=n+1, until the number of iterations n reaches maximum number of iterations NmaxThen tie
Beam operation.
In embodiments of the present invention, after determining optimal solution, optimal solution can be shown, in order to which tenant can directly look into
See this as a result, and choosing corresponding server according to the result.
For example, considering tenant to server unit price sensitivity coefficient bikIn identical situation, it is assumed that the service in cluster
When device number is 5, tenant is divided into LOW, MID and HIGH three classes by the sensitivity to cloud service resource.Server in cluster
Number is 5, specific sensitivity coefficient aikValue is as shown in table 1,
| ai1 | ai2 | ai3 | ai4 | ai5 | |
| LOW | 0.35 | 0.22 | 0.17 | 0.43 | 0.55 |
| MID | 0.7 | 0.44 | 0.34 | 0.86 | 1.1 |
| HIGH | 1.05 | 0.88 | 0.51 | 1.29 | 1.65 |
Table 1
Consider tenant to the service-quality-sensitive coefficient a of cloud service resourceikServer count in identical situation, in cluster
When being 5, by the sensitivity to server unit price, tenant is equally divided into LOW, MID and HIGH three classes.Server in cluster
Number is 5, specific sensitivity coefficient bikValue is as shown in table 2,
| bi1 | bi2 | bi3 | bi4 | bi5 | |
| LOW | 0.62 | 0.81 | 0.54 | 0.71 | 0.92 |
| MID | 1.24 | 1.62 | 1.08 | 1.42 | 1.84 |
| HIGH | 1.86 | 2.43 | 1.62 | 2.13 | 2.76 |
Table 2
Therefore, in the embodiment of the present invention, f is considered according to different types of tenant simultaneouslyijRespectively 5M, 10M and 15M tri-
Kind situation.Correspondingly, the standard price c in cluster before each server discountkAs shown in table 3,
| Coefficient | c1 | c2 | c3 | c4 | c5 |
| Standard price | 2 | 1.5 | 1.6 | 2.4 | 1.8 |
Table 3
Tenant is set in the embodiment of the present invention to the service-quality-sensitive coefficient a of cloud service resourceikFor LOW type and tenant
To server unit price sensitivity coefficient bikFor the tenant of LOW type, as the corresponding data flow f of the cloud service resource of tenant's demandijFor
The case where cluster server loss function H (c) in the case of tri- kinds of 5M, 10M and 15M is minimized is analyzed, specific as schemed
Shown in 2a.
When demand difference of the tenant to cloud service resource, as tenant is multiplied to resource requirement, corresponding collection
The loss of server is also multiplied therewith in group.Meanwhile with the increase of method assessment number, H (c) minimum value convergence rate
Comparatively fast, dynamic coordinate searching algorithm has successfully found out the value of H (c).
Tenant is set in the embodiment of the present invention to the service-quality-sensitive coefficient a of cloud service resourceikFor LOW type and tenant
To server unit price sensitivity coefficient bikFor the tenant of LOW type, as the corresponding data flow f of the cloud service resource of tenant's demandijFor
The maximized situation of change of service quality utility function SF in the case of tri- kinds of 5M, 10M and 15M is analyzed, specific as schemed
Shown in 2b.
When demand difference of the tenant to cloud service resource, as tenant is multiplied to resource requirement, corresponding collection
The satisfaction of tenant also decreases in group.And the decreasing value of SF is the same as 15M situation and 10M situation in the case of 10M situation and 5M
The decreasing value of lower SF is close.Meanwhile with the increase of method assessment number, SF minimum value convergence rate is very fast, and dynamic coordinate is searched
Rope algorithm has successfully found out the value of SF while solving H (c) value.
Observe Fig. 2 a and Fig. 2 b it can be found that with calculation times in dynamic coordinate searching algorithm increase, SF and H (c)
The variation tendency of value is identical, it means that two-way combined optimization strategy is correct.And with H (c) value as convergence tends to
In determination, the interests that represent server in cluster are guaranteed.The value of corresponding SF is also determined, and tenant has obtained accordingly
Best Q oS satisfaction.Therefore, the distribution method for the cloud service resource that the embodiment of the present invention proposes has feasibility.
Service-quality-sensitive coefficient is obtained it can be seen from above-mentioned technical proposal and services monovalent sensitivity coefficient；According to clothes
Business mass-sensitive coefficient services monovalent sensitivity coefficient, each server unit price and each tenant data flow, establishes service quality effectiveness
Function；According to the standard price of each server, each server unit price and each tenant data flow, server loss function is established；
It include each server unit price and each two class of tenant data flow in service quality utility function and server loss function
Variable.In order to guarantee the service quality of each tenant, and the loss in price of server is reduced, in the technical scheme by Service Quality
Dose-effect uses function maximization and server loss function is minimized as objective function.Since each server is mentioned for tenant
When for service, need to change unit price according to cloud service stock number used in last time tenant, so that the price of itself is damaged
It loses and minimizes, form a loop iteration process.By dynamic coordinate searching algorithm, the optimal of objective function can be determined
Solution；Wherein, optimal solution includes the value of each server unit price and the value of each tenant data flow, effective solution the two
Dual-layer optimization problem reduces the loss in price of server under the premise of ensureing the service quality of each tenant.
Fig. 3 is a kind of structural schematic diagram of the distributor of cloud service resource provided in an embodiment of the present invention, including is obtained
Unit 31, first establishing unit 32, second establish unit 33, as unit 34 and determination unit 35；
Acquiring unit 31, for obtaining service-quality-sensitive coefficient and servicing monovalent sensitivity coefficient；
First establishing unit 32, for according to service-quality-sensitive coefficient, the monovalent sensitivity coefficient of service, each server unit price
With each tenant data flow, service quality utility function is established；
Second establishes unit 33, for according to the standard price of each server, each server unit price and each tenant data stream
Amount, establishes server loss function；
As unit 34, for service quality utility function being maximized and server loss function is minimized as mesh
Scalar functions；
Determination unit 35 determines the optimal solution of objective function for utilizing dynamic coordinate searching algorithm；Wherein, optimal
Solution includes the value of each server unit price and the value of each tenant data flow.
Optionally, first establishing unit is specifically used for establishing service quality utility function SF, formula using logarithmic function
As follows,
Wherein, aikIndicate i-th of tenant to the service-quality-sensitive coefficient of kth platform server, bikIndicate i-th of tenant
To the service unit price sensitivity coefficient of kth platform server, cikIndicate the unit price of kth platform server, fijkIndicate kth platform server to
I-th of tenant provides the data flow of jth class resource, and I indicates the total number of tenant, and J indicates the total number of types of cloud service resource, K table
Show server total number.
Optionally, second establish unit be specifically used for according to the following formula, establish server loss function H (c),
Wherein, ckIndicate the standard price of kth platform server.
Optionally, also packet display unit；
Display unit, for after the optimal solution for determining objective function, showing most using dynamic coordinate searching algorithm
Excellent solution.
The explanation of feature may refer to the related description of embodiment corresponding to Fig. 1 in embodiment corresponding to Fig. 3, here no longer
It repeats one by one.
Service-quality-sensitive coefficient is obtained it can be seen from above-mentioned technical proposal and services monovalent sensitivity coefficient；According to clothes
Business mass-sensitive coefficient services monovalent sensitivity coefficient, each server unit price and each tenant data flow, establishes service quality effectiveness
Function；According to the standard price of each server, each server unit price and each tenant data flow, server loss function is established；
It include each server unit price and each two class of tenant data flow in service quality utility function and server loss function
Variable.In order to guarantee the service quality of each tenant, and the loss in price of server is reduced, in the technical scheme by Service Quality
Dose-effect uses function maximization and server loss function is minimized as objective function.Since each server is mentioned for tenant
When for service, need to change unit price according to cloud service stock number used in last time tenant, so that the price of itself is damaged
It loses and minimizes, form a loop iteration process.By dynamic coordinate searching algorithm, the optimal of objective function can be determined
Solution；Wherein, optimal solution includes the value of each server unit price and the value of each tenant data flow, effective solution the two
Dual-layer optimization problem reduces the loss in price of server under the premise of ensureing the service quality of each tenant.
Fig. 4 is a kind of hardware structural diagram of the distributor 40 of cloud service resource provided in an embodiment of the present invention, packet
It includes:
Memory 41, for storing computer program；
Processor 42, the step of for executing computer program to realize the distribution method such as above-mentioned cloud service resource.
The embodiment of the invention also provides a kind of computer readable storage medium, it is stored on computer readable storage medium
Computer program, when computer program is executed by processor the step of the realization such as distribution method of above-mentioned cloud service resource.
It is provided for the embodiments of the invention the distribution method of cloud service resource a kind of, device above and computer-readable deposits
Storage media is described in detail.Each embodiment is described in a progressive manner in specification, and each embodiment stresses
Be the difference from other embodiments, the same or similar parts in each embodiment may refer to each other.For implementing
For device disclosed in example, since it is corresponded to the methods disclosed in the examples, so being described relatively simple, related place ginseng
See method part illustration.It should be pointed out that for those skilled in the art, not departing from original of the invention
, can be with several improvements and modifications are made to the present invention under the premise of reason, these improvement and modification also fall into right of the present invention and want
In the protection scope asked.
Professional further appreciates that, unit described in conjunction with the examples disclosed in the embodiments of the present disclosure
And algorithm steps, can be realized with electronic hardware, computer software, or a combination of the two, in order to clearly demonstrate hardware and
The interchangeability of software generally describes each exemplary composition and step according to function in the above description.These
Function is implemented in hardware or software actually, the specific application and design constraint depending on technical solution.Profession
Technical staff can use different methods to achieve the described function each specific application, but this realization is not answered
Think beyond the scope of this invention.
The step of method described in conjunction with the examples disclosed in this document or algorithm, can directly be held with hardware, processor
The combination of capable software module or the two is implemented.Software module can be placed in random access memory (RAM), memory, read-only deposit
Reservoir (ROM), electrically programmable ROM, electrically erasable ROM, register, hard disk, moveable magnetic disc, CD-ROM or technology
In any other form of storage medium well known in field.
Claims (10)
1. a kind of distribution method of cloud service resource characterized by comprising
It obtains service-quality-sensitive coefficient and services monovalent sensitivity coefficient；
According to the service-quality-sensitive coefficient, the monovalent sensitivity coefficient of the service, each server unit price and each tenant data stream
Amount, establishes service quality utility function；
According to the standard price of each server, each server unit price and each tenant data flow, server damage is established
Lose function；
The service quality utility function is maximized and the server loss function minimizes and is used as objective function；
Using dynamic coordinate searching algorithm, the optimal solution of the objective function is determined；Wherein, the optimal solution includes each service
The value of the value of device unit price and each tenant data flow.
2. the method according to claim 1, wherein described according to the service-quality-sensitive coefficient, the clothes
The monovalent sensitivity coefficient of business, each server unit price and each tenant data flow, establishing service quality utility function includes:
Service quality utility function SF is established using logarithmic function, formula is as follows,
Wherein, aikIndicate i-th of tenant to the service-quality-sensitive coefficient of kth platform server, bikIndicate i-th of tenant to kth
The service unit price sensitivity coefficient of platform server, cikIndicate the unit price of kth platform server, fijkIndicate kth platform server to i-th
Tenant provides the data flow of jth class resource, and I indicates the total number of tenant, and J indicates the total number of types of cloud service resource, and K indicates service
Device total number.
3. according to the method described in claim 2, it is characterized in that, the standard price according to each server, each service
Device unit price and each tenant data flow, establishing server loss function includes:
According to the following formula, server loss function H (c) is established,
Wherein, ckIndicate the standard price of kth platform server.
4. method according to claim 1 to 3, which is characterized in that calculated described using dynamic coordinate search
Method, after the optimal solution for determining the objective function further include:
Show the optimal solution.
5. a kind of distributor of cloud service resource, which is characterized in that established including acquiring unit, first establishing unit, second
Unit, as unit and determination unit；
The acquiring unit, for obtaining service-quality-sensitive coefficient and servicing monovalent sensitivity coefficient；
The first establishing unit, for according to the service-quality-sensitive coefficient, the monovalent sensitivity coefficient of the service, each service
Device unit price and each tenant data flow, establish service quality utility function；
Described second establishes unit, for according to the standard price of each server, each server unit price and each tenant
Data traffic establishes server loss function；
It is described to be used as unit, it is used to maximize the service quality utility function and the server loss function minimizes
As objective function；
The determination unit determines the optimal solution of the objective function for utilizing dynamic coordinate searching algorithm；Wherein, institute
Stating optimal solution includes the value of each server unit price and the value of each tenant data flow.
6. device according to claim 5, which is characterized in that the first establishing unit is specifically used for utilizing logarithmic function
Service quality utility function SF is established, formula is as follows,
Wherein, aikIndicate i-th of tenant to the service-quality-sensitive coefficient of kth platform server, bikIndicate i-th of tenant to kth
The service unit price sensitivity coefficient of platform server, cikIndicate the unit price of kth platform server, fijkIndicate kth platform server to i-th
Tenant provides the data flow of jth class resource, and I indicates the total number of tenant, and J indicates the total number of types of cloud service resource, and K indicates service
Device total number.
7. device according to claim 6, which is characterized in that described second, which establishes unit, is specifically used for according to following public
Formula establishes server loss function H (c),
Wherein, ckIndicate the standard price of kth platform server.
8. according to device described in claim 5-7 any one, which is characterized in that also packet display unit；
The display unit, for it is described utilize dynamic coordinate searching algorithm, determine the objective function optimal solution it
Afterwards, the optimal solution is shown.
9. a kind of distributor of cloud service resource characterized by comprising
Memory, for storing computer program；
Processor, for executing the computer program to realize the cloud service resource as described in Claims 1-4 any one
The step of distribution method.
10. a kind of computer readable storage medium, which is characterized in that be stored with computer on the computer readable storage medium
Program realizes the distribution of the cloud service resource as described in any one of Claims 1-4 when the computer program is executed by processor
The step of method.
Priority Applications (1)
| Application Number | Priority Date | Filing Date | Title |
|---|---|---|---|
| CN201811595260.2A CN109660623A (en) | 2018-12-25 | 2018-12-25 | A kind of distribution method, device and the computer readable storage medium of cloud service resource |
Applications Claiming Priority (1)
| Application Number | Priority Date | Filing Date | Title |
|---|---|---|---|
| CN201811595260.2A CN109660623A (en) | 2018-12-25 | 2018-12-25 | A kind of distribution method, device and the computer readable storage medium of cloud service resource |
Publications (1)
| Publication Number | Publication Date |
|---|---|
| CN109660623A true CN109660623A (en) | 2019-04-19 |
Family
ID=66116326
Family Applications (1)
| Application Number | Title | Priority Date | Filing Date |
|---|---|---|---|
| CN201811595260.2A Pending CN109660623A (en) | 2018-12-25 | 2018-12-25 | A kind of distribution method, device and the computer readable storage medium of cloud service resource |
Country Status (1)
| Country | Link |
|---|---|
| CN (1) | CN109660623A (en) |
Cited By (2)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN110740168A (en) * | 2019-09-24 | 2020-01-31 | 安徽大学 | Self-adaptive method for multi-tenant server in cloud |
| CN111131395A (en) * | 2019-11-29 | 2020-05-08 | 苏州浪潮智能科技有限公司 | FPGA cloud platform task resource allocation device, method and equipment |
Citations (7)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN101977213A (en) * | 2010-10-18 | 2011-02-16 | 南京大学 | Service combination method based on service quality under service oriented architecture (SOA) in network system |
| CN102083191A (en) * | 2009-11-30 | 2011-06-01 | 中国移动通信集团山东有限公司 | Resource allocation method and device as well as data transmission method and equipment |
| CN103338387A (en) * | 2013-06-20 | 2013-10-02 | 上海大学 | Data packet scheduling method for performing combined optimization on energy consumption and video quality under cloud computation |
| CN104598292A (en) * | 2014-12-15 | 2015-05-06 | 中山大学 | Adaptive streaming adaptation and resource optimization method applied to cloud-game system |
| CN106357796A (en) * | 2016-10-12 | 2017-01-25 | 四川用联信息技术有限公司 | Optimal service allocation algorithm for mobile applications under mobile cloud computing |
| CN106357823A (en) * | 2016-11-14 | 2017-01-25 | 阿坝师范学院 | Optimal distribution method for cloud resource for energy-saving control |
| CN107197006A (en) * | 2017-05-12 | 2017-09-22 | 中国人民解放军信息工程大学 | The multiple constraint service selection method and its device decomposed based on global QoS |
-
2018
- 2018-12-25 CN CN201811595260.2A patent/CN109660623A/en active Pending
Patent Citations (7)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN102083191A (en) * | 2009-11-30 | 2011-06-01 | 中国移动通信集团山东有限公司 | Resource allocation method and device as well as data transmission method and equipment |
| CN101977213A (en) * | 2010-10-18 | 2011-02-16 | 南京大学 | Service combination method based on service quality under service oriented architecture (SOA) in network system |
| CN103338387A (en) * | 2013-06-20 | 2013-10-02 | 上海大学 | Data packet scheduling method for performing combined optimization on energy consumption and video quality under cloud computation |
| CN104598292A (en) * | 2014-12-15 | 2015-05-06 | 中山大学 | Adaptive streaming adaptation and resource optimization method applied to cloud-game system |
| CN106357796A (en) * | 2016-10-12 | 2017-01-25 | 四川用联信息技术有限公司 | Optimal service allocation algorithm for mobile applications under mobile cloud computing |
| CN106357823A (en) * | 2016-11-14 | 2017-01-25 | 阿坝师范学院 | Optimal distribution method for cloud resource for energy-saving control |
| CN107197006A (en) * | 2017-05-12 | 2017-09-22 | 中国人民解放军信息工程大学 | The multiple constraint service selection method and its device decomposed based on global QoS |
Non-Patent Citations (1)
| Title |
|---|
| GUANGSHENG FENG: "Optimal Cooperative Wireless Communication for Mobile User Data Offloading", 《IEEE ACCESS》 * |
Cited By (4)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN110740168A (en) * | 2019-09-24 | 2020-01-31 | 安徽大学 | Self-adaptive method for multi-tenant server in cloud |
| CN110740168B (en) * | 2019-09-24 | 2022-06-03 | 安徽大学 | Self-adaptive method for multi-tenant server in cloud |
| CN111131395A (en) * | 2019-11-29 | 2020-05-08 | 苏州浪潮智能科技有限公司 | FPGA cloud platform task resource allocation device, method and equipment |
| CN111131395B (en) * | 2019-11-29 | 2022-06-07 | 苏州浪潮智能科技有限公司 | FPGA cloud platform task resource allocation device, method and equipment |
Similar Documents
| Publication | Publication Date | Title |
|---|---|---|
| CN105103506B (en) | For the method and system for the non-homogeneous bandwidth request allocation bandwidth in system for cloud computing | |
| Al-Haidari et al. | Impact of cpu utilization thresholds and scaling size on autoscaling cloud resources | |
| Quan et al. | Task scheduling for energy consumption constrained parallel applications on heterogeneous computing systems | |
| CN103827826B (en) | Adaptively determining response time distribution of transactional workloads | |
| CN109254842A (en) | Method for managing resource, device and the readable storage medium storing program for executing of distributive type system | |
| CN103064744B (en) | The method for optimizing resources that a kind of oriented multilayer Web based on SLA applies | |
| CN108667867A (en) | Date storage method and device | |
| CN103425536B (en) | A kind of test resource management method of Based on Distributed system performance testing | |
| CN103605714B (en) | The recognition methods of website abnormal data and device | |
| CN102281290A (en) | Emulation system and method for a PaaS (Platform-as-a-service) cloud platform | |
| CN106257893A (en) | Storage server task response method, client, server and system | |
| CN110502321A (en) | A kind of resource regulating method and system | |
| CN108123998A (en) | Towards the heuristic request scheduling method of delay-sensitive application in cloudy data center | |
| CN108574645A (en) | A kind of array dispatching method and device | |
| CN109660623A (en) | A kind of distribution method, device and the computer readable storage medium of cloud service resource | |
| CN109767052A (en) | Autotask distribution method and system | |
| CN106454958A (en) | A network resource allocation method and apparatus | |
| CN106789312A (en) | A kind of secure resources optimizing distribution method based on cloud computing | |
| CN106534303B (en) | A kind of load-balancing method and device applied to reconciliation system | |
| Simonovic et al. | Quantification of resilience to water scarcity, a dynamic measure in time and space | |
| CN101986608B (en) | Method for evaluating heterogeneous overlay network load balance degree | |
| CN107957945B (en) | Monetary fund system automatic performance test method, device, equipment and storage medium | |
| CN105847358A (en) | Method for realizing big data node distribution in cloud computing environment and system thereof | |
| CN104581832B (en) | A kind of realization method and system of data service shunting | |
| CN107196875A (en) | A kind of network resource scheduling system based on Consumer's Experience |
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 | ||
| RJ01 | Rejection of invention patent application after publication |
Application publication date: 20190419 |
|
| RJ01 | Rejection of invention patent application after publication |