CN106790421B - ICN two-step caching method based on community - Google Patents
ICN two-step caching method based on community Download PDFInfo
- Publication number
- CN106790421B CN106790421B CN201611094420.6A CN201611094420A CN106790421B CN 106790421 B CN106790421 B CN 106790421B CN 201611094420 A CN201611094420 A CN 201611094420A CN 106790421 B CN106790421 B CN 106790421B
- Authority
- CN
- China
- Prior art keywords
- community
- icn
- content
- node
- cache
- 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.)
- Active
Links
Images
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
Abstract
The invention relates to an ICN two-step caching method based on a community, which is characterized by comprising the following steps of: the method comprises the steps that firstly, an SDN controller identifies a community structure in an ICN based on an information description length compression technology, and community division is carried out on the ICN; secondly, calculating the importance of the node community of each node; thirdly, the SDN controller collects state information of nodes in each community based on an openflow protocol; fourthly, calculating the one-step cache priority of the nodes of each community; fifthly, the user initiates an interest request and requests interested data content from the network; sixthly, the ICN switch is responsible for routing and searching the interest packet data of the user; seventhly, calculating new caching information by the SDN controller, making a two-step caching strategy and issuing the two-step caching strategy to the ICN switch; and eighthly, executing a two-step caching strategy by each node according to a rule issued by the SDN controller. The invention provides an effective way for further optimization of an ICN cache mechanism.
Description
Technical Field
The invention relates to an ICN two-step caching method based on a community.
Background
The internet industry is rapidly developed, and the requirements for network transmission efficiency are higher and higher due to the fact that novel network applications are in a large number. However, a series of defects are continuously exposed in the existing internet architecture mainly based on the TCP/IP protocol stack, including the problems of structure solidification, poor expansibility, limited mobility support, inherent security and the like, and the existing internet architecture cannot meet the requirements of the current internet development. To thoroughly solve the above problems, the academia has proposed a Software Defined Network (SDN) and an information-centric network (ICN). In order to further optimize the network and reduce the response delay of the content requested by the user, the ICN introduces a caching mechanism to cache the content closer to the user, thereby reducing the access delay of the user and reducing the consumption of network bandwidth and the load of the server. However, among the currently proposed caching mechanisms, the problems of "cache invalidation", "cache homogenization", and the like still exist and need to be solved.
The cache placement strategy is used for determining the cache position of the content and can be divided into a way cache mechanism and a bypass cache mechanism. The en route caching refers to a caching mechanism of the content object on the node through which the content object passes by being cached on the return way of the content object, and comprises everywhere caching, selective caching and the like. The defects of the on-the-way cache are that cache redundancy is easily caused, invalid cache is easily caused, and resources are wasted. The bypass cache mechanism collects network state information in advance and then calculates a global optimization scheme for cache placement. For example, the kudzu and the like propose a path caching strategy based on a maximum content activity factor, firstly, a maximum hot spot request region is found on a forwarding path according to the content activity factor, and then, a cache node in the region is selected by adopting a consistent Hash cooperative cache. And the Liu foreign preferences and the like cache the content to the adjacent nodes by utilizing the idle bandwidth of the link, and the cache probability of the content object on the node is adjusted according to the proportion of the number of the forwarding ports, the link utilization rate of the downstream node, the life cycle of the content and the like.
Different from the existing work, the content objects are cached according to community areas, the cached objects are reasonably dispersed in the whole network range, and the content objects are cached on nodes with different importance degrees in various communities according to the popularity, so that on one hand, the load balance can be realized, and on the other hand, the diversification of the cache contents of the nodes in the various communities can be improved.
Disclosure of Invention
Aiming at the defects of the prior art, the invention provides an ICN two-step caching method based on a community. According to the method, the concept of SDN and the community theory of a complex network are introduced into the ICN, an ICN caching strategy based on community characteristics is provided, community boundaries in the ICN are identified through community analysis, content objects are reasonably cached on appropriate nodes in each community through a two-step caching mechanism, and an effective way is provided for further optimization of the ICN caching mechanism.
In order to achieve the purpose, the invention provides an ICN two-step caching method based on a community, which mainly comprises the following steps:
firstly, an SDN controller identifies a community structure in an ICN based on an information description length compression technology, and community division is carried out on the ICN;
secondly, calculating the importance of the node community of each node;
thirdly, the SDN controller collects state information of nodes in each community based on an openflow protocol;
fourthly, calculating one-step cache priority of the nodes of each community;
fifthly, the user initiates an interest request and requests interested data content from the network;
sixthly, the ICN switch is responsible for routing and searching the interest packet data of the user;
seventhly, calculating new caching information by the SDN controller according to the recalculated popularity, making a two-step caching strategy, and issuing the two-step caching strategy to the ICN switch;
and eighthly, executing a two-step caching strategy by each node according to a rule issued by the SDN controller.
Preferably, the status information in the third step includes remaining storage space, storage capacity, node community importance, content popularity, and the like.
Preferably, in the sixth step, when the content object is requested by a node in the network for the first time, the SDN controller issues a flow table, streams the content object to a node with the highest one-step caching priority of each community, and caches the content by a specified node.
As a further improvement of the above scheme, it is determined whether the one-step cache is overtime in the process that the content objects are directed to the one-step cache of each community, and if not, the content objects continue to wait for overtime.
As a further improvement of the above scheme, in the process that the content objects are led to the one-step cache of each community, when the temporary storage time reaches a given period T, the SDN controller recalculates the global popularity and the local popularity of each temporary storage content, and calculates the two-step cache position of each content object according to the global popularity and the local popularity, so as to realize rationalization of the spatial distribution of the cache content.
In the first step, a community division problem of the ICN is solved by adopting an information description length compression technology. The method comprises the following steps of taking routers/switches as nodes, taking physical connection between the routers/switches as edges to construct a complex network, taking a network modularity formula (1) as an objective function, and dividing the network into different communities by an optimization algorithm:
wherein N iscRepresenting the number of communities in the network, M representing the total number of connections in the network, McRepresenting the number of connections between nodes within a community c, dcRepresenting the sum of the degrees of all nodes in the community c.
In the second step, the importance of the node community refers to the importance of the node in the community where the node is located. It is defined as follows:
where c is the number of communities in the network, viI-th eigenvector, v, representing an adjacency matrix constructed with routers in the network as nodes and physical links between the routers as edgesikRepresenting a feature vector viThe kth element in (1).
In the fourth step, at the initial stage of content object generation, its popularity (including global popularity and local popularity) is difficult to calculate and inaccurate. Therefore, the invention provides a two-step caching mechanism to solve the problem of inaccurate derivation of popularity calculation. Firstly, calculating the priority of a one-step cache content object according to the state information (such as cache capacity, utilization rate, node community importance and the like) of nodes in a community, and temporarily caching the content object in the node with the highest one-step cache priority in the community when the content object is produced and requested by the nodes in the network; secondly, when the content object temporarily exists in the community for a given time period T, the SDN controller calculates the global popularity and the local popularity according to the request condition of the whole network and each community node for the content object, and recalculates the two-step cache position of the content object according to the global popularity and the local popularity. The two-step cache is added, so that the distribution of the content objects in the one-step cache in the cache position and time tends to be more reasonable. Primary cache priority S of node kkIs defined as:
in terms of global popularity, in a certain time period, counting the number of times that the content c is requested by the user, wherein popu (c) represents the access frequency to the content c in the current counting period, and r (c) represents the number of times that the content c is accessed in the current counting period, the popularity of the content c is calculated as follows:
in the aspect of local popularity, aiming at the problem that the local popularity of ICN content is difficult to determine, the invention defines the local popularity of the content in a community structure and provides an ICN local content popularity determination method based on communities. The local popularity can reflect the user interest in the community better, and cache content is replaced according to the local popularity, so that the space-time distribution of the cache content of nodes in the community tends to be reasonable. Counting the number of times that the content c is requested by the user in a community i within a certain time period by Popui(c) Representing the frequency of access to content c in the current statistical period, by Ri(c) Representing the number of accesses to the content c in this period, the popularity of the content c is calculated as follows:
the invention provides an ICN (information center network) two-step caching mechanism based on network community characteristics in an SDN (software defined network) environment. The ICN achieves the purpose of reducing the transmission delay of other users for requesting the data by caching the content object in the nodes of the network in the data transmission process, however, the existing cache node selection mechanism has the defects of homogenization, invalid cache and the like. In order to alleviate the above problems and better exert the advantages of the ICN caching mechanism, the present invention provides a method for selecting a reasonable node cache content object according to the community characteristics of the ICN by analyzing the community structure of the ICN network, which not only improves the diversification of cache contents in the network, but also reduces the probability of invalid cache, specifically comprising: firstly, analyzing the community structure characteristics of the ICN based on the compression technology of the information description length, and analyzing the importance degree of nodes in the community to the community; and secondly, the content objects are reasonably cached on the best node in each community based on the global popularity and the local popularity of the content objects through a two-step caching mechanism. The invention provides an effective way for further optimization of an ICN cache mechanism.
Drawings
FIG. 1 is a schematic flow chart of the implementation of the community-based ICN two-step caching method.
Detailed Description
The invention is described in detail below with reference to the drawings and specific examples, but the invention is not limited thereto.
Referring to fig. 1, an embodiment of the invention provides an ICN two-step caching method based on a community, which mainly includes the following steps:
firstly, an SDN controller identifies a community structure in an ICN based on an information description length compression technology, and community division is carried out on the ICN;
secondly, calculating the importance of the node community of each node;
thirdly, the SDN controller collects state information of nodes in each community based on an openflow protocol, wherein the state information comprises residual storage space, storage capacity, node community importance, content popularity and the like;
fourthly, calculating one-step cache priority of the nodes of each community;
fifthly, the user initiates an interest request and requests interested data content from the network;
sixthly, the ICN switch is responsible for routing and searching the interest packet data of the user;
seventhly, calculating new caching information by the SDN controller according to the recalculated popularity, making a two-step caching strategy, and issuing the two-step caching strategy to the ICN switch;
and eighthly, executing a two-step caching strategy by each node according to a rule issued by the SDN controller.
In the sixth step, when the content object is requested by a node in the network for the first time, the SDN controller issues a flow table, the content object is led to the node with the highest caching priority of each community in one step, and the content is cached by the designated node. And judging whether the one-step cache is overtime or not in the process of guiding the content objects to the one-step cache of each community, and if not, continuing to wait for overtime. And in the process that the content objects are guided to the one-step cache of each community, when the temporary storage time reaches a given period T, the SDN controller recalculates the global popularity and the local popularity of each temporary storage content, and calculates the two-step cache position of each content object according to the global popularity and the local popularity so as to realize rationalization of the spatial distribution of the cache content.
In the first step, a community division problem of the ICN is solved by adopting an information description length compression technology. The method comprises the following steps of taking routers/switches as nodes, taking physical connection between the routers/switches as edges to construct a complex network, taking a network modularity formula (1) as an objective function, and dividing the network into different communities by an optimization algorithm:
wherein N iscRepresenting the number of communities in the network, M representing the total number of connections in the network, McRepresenting the number of connections between nodes within a community c, dcRepresenting the sum of the degrees of all nodes in the community c.
In the second step, the importance of the node community refers to the importance of the node in the community where the node is located. It is defined as follows:
where c is the number of communities in the network, viI-th eigenvector, v, representing an adjacency matrix constructed with routers in the network as nodes and physical links between the routers as edgesikRepresenting a feature vector viThe kth element in (1).
The fourthIn step, at the initial stage of content object generation, its popularity (including global popularity and local popularity) is difficult to calculate and inaccurate. Therefore, the invention provides a two-step caching mechanism to solve the problem of inaccurate derivation of popularity calculation. Firstly, calculating the priority of a one-step cache content object according to the state information (such as cache capacity, utilization rate, node community importance and the like) of nodes in a community, and temporarily caching the content object in the node with the highest one-step cache priority in the community when the content object is produced and requested by the nodes in the network; secondly, when the content object temporarily exists in the community for a given time period T, the SDN controller calculates the global popularity and the local popularity according to the request condition of the whole network and each community node for the content object, and recalculates the two-step cache position of the content object according to the global popularity and the local popularity. The two-step cache is added, so that the distribution of the content objects in the one-step cache in the cache position and time tends to be more reasonable. Primary cache priority S of node kkIs defined as:
in terms of global popularity, in a certain time period, counting the number of times that the content c is requested by the user, wherein popu (c) represents the access frequency to the content c in the current counting period, and r (c) represents the number of times that the content c is accessed in the current counting period, the popularity of the content c is calculated as follows:
in the aspect of local popularity, aiming at the problem that the local popularity of ICN content is difficult to determine, the invention defines the local popularity of the content in a community structure and provides an ICN local content popularity determination method based on communities. The local popularity can reflect the user interest in the community better, and cache content is replaced according to the local popularity, so that the space-time distribution of the cache content of nodes in the community tends to be reasonable. In a certain time period, the statistical content c is requested by the user in a community iThe number of times of calculation is determined by Popui(c) Representing the frequency of access to content c in the current statistical period, by Ri(c) Representing the number of accesses to the content c in this period, the popularity of the content c is calculated as follows:
the invention provides an ICN (information center network) two-step caching mechanism based on network community characteristics in an SDN (software defined network) environment. The ICN achieves the purpose of reducing the transmission delay of other users for requesting the data by caching the content object in the nodes of the network in the data transmission process, however, the existing cache node selection mechanism has the defects of homogenization, invalid cache and the like. In order to alleviate the above problems and better exert the advantages of the ICN caching mechanism, the present invention provides a method for selecting a reasonable node cache content object according to the community characteristics of the ICN by analyzing the community structure of the ICN network, which not only improves the diversification of cache contents in the network, but also reduces the probability of invalid cache, specifically comprising: firstly, analyzing the community structure characteristics of the ICN based on the compression technology of the information description length, and analyzing the importance degree of nodes in the community to the community; and secondly, the content objects are reasonably cached on the best node in each community based on the global popularity and the local popularity of the content objects through a two-step caching mechanism. The invention provides an effective way for further optimization of an ICN cache mechanism.
The invention has been described in detail, but it is apparent that variations and modifications can be effected by one skilled in the art without departing from the scope of the invention as defined by the appended claims.
Claims (3)
1. An ICN two-step caching method based on communities is characterized by mainly comprising the following steps of:
firstly, an SDN controller identifies a community structure in an ICN based on an information description length compression technology, and community division is carried out on the ICN;
secondly, calculating the importance of the node community of each node;
thirdly, the SDN controller collects state information of nodes in each community based on an openflow protocol;
fourthly, calculating one-step cache priority of the nodes of each community;
fifthly, the user initiates an interest request and requests interested data content from the network;
sixthly, the ICN switch is responsible for routing and searching the interest packet data of the user;
seventhly, calculating new caching information by the SDN controller, making a two-step caching strategy, and issuing the two-step caching strategy to the ICN switch;
eighthly, each node executes a two-step caching strategy according to a rule issued by the SDN controller;
in the sixth step, when a content object is requested by a node in a network for the first time, the SDN controller issues a flow table, the content object is guided to the node with the highest caching priority of each community in one step, and the content is cached by a designated node; and in the process that the content objects are guided to the one-step cache of each community, when the temporary storage time reaches a given period T, the SDN controller recalculates the global popularity and the local popularity of each temporary storage content, and calculates the two-step cache position of each content object according to the global popularity and the local popularity so as to realize rationalization of the spatial distribution of the cache content.
2. The two-step ICN caching method based on communities according to claim 1, wherein the status information in the third step comprises remaining storage space, storage capacity, node community importance and content popularity.
3. The method as claimed in claim 1, wherein the content objects are diverted to the community one-step caches to determine whether the one-step cache is overtime, and if not, the method continues to wait for the overtime.
Priority Applications (1)
| Application Number | Priority Date | Filing Date | Title |
|---|---|---|---|
| CN201611094420.6A CN106790421B (en) | 2016-12-01 | 2016-12-01 | ICN two-step caching method based on community |
Applications Claiming Priority (1)
| Application Number | Priority Date | Filing Date | Title |
|---|---|---|---|
| CN201611094420.6A CN106790421B (en) | 2016-12-01 | 2016-12-01 | ICN two-step caching method based on community |
Publications (2)
| Publication Number | Publication Date |
|---|---|
| CN106790421A CN106790421A (en) | 2017-05-31 |
| CN106790421B true CN106790421B (en) | 2020-11-24 |
Family
ID=58884343
Family Applications (1)
| Application Number | Title | Priority Date | Filing Date |
|---|---|---|---|
| CN201611094420.6A Active CN106790421B (en) | 2016-12-01 | 2016-12-01 | ICN two-step caching method based on community |
Country Status (1)
| Country | Link |
|---|---|
| CN (1) | CN106790421B (en) |
Families Citing this family (2)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN108183938A (en) * | 2017-12-20 | 2018-06-19 | 广东技术师范学院 | A kind of ICN caching methods and system based on correlation network fragment |
| CN108173965A (en) * | 2018-01-22 | 2018-06-15 | 广东技术师范学院 | The ICN caching methods that corporations perceive |
Citations (8)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN103581019A (en) * | 2013-10-10 | 2014-02-12 | 北京交通大学 | Information center network mobility management method based on content popularity |
| CN103634231A (en) * | 2013-12-02 | 2014-03-12 | 江苏大学 | Content popularity-based CCN cache partition and substitution method |
| CN103905545A (en) * | 2014-03-22 | 2014-07-02 | 哈尔滨工程大学 | Reinforced LRU cache replacement method in content-centric network |
| CN103905538A (en) * | 2014-03-22 | 2014-07-02 | 哈尔滨工程大学 | Neighbor cooperation cache replacement method in content center network |
| CN103905539A (en) * | 2014-03-22 | 2014-07-02 | 哈尔滨工程大学 | Optimal cache storing method based on popularity of content in content center network |
| CN104821961A (en) * | 2015-04-16 | 2015-08-05 | 广东技术师范学院 | ICN cache strategy based on node community importance |
| CN105635319A (en) * | 2016-03-03 | 2016-06-01 | 北京邮电大学 | Data caching method and device |
| CN105791397A (en) * | 2016-02-26 | 2016-07-20 | 广东技术师范学院 | Caching method of ICN (Information-Centric Networking) based on SDN |
Family Cites Families (2)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN103905332B (en) * | 2012-12-31 | 2017-06-09 | 华为技术有限公司 | A kind of method and apparatus for determining cache policy |
| US20150006621A1 (en) * | 2013-07-01 | 2015-01-01 | Futurewei Technologies, Inc. | Adaptive Video Streaming for Information Centric Networks |
-
2016
- 2016-12-01 CN CN201611094420.6A patent/CN106790421B/en active Active
Patent Citations (8)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN103581019A (en) * | 2013-10-10 | 2014-02-12 | 北京交通大学 | Information center network mobility management method based on content popularity |
| CN103634231A (en) * | 2013-12-02 | 2014-03-12 | 江苏大学 | Content popularity-based CCN cache partition and substitution method |
| CN103905545A (en) * | 2014-03-22 | 2014-07-02 | 哈尔滨工程大学 | Reinforced LRU cache replacement method in content-centric network |
| CN103905538A (en) * | 2014-03-22 | 2014-07-02 | 哈尔滨工程大学 | Neighbor cooperation cache replacement method in content center network |
| CN103905539A (en) * | 2014-03-22 | 2014-07-02 | 哈尔滨工程大学 | Optimal cache storing method based on popularity of content in content center network |
| CN104821961A (en) * | 2015-04-16 | 2015-08-05 | 广东技术师范学院 | ICN cache strategy based on node community importance |
| CN105791397A (en) * | 2016-02-26 | 2016-07-20 | 广东技术师范学院 | Caching method of ICN (Information-Centric Networking) based on SDN |
| CN105635319A (en) * | 2016-03-03 | 2016-06-01 | 北京邮电大学 | Data caching method and device |
Also Published As
| Publication number | Publication date |
|---|---|
| CN106790421A (en) | 2017-05-31 |
Similar Documents
| Publication | Publication Date | Title |
|---|---|---|
| CN104717304B (en) | A kind of CDN P2P content optimizations select system | |
| CN106982248B (en) | caching method and device for content-centric network | |
| CN108366089B (en) | CCN caching method based on content popularity and node importance | |
| Dutta et al. | Caching scheme for information‐centric networks with balanced content distribution | |
| CN106533733B (en) | The CCN collaboration caching method and device routed based on network cluster dividing and Hash | |
| CN111107000B (en) | Content caching method in named data network based on network coding | |
| CN102647357A (en) | Context routing processing method and context routing processing device | |
| CN105656788B (en) | CCN content buffering method based on popularity statistics | |
| Wu et al. | MBP: A max-benefit probability-based caching strategy in information-centric networking | |
| CN108965479B (en) | Domain collaborative caching method and device based on content-centric network | |
| CN108900599B (en) | Software-defined content-centric network device and cluster cache decision method thereof | |
| CN106790421B (en) | ICN two-step caching method based on community | |
| CN108769252A (en) | A kind of ICN network pre-cache methods based on request content relevance | |
| Ben-Ammar et al. | On the performance analysis of distributed caching systems using a customizable Markov chain model | |
| Xiaoqiang et al. | An in-network caching scheme based on betweenness and content popularity prediction in content-centric networking | |
| Yang et al. | A reinforcement learning based data storage and traffic management in information-centric data center networks | |
| Li et al. | Efficient cooperative cache management for latency-aware data intelligent processing in edge environment | |
| Kottursamy et al. | Optimized D-RAN aware data retrieval for 5G information centric networks | |
| Amemiya et al. | Layer-integrated edge distributed data store for real-time and stateful services | |
| CN108809829B (en) | SDN rule deployment method | |
| Cao et al. | Family-aware pricing strategy for accelerating video dissemination over information-centric vehicular networks | |
| CN107302571B (en) | The routing of information centre's network and buffer memory management method based on drosophila algorithm | |
| Shen et al. | Coordinated en-route web caching in multiserver networks | |
| CN110012071B (en) | Caching method and device for Internet of things | |
| Zhang et al. | Degree-based probabilistic caching in content-centric networking |
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 | ||
| CB02 | Change of applicant information |
Address after: 293 No. 510665 Guangdong city of Guangzhou province Tianhe District Zhongshan Shipai Road Applicant after: GUANGDONG POLYTECHNIC NORMAL University Address before: 293 No. 510665 Guangdong city of Guangzhou province Tianhe District Zhongshan Shipai Road Applicant before: GUANGDONG POLYTECHNIC NORMAL University |
|
| CB02 | Change of applicant information | ||
| GR01 | Patent grant | ||
| GR01 | Patent grant |