CN102185713B - Global optimization method of internet service resource distribution - Google Patents
Global optimization method of internet service resource distribution Download PDFInfo
- Publication number
- CN102185713B CN102185713B CN201110113313.4A CN201110113313A CN102185713B CN 102185713 B CN102185713 B CN 102185713B CN 201110113313 A CN201110113313 A CN 201110113313A CN 102185713 B CN102185713 B CN 102185713B
- Authority
- CN
- China
- Prior art keywords
- service
- assembly
- point
- client
- services
- 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.)
- Expired - Fee Related
Links
Landscapes
- Management, Administration, Business Operations System, And Electronic Commerce (AREA)
- Computer And Data Communications (AREA)
Abstract
The invention relates to a global optimization method of internet service resource distribution, which comprises the steps of: A, arranging multiple client point modules and a service resource distribution management module; B, collecting one or more service information of the client points and transmitting the information to the service resource distribution management module by the client point modules; C, analyzing the service information by the service resource distribution management module to obtain N service information types and dividing the multiple client point modules into N types, wherein N is an integer of more than 0; D, arranging N service point modules by the service resource distribution management module; and E, controlling the service point modules to respond to requests of the client point modules by the service resource distribution management module according to the service information types. The services are provided according to the service types to save the network resources; and by using the method, short response time and higher reliability of the network service are obtained.
Description
Technical field
The present invention relates to Internet resources distribution technique, relate in particular to the global optimization method that a kind of internet service resource distributes.
Background technology
Existing technology of distributing for Internet resources is the distribution based on single resource type with research, but under many actual conditions, is only that the distribution of single resource type far can not satisfy the demands.For example, for a p2p system, the needed resource of client may be distributed in the different service provision points in network, and the service of each service provision point confession is not quite similar, and how carrying out service resource allocation is the problem that needs solve.
Summary of the invention
For addressing the above problem, the invention provides the global optimization method that a kind of efficient internet service resource distributes.
For achieving the above object, the technical solution used in the present invention is: the global optimization method that a kind of internet service resource distributes, is characterized in that:
A., a plurality of clients are set and put assembly, service resource allocation Management Unit;
B. client puts assembly collection client and puts one or more information on services, and sends to service resource allocation Management Unit;
C. service resource allocation Management Unit Analysis Service information type is N, a plurality of clients is put to assembly and be divided into N kind, and described N is greater than 0 integer; D. service resource allocation Management Unit is established N service point assembly;
E. service resource allocation Management Unit is put components request according to information on services Type Control service point component responds client.
Present invention further optimization scheme is that in described step C, service resource allocation Management Unit comprises that client puts log-on message analytic unit and service point component register information analysis assembly.
Technical advantage of the present invention is: according to COS, provide service, saved Internet resources, the method makes network service response time short, and reliability is higher.
The present invention will be further described with embodiment by reference to the accompanying drawings.
Accompanying drawing explanation
Fig. 1 is the present embodiment structural representation.
Embodiment
With reference to figure 1, the global optimization method that a kind of internet service resource distributes,
A., a plurality of clients are set and put assembly, service resource allocation Management Unit;
B. client puts assembly collection client and puts one or more information on services, and sends to service resource allocation Management Unit;
C. service resource allocation Management Unit Analysis Service information type is N, a plurality of clients is put to assembly and be divided into N kind, and described N is greater than 0 integer; D. service resource allocation Management Unit is established N service point assembly;
E. service resource allocation Management Unit is put components request according to information on services Type Control service point component responds client.
In step C, service resource allocation Management Unit comprises that client puts log-on message analytic unit and service point component register information analysis assembly.After steps A completes, client puts assembly and by client, puts log-on message analytic unit and distribute to resource, and in step D, service point assembly is registered analytic unit by service point and registered to service resource allocation Management Unit, reaches the setting described in D.
In the present embodiment, step C is subdivided into following content, considers that a plurality of clients put assembly and a plurality of service point assembly in the Internet, and the distance that service point assembly and client have put between assembly is arbitrarily to issue a request to the required time of acceptance response.Each some p in P represents a service point assembly, and can provide several services under the restriction of a limited capacity p.w.Each some o in O represents that a client puts assembly, can need several different services, and each service is had to some requirements.Allow the C be the set Class of COS, so every kind of service has it to provide a c.P to belong to P, so p can belong to the service of some type, and p ∈ c
1.P with p ∈ c
2.P represent that p can provide c
1and c
2two kinds of services.The demand of each some o can be expressed as (c
i, w
i) { (class, capacity) }, need c
ithe service w of type
iindividual.The target that this Internet service distributes is to guarantee that all demands are all satisfied as far as possible, allows on this basis overall distribution cost (right " distance service time " of point after distributing) minimum.One group of client that our model comprises in D puts assembly O and one group of service point assembly P, also has the set C of one group of COS simultaneously.Without loss of generality, we suppose that client puts assembly ∈ O and has a kind of demand for services o.c ∈ C to represent COS and o.w points out the quantity of the service o.c of needs.Many demands for services that we can come client of modeling to order like this, split into a plurality of clients that only have a kind of demand for services by the client of demand for services more than.
Need the o ∈ O of polytype service to change into the o of a kind of type of service of a plurality of needs, i.e. O={o each
1c
1, o
1c
2, o
2c
1, o
2c
3, and removing repetition, we have only selected subset, i.e. { a p of P
2, p
3, p
4p wherein
2.w=30, p
3.w=15, p
4.w=100.This circulation figure is an O, the triple directed graphs between P * C and P, and be called for starting point and terminal with particular point s and t() expand, each line has two variablees to represent (between 2 " distance service time ", maximum service capacity).Especially, establish V=O * (P * C) * { s, t}.Here, we claim that the point in P * C is service class supplier (SCP).The form that each SCP point is named into pc represents that p provides the capacity of COS c.For example, p
3service c is provided
1and c
2, then we construct respectively a p
3c
1and p
3c
2.Allow E represent the set in circulation.Each directed edge e (v
i, v
j) ∈ E represents from v
ito v
jfluid ability (capacity), this fluid ability represents v
imay be from v
jthe volume of services obtaining.Therefore, limit e (v
i, v
j) there is a weight w (v
i, v
j) and a capacity cap (v
i, v
j), solution that it should be noted that us does not go the weight of calculating limit to avoid a large amount of distances to calculate, and the substitute is us and with NN, operates to obtain arest neighbors and reach stable allocation.The set of limit E comprises 4 parts:
(i) with limit e (s, o
i) connection s and each o
i∈ O, here w (s, o
i)=0, cap (s, o
i)=o
i.w
(ii) with limit e (o
i, p
jc
k), meet o
i.c=c
k, w (o
i, p
jc
k)=dist (o
i, p
j), cap (o
i, p
jc
k)=o
i.w;
(iii) with limit e (p
jc
k, p
j) connect each SCP point p
jc
kto the service provision point p corresponding with it
j, meet w (p
jc
k, p
j)=0, cap (p
jc
k, p
j)=p
j.w;
(iv) with limit e (p
j, t) connect each p
j∈ P, meets w (p
j, t)=0, cap (p
j, t)=p
j.w.
Consider that is carried out a circulation figure for assignment problem since then, allow η (s, o
i, p
jc
k, p
j, t) represent a process point o from s to t
i, p
jc
k, p
jcirculation path.We define f
ηequal the minimum circulation through this paths.This paths means that we are from p
jto o
idistribute cap
ηthe service c of quantity
k.
The present invention is not limited only to the protection range shown in above-described embodiment, and all invention thought based on the present embodiment, all in protection scope of the present invention.
Claims (1)
1. the global optimization method that internet service resource distributes, is characterized in that:
A., a plurality of clients are set and put assembly, service resource allocation Management Unit;
B. client puts assembly collection client and puts one or more information on services, and sends to service resource allocation Management Unit;
C. service resource allocation Management Unit Analysis Service information type is N, a plurality of clients is put to assembly and be divided into N kind, and described N is greater than 0 integer;
D. service resource allocation Management Unit is established N service point assembly;
E. service resource allocation Management Unit is put components request according to information on services Type Control service point component responds client;
Wherein, step C is subdivided into following content:
In the Internet, consider that a plurality of clients put assembly and a plurality of service point assembly, the distance that service point assembly and client put between assembly is arbitrarily to issue a request to the required time of acceptance response; Each some p in P represents a service point assembly, and under the restriction of a limited capacity p.w, provide several services: each the some o in O represents that a client puts assembly, need several different services, and each service is had to some requirements, allow the C be the set Class of COS, so every kind of service has it to provide a c.P to belong to P, so p belongs to the service of some type, and p ∈ c
1.P with p ∈ c
2.P represent that p provides c
1and c
2two kinds of services, the demand schedule of each some o is shown as (c
i, w
i) { (class, capacity) }, need c
ithe service w of type
iindividual; The target that this Internet service distributes is to guarantee that all demands are all satisfied as far as possible, allows on this basis overall distribution cost distribute right " distance service time " minimum of rear point; One group of client that model comprises in set D puts assembly O and one group of service point assembly P, also has the set C of one group of COS simultaneously, and described set D comprises that one group of client puts assembly O and one group of service point assembly P; Client puts assembly ∈ O has a kind of demand for services o.c ∈ C to represent COS and o.w points out the quantity of the service o.c of needs; Many demands for services of ordering by client of modeling, split into a plurality of clients that only have a kind of demand for services by the client of demand for services more than;
Need the o ∈ O of polytype service to change into the o of a kind of type of service of a plurality of needs, i.e. O={o each
1c
1, o
1c
2, o
2c
1, o
2c
3, and remove repetition, select subset, i.e. { a p of P
2, p
3, p
4; With circulation figure, represent an O, triple directed graphs between P * C and P, and expand with some s and t, described s, t are particular point, be called starting point and terminal, each line has two variablees to represent respectively: " distance service time " and maximum service capacity between 2; If V=O * (P * C) * { s, t}; Here, we claim that the point in P * C is service class supplier SCP; The form that each SCP point is named into pc represents that p provides the capacity of COS c; Allow E represent the set in circulation; Each directed edge e (v
i, v
j) ∈ E represents from v
ito v
jfluid ability, this fluid ability represents v
imay be from v
jthe volume of services obtaining; Limit e (v
i, v
j) there is a weight w (v
i, v
j) and a capacity cap (v
i, v
j), with NN, operating to obtain arest neighbors and reach stable allocation, the set of limit E comprises 4 parts:
(i) with limit e (s, o
i) connection s and each o
i∈ O, here w (s, o
i)=0, cap (s, o
i)=oi.w;
(ii) with limit e (o
i, p
jc
k), meet o
i.c=c
k, w (o
i, p
jc
k)=dist (o
i, p
j), cap (o
i, p
jc
k)=o
i.w;
(iii) with limit e (p
jc
k, p
j) connect each SCP point p
jc
kto the service provision point p corresponding with it
j, meet w (p
jc
k, p
j)=0, cap (p
jc
k, p
j)=p
j.w;
(iv) with limit e (p
j, t) connect each p
j∈ P, meets w (p
j, t)=0, cap (p
j, t)=p
j.w;
Allow η (s, o
i, p
jc
k, p
j, t) represent a process point o from s to t
i, p
jc
k, p
jcirculation path, definition f
ηequal the minimum circulation through circulation path, circulation path means that we are from p
jto o
idistribute cap
ηthe service c of quantity
k.
2. the global optimization method that internet service resource according to claim 1 distributes, is characterized in that: in described step C, service resource allocation Management Unit comprises that client puts log-on message analytic unit and service point component register information analysis assembly.
Priority Applications (1)
| Application Number | Priority Date | Filing Date | Title |
|---|---|---|---|
| CN201110113313.4A CN102185713B (en) | 2011-05-04 | 2011-05-04 | Global optimization method of internet service resource distribution |
Applications Claiming Priority (1)
| Application Number | Priority Date | Filing Date | Title |
|---|---|---|---|
| CN201110113313.4A CN102185713B (en) | 2011-05-04 | 2011-05-04 | Global optimization method of internet service resource distribution |
Publications (2)
| Publication Number | Publication Date |
|---|---|
| CN102185713A CN102185713A (en) | 2011-09-14 |
| CN102185713B true CN102185713B (en) | 2014-07-30 |
Family
ID=44571786
Family Applications (1)
| Application Number | Title | Priority Date | Filing Date |
|---|---|---|---|
| CN201110113313.4A Expired - Fee Related CN102185713B (en) | 2011-05-04 | 2011-05-04 | Global optimization method of internet service resource distribution |
Country Status (1)
| Country | Link |
|---|---|
| CN (1) | CN102185713B (en) |
Families Citing this family (3)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN102662764B (en) * | 2012-04-25 | 2015-07-29 | 梁宏斌 | A kind of dynamic cloud computational resource optimizing distribution method based on SMDP |
| CN103237072B (en) * | 2013-04-22 | 2015-09-16 | 上海交通大学 | A kind of data center services method for arranging based on user satisfaction perception |
| CN106506594B (en) * | 2016-09-30 | 2019-09-03 | 科大讯飞股份有限公司 | A kind of concurrent computation resource distribution method and device |
Family Cites Families (4)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN100484052C (en) * | 1999-07-09 | 2009-04-29 | 马利布网络有限公司 | TCP/IP packet-centric wireless communication system and method for distributing wireless bandwidth therein |
| CN101662504B (en) * | 2009-09-25 | 2012-07-04 | 中国电信股份有限公司 | Method and system for realizing point-to-point content distribution under wireless network environment |
| CN101969459B (en) * | 2009-09-30 | 2013-07-10 | 突触计算机系统（上海）有限公司 | Method and apparatus for controlling data block distribution |
| CN101827396B (en) * | 2010-04-29 | 2014-03-26 | 北京邮电大学 | Multi-net cooperative transmission resource distribution system in heterogeneous wireless environment and method |
-
2011
- 2011-05-04 CN CN201110113313.4A patent/CN102185713B/en not_active Expired - Fee Related
Also Published As
| Publication number | Publication date |
|---|---|
| CN102185713A (en) | 2011-09-14 |
Similar Documents
| Publication | Publication Date | Title |
|---|---|---|
| CN105635283A (en) | Organization and management and using method and system for cloud manufacturing service | |
| CN105049268A (en) | Distributed computing resource allocation system and task processing method | |
| CN104038540A (en) | Method and system for automatically selecting application proxy server | |
| CN103944769A (en) | RPC (Remote Procedure Call) protocol based cluster resource unified management system | |
| CN105912397A (en) | Resources management method and device | |
| CN110198339B (en) | QoE (quality of experience) perception-based edge computing task scheduling method | |
| Amokrane et al. | Greenslater: On satisfying green SLAs in distributed clouds | |
| CN104281496A (en) | Virtual resource distribution method and virtual resource distribution device | |
| CN103237037A (en) | Media format conversion method and system based on cloud computing architecture | |
| Almutairi et al. | Delay-optimal task offloading for UAV-enabled edge-cloud computing systems | |
| CN103731372A (en) | Resource supply method for service supplier under hybrid cloud environment | |
| CN105515977B (en) | Method, device and system for acquiring transmission path in network | |
| CN104579761A (en) | Automatic nosql cluster configuration system and method based on cloud computing | |
| CN103812789A (en) | Cloud service resource automatic allocating method and system | |
| CN109656685A (en) | Container resource regulating method and system, server and computer readable storage medium | |
| CN103997523A (en) | Smart city service system based on cloud services and implementation method thereof | |
| CN107395731A (en) | A kind of adjusting method and device of the container cluster based on service orchestration | |
| CN103455633A (en) | Method of distributed analysis for massive network detailed invoice data | |
| CN102185713B (en) | Global optimization method of internet service resource distribution | |
| CN115421930B (en) | Task processing method, system, device, equipment and computer readable storage medium | |
| CN110149377A (en) | A kind of video service node resource allocation methods, system, device and storage medium | |
| Amokrane et al. | On satisfying green SLAs in distributed clouds | |
| CN104537045A (en) | Service distribution method and device based on distributive system | |
| Neglia et al. | Geographical load balancing across green datacenters: A mean field analysis | |
| Yao et al. | COMIC: Cost optimization for internet content multihoming |
Legal Events
| Date | Code | Title | Description |
|---|---|---|---|
| C06 | Publication | ||
| PB01 | Publication | ||
| C10 | Entry into substantive examination | ||
| SE01 | Entry into force of request for substantive examination | ||
| C14 | Grant of patent or utility model | ||
| GR01 | Patent grant | ||
| CF01 | Termination of patent right due to non-payment of annual fee | ||
| CF01 | Termination of patent right due to non-payment of annual fee |
Granted publication date: 20140730 |