[go: up one dir, main page]
More Web Proxy on the site http://driver.im/

CN106487923A - Configurable mobile terminal cooperation caching method - Google Patents

Configurable mobile terminal cooperation caching method Download PDF

Info

Publication number
CN106487923A
CN106487923A CN201611025256.3A CN201611025256A CN106487923A CN 106487923 A CN106487923 A CN 106487923A CN 201611025256 A CN201611025256 A CN 201611025256A CN 106487923 A CN106487923 A CN 106487923A
Authority
CN
China
Prior art keywords
node
file
utility
cache
default file
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
Application number
CN201611025256.3A
Other languages
Chinese (zh)
Other versions
CN106487923B (en
Inventor
徐恪
葛志诚
杨戬
沈蒙
Current Assignee (The listed assignees may be inaccurate. Google has not performed a legal analysis and makes no representation or warranty as to the accuracy of the list.)
Tsinghua University
Original Assignee
Tsinghua University
Priority date (The priority date 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 date listed.)
Filing date
Publication date
Application filed by Tsinghua University filed Critical Tsinghua University
Priority to CN201611025256.3A priority Critical patent/CN106487923B/en
Publication of CN106487923A publication Critical patent/CN106487923A/en
Application granted granted Critical
Publication of CN106487923B publication Critical patent/CN106487923B/en
Active legal-status Critical Current
Anticipated expiration legal-status Critical

Links

Classifications

    • HELECTRICITY
    • H04ELECTRIC COMMUNICATION TECHNIQUE
    • H04LTRANSMISSION OF DIGITAL INFORMATION, e.g. TELEGRAPHIC COMMUNICATION
    • H04L67/00Network arrangements or protocols for supporting network services or applications
    • H04L67/50Network services
    • H04L67/56Provisioning of proxy services
    • H04L67/568Storing data temporarily at an intermediate stage, e.g. caching

Landscapes

  • Engineering & Computer Science (AREA)
  • Computer Networks & Wireless Communication (AREA)
  • Signal Processing (AREA)
  • Mobile Radio Communication Systems (AREA)

Abstract

The present invention proposes a kind of configurable mobile terminal cooperation caching method, comprises the following steps:S1:According to the statistical information of the base station in Preset Time, determine the operational factor of base station system;S2:Base station receives the request to default file for the node, is node distribution file request source node, and calculates the overall value of utility of default file;S3:In overall value of utility according to default file and caching, the overall value of utility of alternative document enters row cache and replaces;S4:Often through prefixed time interval, update the overall value of utility of base station system state and each nodal cache file.The present invention can make mobile terminal from content needed for network edge acquisition as far as possible, it is to avoid access network core, reduce circuit congestion, be obviously improved efficiency, thus significantly increasing the utilization ratio of caching, lifting Consumer's Experience, having wide applicability and motility.

Description

Configurable mobile terminal cooperation caching method
Technical field
The present invention relates to mobile content distribution network technical field, cooperate particularly to a kind of configurable mobile terminal slow Deposit method.
Background technology
In conventional internet, the network bandwidth is far from enough for huge user's visit capacity, network point distribution in addition So that user is often required to experience longer time delay, Consumer's Experience is difficult to be lifted inequality.
Content of the invention
It is contemplated that at least solving one of above-mentioned technical problem.
For this reason, it is an object of the invention to proposing a kind of configurable mobile terminal cooperation caching method, the method can Make mobile terminal from content needed for network edge acquisition, it is to avoid access network core, reduce circuit congestion, be obviously improved effect as far as possible Rate, thus significantly increasing the utilization ratio of caching, lifting Consumer's Experience, having wide applicability and motility.
To achieve these goals, embodiment of the invention discloses that a kind of configurable mobile terminal cooperation caching side Method, comprises the following steps:S1:According to the statistical information of the base station in Preset Time, determine the operational factor of base station system;S2: Described base station receives the request to default file for the node, is described node distribution file request source node, and calculates described pre- If the overall value of utility of file;S3:The overall effectiveness of alternative document in overall value of utility according to described default file and caching It is worth and replace into row cache;S4:Often through prefixed time interval, update base station system state and the overall situation of each nodal cache file Value of utility.
In addition, configurable mobile terminal cooperation caching method according to the above embodiment of the present invention can also have as follows Additional technical characteristic:
In some instances, described S1, further includes:S11:Described base station statistical system interior nodes in Preset Time Quantity, nodal cache situation and requested quantity of documents;S12:Obtain the maximum uploading bandwidth of all nodes and maximum lower carrier band Wide;S13:By parameter preset, determine time delay and Consumer's Experience corresponding relation function;S14:Configure each node and obtain resource Both candidate nodes set;S15:According to the ranking information of each node file request, determine that described node please in subsequent time period Seek the probability of default file;S16:Ask the probability of default file according to described node in subsequent time period, choose user's body Test server load weight.
In some instances, in described S13, described time delay with Consumer's Experience corresponding relation function is:
Wherein, t is time delay variable, and g (t) is Consumer's Experience, and t is the time downloading unit-sized file, u and a is described Parameter preset.
In some instances, described S2, further includes:S21:Determine that described node obtains coming of described default file Source;S22:Judge whether described node residue shared buffer memory space can accommodate described default file, if it is, directly caching Described default file, and change nodal cache matrix relevant position be xin=1, and execution step S32, otherwise enter row cache and replace Change, and execution step S23;S23:Calculate the overall value of utility of default file described in described nodal cache.
In some instances, described S3, further includes:S31:By in the overall value of utility of described default file and caching The overall value of utility of alternative document is compared, if the overall value of utility of alternative document is all higher than the overall situation of described default file Value of utility, then do not cache new demand file, otherwise, enters row cache and replaces;S32:In described prefixed time interval, if base station Receive new file request, then return and execute described step S21, otherwise, execute described step S4.
In some instances, described S21, further includes:S211:By yijMatrix obtains described node j and can obtain The source node set A of described default file njnIf node j can obtain default file n with from node i, and node i must is fulfilled for Pre-conditioned, wherein, described pre-conditioned inclusion:Node i is the source node of node j, and node i has cached default file n; S212:There is provided file n if there is no node for node i, then node i obtains described presetting by base station from external core network File n, wherein, obtains the download bandwidth Bw of default file ninMaximum download bandwidth for node iS213:If deposited Default file n can be provided in node for node i, then node i obtains described default file n from the maximum node of uploading bandwidth, Wherein, obtain the download bandwidth Bw of default file ninFor node i download bandwidthWith the node providing default file n Uploading bandwidthMinima.
In some instances, described S23, further includes:S231:After obtaining node i cache file n, all uncached The average user experience of the node visit file n of file nAnd before node i cache file n, other all uncached files The average user experience User of the node visit file n of nin, and according to describedWith described UserinCalculate user utility Value gain delta Userin;S232:After obtaining node i cache file n, the node of all uncached file n obtains literary composition from internal node Part n accounts for the proportion of total requestAnd before point i cache file n, the node of all uncached file n obtains from internal node File n accounts for the proportion Server of total requestin, and according to describedWith described ServerinCalculation server effectiveness gain ΔServerin;S233:According to described load weight w obtaining in step S16, by formula Utilityin=Δ Userin·w +ΔServerin(1-w), calculate the overall value of utility Utility of described nodal cache default filein.
In some instances, described S231, further includes:Calculate average user experience User according to equation belowin
Wherein, B is base station sets unit file size, RjnIt is accessed for probability, Bw for default file njn, for default literary composition The acquisition bandwidth of part n;
Described user utility value gain delta User is obtained according to above-mentioned formula:
Described S232, further includes in some instances;It is calculated described server effectiveness by equation below to increase Beneficial Serverin
Described server effectiveness gain delta Server is calculated by equation belowin
Wherein, RjnIt is accessed for probability for default file n, access labelling innerinRepresent node i demand file whether from Internal node obtains, if obtained from internal node, innerin=1, otherwise, innerin=0.
In some instances, in described S31, described enter row cache replace, specifically include:If abandoning overall value of utility The one or more files less than the overall value of utility of default file, remaining cache space can accommodate described default file, then delay Deposit described default file;If lose multiple files that overall value of utility is less than the overall value of utility of described default file, and remaining Spatial cache still can not accommodate described default file, then do not cache described default file.
Configurable mobile terminal cooperation caching method according to embodiments of the present invention, by the configuration to weight parameter, Optimum results can be made to consider increase Consumer's Experience and reduce two targets of server load.In actual applications, each Base station all can determine respective goal orientation according to current network condition, so that algorithm has wider practicality.Pass through Configuration Consumer's Experience and load of base station weight parameter, make system meet Consumer's Experience good on the premise of, reduce base as far as possible Outside access of standing loads, and making network edge, thus reducing core network congestion, being obviously improved efficiency.This method can be transferred In mobile terminal for exploiting natural resources, have network edge preferably, the characteristic of the flexibility of configuration, using in terminal Application software, the operation of this method can complete in base station, has stronger economy.In addition, by each nodal cache Rational management, can significantly increase the utilization ratio of caching, lift Consumer's Experience.
The additional aspect of the present invention and advantage will be set forth in part in the description, and partly will become from the following description Obtain substantially, or recognized by the practice of the present invention.
Brief description
The above-mentioned and/or additional aspect of the present invention and advantage will become from reference to the description to embodiment for the accompanying drawings below Substantially and easy to understand, wherein:
Fig. 1 is the configuration diagram of mobile content distribution network CDN in the embodiment of the present invention;
Fig. 2 is the configurable mobile terminal cooperation caching method flow chart of the embodiment of the present invention;
Fig. 3 is the detail flowchart of the configurable mobile terminal cooperation caching method of another embodiment of the present invention;With And
Fig. 4 is that the configurable mobile terminal cooperation caching method cooperation caching of one specific embodiment of the present invention is illustrated Figure.
Specific embodiment
Embodiments of the invention are described below in detail, the example of described embodiment is shown in the drawings, wherein from start to finish The element that same or similar label represents same or similar element or has same or like function.Below with reference to attached The embodiment of figure description is exemplary, is only used for explaining the present invention, and is not considered as limiting the invention.
In describing the invention it is to be understood that term " " center ", " longitudinal ", " horizontal ", " on ", D score, The orientation of instruction such as "front", "rear", "left", "right", " vertical ", " level ", " top ", " bottom ", " interior ", " outward " or position relationship are Based on orientation shown in the drawings or position relationship, it is for only for ease of the description present invention and simplifies description, rather than instruction or dark Show the device of indication or element must have specific orientation, with specific azimuth configuration and operation, therefore it is not intended that right The restriction of the present invention.Additionally, term " first ", " second " are only used for describing purpose, and it is not intended that instruction or hint are relative Importance.
In describing the invention, it should be noted that unless otherwise clearly defined and limited, term " installation ", " phase Even ", " connection " should be interpreted broadly, for example, it may be being fixedly connected or being detachably connected, or is integrally connected;Can To be to be mechanically connected or electrical connection;Can be to be joined directly together it is also possible to be indirectly connected to by intermediary, Ke Yishi The connection of two element internals.For the ordinary skill in the art, above-mentioned term can be understood at this with concrete condition Concrete meaning in invention.
Below in conjunction with Description of Drawings configurable mobile terminal cooperation caching method according to embodiments of the present invention.
The applied environment of the configurable mobile terminal cooperation caching method of the embodiment of the present invention is service mobile terminal Content distributing network (Content Delivery Network, CDN), in the range of each base station, has numerous mobile terminals, Therefore in an embodiment of the present invention, base station act as the role of a centralization node, and a range of institute about There is mobile terminal, all can be used as node.Wherein, in conjunction with shown in Fig. 1, CDN is that one kind has high-performance, extensibility and low one-tenth This new network content service system.While improving the quality of content delivery service, CDN can save backbone network band Width, significantly improves whole efficiency and the Consumer's Experience of network.
Due to the fast development of mobile network, the global optimization of the CDN of service mobile terminal is particularly important, its In, buffer scheduling is a particularly important link.And under the basis of CDN, by configuring, can make mobile whole as far as possible End content needed for network edge obtains, it is to avoid access network core, reduce circuit congestion, be obviously improved efficiency.The present invention is just It is based on from the aspect of this, achieve this target from the angle of buffer scheduling.The present invention is by the conjunction to each nodal cache Reason scheduling, can significantly increase the utilization ratio of caching, lift Consumer's Experience.
Based on this, Fig. 2 is the flow process of configurable mobile terminal cooperation caching method according to an embodiment of the invention Figure.Fig. 3 is the detail flowchart of configurable mobile terminal cooperation caching method in accordance with another embodiment of the present invention.As figure Shown in 2, and combine Fig. 3, the method comprises the following steps:
Step S1:According to the statistical information of the base station in Preset Time, determine the operational factor of base station system.In other words, I.e. base station system parameter determination process.Base station, according to the statistical information in a period of time (Preset Time), determines the operation of system Parameter.
Specifically, step S1 further includes:
Step S11:Base station statistical system interior nodes quantity, nodal cache situation and requested number of files in Preset Time Amount.Specifically, base station can obtain system interior nodes number M, and total number of files N in system, if volume S of each file1,S2… SN, the shared buffer memory capacity B of each node1,B2…BM.Additionally, base station understands each which file of node current cache.Base station Safeguard a nodal cache matrix xin, that is, as node i cache file n, xin=1;Otherwise, xin=0.
Step S12:Obtain the maximum uploading bandwidth of all nodes and maximum download bandwidth.Specifically, base station is passed through eventually End application obtains upload and the download capabilities of node.By statistics, base station understands maximum uploading bandwidth and the maximum of all nodes Download bandwidth.Base station is by safeguarding uploading bandwidth vectorWith download bandwidth vectorAnd preserve.
Step S13:By parameter preset, determine time delay and Consumer's Experience corresponding relation function.
Wherein, above-mentioned time delay and Consumer's Experience corresponding relation function are:
Wherein, t is time delay variable, and g (t) is Consumer's Experience, and t is the time downloading unit-sized file, u and a is this letter The parameter of number, i.e. parameter preset.Herein, base station sets unit file size B.U and a is that the parameter of this function (presets ginseng Number), base station can be extrapolated by the overall download delay profiles of active user, specific as follows:Base station determines that active user is excellent Download bandwidth BwgoodWith difference download bandwidth Bwbad, and then the limit of time delay b and bad the limit of time delay can have been tried to achieve by t=B/Bw c.I.e. b=B/Bwgood, c=B/Bwbad.Parameter a be can determine that by a=(b+c)/2.Base station determines the limit of time delay Consumer's Experience G, substitutes into t=b, and g (t)=G can obtain u, that is,:
Step S14:Configure the both candidate nodes set that each node obtains resource.Specifically, base station is by safeguarding yijSquare Battle array determines that node j can obtain the source node set of file.That is, if node j can obtain file, y with from node iij=1;No Then, yij=0.
Step S15:According to the ranking information of each node file request, determine that node is asked in subsequent time period default The probability of file.Specifically, base station individually carries out file request statistics, according to the history file of this node for each node Request, the file temperature that can be directed to a node carries out ranking.Base station maintenance file temperature ranking matrix RankjnPreserve this letter Breath, if Rankjn=k represents for node j, and file n temperature ranking is k.According to file temperature ranking Rankjn, can be according to assistant Husband's distribution Zipf (q, α) obtains this document and is accessed for probability Rin.Specific as follows:
Herein, base station needs to specify parameter q of assistant husband's distribution, α.In some instances, q=0, α=1.2 are for example taken.
Step S16:Ask the probability of default file according to node in subsequent time period, choose Consumer's Experience server Load weight w.
Step S2:The request to default file n for the base station receiving node j, and calculate the overall value of utility of default file.
Specifically, step S2 further includes:
Step S21:Determine that node obtains the source of default file.In other words, that is, base station determines that node obtains in advance from where If file.
Specifically, step S21 further includes:
Step S211:By yijMatrix obtains the source node set A that node j can obtain default file njnIf, node J can with from node i obtain default file n, then node i must be fulfilled for pre-conditioned.More specifically, pre-conditioned inclusion:Section Point i is the source node of node j, i.e. yij=1, and node i to have cached default file n be xin=1.
Step S212:There is provided file n, i.e. A if there is no node for node ijn=, then node i passes through base station from outside Core network obtains default file n, wherein, obtains the download bandwidth Bw of default file ninMaximum download bandwidth for node i
Step S213:Default file n can be provided if there is node for node i, then node i is from uploading bandwidth maximum Node obtains default file n, wherein, obtains the download bandwidth Bw of default file ninFor node i download bandwidthAnd offer The uploading bandwidth of the node of default file nMinima, that is,
Step S22:Whether decision node residue shared buffer memory space can accommodate default file, if it is, directly delaying Deposit this default file, and to change the relevant position of nodal cache matrix be xin=1, and execution step S32, otherwise (i.e. remaining empty Between not enough) enter row cache and replace, and execution step S23.
Step S23:Calculate node caches the overall value of utility Utility of default filein.
Specifically, step S23 further includes:
Step S231:After obtaining node i cache file n, the average use of the node visit file n of all uncached file n Family is experiencedAnd before node i cache file n, the average user body of the node visit file n of other all uncached file n Test Userin, and according toAnd UserinCalculate user utility value gain delta Userin.In other words, that is, calculate user utility value Gain delta Userin.User utility value gain delta UserinAfter being defined as node i cache file n, the section of all uncached file n Point accesses the average user experience of file nBefore deducting node i cache file n, the node of other all uncached file n Access the average user experience User of file nin.
More specifically, step S231 further includes:For other nodes j in addition to i, it is determined according to step S21 Obtain the source of file n and obtain bandwidth B wjn;For i-node itself, before cache file n, true using step S21 method Determine file n source, after cache file n, it obtains the bandwidth of file n and is considered as infinity, i.e. Bwin=inf.Based on this, according to such as Lower formula calculates average user experience Userin
Wherein, B is base station sets unit file size, RjnIt is accessed for probability, Bw for default file njn, for default literary composition The acquisition bandwidth of part n.Parameter B, RjnObtained by step S14, step S15.
And then, user utility value gain delta User is obtained according to above-mentioned formula:
Step S232:After obtaining node i cache file n, the node of all uncached file n obtains file from internal node N accounts for the proportion of total requestAnd before point i cache file n, the node of all uncached file n obtains literary composition from internal node Part n accounts for the proportion Server of total requestin, and according toAnd ServerinCalculation server effectiveness gain delta Serverin. In other words, i.e. calculation server effectiveness gain delta Serverin.Server effectiveness gain delta ServerinIt is defined as:Node i caches After file n, the node of all uncached file n obtains file n from internal node and (obtains from external core network with respect to node i Take file) account for total proportion askedBefore deducting node i cache file n, the node of all uncached file n is from inside Node obtains the proportion Server that file n accounts for total requestin.
Specifically, step S232 further includes:Similar with step S231, base station only need to count certain nodal cache certain Before and after file, system interior nodes obtain the proportion of file from internal node.Note accesses labelling innerinRepresent node i request Whether file obtains from internal node.If obtaining from internal node, innerin=1, otherwise, innerin=0.Based on this, can Server effectiveness gain Server is calculated by equation belowin
And then, server effectiveness gain delta Server is calculated by equation belowin
Wherein, RjnIt is accessed for probability, parameter R for default file njnDetermined by step S15.
Step S233:According to load weight w obtaining in step S16, by formula Utilityin=Δ Userin·w+ ΔServerin(1-w), calculate node caches the overall value of utility Utility of default filein.
S3:In overall value of utility according to default file and caching, the overall value of utility of alternative document enters row cache and replaces.
Specifically, step S3 further includes:
Step S31:The overall value of utility of the overall value of utility of default file and alternative document in caching is compared, such as The overall value of utility of fruit alternative document is all higher than the overall value of utility of default file, then do not cache new demand file and (do not cache Default file), otherwise, enter row cache and replace.
Specifically, in step S31, enter row cache and replace, specifically include:If abandoning overall value of utility to compare default file The little one or more files of overall value of utility, remaining cache space can accommodate default file, then cache default file;If Lose overall value of utility be less than default file overall value of utility multiple files, and remaining cache space still can not accommodate default File, then do not cache default file.
Step S32:In prefixed time interval Δ t, if base station receives new file request, return execution step S21, otherwise (reaches prefixed time interval Δ t), execution step S4.
Step S4:Base station periodically updates.I.e. often through prefixed time interval Δ t, update base station system state and each The overall value of utility of nodal cache file.
Specifically, step S4 further includes:
Step S41:Relevant parameter is redefined to step S16 according to step S11.
Step S42:Update the overall value of utility of each nodal cache file according to step S23, and be back to step S2.
To sum up, the configurable mobile terminal cooperation caching method of the embodiment of the present invention be by existing by numerous sections Increase by one layer of new network architecture, i.e. CDN on the basis of the Internet that point server is constituted.Internet resources are carried out more by CDN The configuration optimizing, reduces " distance " of user and Web content needed for it as possible, makes user can obtain required content nearby, Substantially reduce the waiting time of user.The present invention is intended to avoid in network to be number using the design of content distributing network as far as possible According to speed and the link that has undesirable effect of stability of transmission, make content transmission obtain faster, more stable.On the basis of CDN, The content transmission of network can be disposed from overall, so that data transmission efficiency has great optimization space.
In other words, the cardinal principle of the configurable mobile terminal cooperation caching method of the above embodiment of the present invention can be summarized For:On the basis of the mobile CDN model being pre-designed, the experience that user obtains content is maximized using innovation algorithm Weighted mean with base station outside access ratio.From overall angle, many assessments are carried out to each cache decision, examines Consider many details of the load of impact Consumer's Experience and base station outside access core network.For base station, base station wishes to use Family request meets local as much as possible, at utmost to reduce core network load, makes accentuated edges network function;To user For, user wishes to obtain resource with optimum experience.This method, according to the real-time status of network, considers base station outside access Amount and the experience of user's acquisition resource.In the cache decision finally integrated out, with the compromise of Consumer's Experience and load of base station as core The utility function of the heart, using utility function, gives a value of utility for a certain resource file of each nodal cache, is delayed accordingly Deposit replacement.Thus considering two targets, optimize the whole efficiency of network.Additionally, the present invention have wide applicability and Motility, tends to different targets by the control of parameters some in algorithm can be made with result
For the ease of more fully understanding the present invention, below in conjunction with accompanying drawing, with specific embodiment, the present invention be can configure Mobile terminal cooperation caching method be specifically described in detail.
In conjunction with shown in Fig. 4, in the present embodiment, the concrete application flow process of the method is as follows:
First, the parameter such as base station statistical system number of nodes, nodal cache situation, requested file amount.In the present embodiment In, in system as shown in Figure 4, total M=7 node, N=7 file.If the shared buffer memory capacity B of each nodemIt is 1000Mb, size S of each filenIt is 333Mb.Node 4 has cached file 4, file 5 and file 7, then x44=x45=x47 =1.
Upload and download bandwidth has been marked in Fig. 4 interior joint legend.For node 4,
Then, base station determines time delay-Consumer's Experience corresponding relation function.In system shown in Fig. 4, base station determines unit File size B=1000Kb, excellent download bandwidth Bwgood=500kbps, difference download bandwidth Bwbad=100kbps.Accordingly, can ask Obtain b=2s, c=10s, therefore a=6s.Take G=0.943, u ≈ 0.7 can be tried to achieve.Therefore time delay and Consumer's Experience in system shown in Figure 4 Relation be:
Afterwards, base station configures the both candidate nodes set that each node obtains resource, and except node 4, each node can Obtain file from its adjacent node;Node 4 can obtain file with from node 1,2,6,7.Then for node 4, y14=y24=y64= y74=1;For node 3, y13=y43=y63=1, other nodes are similar to.
Base station needs to specify parameter q and the α of assistant husband's distribution.In the present embodiment, take q=0, α=1.2, if file 1 for The temperature ranking of different nodes is a vectorial Ranki1, Ranki1=[5,7,6,5,3,4,2].Then its access frequency vector Ranki1 =[0.145,0.097,0.116,0.145,0.268,0.189,0.435].
In specified Consumer's Experience server load weight w.Take a compromise weighted value, such as w=0.5.
After base station receives the request of certain node, base station determines that this node obtains this document from where.
For example, if node 3 demand file 2, base station is passed through vector and is understood that node 3 can obtain file with from node 1,4,6, But only node 1 and node 6 have cached file 2, then node 3 from node 1 and node 6 may only obtain file 2, i.e. A32=1, 6}.But the uploading bandwidth (300kbps) due to node 1 is more than the uploading bandwidth (100kbps) of node 6, therefore node 3 from node 1 Obtain file 2.
Before node 4 demand file 1, the situation that system interior nodes obtain file 1 is:Node 1 obtains from outside, and speed is 600kbps;Node 2 from node 5 obtains, speed 200kbps;Node 3 obtains from outside, speed 400kbps;Node 4 from node 7 Obtain, speed 100kbps;Node 6 from node 7 obtains, speed 100kbps.Using the parameter value in step S14 and step S15, Substituting into average user experience computing formula can be in the hope of User41=0.475518033849.In the same manner, in node 4 cache file 1 Afterwards, in system, the situation of each node acquisition file 1 is:Node 1 from node 4 obtains, speed 200kbps;Node 2 from node 5 obtains , speed 200kbps;Node 3 from node 4 obtains, speed 200kbps;Node 4 obtains from itself, and speed is infinitely great;Node 6 From node 7 obtains, speed 200kbps.Now, calculate average user experience.Try to achieveTherefore ask Obtain Δ User=0.259018718371.Additionally, trying to achieveServer41=0.622569222537, then Δ Serverin=0.377430777463.According to parameters obtained, the overall value of utility of node 4 cache file 1 should be Utility41 =0.306383542008, the overall value of utility of the cache file of node 4 is respectively Utility44=0.1, Utility45= 0.2, Utility47=0.3.According to the example in step S233, Utility41=0.306383542008.Because of Utility44? Little, therefore node 4 should abandon file 4, cache file 1.
To sum up, the method for the embodiment of the present invention, with respect to traditional buffer scheduling strategy, has better think of of overall importance Examine, the center of optimization is placed on target the most directly perceived and basic, that is, on lifting Consumer's Experience, can more efficiently improve data and pass Defeated efficiency.Using multiple mathematical tools, more proper simulation is carried out to actual environment in modeling process it is ensured that algorithm High feasibility and practicality.
In addition, when certain nodal cache space is full, when now receiving the request to the file being not present in spatial cache, Which then need to be weighed using this algorithm, to decide whether to cache this new file and should be replaced the literary composition in spatial cache Part.
Further, the present invention carries out cache optimization from overall angle, by caching, to certain, the overall situation receipts that certain file brings Beneficial angle configuring the spatial cache of each node, can lift Consumer's Experience from more fully angle and reduce server and bear Carry.And have the characteristics that to tend to multiple targets, by the setting to weight parameter in algorithm, algorithm can be made to tend to be lifted Consumer's Experience or mitigation two targets of server load.In the presence of here strategy, whole network can more neatly obtain The optimization of overall efficiency.
Configurable mobile terminal cooperation caching method according to embodiments of the present invention, by the configuration to weight parameter, Optimum results can be made to consider increase Consumer's Experience and reduce two targets of server load.In actual applications, each Base station all can determine respective goal orientation according to current network condition, so that algorithm has wider practicality.Pass through Configuration Consumer's Experience and load of base station weight parameter, make system meet Consumer's Experience good on the premise of, reduce base as far as possible Outside access of standing loads, and making network edge, thus reducing core network congestion, being obviously improved efficiency.This method can be transferred In mobile terminal for exploiting natural resources, have network edge preferably, the characteristic of the flexibility of configuration, using in terminal Application software, the operation of this method can complete in base station, has stronger economy.In addition, by each nodal cache Rational management, can significantly increase the utilization ratio of caching, lift Consumer's Experience.
In the description of this specification, reference term " embodiment ", " some embodiments ", " example ", " specifically show The description of example " or " some examples " etc. means specific features, structure, material or the spy describing with reference to this embodiment or example Point is contained at least one embodiment or the example of the present invention.In this manual, to the schematic representation of above-mentioned term not Necessarily refer to identical embodiment or example.And, the specific features of description, structure, material or feature can be any One or more embodiments or example in combine in an appropriate manner.
Although an embodiment of the present invention has been shown and described, it will be understood by those skilled in the art that:Not Multiple changes, modification, replacement and modification can be carried out to these embodiments in the case of the principle of the disengaging present invention and objective, this The scope of invention by claim and its is equal to limit.

Claims (10)

1. a kind of configurable mobile terminal cooperation caching method is it is characterised in that comprise the following steps:
S1:According to the statistical information of the base station in Preset Time, determine the operational factor of base station system;
S2:Described base station receives the request to default file for the node, is described node distribution file request source node, and calculates The overall value of utility of described default file;
S3:In overall value of utility according to described default file and caching, the overall value of utility of alternative document enters row cache and replaces;
S4:Often through prefixed time interval, update the overall value of utility of base station system state and each nodal cache file.
2. configurable mobile terminal cooperation caching method according to claim 1, it is characterised in that described S1, enters one Step includes:
S11:Described base station statistical system interior nodes quantity, nodal cache situation and requested quantity of documents in Preset Time;
S12:Obtain the maximum uploading bandwidth of all nodes and maximum download bandwidth;
S13:By parameter preset, determine time delay and Consumer's Experience corresponding relation function;
S14:Configure the both candidate nodes set that each node obtains resource;
S15:According to the ranking information of each node file request, determine that described node asks default file in subsequent time period Probability;
S16:Ask the probability of default file according to described node in subsequent time period, choose the load of Consumer's Experience server Weight.
3. configurable mobile terminal cooperation caching method according to claim 2 is it is characterised in that in described S13, Described time delay with Consumer's Experience corresponding relation function is:
g ( t ) = 1 1 + e u ( t - a ) ,
Wherein, t is time delay variable, and g (t) is Consumer's Experience, and t is the time downloading unit-sized file, u and a is described default Parameter.
4. configurable mobile terminal cooperation caching method according to claim 2, it is characterised in that described S2, enters one Step includes:
S21:Determine that described node obtains the source of described default file;
S22:Judge whether described node residue shared buffer memory space can accommodate described default file, if it is, directly delaying Deposit described default file, and to change the relevant position of nodal cache matrix be xin=1, and execution step S32, otherwise enter row cache Replace, and execution step S23;
S23:Calculate the overall value of utility of default file described in described nodal cache.
5. configurable mobile terminal cooperation caching method according to claim 4, it is characterised in that described S3, enters one Step includes:
S31:The overall value of utility of the overall value of utility of described default file and alternative document in caching is compared, if its The overall value of utility of his file is all higher than the overall value of utility of described default file, then do not cache new demand file, otherwise, carries out Caching is replaced;
S32:In described prefixed time interval, if base station receives new file request, return and execute described step S21, Otherwise, execute described step S4.
6. configurable mobile terminal cooperation caching method according to claim 4, it is characterised in that described S21, enters one Step includes:
S211:By yijMatrix obtains the source node set A that described node j can obtain described default file njnIf, node j Can with from node i obtain default file n, then node i must be fulfilled for pre-conditioned, wherein, described pre-conditioned inclusion:Node i It is the source node of node j, and node i has cached default file n;
S212:There is provided file n if there is no node for node i, then node i passes through base station from described in external core network acquisition Default file n, wherein, obtains the download bandwidth Bw of default file ninMaximum download bandwidth for node i
S213:Default file n can be provided if there is node for node i, then node i obtains from the maximum node of uploading bandwidth Described default file n, wherein, obtains the download bandwidth Bw of default file ninFor node i download bandwidthDefault with providing The uploading bandwidth of the node of file nMinima.
7. configurable mobile terminal cooperation caching method according to claim 4, it is characterised in that described S23, enters one Step includes:
S231:After obtaining node i cache file n, the average user experience of the node visit file n of all uncached file nAnd before node i cache file n, the average user experience of the node visit file n of other all uncached file n Userin, and according to describedWith described UserinCalculate user utility value gain delta Userin
S232:After obtaining node i cache file n, the node of all uncached file n obtains file n from internal node and accounts for total asking The proportion askedAnd before point i cache file n, the node of all uncached file n obtains file n from internal node and accounts for always The proportion Server of requestin, and according to describedWith described ServerinCalculation server effectiveness gain delta Serverin
S233:According to described load weight w obtaining in step S16, by formula Utilityin=Δ Userin·w+Δ Serverin(1-w), calculate the overall value of utility Utility of described nodal cache default filein.
8. configurable mobile terminal cooperation caching method according to claim 7, it is characterised in that described S231, enters One step includes:
Calculate average user experience User according to equation belowin
User i n = Σ j ∈ { j , x j n = 0 } R j n / ( 1 + e u ( B Bw j n - a ) ) Σ j ∈ { j , x j n = 0 } R j n ,
Wherein, B is base station sets unit file size, RjnIt is accessed for probability, Bw for default file njn, it is default file n Obtain bandwidth;
Described user utility value gain delta User is obtained according to above-mentioned formula:
9. configurable mobile terminal cooperation caching method according to claim 7, it is characterised in that described S232, enters One step includes;
Described server effectiveness gain Server is calculated by equation belowin
Server i n = Σ j ∈ { j , x j n = 0 } R j n · inner j n Σ j ∈ { j , x j n = 0 } R j n ,
Described server effectiveness gain delta Server is calculated by equation belowin
Wherein, RjnIt is accessed for probability for default file n, access labelling innerinRepresent node i demand file whether from inside Node obtains, if obtained from internal node, innerin=1, otherwise, innerin=0.
10. configurable mobile terminal cooperation caching method according to claim 5 is it is characterised in that in described S31 In, described enter row cache replace, specifically include:
If abandoning the overall value of utility one or more files less than the overall value of utility of default file, remaining cache space energy Accommodate described default file, then cache described default file;
If losing multiple files that overall value of utility is less than the overall value of utility of described default file, and remaining cache space being still Described default file can not be accommodated, then do not cache described default file.
CN201611025256.3A 2016-11-15 2016-11-15 Configurable mobile terminal cooperation caching method Active CN106487923B (en)

Priority Applications (1)

Application Number Priority Date Filing Date Title
CN201611025256.3A CN106487923B (en) 2016-11-15 2016-11-15 Configurable mobile terminal cooperation caching method

Applications Claiming Priority (1)

Application Number Priority Date Filing Date Title
CN201611025256.3A CN106487923B (en) 2016-11-15 2016-11-15 Configurable mobile terminal cooperation caching method

Publications (2)

Publication Number Publication Date
CN106487923A true CN106487923A (en) 2017-03-08
CN106487923B CN106487923B (en) 2019-07-02

Family

ID=58272789

Family Applications (1)

Application Number Title Priority Date Filing Date
CN201611025256.3A Active CN106487923B (en) 2016-11-15 2016-11-15 Configurable mobile terminal cooperation caching method

Country Status (1)

Country Link
CN (1) CN106487923B (en)

Cited By (2)

* Cited by examiner, † Cited by third party
Publication number Priority date Publication date Assignee Title
CN111654873A (en) * 2019-09-27 2020-09-11 西北大学 Mobile CDN link selection energy consumption optimization method based on global utility cache strategy
CN112995636A (en) * 2021-03-09 2021-06-18 浙江大学 360-degree virtual reality video transmission system based on edge calculation and active cache and parameter optimization method

Citations (5)

* Cited by examiner, † Cited by third party
Publication number Priority date Publication date Assignee Title
CN103237068A (en) * 2013-04-17 2013-08-07 北京科技大学 Content-attribute-distinguishable streaming media cache replacement method for CDN-P2P (content delivery network and peer-to-peer)
CN104967861A (en) * 2015-05-27 2015-10-07 上海美琦浦悦通讯科技有限公司 CDN video buffer system and method
CN105227665A (en) * 2015-07-20 2016-01-06 中国科学院计算技术研究所 A kind of caching replacement method for cache node
CN105406986A (en) * 2015-10-23 2016-03-16 北京邮电大学 Content distribution control method and center controller
CN105653473A (en) * 2015-12-31 2016-06-08 中国科学院信息工程研究所 Cache data access method and device based on binary identification

Patent Citations (5)

* Cited by examiner, † Cited by third party
Publication number Priority date Publication date Assignee Title
CN103237068A (en) * 2013-04-17 2013-08-07 北京科技大学 Content-attribute-distinguishable streaming media cache replacement method for CDN-P2P (content delivery network and peer-to-peer)
CN104967861A (en) * 2015-05-27 2015-10-07 上海美琦浦悦通讯科技有限公司 CDN video buffer system and method
CN105227665A (en) * 2015-07-20 2016-01-06 中国科学院计算技术研究所 A kind of caching replacement method for cache node
CN105406986A (en) * 2015-10-23 2016-03-16 北京邮电大学 Content distribution control method and center controller
CN105653473A (en) * 2015-12-31 2016-06-08 中国科学院信息工程研究所 Cache data access method and device based on binary identification

Cited By (4)

* Cited by examiner, † Cited by third party
Publication number Priority date Publication date Assignee Title
CN111654873A (en) * 2019-09-27 2020-09-11 西北大学 Mobile CDN link selection energy consumption optimization method based on global utility cache strategy
CN111654873B (en) * 2019-09-27 2022-08-16 西北大学 Mobile CDN link selection energy consumption optimization method based on global utility cache strategy
CN112995636A (en) * 2021-03-09 2021-06-18 浙江大学 360-degree virtual reality video transmission system based on edge calculation and active cache and parameter optimization method
CN112995636B (en) * 2021-03-09 2022-03-25 浙江大学 360-degree virtual reality video transmission system based on edge calculation and active cache and parameter optimization method

Also Published As

Publication number Publication date
CN106487923B (en) 2019-07-02

Similar Documents

Publication Publication Date Title
CN106331083B (en) A kind of heterogeneous network selection method considering content distribution energy consumption
CN112218337A (en) Cache strategy decision method in mobile edge calculation
CN109729507B (en) D2D cooperative caching method based on incentive mechanism
CN108174397A (en) A kind of multiple gateway Synergistic method of task-driven
CN104507124A (en) Management method for base station cache and user access processing method
Sinky et al. Responsive content-centric delivery in large urban communication networks: A LinkNYC use-case
Zhang et al. Clustered device-to-device caching based on file preferences
Assila et al. Achieving low-energy consumption in fog computing environment: A matching game approach
CN106487923A (en) Configurable mobile terminal cooperation caching method
Li et al. Caching resource management of mobile edge network based on Stackelberg game
Le et al. Joint cache allocation with incentive and user association in cloud radio access networks using hierarchical game
Xie et al. Caching resource sharing in radio access networks: a game theoretic approach
CN110113213A (en) A kind of cooperative caching dispositions method based on cloud wireless access planar network architecture
Li et al. Collaborative optimization of edge-cloud computation offloading in internet of vehicles
Guo et al. Joint optimization of caching and routing strategies in content delivery networks: A big data case
Wang et al. In-network caching: An efficient content distribution strategy for mobile networks
Deng et al. Rl-based radio resource slicing strategy for software-defined satellite networks
Fang et al. Offloading strategy for edge computing tasks based on cache mechanism
CN106304307A (en) A kind of resource allocation methods under heterogeneous network converged
Krolikowski et al. Fair distributed user-traffic association in cache equipped cellular networks
CN108990111A (en) A kind of content popularit change over time under node B cache method
Assila et al. Improving caching resource management: A pricing economic approach using Cournot, Bertrand, and Stackelberg game models
CN105897870B (en) A kind of method of the congestion control and load balancing of Internet video caching system
Ghosh et al. Improving network throughput by hardware realization of a dynamic content caching scheme for information-centric networking (ICN)
Li et al. Adaptive handover based on traffic balancing and multi-dimensional collaborative resource management in MEC environment

Legal Events

Date Code Title Description
C06 Publication
PB01 Publication
SE01 Entry into force of request for substantive examination
SE01 Entry into force of request for substantive examination
GR01 Patent grant
GR01 Patent grant