CN104484233A - Method of allocating resources - Google Patents
Method of allocating resources Download PDFInfo
- Publication number
- CN104484233A CN104484233A CN201410602590.5A CN201410602590A CN104484233A CN 104484233 A CN104484233 A CN 104484233A CN 201410602590 A CN201410602590 A CN 201410602590A CN 104484233 A CN104484233 A CN 104484233A
- Authority
- CN
- China
- Prior art keywords
- resource
- parallel processing
- redundancy
- processing scheme
- tasks
- 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
Abstract
The invention discloses a method of allocating resources. The method comprises the steps of generating a plurality of parallelization processing plans of an alternative task corresponding to tasks to be performed, determining reference operating performance of the parallelization processing plans of the alternative task, screening the parallelization processing plans of a feasible task by combining a preset real-time requirement and local resource parameters of a base station, mapping the screened parallelization processing plans of the feasible task to one or more than one physical implementation plans, and determining an optimal physical implementation plan according to consumed resources of each physical implementation plan and a multi-attribute decision-making strategy. The final resource allocating plan can be matched with the current environment, so that the method can be supported by available resources in a resource pool, and the resources can meet the real-time requirement.
Description
Technical field
The present invention relates to communication technical field, particularly a kind of resource allocation methods.
Background technology
A traditional communication facilities often manufacturer provides a whole set of solution, system maintenance or upgrading dependence high.And along with energy resources were nervous in recent years, the cost pressure that global mobile communication network operators face is day by day serious.Most of mainstream carrier has the network of multiple different communication standard usually, for ensureing the service quality of network, needs to dispose a large amount of base stations to solve the problem of the network coverage.But the relative scarcity of site and machine room resource, forms with the demand of a large amount of base station deployment the contradiction being difficult to coordinate.And due to the cut-throat competition of Mobile Communications Market, single user average income increasess slowly and even declines, and " profit " ability of operator does not improve thereupon, this will cause the compression of networking and equipment purchase investment.Continue profit and long-run development consideration for industry, Mobile Communication Industry circle proposes to address this problem by changing access network framework.
But inventor is realizing finding in the multiplexing process of equipment by changing access network framework, and existing base station resource pond platform architecture adopts general processor usually, is dispatched multinomial Processing tasks by operating system.Different from the Resourse Distribute visual angle in existing virtual resources dispatching system, not only relate to the distribution of process/multi dimensional resource such as computational resource, storage resources in base station resource pond, also need the requirement of real-time considering Base-Band Processing.For ensureing requirement of real-time, because interface communication amount is comparatively large, the scheduling of resource between server will be restricted.And being different from conventional baseband solution, base station resource pond should select suitable physical resource to complete Base-Band Processing process for Current resource pool environment.Therefore, although related to the dispatching distribution of resource pool multi dimensional resource in current existing scheme, but still there are the following problems: do not take explicitly into account requirement of real-time in implementation method, the resource of resource pool multiserver is considered as equal resource, resource dispatch area in the scheduling of resource between multiserver and server is not divided, but can relate to compared with multi-interface communication amount due to the scheduling of resource between server thus affect the real-time of task process.In addition, existing method adopts fixing baseband processing arrangements usually, does not consider how scheduling of resource adapts with current environment.
Summary of the invention
The invention provides a kind of resource allocation methods, not high in order to solve resource distribution mode real-time in prior art, inflexible problem, the method comprises:
Generate multiple and that pending task is corresponding alternative tasks in parallel processing scheme, described alternative tasks in parallel processing scheme is the set of the parallel processing plan corresponding with described pending task;
Determine the reference runnability of each described alternative tasks in parallel processing scheme, described is the runnability that described base station resource pond individually performs each described alternative tasks in parallel processing scheme with reference to runnability;
The resource parameters current according to requirement of real-time, the described base station resource pond of presetting and the reference runnability of each described alternative tasks in parallel processing scheme, screen feasible tasks in parallel processing scheme from described alternative tasks in parallel processing scheme; Described resource parameters comprise current available resources, working time amount of redundancy and resource consumption amount of redundancy, the described number percent that working time, amount of redundancy additionally needed when performing each described alternative tasks in parallel processing scheme the working time consumed for described base station resource pond, described resource consumption amount of redundancy additionally needs the number percent of the resource of consumption when performing each described alternative tasks in parallel processing scheme for described base station resource pond;
By each feasible tasks in parallel processing scheme that filters out respectively correspondence mappings be one or more physical implementation, the set that physical implementation forms after being distributed to the current available physical resource in described base station resource pond for feasible tasks in parallel processing scheme;
The resource consumed according to each described physical implementation and multiple attribute decision making (MADM) strategy determination optimal physical implementation, and carry out Resourse Distribute according to described optimal physical implementation.
As can be seen here, by applying above technical scheme, first the alternative tasks in parallel processing scheme that multiple and pending task is corresponding is generated, after the reference runnability determining each alternative tasks in parallel processing scheme, feasible tasks in parallel processing scheme is screened in conjunction with the current resource parameters of the requirement of real-time preset and base station resource pond, then by each feasible tasks in parallel processing scheme that filters out respectively correspondence mappings be one or more physical implementation, and the resource consumed according to each described physical implementation and multiple attribute decision making (MADM) strategy determination optimal physical implementation.Final Resource Allocation Formula is mated with current environment, and assured plan is that resource pool current available resource can be supported and energy requirement of real time.
Accompanying drawing explanation
Fig. 1 is the schematic flow sheet of a kind of resource allocation methods that the present invention proposes.
Embodiment
In order to solve the problem proposed in background technology, the present invention proposes a kind of physical layer resources distribution method of base station resource pond, first parallelization process is carried out to Physical layer base band calculation task, formed multiple base band Parallelization Scheme composition scheme set and statistical-reference runnability, then from alternatives set, feasible alternatives collection is determined according to requirement of real-time and Current resource pool environment, finally the scheme that alternatives is concentrated is mapped as physical implementation, form implementation set, the implementation mated with resource pool current environment is selected again based on multiple attributive decision making method.
As shown in Figure 1, be the physical layer resources distribution method schematic flow sheet in a kind of base station resource pond that the present invention proposes, the method is applied in base station resource pond, and described base station resource pond is connected by optical transport network with described RRU as BBU, comprises the following steps:
S101, generates the alternative tasks in parallel processing scheme that multiple and pending task is corresponding, and described alternative tasks in parallel processing scheme is the set of the parallel processing plan corresponding with described pending task.
For pending task, first the present invention carries out parallelization process to Physical layer base band calculation task, formed multiple base band Parallelization Scheme composition scheme set and statistical-reference runnability.Particularly, described pending Task-decomposing is treated to described each parallel processing plan by tasks in parallel by this step, using the set of each parallel processing plan as described alternative tasks in parallel processing scheme.
S102, determines the reference runnability of each described alternative tasks in parallel processing scheme, and described is the runnability that described base station resource pond individually performs each described alternative tasks in parallel processing scheme with reference to runnability.
S103, the resource parameters current according to requirement of real-time, the described base station resource pond of presetting and the reference runnability of each described alternative tasks in parallel processing scheme, screen feasible tasks in parallel processing scheme from described alternative tasks in parallel processing scheme.
Based on the result of S101 and S102, the present invention arranges the amount of redundancy of working time and resource consumption according to the position distribution of resource pool current idle processing power, idling-resource, the situation of task scheduling migration, and from alternatives set, selects alternatives feasible under the present circumstances according to reference to runnability and amount of redundancy.Wherein, described resource parameters comprise current available resources, working time amount of redundancy and resource consumption amount of redundancy, the described number percent that working time, amount of redundancy additionally needed when performing each described alternative tasks in parallel processing scheme the working time consumed for described base station resource pond, described resource consumption amount of redundancy additionally needs the number percent of the resource of consumption when performing each described alternative tasks in parallel processing scheme for described base station resource pond.
In addition, before this step, the environmental parameter current according to described base station resource pond is also arranged amount of redundancy and described resource consumption amount of redundancy described working time by the present invention, described environmental parameter comprises the current free processing capacity in described base station resource pond, idling-resource position distribution, task scheduling migration situation, and concrete arranging is regular as follows:
If described free processing capacity is comparatively large, then amount of redundancy and resource consumption amount of redundancy less working time is set;
If the scheduling of described pending task need perform according to load balancing, then less amount of redundancy working time is set;
If described task scheduling migration situation is comparatively frequent, then less amount of redundancy working time is set, and larger resource consumption amount of redundancy is set;
If described idling-resource position distribution is comparatively concentrated, then less amount of redundancy working time is set;
If described idling-resource position distribution is comparatively disperseed, then larger amount of redundancy working time is set.
S104, by each feasible tasks in parallel processing scheme that filters out respectively correspondence mappings be one or more physical implementation, the set that physical implementation forms after being distributed to the current available physical resource in described base station resource pond for feasible tasks in parallel processing scheme.
Based on the result of S103, first this step obtains the reference working time and reference resources consumption that comprise in the reference runnability of alternative tasks in parallel processing scheme to be screened; If described with reference to being still less than described requirement of real-time according to amount of redundancy described working time after increasing working time, and described reference resources consumption is still less than described available resources after increasing according to described resource consumption amount of redundancy, then using described alternative resource allocative decision as described feasible alternative resource allocative decision.
S105, the resource consumed according to each described physical implementation and multiple attribute decision making (MADM) strategy determination optimal physical implementation, and carry out Resourse Distribute according to described optimal physical implementation.
After S101-S104 is finished, the scheme that alternatives is concentrated is mapped as physical implementation by the present invention, forms implementation set, then selects the implementation that mates with resource pool current environment based on multiple attributive decision making method.Particularly, the interface resource that the idle available processing resources, idle available storage resources and the scheme that perform after each described physical implementation consume by this step is as the input attributes of scheme, the synthesized attribute value of each described physical implementation is determined according to described multiple attribute decision making (MADM) strategy, and using physical implementation the highest for synthesized attribute value as described optimal physical implementation.
It is to be noted, in order to reduce the processing load of this step, before this step, can according to the multiple interface resource consumption level preset, the physical implementation corresponding with each described feasible tasks in parallel processing scheme is screened, retains the physical implementation of interface resource consumption level minimum in each described feasible tasks in parallel processing scheme.
In order to set forth technological thought of the present invention further, now in conjunction with concrete application scenarios, technical scheme of the present invention is described.This specific embodiment is divided into following three steps:
Step 1: parallelization process is carried out to Physical layer base band calculation task based on load balancing principle, formed multiple base band Parallelization Scheme composition scheme set and statistical-reference runnability
The Physical layer base band signal process of wireless communication system, by multiple calculation task or Algorithm constitution, wherein comprises some computation-intensive algorithms, and as input, channel decoding etc., their calculated amount is large, complexity is high.Another feature of physical layer algorithm has clear and definite order to perform relation between calculation task, and namely the output of a calculation task is using the input as next calculation task.If do not carry out parallelization process to computation-intensive algorithm, it will become the bottleneck of Physical layer Base-Band Processing, causes calculation task elapsed time excessive, cannot meet real-time demand.
Therefore for meeting system real time requirement, need algorithm, especially computation-intensive algorithm carries out splitting to realize parallelization process.Because a certain calculation task or algorithm can have multiple parallelization processing mode, the Physical layer baseband processing arrangements be made up of multiple calculation task also has multiple parallel structure.Its all kinds of resources consumed of the scheme adopting different parallel structure to design are different, and as computational resource, storage resources, interface resource etc., the time of operation is also different.Manage choosing of layered scheme base station resource mediocre person to need to consider that the factor such as requirement of real-time, current idle resource situation is to adapt to resource pool environmental change, so it is alternative that kinds of schemes can be provided to form scheme set.
Step 1.1 pair Physical layer Base-Band Processing carries out paralell design, forms alternatives set
Because base station resource pond often adopts general purpose processor platform, for ensureing that polycaryon processor is fully used, can consider that the principle based on load balancing carries out Task-decomposing to calculation task especially computation-intensive task, go out multiple parallel processing plan by the patten's design of streamline, tasks in parallel.These parallel processing plan constitute alternatives set.
Step 1.2 obtains the reference runnability of alternatives
When to refer to without other baseband processing arrangements in base station resource pond with reference to runnability, perform separately the runnability of a certain baseband processing arrangements.According to the business difference of the Base-Band Processing that agreement specifies, the data volume of respective handling is also different.For different pieces of information amount, a certain scheme also has multiple with reference to runnability.
The working time of each scheme, all kinds of resource situation of consumption are comprised with reference to runnability.The logical resource consumed when all kinds of resources wherein consumed refer to that calculation task performs, comprises process/computational resource, storage resources.
Can online under perform alternatives in advance to obtain with reference to runnability.According to descending by ranking alternatives with reference to working time, and record other runnabilities.Following table provides record alternatives and the example with reference to runnability thereof.
Table 1 records alternatives and the example with reference to runnability thereof
Step 2: determine feasible alternatives collection according to requirement of real-time and Current resource pool environment from alternatives set
Have in base station resource pond a large amount of community, user data process, when certain user data arrive base station resource pond time, the baseband processing arrangements adopted should be selected according to Current resource pool environment.And the reference performance difference to some extent that working time, all kinds of resource situation that the scheme chosen consumes are added up because there being other schemes, under impact that data processing is brought and line.Therefore can not directly with reference to runnability foundation alternatively.Because carrying out practically performance is by resource pool environmental impact, need to consider current environment influence factor.
Step 2.1 arranges the amount of redundancy of working time and resource consumption according to base station resource pond current environment
Need the base station resource pond current environment factor considered that the amount of redundancy of working time and resource consumption is set, comprising: the position distribution of current idle processing power, idling-resource, the situation of task scheduling migration.Wherein current idle processing power can be represented by the ratio of current open ended portfolio and the open ended total traffic of resource pool.Task scheduling, migration refer to that pending calculation task is assigned to processor and carries out calculation task remapping to physical resource according to resource pool current environment respectively.The position distribution of idling-resource can be concentrated/degree of scatter measurement by idling-resource.
Working time and resource consumption amount of redundancy is represented respectively with percent value a%, b%.Amount of redundancy is arranged according to resource pool current environment factor and experience.If current idle processing power is comparatively large, then less working time and resource consumption amount of redundancy can be set.If the scheduling reference fairness of task, load balancing principle perform, then less amount of redundancy working time should be set.Usually due to cannot reach working time requirement of real-time or resource comparatively idle time, need to carry out task immigration.If task immigration is comparatively frequent, then amount of redundancy and larger resource consumption amount of redundancy less working time should be set.If there is more idling-resource integrated distribution, less amount of redundancy working time then can be set, if idling-resource distribution dispersion, mean and will expend more interface communication amount and make the resource coordinating work of dispersion, cause real-time to be affected, then need to arrange larger amount of redundancy working time.
Step 2.2. selects alternatives feasible under the present circumstances according to reference to runnability and amount of redundancy from alternatives set
The resource that feasible alternatives needs should be that resource pool current available resource can be supported and energy requirement of real time.The selection of therefore feasible alternatives needs to consider current environment.
First the reference of scheme each in alternatives set is compared in conjunction with amount of redundancy and requirement of real-time working time, select the scheme conforming with requirement of real-time.Judgement mode is as follows: with reference to * (1+a%) < requirement of real-time working time, be then judged to feasible alternatives.
Then the reference resources consumption of each scheme in the alternatives set of requirement of real time is compared in conjunction with resource consumption amount of redundancy and current available resource, select the scheme meeting available resources support.Judgement mode is as follows: reference resources consumption * (1+b%) < current available resource, be then judged to feasible alternatives.Wherein process/computational resource, storage resources need calculate respectively.
Finally all qualified feasible alternativess form feasible alternatives collection.
Step 3: alternatives is mapped as physical implementation, forms implementation set, selects the implementation mated with resource pool current environment based on multiple attributive decision making method
This step will be selected final implementation and be mapped on physical resource from feasible alternatives.Physical resource comprises actual process/computational resource, storage resources, interface resource.The working time of usual scheme and the resource of consumption are contradiction.Selection scheme should make the resource of consumption the least possible when mapping under requirement of real time.
Alternatives is mapped as physical implementation by step 3.1, forms implementation set
Alternatives is mapped as physical implementation and refers to that the alternatives obtained according to the first step is with reference to consumption of natural resource, is distributed to the calculation task of alternatives in current available physical resource.Only consider logical resource, i.e. the consumption of process/computational resource, storage resources with reference to consumption of natural resource, need to consider process/computational resource, the distribution of storage resources in resource pool when carrying out physical resource and mapping.If alternatives adopts multiple processor to work in coordination with a certain calculation task, multiple processor distributions (as being distributed on different server) comparatively far away then need to consume more interface communication visit capacity.Therefore, when carrying out physical resource and mapping, the consumption considering interface resource is also needed, i.e. the size of interface communication amount.Process/computational resource, storage resources are distributed with multiple situation in resource pool, even if same scheme consumes identical process/computational resource, storage resources, corresponding interface resource also may be different.Therefore an alternatives can corresponding multiple physical implementation.
The distributions that resource pool tackles wherein each physical resource is monitored, and understands available process/computational resource, the position of storage resources in real time.When carrying out physical resource and mapping, search according to the logical resource of alternatives needs and choose available physical resources, and added up the interface resource of project task, form the physical implementation set that alternatives is corresponding.Following table gives the example of physical implementation consumption of natural resource.
The example of the physical implementation consumption of natural resource that table 2 alternatives is corresponding
When the idling-resource of resource pool is more, available physical resources and position distribution situation more, the physical implementation causing alternatives corresponding is more, judges overlong time.Therefore can by the distribution of the physical resource of resource pool with the interface resource divided rank consumed.The interface communication amount consumed during two physical resource co-ordinations is comparatively large, then they belong to higher interface resource grade.First should choose process/computational resource, storage resources in the physical resource of lower same interface resource grade.If low-grade physical resource cannot meet the demands, then in more high-grade physical resource, search available resources.Such as because base station resource pond comprises multiple servers usually, the processor collaborative work on different server, can consume relatively large server interface communication.Therefore the process resource of different server belongs to the physical resource of higher interface resource grade, and the process resource in same server belongs to the physical resource of lower interface resource grade.First can search available resources in server, if not, then be mapped to again in the resource between server.All possible implementation need not be enumerated.
Step 3.2 selects the implementation mated with resource pool current environment based on multiple attributive decision making method
To from feasible implementation set, select the implementation of coupling current environment as Multiple Attribute Decision Problems.Wish that the scheme chosen consumes less interface resource and makes the process resource of residue free time, storage resources more when reaching requirement of real-time.
If the implementation obtained by previous step integrates as X=(x
1, x
2... x
n), wherein x
irepresent i-th implementation, i=1,2...n, n are implementation number.Property set P=(p
1, p
2, p
3), p
1process resource idle available after referring to use the program, the reference consumption process stock number being deducted the program by Current resource pond available processing resources amount obtains, p
2storage resources amount idle available after referring to use the program, can be deducted the reference consumption storage resources amount acquisition of the program, p by storage resources amount by Current resource pond
3refer to the interface resource amount consumed.P
1, p
2profit evaluation model attribute, p
3it is cost type attribute.
For a certain implementation x
i, by attribute p
jestimate, obtain x
iabout p
jproperty value α
ij, form decision matrix Γ=(α
ij)
n × 3, as follows:
| p 1 | p 2 | p 3 | |
| x 1 | α 11 | α 12 | α 13 |
| x 2 | α 21 | α 22 | α 23 |
| … | |||
| x n | α n1 | α n2 | α n3 |
Standardization is carried out to above-mentioned matrix and obtains Standard Process R=(r
ij)
n × m, wherein for p
1, p
2property value α
ij, j ∈ 1,2, order
for p
3property value α
i3, order
j=3.
Obtain normalization matrix further,
wherein
Calculate p
jthe information entropy exported,
j=1,2,3.
Calculate weight vectors, β=(β
1, β
2, β
3), wherein
Foundation
numerical procedure x
isynthesized attribute value z
i(β) (i=1,2 ..., n).Utilize z
i(β) sequence is carried out to scheme and choose maximal value as final implementation.
Have employed information entropy in previous step as weight, also can rule of thumb set weight beta=(β
1, β
2, β
3), make
calculate z according to this
i(β) final implementation is chosen.
By applying above technical scheme, first the alternative tasks in parallel processing scheme that multiple and pending task is corresponding is generated, after the reference runnability determining each alternative tasks in parallel processing scheme, feasible tasks in parallel processing scheme is screened in conjunction with the current resource parameters of the requirement of real-time preset and base station resource pond, then by each feasible tasks in parallel processing scheme that filters out respectively correspondence mappings be one or more physical implementation, and the resource consumed according to each described physical implementation and multiple attribute decision making (MADM) strategy determination optimal physical implementation.Final Resource Allocation Formula is mated with current environment, and assured plan is that resource pool current available resource can be supported and energy requirement of real time.
Through the above description of the embodiments, those skilled in the art can be well understood to the present invention can by hardware implementing, and the mode that also can add necessary general hardware platform by software realizes.Based on such understanding, technical scheme of the present invention can embody with the form of software product, it (can be CD-ROM that this software product can be stored in a non-volatile memory medium, USB flash disk, portable hard drive etc.) in, comprise some instructions and perform each method implementing described in scene of the present invention in order to make a computer equipment (can be personal computer, server, or the network equipment etc.).
It will be appreciated by those skilled in the art that accompanying drawing is a schematic diagram preferably implementing scene, the module in accompanying drawing or flow process might not be that enforcement the present invention is necessary.
It will be appreciated by those skilled in the art that the module in the device implemented in scene can carry out being distributed in the device of enforcement scene according to implementing scene description, also can carry out respective change and being arranged in the one or more devices being different from this enforcement scene.The module of above-mentioned enforcement scene can merge into a module, also can split into multiple submodule further.
The invention described above sequence number, just to describing, does not represent the quality implementing scene.
Be only several concrete enforcement scene of the present invention above, but the present invention is not limited thereto, the changes that any person skilled in the art can think of all should fall into protection scope of the present invention.
Claims (6)
1. a resource allocation methods, is characterized in that, described method is applied in base station resource pond, and described base station resource pond is connected by optical transport network with described RRU as BBU, and the method comprises:
Generate multiple and that pending task is corresponding alternative tasks in parallel processing scheme, described alternative tasks in parallel processing scheme is the set of the parallel processing plan corresponding with described pending task;
Determine the reference runnability of each described alternative tasks in parallel processing scheme, described is the runnability that described base station resource pond individually performs each described alternative tasks in parallel processing scheme with reference to runnability;
The resource parameters current according to requirement of real-time, the described base station resource pond of presetting and the reference runnability of each described alternative tasks in parallel processing scheme, screen feasible tasks in parallel processing scheme from described alternative tasks in parallel processing scheme; Described resource parameters comprise current available resources, working time amount of redundancy and resource consumption amount of redundancy, the described number percent that working time, amount of redundancy additionally needed when performing each described alternative tasks in parallel processing scheme the working time consumed for described base station resource pond, described resource consumption amount of redundancy additionally needs the number percent of the resource of consumption when performing each described alternative tasks in parallel processing scheme for described base station resource pond;
By each feasible tasks in parallel processing scheme that filters out respectively correspondence mappings be one or more physical implementation, the set that physical implementation forms after being distributed to the current available physical resource in described base station resource pond for feasible tasks in parallel processing scheme;
The resource consumed according to each described physical implementation and multiple attribute decision making (MADM) strategy determination optimal physical implementation, and carry out Resourse Distribute according to described optimal physical implementation.
2. the method for claim 1, is characterized in that, generates the alternative tasks in parallel processing scheme that multiple and pending task is corresponding, is specially:
By tasks in parallel, described pending Task-decomposing is treated to described each parallel processing plan, using the set of each parallel processing plan as described alternative tasks in parallel processing scheme.
3. the method for claim 1, it is characterized in that, before the reference runnability of the resource parameters current according to requirement of real-time, the described base station resource pond of presetting and each described alternative tasks in parallel processing scheme screens feasible tasks in parallel processing scheme from described alternative tasks in parallel processing scheme, also comprise:
The environmental parameter current according to described base station resource pond arranges amount of redundancy and described resource consumption amount of redundancy described working time, and described environmental parameter comprises the current free processing capacity in described base station resource pond, idling-resource position distribution, task scheduling migration situation; Wherein,
If described free processing capacity is comparatively large, then amount of redundancy and resource consumption amount of redundancy less working time is set;
If the scheduling of described pending task need perform according to load balancing, then less amount of redundancy working time is set;
If described task scheduling migration situation is comparatively frequent, then less amount of redundancy working time is set, and larger resource consumption amount of redundancy is set;
If described idling-resource position distribution is comparatively concentrated, then less amount of redundancy working time is set;
If described idling-resource position distribution is comparatively disperseed, then larger amount of redundancy working time is set.
4. method as claimed in claim 3, it is characterized in that, the resource parameters current according to requirement of real-time, the described base station resource pond of presetting and the reference runnability of each described alternative resource allocative decision carry out the screening of feasible alternative tasks in parallel processing scheme, are specially:
Obtain the reference working time and reference resources consumption that comprise in the reference runnability of alternative tasks in parallel processing scheme to be screened;
If described with reference to being still less than described requirement of real-time according to amount of redundancy described working time after increasing working time, and described reference resources consumption is still less than described available resources after increasing according to described resource consumption amount of redundancy, then using described alternative resource allocative decision as described feasible alternative resource allocative decision.
5. the method for claim 1, is characterized in that, described resource comprises process resource, storage resources and interface resource, and the resource consumed according to each described physical implementation and multiple attribute decision making (MADM) strategy determination optimal physical implementation, be specially:
The interface resource idle available processing resources, idle available storage resources and the program that perform after each described physical implementation consumed is as the input attributes of scheme, the synthesized attribute value of each described physical implementation is determined according to described multiple attribute decision making (MADM) strategy, and using physical implementation the highest for synthesized attribute value as described optimal physical implementation.
6. method as claimed in claim 5, is characterized in that, before the resource consumed according to each described physical implementation and multiple attribute decision making (MADM) strategy determination optimal physical implementation, also comprise:
According to the multiple interface resource consumption level preset, the physical implementation corresponding with each described feasible tasks in parallel processing scheme is screened, retains the physical implementation of interface resource consumption level minimum in each described feasible tasks in parallel processing scheme.
Priority Applications (1)
| Application Number | Priority Date | Filing Date | Title |
|---|---|---|---|
| CN201410602590.5A CN104484233B (en) | 2014-10-31 | 2014-10-31 | A kind of resource allocation methods |
Applications Claiming Priority (1)
| Application Number | Priority Date | Filing Date | Title |
|---|---|---|---|
| CN201410602590.5A CN104484233B (en) | 2014-10-31 | 2014-10-31 | A kind of resource allocation methods |
Publications (2)
| Publication Number | Publication Date |
|---|---|
| CN104484233A true CN104484233A (en) | 2015-04-01 |
| CN104484233B CN104484233B (en) | 2017-12-05 |
Family
ID=52758777
Family Applications (1)
| Application Number | Title | Priority Date | Filing Date |
|---|---|---|---|
| CN201410602590.5A Active CN104484233B (en) | 2014-10-31 | 2014-10-31 | A kind of resource allocation methods |
Country Status (1)
| Country | Link |
|---|---|
| CN (1) | CN104484233B (en) |
Cited By (8)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN106155807A (en) * | 2015-04-15 | 2016-11-23 | 阿里巴巴集团控股有限公司 | A kind of method and apparatus realizing scheduling of resource |
| CN106155977A (en) * | 2015-06-03 | 2016-11-23 | 上海红神信息技术有限公司 | Restructural method for managing resource in reconfigurable system and system |
| CN107025137A (en) * | 2016-11-24 | 2017-08-08 | 阿里巴巴集团控股有限公司 | A kind of resource query method and device |
| CN107239337A (en) * | 2016-03-28 | 2017-10-10 | 北京智梵网络科技有限公司 | The distribution of virtual resources and dispatching method and system |
| CN108628667A (en) * | 2017-03-16 | 2018-10-09 | 哈尔滨英赛克信息技术有限公司 | A kind of heuristic dynamic task scheduling system and its implementation based on multiple attribute decision making (MADM) |
| CN109831321A (en) * | 2019-01-04 | 2019-05-31 | 东南大学 | RDMA application transport parameter adaptive selection method in a kind of data center |
| CN112449021A (en) * | 2016-01-27 | 2021-03-05 | 创新先进技术有限公司 | Method and device for screening internet resources |
| CN113992666A (en) * | 2021-09-18 | 2022-01-28 | 阿里巴巴（中国）有限公司 | Cloud resource allocation method, system, device and storage medium |
Citations (4)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN101119314A (en) * | 2007-09-14 | 2008-02-06 | 中国科学院计算技术研究所 | Multimode terminal service stream control system and device and method |
| CN102780765A (en) * | 2012-06-27 | 2012-11-14 | 浙江大学 | Cloud manufacturing service resource match and combination method based on performance fusion |
| US20130235748A1 (en) * | 2008-07-07 | 2013-09-12 | Apple Inc. | Medium Access Control for Wireless Systems |
| CN103841647A (en) * | 2014-03-07 | 2014-06-04 | 北京邮电大学 | Multi-granularity telescopic packaging device and method based on base station resource pool |
-
2014
- 2014-10-31 CN CN201410602590.5A patent/CN104484233B/en active Active
Patent Citations (4)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN101119314A (en) * | 2007-09-14 | 2008-02-06 | 中国科学院计算技术研究所 | Multimode terminal service stream control system and device and method |
| US20130235748A1 (en) * | 2008-07-07 | 2013-09-12 | Apple Inc. | Medium Access Control for Wireless Systems |
| CN102780765A (en) * | 2012-06-27 | 2012-11-14 | 浙江大学 | Cloud manufacturing service resource match and combination method based on performance fusion |
| CN103841647A (en) * | 2014-03-07 | 2014-06-04 | 北京邮电大学 | Multi-granularity telescopic packaging device and method based on base station resource pool |
Non-Patent Citations (1)
| Title |
|---|
| 王勇: "未来移动通信基站体系结构-定性理论、方法与实践", 《中国博士学位论文全文数据库 信息科技辑》 * |
Cited By (13)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN106155807A (en) * | 2015-04-15 | 2016-11-23 | 阿里巴巴集团控股有限公司 | A kind of method and apparatus realizing scheduling of resource |
| US10789100B2 (en) | 2015-04-15 | 2020-09-29 | Alibaba Group Holding Limited | System, apparatus and method for resource provisioning |
| CN106155977B (en) * | 2015-06-03 | 2019-07-30 | 上海红神信息技术有限公司 | Restructural method for managing resource and system in reconfigurable system |
| CN106155977A (en) * | 2015-06-03 | 2016-11-23 | 上海红神信息技术有限公司 | Restructural method for managing resource in reconfigurable system and system |
| CN112449021A (en) * | 2016-01-27 | 2021-03-05 | 创新先进技术有限公司 | Method and device for screening internet resources |
| CN112449021B (en) * | 2016-01-27 | 2023-10-27 | 创新先进技术有限公司 | Internet resource screening method and device |
| CN107239337A (en) * | 2016-03-28 | 2017-10-10 | 北京智梵网络科技有限公司 | The distribution of virtual resources and dispatching method and system |
| CN107025137A (en) * | 2016-11-24 | 2017-08-08 | 阿里巴巴集团控股有限公司 | A kind of resource query method and device |
| CN108628667A (en) * | 2017-03-16 | 2018-10-09 | 哈尔滨英赛克信息技术有限公司 | A kind of heuristic dynamic task scheduling system and its implementation based on multiple attribute decision making (MADM) |
| CN109831321A (en) * | 2019-01-04 | 2019-05-31 | 东南大学 | RDMA application transport parameter adaptive selection method in a kind of data center |
| CN109831321B (en) * | 2019-01-04 | 2021-02-09 | 东南大学 | RDMA application transmission parameter self-adaptive selection method in data center |
| CN113992666A (en) * | 2021-09-18 | 2022-01-28 | 阿里巴巴（中国）有限公司 | Cloud resource allocation method, system, device and storage medium |
| CN113992666B (en) * | 2021-09-18 | 2023-12-29 | 阿里巴巴（中国）有限公司 | Cloud resource allocation method, system, equipment and storage medium |
Also Published As
| Publication number | Publication date |
|---|---|
| CN104484233B (en) | 2017-12-05 |
Similar Documents
| Publication | Publication Date | Title |
|---|---|---|
| CN104484233A (en) | Method of allocating resources | |
| CN104038540B (en) | Method and system for automatically selecting application proxy server | |
| CN103780646B (en) | Cloud resource scheduling method and system | |
| Tziritas et al. | Application-aware workload consolidation to minimize both energy consumption and network load in cloud environments | |
| CN103885831B (en) | The system of selection of virtual machine host machine and device | |
| CN108076486A (en) | A kind of dynamic radio resource allocation algorithm based on load balancing | |
| CN111614754B (en) | Fog-calculation-oriented cost-efficiency optimized dynamic self-adaptive task scheduling method | |
| CN108901075A (en) | A kind of resource allocation methods based on GS algorithm | |
| CN110502321A (en) | A kind of resource regulating method and system | |
| CN103841647A (en) | Multi-granularity telescopic packaging device and method based on base station resource pool | |
| CN106656555A (en) | Dynamic adjustment method of service resources of cloud computing system | |
| CN112365366A (en) | Micro-grid management method and system based on intelligent 5G slice | |
| CN110061881A (en) | A kind of energy consumption perception virtual network mapping algorithm based on Internet of Things | |
| DE112016006705T5 (en) | Method for providing operating information for a network | |
| US8683479B1 (en) | Shifting information technology workload demands | |
| CN109343945A (en) | A kind of multitask dynamic allocation method based on contract net algorithm | |
| CN116340003A (en) | Self-adaptive edge computing resource management method and system based on deep reinforcement learning | |
| CN103713852A (en) | Method for processing information, service platform and electronic devices | |
| CN103077127B (en) | A kind of method and apparatus of specified data migrating objects | |
| CN112465371B (en) | Resource data distribution method, device and equipment | |
| CN103501509B (en) | A kind of method and device equalizing radio network controller load | |
| WO2023222061A1 (en) | Intent-driven wireless network resource conflict resolution method and apparatus | |
| CN104507166A (en) | Method for sharing virtual resource configuration in baseband pooling | |
| CN105049475B (en) | The data efficient storage optimization method and system of extensive community | |
| Kolomvatsos et al. | Scheduling the execution of tasks at the edge |
Legal Events
| Date | Code | Title | Description |
|---|---|---|---|
| C06 | Publication | ||
| PB01 | Publication | ||
| C10 | Entry into substantive examination | ||
| SE01 | Entry into force of request for substantive examination | ||
| GR01 | Patent grant | ||
| GR01 | Patent grant |