CN110572432A - Spatial cooperation caching and optimizing method for heterogeneous network - Google Patents
Spatial cooperation caching and optimizing method for heterogeneous network Download PDFInfo
- Publication number
- CN110572432A CN110572432A CN201910717939.2A CN201910717939A CN110572432A CN 110572432 A CN110572432 A CN 110572432A CN 201910717939 A CN201910717939 A CN 201910717939A CN 110572432 A CN110572432 A CN 110572432A
- Authority
- CN
- China
- Prior art keywords
- helper
- content
- edge server
- probability
- caching
- 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
Classifications
-
- H—ELECTRICITY
- H04—ELECTRIC COMMUNICATION TECHNIQUE
- H04L—TRANSMISSION OF DIGITAL INFORMATION, e.g. TELEGRAPHIC COMMUNICATION
- H04L67/00—Network arrangements or protocols for supporting network services or applications
- H04L67/50—Network services
- H04L67/56—Provisioning of proxy services
- H04L67/568—Storing data temporarily at an intermediate stage, e.g. caching
Landscapes
- Engineering & Computer Science (AREA)
- Computer Networks & Wireless Communication (AREA)
- Signal Processing (AREA)
- Information Transfer Between Computers (AREA)
- Information Retrieval, Db Structures And Fs Structures Therefor (AREA)
Abstract
The invention discloses a space cooperation caching and optimizing method of a heterogeneous network, which comprises five parts: determining the caching probability of the content combination in the Edge server and the Helper, deriving an objective function according to the caching probability, carrying out subproblem division on the objective function and solving subproblems, and solving an accurate solution and model simulation when the caching capacity of the Edge server and the Helper is 1. Unlike common probabilistic caching strategies, Edge server and Helper independently cache content according to caching probability. In this strategy, the content cached by the Helper is affected by the content cached on a nearby Edge server. Repeated caching in the Helper can be effectively reduced, the utilization rate of caching resources in the Helper is improved, and the performance of a caching network is improved.
Description
Technical Field
The invention belongs to the technical field of space cooperative caching and optimization, and particularly relates to a space cooperative caching and optimizing method for a heterogeneous network.
Background
as the mobile data traffic generated by the mobile device is continuously increased, the Edge server is used for providing cache resources for the user, so that the transmission delay can be reduced, and the load of the network can be released and lightened. However, because the cache capacity of the Edge server is limited, an effective content placement strategy needs to be designed to reasonably store the content on the Edge server, so as to improve the data streaming rate. The existing processing strategies are generally Hybird storage strategy and MPC (most popular content storage) strategy. The Hybrid storage strategy is to take the content which is most popular with users (the content with the largest downloading access times) to be preferentially stored on the Edge server and the content which is least popular with users to be stored on the Helper when the content stored on the Edge server is considered, so that the low-delay content delivery is realized. However, if the Edge servers are sparsely distributed in an area, multiple users can access the same Edge server at the same time, which can result in a decrease in data offload ratio. While the MPC strategy takes the storage content on the Edge server into account, what is adopted is to store the content with the largest number of times of downloading and accessing by the user into the Edge server and the Helper at the same time, which easily causes redundant storage of space and wastes storage space.
Disclosure of Invention
The invention aims to provide a space cooperation caching and optimizing method of a heterogeneous network, so as to solve the problems.
in order to achieve the purpose, the invention adopts the following technical scheme:
a spatial cooperation caching and optimizing method for a heterogeneous network comprises the following steps:
Step 1, determining the cache probability of a content combination m in an Edge server and a Helper; the cache capacities of Edge server and Helper are respectively expressed as Neand Ndand the communication ranges of Edge server and Helper are respectively denoted as ReAnd Rd(ii) a Acquiring contents from an Edge server of an overlay user and a Helper of the overlay user, and if the user acquires the requested contents, the contents are called as hits; assume that the positions of Edge server and Helper, respectively, follow a density of λeand λdPoisson Point Process (PPP); helper is divided into two kinds: the Helper covered by the Edge server and the Helper not covered by the Edge server;
Step 2, deriving a target function according to the cache probability, and using H1(m) represents the probability that the user will get the content he requested from an uncovered Helper; note H2(m) probability of a user obtaining the content they requested from the overlaid Helper;
step 3, performing subproblem division on the objective function and solving the subproblems, and maximizing the objective function by optimizing the cache probability of the content combination on the Edge server and the cache probability of the content combination on the covered Helper and the uncovered Helper;
step 4, solving an accurate solution when the cache capacities of the Edge server and the Helper are 1;
And 5, simulating the model.
Further, if a Helper is covered by an Edge server, the Helper does not store the content stored on the Edge server nearest to the Helper; if the Helper is not covered by any Edge server, it can cache any content;
for the covered Helper, the content which can be stored by the Helper is determined by the content cached in the Edge server which is nearest to the Helper; is provided withrepresenting M contents in a database; assuming that all content has the same size, let it be 1, in Edge server, it will ben in (1)ethe individual different content is considered as a combination; in the Helper layer, every NdDifferent contents form a combination; is provided withRepresenting a combined set containing the content m in the Edge server;Set representing a combination containing content m in an uncovered HelperCombining;representing the set of the combination containing the content m in the overlaid Helper, wherein the nearest Edge server cache content combination is i; combining and storing the contents on the Edge server and the Helper by adopting a probability cache strategy; by usingA caching probability matrix representing Edge server,representing the storage probability of the content combination i in the Edge server;
For uncovered Helper, useIndicating the probability of their caching,Representing the storage probability of the content combination j on the Helper; remember that Helper has a caching probability ofWhere Helper is overlaid by Edge server storing content combination i,representing the storage probability of the content combination j on the Helper; for each content combination i stored in Edge server, it has a content in HelperCorresponding to it; at the same time, Ge,GhAndthe elements in (1) should satisfy the following conditions:
For the overlaid Helper, if any content in the content combination j has already been stored in its nearest Edge server, the caching probability of the combination j will be set to 0;
the cache content in Edge server is m,The probability of (c) is:
The content m is a content of a content m,probability of caching in uncovered Helper:
the content m is a content of a content m,probability of caching in the overlaid Helper:
i represents the combination of contents stored in Edge server closest to Helper.
Further, the overall objective function is defined as:
u represents a data offload ratio; s0indicating the probability that a particular user is not covered by any Edge server, S (m) indicating the probability that a certain user will obtain the content requested from an Edge server; the position of the Edge server with the cache content of m follows sparse PPP; according to PPP attribute, the number of Edge servers follows Poisson distribution, so that S can be obtained0,SmThe expression of (1);
For the uncovered Helper, according to the proposed space cooperation caching strategy, the cached content is not influenced by the Edge server; the uncovered Helper can be regarded as a single-layer auxiliary network in the area uncovered by the Edge server; the probability that a particular user gets its requested content from an uncovered Helper can be expressed as:
for the overlaid Helper, they cannot cache the content stored by the Edge server nearest to the overlay; there are a total of I different combinations in Edge server; for each combination in the Edge server, the Helper covered by the combination has different potential content sets and corresponding optimal caching probability; it should be noted that if the user needs to get content m from the uncovered Helper, the nearest Edge server does not cache content m; is provided withRepresents a content combination including a content m; h2(m) is represented by:
Will S0,SmSubstituting (7) into (8) and (9), the expression for the objective function can be written as Eqn. (10):
Further, the following problem is obtained from the objective function (10):
first, when the optimal caching probability of Edge server is designed, the problem is regarded as the probability caching problem of one layer of network:
by using the optimization tool in MATLAB, a numerical solution to problem P2 was obtained and recorded as
Regarding the uncovered Helper as a single-layer cache network in the area; placing a design strategy for the content of the uncovered Helper, wherein the strategy is independent of the Edge server and the covered Helper;
problem P3 is similar to problem P2; by using the optimization tool, a numerical solution to problem P3 is derived and noted
For the overlaid Helper, the design of the content placement policy is shadowed by its nearest Edge serverSounding; in problems P2 and P3, optimal solutions were obtainedandWill be provided withAndSubstituting Eqn. (10), omitting irrelevant elements to obtain an objective function Eqn. (11);
variables hereinAs derived from the problem P1,is a constant; for each combination i in Edge server, the overlaid Helper has a different set of content combinationsand corresponding cache probabilities; for the Independently ofthus obtaining the best caching probability of the covered Helper for each combination i; the optimization problem is expressed as follows:
Beta in this casemIs a constant number composed ofObtaining;
Problem P4 is similar to problem P2; get a numerical solution for each combination i, which is noted
further, the cache capacity of Edge server and Helper is the unit cache size, i.e. Ne1 or Nd=1;
When N is presenteQuestion P2 is described as:
By using a similar method to solve problem P2, the lagrange multiplier method is used; deducingExpression (c):
When N is presentdProblem P3 is described as:
problem P4 is described as:
The optimal solution to the problem P6 is derived by:
The optimal solution to the problem P7 is derived by:
Using the algorithm CPC, the optimal solutions of the problems P6 and P7 are obtained respectively,and
further, the algorithm CPC: directly solving problems P5, P6 and P7, and if the obtained solution is within [0,1], not performing any treatment; if the obtained solution is more than 1, respectively setting the solutions more than 1 as 1; if the obtained solutions are less than 0, the solutions less than 0 are respectively set to 0 in sequence.
Further, the densities of Edge server and Helper are set to 3/km respectively2and 500/km2(ii) a Hypothetical content setthere are 6 contents; the cache capacities of the Edge server and the Helper are respectively set to be 2 and 1; communication range, i.e. ReAnd RdAre respectively set to be 500 meters and 50 meters。
Compared with the prior art, the invention has the following technical effects:
the invention provides a spatial cooperation caching strategy of a double-layer heterogeneous network. Unlike common probabilistic caching strategies, Edge server and Helper independently cache content according to caching probability. In this strategy, the content cached by the Helper is affected by the content cached on a nearby Edge server. Repeated caching in the Helper can be effectively reduced, the utilization rate of caching resources in the Helper is improved, and the performance of a caching network is improved.
The invention analyzes the performance of the space cooperation caching strategy by using a random geometric theory, analyzes the performance index from the aspect of hit rate (hit rate), and verifies the correctness of the theoretical result through a simulation experiment.
The invention maximizes the hit probability of the double-layer heterogeneous network by optimizing the cache probability of the content combination on the Edge server and the Helper. When the Edge server or Helper storage space is 1, a closed-form solution of the optimal storage probability is obtained. Compared with the existing caching strategy, the optimal caching probability of the invention is more excellent than that of the existing Hybrid storage strategy and MPC strategy.
drawings
Fig. 1 is a network caching model of a heterogeneous network space caching strategy.
FIG. 2 shows the density λ of the liquid crystal at different valuesdLower (lambda)e=3/km2) Analysis results and simulation results of Helper.
FIG. 3 is Phitand γ.
FIG. 4 is Phitand λeThe relationship between them.
FIG. 5 is PhitAnd Rethe relationship between them.
FIG. 6 is PhitAnd RdThe relationship between them.
Detailed Description
The invention is further described below with reference to the accompanying drawings:
The spatial cooperation caching and optimizing method of the heterogeneous network comprises five parts. Respectively as follows: determining the caching probability of the content combination m in the Edge server and the Helper, deriving an objective function according to the caching probability, dividing the objective function into subproblems, solving the accurate solution when the caching capacity of the Edge server and the Helper is 1, and performing model simulation.
1. and determining the probability that the content combination m is cached in the Edge server and the Helper.
The invention provides a space cooperation caching strategy, which is used for a double-layer heterogeneous network comprising an Edge server and a Helper and adopts random geometry to simulate the whole network. Edge server and Helper are characterized by different cache capacities and communication ranges. The cache capacities of Edge server and Helper are respectively expressed as Neand NdAnd the communication ranges of Edge server and Helper are respectively denoted as ReAnd Rd. For a particular user, it may obtain content from the overlay user's Edge server and the overlay user's Helper. If the user can obtain the content he requested, it is called a hit. Assume that the positions of Edgeserver and Helper, respectively, follow a density of λeAnd λdPoisson Point Process (PPP). A distance-based communication model is employed in this model. A specific network caching model is shown in fig. 1.
In the present invention, the Helper is divided into two types: the Helper covered by Edge server and the Helper not covered by Edge server. If a Helper is overwritten by an Edge server, the Helper does not store the content stored on the Edge server closest to it. If the Helper is not overridden by any Edge server, it can cache any content.
For the overlaid Helper, the content it can store is determined by the content cached in its nearest neighbor Edge server. Is provided withRepresenting M contents in the database. In the caching model, different sizes of content do not affect the design of the optimal content placement strategy, which is set to 1 for simplicity, assuming that all content has the same size. In Edge server, willN in (1)eThe different contents are regarded as a combination. In the Helper layer, every NdThe different contents constitute a combination. Is provided withRepresenting the combined set containing content m in Edge server.Indicating that the collection of combinations of content m is contained in an uncovered Helper.And indicating that the overlaid Helper contains the combination set of the content m, and the nearest Edge server cache content combination is i. And combining and storing the contents on the Edgeserver and the Helper by adopting a probability cache strategy. By usingA caching probability matrix representing Edge server,representing the storage probability of the content combination i in the Edge server;
for uncovered Helper, useindicating the probability of their caching,Indicating the storage probability of the content combination j on the Helper. Remember that Helper has a caching probability ofWhere Helper is overlaid by Edge server storing content combination i,Indicates the content combination j is inprobability of storage on Helper. For each content combination i stored in Edge server, it has a content in HelperCorresponding to it. At the same time, Ge,GhAndThe elements in (1) should satisfy the following conditions:
For the overlaid Helper, if any of the content combinations j has already been stored in its nearest Edge server, the caching probability for combination j will be set to 0.
The cache content in Edge server is mThe probability of (c) is:
Content mprobability of caching in uncovered Helper:
Content mprobability of caching in the overlaid Helper:
i represents the combination of contents stored in Edge server closest to Helper.
2. Deriving objective function from cache probability
by H1(m) represents the probability that the user will get the content he requested from the uncovered Helper. Note H2(m) is the probability that the user gets the content he requested from the overlaid Helper. The overall objective function is defined as:
u represents a data offload ratio. S0indicating the probability that a particular user is not covered by any Edge server and S (m) indicating the probability that a user can obtain the content requested from an Edge server. The location of Edge server with m cache content follows sparse PPP. According to PPP attribute, the number of Edge servers follows Poisson distribution, so that S can be obtained0,Smis described in (1).
For the uncovered Helper, according to the proposed spatial collaborative caching strategy, the cached content is not affected by the Edge server. The uncovered Helper can be viewed as a single-layer auxiliary network in the area uncovered by the Edge server. The probability that a particular user gets its requested content from an uncovered Helper can be expressed as:
For the overlaid Helper, they cannot cache the content stored by the Edge server closest to it. There are a total of I different combinations in Edge server. For each combination in Edge server, the Helper it covers has a different set of potential content and corresponding best caching probability. It should be noted that if the user needs to get content m from an uncovered Helper, the nearest Edge server does not cache content m. Is provided withRepresenting a content combination comprising content m. H2(m) may be expressed as:
Will S0,SmSubstituting (7) into (8) and (9), the expression for the objective function can be written as Eqn. (10):
3. Sub-problem division is carried out on the objective function and the sub-problems are solved
The objective function is maximized by optimizing the caching probability of the content combination on Edge server, the caching probability of the content combination on covered Helper and uncovered Helper.
from the objective function (10) the following problem can be derived:
Note that problem P1 relates toand it is an optimization problem with a large number of variables. There are (I + J + I × J) variables in the objective function in total, and it is difficult to obtain an optimal solution to the problem P1.
To facilitate solving this optimization problem, the process of content placement is divided into two steps. First, the optimal caching probability for Edge server is designed, without considering the content placement problem on Helper. Then, based on the content cached on the Edge server, an optimal caching probability is designed for all the Helper.
first, when the optimal caching probability of Edge server is designed, the problem can be regarded as the probability caching problem of one layer of network:
by using an optimization tool in MATLAB, a numerical solution to problem P2 can be obtained,Is marked as
For the uncovered Helper, it can be considered as a single-layer cache network in the area. The content placement design strategy of the uncovered Helper is independent of the Edge server and the covered Helper.
Problem P3 is similar to problem P2. By using the optimization tool, a numerical solution to problem P3, denoted as
for the overlaid Helper, the design of the content placement policy is affected by its nearest Edge server. In problems P2 and P3, optimal solutions were obtainedAndWill be provided withandsubstitution Eqn. (10), omitting irrelevant elements, can result in an objective function Eqn. (11).
Variable g hereeiAs derived from the problem P1,Is a constant. For each combination i in Edge server, the overlaid Helper has a different set of content combinationsAnd corresponding caching probabilities. For the Independently ofThe best caching probability of the overlaid Helper for each combination i can thus be obtained. The optimization problem is expressed as follows:
beta in this casemIs a constant number composed ofAnd (6) obtaining.
Problem P4 is similar to problem P2. We can get a numerical solution for each combination i, denoted as
4. Solving the accurate solution when the cache capacity of Edge server and Helper is 1
Consider a specific example of a collaborative caching policy: the cache capacity of Edge server and Helper is the unit cache size. Namely Ne1 or Nd=1。
when N is presenteProblem P2 may be described as:
The lagrangian multiplier method is used by using a similar method to solve the problem P2. Can deduceExpression (c):
It should be noted that the optimal solution derived from Eqn. (12) may not be within [0,1 ]. In order for the optimal solution to satisfy the first constraint in problem P4, a cache probability transformation (CPC) algorithm is designed.
When N is presentdwhen 1, the problem P3 can be described as:
problem P4 may be described as:
the optimal solution to the problem P6 may be derived by:
The optimal solution to the problem P7 may be derived by:
Using the algorithm CPC, optimal solutions to the problems P6 and P7 can be obtained,And
Algorithm CPC: for the problem (P5, P6, P7), the solution is directly solved, and if the obtained solution is within [0,1], no treatment is carried out; if the obtained solution is larger than 1, sequentially setting the solutions larger than 1 (starting from the solution with the largest difference from 0) as 1; if the obtained solution is less than 0, sequentially setting the solutions less than 0 (starting from the solution with the largest difference from 0) as 0 respectively; the problem is solved by an algorithm CPC, and the results of all solutions can be unified and can be reduced to [0,1 ].
5. simulation of a model
the invention evaluates performance from a hit probability perspective and compares it to two available strategies. The first baseline is the most popular caching policy, where Edge server and Helper cache the most popular content. Another baseline is a Hybrid Caching (HC) policy, where Edge server caches the most popular content, while Helper employs a probabilistic caching policy to cache other content. The densities of Edge server and Helper are set to 3/km respectively2and 500/km2. Hypothetical content setThere are 6 contents. The cache capacities of Edge server and Helper are set to 2 and 1, respectively. Communication range, i.e. Reand RdSet to 500 meters and 50 meters, respectively. Fig. 2, 3, 4, 5 and 6 are simulation results obtained by considering different factors respectively.
From the simulation results, when all possible influence factors are considered, the hit probability of the method is slightly higher than that of the existing HC strategy and MPC strategy, and the optimal cache probability is obviously better than that of the existing HC strategy and MPC strategy.
Claims (7)
1. A spatial cooperative caching and optimizing method for a heterogeneous network is characterized by comprising the following steps:
Step 1, determining the cache probability of a content combination m in an Edge server and a Helper; the cache capacities of Edge server and Helper are respectively expressed as NeAnd Ndand the communication ranges of Edge server and Helper are respectively denoted as ReAnd Rd(ii) a Acquiring contents from an Edge server of an overlay user and a Helper of the overlay user, and if the user acquires the requested contents, the contents are called as hits; assume that the positions of Edge server and Helper, respectively, follow a density of λeAnd λdPoisson Point Process (PPP); the Helper is divided into two categories: quiltThe Helper covered by the Edge server and the Helper not covered by the Edge server;
step 2, deriving a target function according to the cache probability, and using H1(m) represents the probability that the user will get the content he requested from an uncovered Helper; note H2(m) probability of a user obtaining the content they requested from the overlaid Helper;
Step 3, performing subproblem division on the objective function and solving the subproblems, and maximizing the objective function by optimizing the cache probability of the content combination on the Edge server and the cache probability of the content combination on the covered Helper and the uncovered Helper;
Step 4, solving an accurate solution when the cache capacities of the Edge server and the Helper are 1;
And 5, simulating the model.
2. The method for caching and optimizing spatial collaboration in a heterogeneous network according to claim 1, wherein in step 1, if a Helper is covered by an Edge server, the Helper does not store the content stored on the Edge server nearest to the Helper; if the Helper is not covered by any Edge server, it can cache any content;
For the covered Helper, the content which can be stored by the Helper is determined by the content cached in the Edge server which is nearest to the Helper; is provided withRepresenting M contents in a database; assuming that all content has the same size, let it be 1, in Edge server, it will beN in (1)ethe individual different content is considered as a combination; in the Helper layer, every NdDifferent contents form a combination; is provided withRepresenting a combined set containing the content m in the Edge server;a set representing a combination containing content m in an uncovered Helper;Representing the set of the combination containing the content m in the overlaid Helper, wherein the nearest Edge server cache content combination is i; combining and storing the contents on the Edge server and the Helper by adopting a probability cache strategy; by usinga caching probability matrix representing Edge server,Representing the storage probability of the content combination i in the Edge server;
for uncovered Helper, useindicating the probability of their caching,Representing the storage probability of the content combination j on the Helper; remember that Helper has a caching probability ofWhere Helper is overlaid by Edge server storing content combination i,Representing the storage probability of the content combination j on the Helper; for each content combination i stored in Edge server, it has a content in Helpercorresponding to it; at the same time, Ge,GhandThe elements in (1) should satisfy the following conditions:
For the overlaid Helper, if any content in the content combination j has already been stored in its nearest Edge server, the caching probability of the combination j will be set to 0;
the cache content in Edge server is m,The probability of (c) is:
the content m is a content of a content m,Probability of caching in uncovered Helper:
The content m is a content of a content m,probability of caching in the overlaid Helper:
i represents the combination of contents stored in Edge server closest to Helper.
3. The spatial collaborative caching and optimizing method for the heterogeneous network according to claim 1, wherein in the step 2, the overall objective function is defined as:
u represents a data offload ratio; s0Indicating the probability that a particular user is not covered by any Edge server, S (m) indicating the probability that a certain user will obtain the content requested from an Edge server; the position of the Edge server with the cache content of m follows sparse PPP; according to PPP attribute, the number of Edge servers follows Poisson distribution, so that S can be obtained0,Smthe expression of (1);
for the uncovered Helper, according to the proposed space cooperation caching strategy, the cached content is not influenced by the Edge server; the uncovered Helper can be regarded as a single-layer auxiliary network in the area uncovered by the Edge server; the probability that a particular user gets its requested content from an uncovered Helper can be expressed as:
For the overlaid Helper, they cannot cache the content stored by the Edge server nearest to the overlay; there are a total of I different combinations in Edge server; for each combination in the Edge server, the Helper covered by the combination has different potential content sets and corresponding optimal caching probability; it should be noted that if the user needs to get content m from the uncovered Helper, the nearest Edge server does not cache content m; is provided withrepresents a content combination including a content m; h2(m) is represented by:
Will S0,SmSubstituting (7) into (8) and (9), the expression for the objective function can be written as Eqn. (10):
4. The spatial collaborative caching and optimizing method for the heterogeneous network according to claim 1, wherein in step 3, the following problem is obtained from the objective function (10):
first, when the optimal caching probability of Edge server is designed, the problem is regarded as the probability caching problem of one layer of network:
By using the optimization tool in MATLAB, a numerical solution to problem P2 was obtained and recorded as
regarding the uncovered Helper as a single-layer cache network in the area; placing a design strategy for the content of the uncovered Helper, wherein the strategy is independent of the Edge server and the covered Helper;
Problem P3 is similar to problem P2; by using the optimization tool, a numerical solution to problem P3 is derived and noted
For the overlaid Helper, the design of the content placement strategy is affected by the nearest Edge server; in problems P2 and P3, optimal solutions were obtainedandWill be provided withandsubstituting Eqn. (10), omitting irrelevant elements to obtain an objective function Eqn. (11);
Variables hereinAs derived from the problem P1,Is a constant; for each combination i in Edge server, the overlaid Helper has a different set of content combinationsAnd corresponding cache probabilities; for the Independently ofthus obtaining the best caching probability of the covered Helper for each combination i; the optimization problem is expressed as follows:
Beta in this casemis a constant number composed ofobtaining;
Problem P4 is similar to problem P2; get a numerical solution for each combination i, which is noted
5. the method according to claim 1, wherein in step 4, the cache capacity of Edge server and Helper is the unit cache size, that is, Ne1 or Nd=1;
When N is presenteQuestion P2 is described as:
by using a similar method to solve problem P2, the lagrange multiplier method is used; deducingexpression (c):
When N is presentdproblem P3 is described as:
problem P4 is described as:
The optimal solution to the problem P6 is derived by:
the optimal solution to the problem P7 is derived by:
Using the algorithm CPC, the optimal solutions of the problems P6 and P7 are obtained respectively,and
6. The spatial collaborative caching and optimizing method for the heterogeneous network according to claim 5, wherein an algorithm CPC: directly solving problems P5, P6 and P7, and if the obtained solution is within [0,1], not performing any treatment; if the obtained solution is more than 1, respectively setting the solutions more than 1 as 1; if the obtained solutions are less than 0, the solutions less than 0 are respectively set to 0 in sequence.
7. The method for spatial collaborative caching and optimizing of heterogeneous networks according to claim 1, wherein in step 5, the densities of Edge server and Helper are set to 3/km respectively2and 500/km2(ii) a Hypothetical content setthere are 6 contents; the cache capacities of the Edge server and the Helper are respectively set to be 2 and 1; communication range, i.e. ReAnd Rdset to 500 meters and 50 meters, respectively.
Priority Applications (1)
Application Number | Priority Date | Filing Date | Title |
---|---|---|---|
CN201910717939.2A CN110572432B (en) | 2019-08-05 | 2019-08-05 | Spatial cooperation caching and optimizing method for heterogeneous network |
Applications Claiming Priority (1)
Application Number | Priority Date | Filing Date | Title |
---|---|---|---|
CN201910717939.2A CN110572432B (en) | 2019-08-05 | 2019-08-05 | Spatial cooperation caching and optimizing method for heterogeneous network |
Publications (2)
Publication Number | Publication Date |
---|---|
CN110572432A true CN110572432A (en) | 2019-12-13 |
CN110572432B CN110572432B (en) | 2020-12-04 |
Family
ID=68774630
Family Applications (1)
Application Number | Title | Priority Date | Filing Date |
---|---|---|---|
CN201910717939.2A Active CN110572432B (en) | 2019-08-05 | 2019-08-05 | Spatial cooperation caching and optimizing method for heterogeneous network |
Country Status (1)
Country | Link |
---|---|
CN (1) | CN110572432B (en) |
Citations (3)
Publication number | Priority date | Publication date | Assignee | Title |
---|---|---|---|---|
EP2800386A1 (en) * | 2013-01-25 | 2014-11-05 | Huawei Technologies Co., Ltd. | Child node, father node and buffer method and system for multi-layer video network |
CN109362064A (en) * | 2018-09-14 | 2019-02-19 | 重庆邮电大学 | The task buffer allocation strategy based on MEC in mobile edge calculations network |
CN109450512A (en) * | 2018-09-17 | 2019-03-08 | 厦门大学 | A kind of method that network code cooperates with wireless relay in edge cache |
-
2019
- 2019-08-05 CN CN201910717939.2A patent/CN110572432B/en active Active
Patent Citations (3)
Publication number | Priority date | Publication date | Assignee | Title |
---|---|---|---|---|
EP2800386A1 (en) * | 2013-01-25 | 2014-11-05 | Huawei Technologies Co., Ltd. | Child node, father node and buffer method and system for multi-layer video network |
CN109362064A (en) * | 2018-09-14 | 2019-02-19 | 重庆邮电大学 | The task buffer allocation strategy based on MEC in mobile edge calculations network |
CN109450512A (en) * | 2018-09-17 | 2019-03-08 | 厦门大学 | A kind of method that network code cooperates with wireless relay in edge cache |
Non-Patent Citations (2)
Title |
---|
SHUBIN ZHANG等: ""An Optimized Spatially Cooperative Caching Strategy for Heterogeneous Caching Network"", 《2019 15TH INTERNATIONAL WIRELESS COMMUNICATIONS & MOBILE COMPUTING CONFERENCE (IWCMC)》 * |
葛志诚等: ""一种移动内容分发网络的分层协同缓存机制 "", 《计算机学报 》 * |
Also Published As
Publication number | Publication date |
---|---|
CN110572432B (en) | 2020-12-04 |
Similar Documents
Publication | Publication Date | Title |
---|---|---|
CN101692229B (en) | Self-adaptive multilevel cache system for three-dimensional spatial data based on data content | |
CN103366016B (en) | E-file based on HDFS is centrally stored and optimization method | |
CN103425756B (en) | The replication strategy of data block in a kind of HDFS | |
CN107040422A (en) | A kind of network big data method for visualizing cached based on materialization | |
CN107770259A (en) | Copy amount dynamic adjusting method based on file temperature and node load | |
CN104407879B (en) | A kind of power network sequential big data loaded in parallel method | |
CN103077125B (en) | A kind of tower caching method of self-adaptation self-organization of efficiency utilization storage space | |
CN112218337A (en) | Cache strategy decision method in mobile edge calculation | |
CN101370025A (en) | Storing method, scheduling method and management system for geographic information data | |
CN103595805A (en) | Data placement method based on distributed cluster | |
CN103118132B (en) | A kind of distributed cache system towards space-time data and method | |
CN103701619A (en) | Internet content distribution method based on CDN (Content Distribution Network) and data center dynamic selection | |
CN108366089A (en) | A kind of CCN caching methods based on content popularit and pitch point importance | |
CN110018997B (en) | Mass small file storage optimization method based on HDFS | |
CN103631933A (en) | Distributed duplication elimination system-oriented data routing method | |
CN110062280A (en) | P2P-oriented video cache management and playing method, system and medium | |
CN104035807B (en) | Metadata cache replacement method of cloud storage system | |
CN111491331A (en) | Network perception self-adaptive caching method based on transfer learning in fog computing network | |
CN103838680B (en) | A kind of data cache method and device | |
CN109407997A (en) | A kind of data processing method, device, equipment and readable storage medium storing program for executing | |
CN110572432B (en) | Spatial cooperation caching and optimizing method for heterogeneous network | |
CN113127741B (en) | Cache method for reading and writing data of mass users and posts in part-time post recommendation system | |
CN112887943B (en) | Cache resource allocation method and system based on centrality | |
CN108600365A (en) | A kind of Wireless Heterogeneous Networks caching method based on sequence study | |
CN109635161B (en) | Cross-domain allopatric collaborative design method in mass data environment |
Legal Events
Date | Code | Title | Description |
---|---|---|---|
PB01 | Publication | ||
PB01 | Publication | ||
SE01 | Entry into force of request for substantive examination | ||
SE01 | Entry into force of request for substantive examination | ||
GR01 | Patent grant | ||
GR01 | Patent grant |