CN107864092B - Cloud content distribution method and device based on multicast technology - Google Patents
Cloud content distribution method and device based on multicast technology Download PDFInfo
- Publication number
- CN107864092B CN107864092B CN201711049341.8A CN201711049341A CN107864092B CN 107864092 B CN107864092 B CN 107864092B CN 201711049341 A CN201711049341 A CN 201711049341A CN 107864092 B CN107864092 B CN 107864092B
- Authority
- CN
- China
- Prior art keywords
- node
- nodes
- subset
- multicast group
- distribution
- Prior art date
- Legal status (The legal status is an assumption and is not a legal conclusion. Google has not performed a legal analysis and makes no representation as to the accuracy of the status listed.)
- Expired - Fee Related
Links
Images
Classifications
-
- H—ELECTRICITY
- H04—ELECTRIC COMMUNICATION TECHNIQUE
- H04L—TRANSMISSION OF DIGITAL INFORMATION, e.g. TELEGRAPHIC COMMUNICATION
- H04L45/00—Routing or path finding of packets in data switching networks
- H04L45/16—Multipoint routing
-
- H—ELECTRICITY
- H04—ELECTRIC COMMUNICATION TECHNIQUE
- H04L—TRANSMISSION OF DIGITAL INFORMATION, e.g. TELEGRAPHIC COMMUNICATION
- H04L12/00—Data switching networks
- H04L12/02—Details
- H04L12/16—Arrangements for providing special services to substations
- H04L12/18—Arrangements for providing special services to substations for broadcast or conference, e.g. multicast
- H04L12/1845—Arrangements for providing special services to substations for broadcast or conference, e.g. multicast broadcast or multicast in a specific location, e.g. geocast
-
- H—ELECTRICITY
- H04—ELECTRIC COMMUNICATION TECHNIQUE
- H04L—TRANSMISSION OF DIGITAL INFORMATION, e.g. TELEGRAPHIC COMMUNICATION
- H04L12/00—Data switching networks
- H04L12/02—Details
- H04L12/16—Arrangements for providing special services to substations
- H04L12/18—Arrangements for providing special services to substations for broadcast or conference, e.g. multicast
- H04L12/185—Arrangements for providing special services to substations for broadcast or conference, e.g. multicast with management of multicast group membership
-
- H—ELECTRICITY
- H04—ELECTRIC COMMUNICATION TECHNIQUE
- H04L—TRANSMISSION OF DIGITAL INFORMATION, e.g. TELEGRAPHIC COMMUNICATION
- H04L45/00—Routing or path finding of packets in data switching networks
- H04L45/18—Loop-free operations
-
- H—ELECTRICITY
- H04—ELECTRIC COMMUNICATION TECHNIQUE
- H04L—TRANSMISSION OF DIGITAL INFORMATION, e.g. TELEGRAPHIC COMMUNICATION
- H04L45/00—Routing or path finding of packets in data switching networks
- H04L45/30—Routing of multiclass traffic
-
- 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
- H04L67/01—Protocols
- H04L67/10—Protocols in which an application is distributed across nodes in the network
Landscapes
- Engineering & Computer Science (AREA)
- Computer Networks & Wireless Communication (AREA)
- Signal Processing (AREA)
- Data Exchanges In Wide-Area Networks (AREA)
Abstract
The invention relates to a cloud content distribution method and a device based on a multicast technology, wherein the method comprises the following steps: receiving nodes of a cloud site, establishing a node set, dividing the node set into a plurality of subsets, and expressing the nodes by adopting coordinates; determining a key node of each subset by using a shortest Euclidean distance method according to the average coordinate of each subset; taking a source server node in a cloud station as a multicast group leader node, and taking a key node as a multicast group member node; and the multicast group leader node sends a broadcast message to the member nodes, and the member nodes determine the distribution path of the cloud content according to the broadcast message and transmit the cloud content according to the distribution path.
Description
Technical Field
The invention relates to the field of cloud content distribution networks, in particular to a cloud content distribution method and device based on a multicast technology.
Background
The cloud content distribution network distributes the source station content to all nodes in the country, so that the delay of a user for checking an object can be effectively shortened, the response speed of the user for accessing the website and the usability of the website are improved, and the problems of small network bandwidth, large user access amount, uneven website distribution and the like are solved. At present, although a cloud content distribution network is used for distributing data content, compared with a traditional content distribution network, a large amount of operation cost can be saved, the problems of high content distribution cost, high distribution energy consumption, poor user service quality and the like are more and more serious with the continuous development of the cloud storage content distribution network, and the traditional content distribution energy consumption optimization strategy cannot adapt to cloud storage distribution, so that the search for an energy consumption optimization distribution method becomes a hotspot.
Disclosure of Invention
Aiming at the defects in the prior art, the invention provides a cloud content distribution method based on a multicast technology, which enables the cloud content distribution to cover the whole network as far as possible through a key node selection strategy with the shortest distance, and saves the cloud content copy distribution cost by combining a multicast routing strategy with the cloud content with the minimized distribution cost.
The technical scheme of the invention is as follows:
a cloud content distribution method based on multicast technology comprises the following steps:
receiving nodes of a cloud site, establishing a node set, dividing the node set into a plurality of subsets, and expressing the nodes by adopting coordinates;
determining a key node of each subset by using a shortest Euclidean distance method according to the average coordinate of each subset;
taking a source server node in a cloud station as a multicast group leader node, and taking a key node as a multicast group member node;
and the multicast group leader node sends a broadcast message to the member nodes, and the member nodes determine the distribution path of the cloud content according to the broadcast message and transmit the cloud content according to the distribution path.
Further, the partitioning of the set of nodes into subsets comprises:
and determining the number of groups by adopting a K-Canopy method, and dividing the node set into a plurality of subsets according to the number of the groups.
Further, determining the number of packets in the node set by using a K-Canopy method includes:
(31) initializing threshold T1,T2Wherein T is2Centralizing all nodes for a nodeAverage distance of (1), T1Is twice T2Initializing k to 0;
(32) if the node set is not empty, randomly selecting a node r from the node set0As a center, and adding 1 to the value of k;
(33) computing the remaining nodes in the node set to r0If d is less than T2Then the node is assigned to r0A subset which is central, and the node is deleted from the node set; if d is greater than T2Less than T1Then the node is assigned to r0A centered subset; if d is greater than T1No operation is performed;
(34) and (4) repeating the steps (31) to (33) until the node set is empty, and obtaining the grouping number k.
Further, the determining, by the member node, the distribution path of the cloud content according to the broadcast message includes: the member nodes receiving the broadcast message are activated, and a distribution path is established between the activated member nodes to minimize distribution energy consumption.
Further, the establishing of the distribution path for minimizing distribution energy consumption includes:
the activated member node is used as a sending node, and sends request information to other member nodes to request to establish connection with the other member nodes;
the member node receiving the request message judges whether the member node is the optimal node, if the member node is the optimal node, the member node replies the request message to the sending node according to the reverse route;
and when the number of the replies received by the sending node is more than or equal to 1, establishing a unique path between the sending node and the member node closest to the sending node, and traversing each member node to form a distribution path.
Further, the selecting of the optimal node includes: comparing whether the distance from the node to the multicast group leader node is smaller than the distance from the sending node to the multicast group leader node, if not, judging the node to be a non-optimal node; if yes, checking whether the sending node receives the request information sent by the same sending node, if not, judging the sending node to be the optimal node, if so, comparing the historical request information, selecting the sending node with the shortest path length and the smallest hop number, and replying the request information to the sending node according to a reverse route.
Further, traversing each member node comprises: and determining a previous hop node and a next hop node of the unique path, and sending the path to the next hop node.
Further, adding a relay node to the distribution path, and deleting a loop if the relay node and the distribution path form the loop.
The invention also provides a storage device, which stores a plurality of instructions, wherein the instructions are loaded by a processor and execute the following processing:
receiving nodes of a cloud site, establishing a node set, dividing the node set into a plurality of subsets, and expressing the nodes by adopting coordinates;
determining a key node of each subset by using a shortest Euclidean distance method according to the average coordinate of each subset;
taking a source server node in a cloud station as a multicast group leader node, and taking a key node as a multicast group member node;
and the multicast group leader node sends a broadcast message to the member nodes, and the member nodes determine the distribution path of the cloud content according to the broadcast message and transmit the cloud content according to the distribution path.
The invention also provides a cloud content distribution device based on the multicast technology on the basis of the storage device, which comprises a processor and a storage unit, wherein the processor is used for realizing each instruction; and storage means for storing a plurality of instructions, the instructions being loaded by the processor and performing the following:
receiving nodes of a cloud site, establishing a node set, dividing the node set into a plurality of subsets, and expressing the nodes by adopting coordinates;
determining a key node of each subset by using a shortest Euclidean distance method according to the average coordinate of each subset;
taking a source server node in a cloud station as a multicast group leader node, and taking a key node as a multicast group member node;
and the multicast group leader node sends a broadcast message to the member nodes, and the member nodes determine the distribution path of the cloud content according to the broadcast message and transmit the cloud content according to the distribution path.
The invention has the beneficial effects that:
according to the method and the system, the copy distribution of the cloud content covers the whole network as far as possible through the key node selection strategy based on the shortest distance, and the copy distribution cost is saved by placing the multicast routing strategy through the copy with the minimized distribution cost. According to the method, a distribution tree connecting all key nodes is constructed, the copy content is only distributed along the distribution tree, and compared with the existing cloud content distribution network, the method can effectively reduce the message complexity of the system, reduce the energy consumption and improve the service quality of users.
Drawings
FIG. 1 is a flow chart of the method of the present invention.
The specific implementation mode is as follows:
the invention will be further illustrated with reference to the following examples and drawings:
it should be noted that the following detailed description is exemplary and is intended to provide further explanation of the disclosure. Unless defined otherwise, all technical and scientific terms used herein have the same meaning as commonly understood by one of ordinary skill in the art to which this application belongs.
It is noted that the terminology used herein is for the purpose of describing particular embodiments only and is not intended to be limiting of example embodiments according to the present application. As used herein, the singular forms "a", "an" and "the" are intended to include the plural forms as well, and it should be understood that when the terms "comprises" and/or "comprising" are used in this specification, they specify the presence of stated features, steps, operations, devices, components, and/or combinations thereof, unless the context clearly indicates otherwise.
An exemplary embodiment of the invention is:
as shown in fig. 1, in the embodiment of the present invention, a coordinate set R of all cloud sites in a cloud content distribution network is first input, and then the number of groups is determined by a K-Canopy algorithmMeasuring the number K, then dividing the whole network into K subsets by utilizing K-Means clustering, and also forming clusters, selecting a key node, namely a key node, for each cluster by using a key node selection algorithm based on the shortest distance, wherein M (M) is used0,M1,M2,...,Mk) Representing all first joints as a set of nodes.
The method for determining the number of the packets in the embodiment comprises the following steps:
first, a threshold value T is initialized1,T2Wherein T is2Is the average distance, T, of all nodes in the set1Is twice T2Initializing k to 0;
then if the node set is not empty, randomly selecting a node r from the node set0As a center, and adding 1 to the value of k;
then calculating the remaining nodes in the node set to r0If d is less than T2Then the node is assigned to r0A subset which is central, and the node is deleted from the node set; if d is greater than T2Less than T1Then the node is assigned to r0A centered subset; if d is greater than T1No operation is performed;
and finally, repeating the steps until the node set is empty to obtain the number k of the groups.
After the grouping number is determined, the node set is divided into a plurality of subsets according to the grouping number, the average coordinate value of each subset is calculated, and the node closest to the Euclidean distance of the average coordinate is found to be used as the key node of each subset, namely the key node. Wherein M is0Representing source server nodes, M1,M2,...,MkRepresenting selected key nodes
After determining the key nodes, placing a multicast routing strategy according to the cloud content copy with the minimized distribution cost to establish a distribution tree connecting all the key nodes, in the process, selecting a source server node as a group leader node of the distribution tree, selecting the selected key nodes as multicast member nodes, and establishing a distribution tree connecting all the multicast member nodes and allowing the relay nodes to join in a mode of establishing a connection to the nearest neighbor member node for each member node.
We will now mainly describe the specific process of building a distribution tree connecting all multicast member nodes by multicast routing.
Step 1: the source server node is used as a multicast group leader node, and the selected key node is used as a multicast group member node. The group leader node sends a broadcast message to wake up all member nodes.
The format of the broadcast message in this process is: group leader node address, target node address #1, target node address #2.
If the node receiving the message is a member node, each member node has a unique multicast routing table, and after receiving the broadcast information, the multicast routing table of the node is updated, the group address is set as the group address of the multicast group, and the group length address of the multicast group is set as the group length address of the multicast group. If not, the message is forwarded continuously until all multicast group member nodes are activated.
The multicast routing table contains the following information: multicast group ID, multicast group Long Address, destination node Address, Next hop Address
Step 2: each multicast group member node takes itself as a sending node, and sends RREQ _ JOIN request information, or can be a request message.
The format of the RREQ _ JOIN message is as follows: multicast group ID, sending node address, node sequence, path length, hop count, last hop node address.
And step 3: the member node receiving the request message judges whether the member node is the optimal node, if the member node is the optimal node, the member node replies the request message to the sending node according to the reverse route;
the judgment of the optimal node adopts the following method: updating the path length of the message to be the path length plus the path length from one hop to the current node; adding 1 to the hop count; adding the self into the node sequence and continuously forwarding the message; checking a multicast routing table of the node to see whether the node is a member node of a multicast group which the sending node wants to JOIN, namely whether the multicast group ID of the node is the same as the group ID of the sending node, if so, comparing whether the distance from the node to a source node is smaller than the distance from the sending node to the source node, if so, checking whether the node receives a RREQJOIN message sent by the same sending node, if so, comparing the path lengths of the node and the source node and the hop count reaching the sending node, selecting the RREQJOIN with the shortest path length and the smallest hop count, and if the node is selected to be optimal, sending the RREQJOIN to the sending node according to reverse routing information carried when the RREQJOIN sends the RREQ JOIN.
The format of the RREP _ J message is as follows: multicast group ID, sending node address, responding node address, node sequence, path length, hop count.
While the RREP _ J propagates along the reverse path, the along-route node adds the path information of the node to the multicast group in its unicast routing table, wherein the source node address fills the node's own address, and the destination node address fills the sending node address that sends the RREQ _ JOIN.
The unicast routing table contains the following information: source node address, destination node address, previous hop address, next hop address
And 4, step 4: after broadcasting the RREQ _ JOIN for a period of time, the sending node waits for the RREP _ J, and if the RREP _ J with the quantity greater than 1 is received, the sending node needs to perform a preference process to select the RREP _ J sent by the multicast group member node closest to the sending node. In this process, if no member node is closer to the source node than the sending node, the sending node establishes a link directly with the source node.
And 5: after the preference process is completed, the sending node has already selected a path to reach the multicast group. Then the sending node sends MACT _ Confirm message to the multicast member node nearest to itself according to reverse route, the multicast member node receiving the message sends MACT route activation information, activates a path from the member node to the sending node, adds the destination node address in the multicast route table as the address of the sending node, the next hop address as the address of the next hop node reaching the sending node, and receives MACT messageThe neighbor node adds a column of information in the unicast routing table<Mj1，Mj2，PHj，NHj>，Mj1,Mj2Respectively representing the address of the member node sending the MACT message and the address, PH, of the member node needing to receive the MACT messagej，NHjRespectively representing the previous hop and the next hop of the current node to reach the destination node.
The format of the MACT _ Confirm message is as follows: source node address, destination node address, node sequence
The format of the MACT message is: source node address, destination node address, node sequence
Further, for one relay node u, if u is a relay shared by a plurality of pairs of member nodes, a loop may be generated, and in this embodiment, canceling the loop by sending a MACT _ elimate message specifically includes:
if the relay node u is a relay that is common to multiple sets of receiving nodes, it will likely create a loop, and this process checks for the presence of such a loop and cancels the loop.
If the relay node u is a relay of k sets of receiving node pairs, these node pairs are denoted as (M)11,M12)，(M21，M22)，...，(Mk1，Mk2) We assume Mi1Is than Mi2(i is more than or equal to 1 and less than or equal to k) multicast group member nodes which are closer to the source node, and the relay node records the slave Mi1To Mi2Its previous and next hops in the path of (1), respectively using the PHiAnd NHiAnd (4) showing. Randomly selecting a set of receiving node pairs (M)j1,Mj2) Holding information (M)j1，Mj2，PHj，NHj) Unchanged for other (M)i1，Mi2) To when M isi1≠Mj1The relay node u modifies the information of the unicast routing table into (M)j1，Mi2，PHj，NHi) That is, the source node is modified to be the source node of the reserved path, and the previous hop is modified to be the previous hop of the relay node in the reserved path. Finally, sending MACT _ Eliminate message<Mi1，Mi2,PHi>。
If the node w receiving the MACT _ Eliminate message is the last hop node PHiAnd the node is not a multicast member node, the following operations are carried out: modifying PH of MACT _ Elimate messageiIs from Mi1To Mi2The last hop of the w node on the path; continuously sending the MACT _ Eliminate message to the last hop; deleting routing information of w node in unicast routing table<Mi1,Mi2,PHi,NHi>. This operation was repeated until pHiIs multicast to the member nodes, thus eliminating redundant paths.
The format of the MACT _ Elimate message is: source node address destination node address last hop address
Therefore, a distribution tree connecting all multicast member nodes, namely a distribution path is established, and cloud content is transmitted along the distribution path, which is beneficial to reducing energy consumption.
Finally, we introduce the energy consumption of the EEDM model proposed herein, and compare it with the energy consumption of copy distribution using broadcasting. The specific process is as follows:
1. and calculating the energy consumption of the EEDM model.
The first step is as follows: and determining an energy consumption calculation formula of the EEDM model.
The energy consumption of data distribution in the EEDM model is mainly determined by the length of the distribution tree and the number of messages exchanged when the distribution tree is constructed, and the energy consumption cost is directly proportional to the length of the distribution tree and the number of messages exchanged. We establish an energy consumption formula for CCDN data distribution, expressed as:
P＝T×(La+mb) (1)
where P represents the total energy consumption in J resulting from the distribution of a unit of data; t is the number of transmitted data packets; l is the total length of the constructed distribution tree; m is the total amount of information exchanged during the data distribution process; a and b are power consumption parameters representing the energy consumption required to transmit a unit length of data and exchange a piece of information, respectively.
The second step is that: setting a parameter value.
Let us assume that the nodes are distributed in a 100 x 100 square areaSetting the current distribution task as T-103And each data packet has the size of 20k, and a is set to be 50 nJ/bit.
The third step: and (5) a specific calculation process.
Firstly, the formula (1) is simplified according to the determined parameter values, and the parameter values are substituted into the formula to obtain:
P＝T×(La+mb)＝20×103×103×(L+m)×50×10-9＝(L+m)
when the nodes obey normal distribution and the clustering algorithm adopts K-Means, taking the current network size of 500 as an example, the total length of the obtained distribution tree is 283, the total quantity of the obtained exchange information is 806, and the total energy consumption is 1089J at the moment.
2. Energy consumption for copy distribution using broadcasting is calculated.
The first step is as follows: and determining an energy consumption calculation formula.
When the broadcast is used for copy distribution, a source node and a destination node are known, and the source node sends a broadcast message and sends data to all the destination nodes. The length of a distribution tree for data distribution in a broadcast mode is the length of a path from a source node to all destination nodes, and the quantity of exchange messages is the quantity of all node broadcast messages from the source node to all the destination nodes. We still use equation (1) as the energy consumption calculation equation.
The second step is that: setting a parameter value.
Let us assume that nodes are distributed in a 100 × 100 square area, and set the current distribution task to T-103And each data packet has the size of 20k, and a is set to be 50 nJ/bit.
The third step: and (5) a specific calculation process.
When the nodes obey normal distribution and the clustering algorithm adopts K-Means, taking the current network size of 500 as an example, the total length of the obtained distribution tree is 860, the total amount of the obtained exchange information is 2960, and the total energy consumption is 3820J at the moment.
3. When the nodes are subjected to normal distribution and the clustering algorithm adopts K-Means, taking the network size of 500 as an example, the energy consumption obtained by the EEDM model and the data distribution by broadcasting is 1089 and 3820 respectively. It is clear that the energy consumption for data distribution using the EEDM model is much lower.
The above description is only a preferred embodiment of the present application and is not intended to limit the present application, and various modifications and changes may be made by those skilled in the art. Any modification, equivalent replacement, improvement and the like made within the spirit and principle of the present application shall be included in the protection scope of the present application.
Claims (7)
1. A cloud content distribution method based on multicast technology is characterized by comprising the following steps:
receiving nodes of a cloud site, establishing a node set, dividing the node set into a plurality of subsets, and expressing the nodes by adopting coordinates;
dividing the set of nodes into subsets comprises: determining the grouping number by adopting a K-Canopy method, and dividing the coordinate set into a plurality of subsets according to the grouping number;
the method for determining the number of the packets by adopting the K-Canopy method comprises the following steps:
(31) initializing threshold T1,T2Wherein T is2Is the average distance, T, of all nodes in the set1Is twice T2Initializing k to 0;
(32) if the node set is not empty, randomly selecting a node r from the node set0As a center, and adding 1 to the value of k;
(33) computing the remaining nodes in the node set to r0If d is less than T2Then the node is assigned to r0A subset which is central, and the node is deleted from the node set; if d is greater than T2Less than T1Then the node is assigned to r0A centered subset; if d is greater than T1No operation is performed;
(34) repeating the steps (31) - (33) until the node set is empty, and obtaining a grouping number k;
determining a key node of each subset by using a shortest Euclidean distance method according to the average coordinate of each subset;
taking a source server node in a cloud station as a multicast group leader node, and taking a key node as a multicast group member node;
and the multicast group leader node sends a broadcast message to the member nodes, and the member nodes determine the distribution path of the cloud content according to the broadcast message and transmit the cloud content according to the distribution path.
2. The method of claim 1, wherein determining, by a member node, a distribution path of cloud content from the broadcast message comprises: the member nodes receiving the broadcast message are activated, a distribution path aiming at minimizing distribution energy consumption is established among the activated member nodes, and the establishment of the distribution path aiming at minimizing the distribution energy consumption comprises the following steps:
the activated member node is used as a sending node, and sends request information to other member nodes to request to establish connection with the other member nodes;
the member node receiving the request message judges whether the member node is the optimal node, if the member node is the optimal node, the member node replies the request message to the sending node according to the reverse route;
and when the number of the replies received by the sending node is more than or equal to 1, establishing a unique path between the sending node and the member node closest to the sending node, and traversing each member node to form a distribution path.
3. The method of claim 2, wherein the selection of the optimal node comprises: comparing whether the distance from the node to the multicast group leader node is smaller than the distance from the sending node to the multicast group leader node, if not, judging the node to be a non-optimal node; if yes, checking whether the sending node receives the request information sent by the same sending node, if not, judging the sending node to be the optimal node, if so, comparing the historical request information, selecting the sending node with the shortest path length and the smallest hop number, and replying the request information to the sending node according to a reverse route.
4. The method of claim 2, wherein traversing each member node comprises: and determining a previous hop node and a next hop node of the unique path, and sending the path to the next hop node.
5. The method of claim 2, further comprising adding a relay node to the distribution path and removing a loop if the relay node forms a loop with the distribution path.
6. A memory device storing a plurality of instructions, the instructions being loaded by a processor and performing the following:
receiving nodes of a cloud site, establishing a node set, dividing the node set into a plurality of subsets, and expressing the nodes by adopting coordinates; dividing the set of nodes into subsets comprises: determining the grouping number by adopting a K-Canopy method, and dividing the coordinate set into a plurality of subsets according to the grouping number;
the method for determining the number of the packets by adopting the K-Canopy method comprises the following steps:
(31) initializing threshold T1,T2Wherein T is2Is the average distance, T, of all nodes in the set1Is twice T2Initializing k to 0;
(32) if the node set is not empty, randomly selecting a node r from the node set0As a center, and adding 1 to the value of k;
(33) computing the remaining nodes in the node set to r0If d is less than T2Then the node is assigned to r0A subset which is central, and the node is deleted from the node set; if d is greater than T2Less than T1Then the node is assigned to r0A centered subset; if d is greater than T1No operation is performed;
(34) repeating the steps (31) - (33) until the node set is empty, and obtaining a grouping number k;
determining a key node of each subset by using a shortest Euclidean distance method according to the average coordinate of each subset;
taking a source server node in a cloud station as a multicast group leader node, and taking a key node as a multicast group member node;
and the multicast group leader node sends a broadcast message to the member nodes, and the member nodes determine the distribution path of the cloud content according to the broadcast message and transmit the cloud content according to the distribution path.
7. A cloud content distribution device based on multicast technology comprises a processor, a server and a server, wherein the processor is used for realizing instructions; and storage means for storing a plurality of instructions, wherein the instructions are loaded by the processor and perform the following:
receiving nodes of a cloud site, establishing a node set, dividing the node set into a plurality of subsets, and expressing the nodes by adopting coordinates; dividing the set of nodes into subsets comprises: determining the grouping number by adopting a K-Canopy method, and dividing the coordinate set into a plurality of subsets according to the grouping number;
the method for determining the number of the packets by adopting the K-Canopy method comprises the following steps:
(31) initializing threshold T1,T2Wherein T is2Is the average distance, T, of all nodes in the set1Is twice T2Initializing k to 0;
(32) if the node set is not empty, randomly selecting a node r from the node set0As a center, and adding 1 to the value of k;
(33) computing the remaining nodes in the node set to r0If d is less than T2Then the node is assigned to r0A subset which is central, and the node is deleted from the node set; if d is greater than T2Less than T1Then the node is assigned to r0A centered subset; if d is greater than T1No operation is performed;
(34) repeating the steps (31) - (33) until the node set is empty, and obtaining a grouping number k;
determining a key node of each subset by using a shortest Euclidean distance method according to the average coordinate of each subset;
taking a source server node in a cloud station as a multicast group leader node, and taking a key node as a multicast group member node;
and the multicast group leader node sends a broadcast message to the member nodes, and the member nodes determine the distribution path of the cloud content according to the broadcast message and transmit the cloud content according to the distribution path.
Priority Applications (1)
| Application Number | Priority Date | Filing Date | Title |
|---|---|---|---|
| CN201711049341.8A CN107864092B (en) | 2017-10-31 | 2017-10-31 | Cloud content distribution method and device based on multicast technology |
Applications Claiming Priority (1)
| Application Number | Priority Date | Filing Date | Title |
|---|---|---|---|
| CN201711049341.8A CN107864092B (en) | 2017-10-31 | 2017-10-31 | Cloud content distribution method and device based on multicast technology |
Publications (2)
| Publication Number | Publication Date |
|---|---|
| CN107864092A CN107864092A (en) | 2018-03-30 |
| CN107864092B true CN107864092B (en) | 2020-03-27 |
Family
ID=61697029
Family Applications (1)
| Application Number | Title | Priority Date | Filing Date |
|---|---|---|---|
| CN201711049341.8A Expired - Fee Related CN107864092B (en) | 2017-10-31 | 2017-10-31 | Cloud content distribution method and device based on multicast technology |
Country Status (1)
| Country | Link |
|---|---|
| CN (1) | CN107864092B (en) |
Families Citing this family (4)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN109922161B (en) * | 2019-04-10 | 2021-10-19 | 山东师范大学 | Content distribution method, system, device and medium for dynamic cloud content distribution network |
| CN112218121B (en) * | 2019-07-09 | 2022-12-30 | 中国移动通信集团安徽有限公司 | Content delivery network scheduling method and device |
| CN111629037B (en) * | 2020-05-14 | 2022-05-27 | 山东师范大学 | Dynamic cloud content distribution network content placement method based on collaborative reinforcement learning |
| CN115086884B (en) * | 2022-04-22 | 2023-10-17 | 三维通信股份有限公司 | Narrow-wave multicast directional transmission method, system and readable storage medium |
Citations (7)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| JP2007036681A (en) * | 2005-07-27 | 2007-02-08 | Hitachi Communication Technologies Ltd | Multicast distribution method and system, and content server |
| JP2010148046A (en) * | 2008-12-22 | 2010-07-01 | Toshiba Corp | Distribution management apparatus and content distribution method |
| CN103179037A (en) * | 2012-12-13 | 2013-06-26 | 清华大学 | Data transmission method of content-centric datacenter network |
| CN103188278A (en) * | 2011-12-27 | 2013-07-03 | 中国电信股份有限公司 | Method and system for content data distribution |
| CN103905315A (en) * | 2012-10-22 | 2014-07-02 | 阿瓦亚公司 | Architecture for virtualization and distribution of routing information used in a transport network |
| CN106162209A (en) * | 2016-06-30 | 2016-11-23 | 中国科学院计算技术研究所 | A kind of content distributing network live broadcast system based on SDN technology and method |
| CN106330731A (en) * | 2016-09-12 | 2017-01-11 | 北京交通大学 | Wireless Ad hoc network multicast tree establishing method |
-
2017
- 2017-10-31 CN CN201711049341.8A patent/CN107864092B/en not_active Expired - Fee Related
Patent Citations (7)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| JP2007036681A (en) * | 2005-07-27 | 2007-02-08 | Hitachi Communication Technologies Ltd | Multicast distribution method and system, and content server |
| JP2010148046A (en) * | 2008-12-22 | 2010-07-01 | Toshiba Corp | Distribution management apparatus and content distribution method |
| CN103188278A (en) * | 2011-12-27 | 2013-07-03 | 中国电信股份有限公司 | Method and system for content data distribution |
| CN103905315A (en) * | 2012-10-22 | 2014-07-02 | 阿瓦亚公司 | Architecture for virtualization and distribution of routing information used in a transport network |
| CN103179037A (en) * | 2012-12-13 | 2013-06-26 | 清华大学 | Data transmission method of content-centric datacenter network |
| CN106162209A (en) * | 2016-06-30 | 2016-11-23 | 中国科学院计算技术研究所 | A kind of content distributing network live broadcast system based on SDN technology and method |
| CN106330731A (en) * | 2016-09-12 | 2017-01-11 | 北京交通大学 | Wireless Ad hoc network multicast tree establishing method |
Non-Patent Citations (2)
| Title |
|---|
| 《K-Canopy: 一种面向话题发现的快速数据切分算法》;陈强等;《山东大学学报（理学版）》;20160930;第51卷(第9期);全文 * |
| 《Multicasting versus anycasting: How to efficiently deliver content in elastic optical networks》;Machal Aibin;《2016 18th International Conference on Transparent Optical Networks》;20160731;全文 * |
Also Published As
| Publication number | Publication date |
|---|---|
| CN107864092A (en) | 2018-03-30 |
Similar Documents
| Publication | Publication Date | Title |
|---|---|---|
| CN107864092B (en) | Cloud content distribution method and device based on multicast technology | |
| US9877260B2 (en) | Data forwarding in hybrid mesh networks | |
| Prodhan et al. | TTL based routing in opportunistic networks | |
| US8824471B2 (en) | Maintained message delivery during routing domain migration | |
| CN102056263B (en) | Routing method and device as well as sensor equipment based on wireless sensor tree network | |
| JP2005065267A (en) | Method for discovering route from source node to destination node | |
| JP2007235444A (en) | Mobile terminal device, control method and mobile communication system | |
| US9979643B2 (en) | Communication apparatus, communication method, and computer-readable recording medium | |
| CN110943918B (en) | Networking method of centerless multi-channel concurrent transmission system | |
| Ahmadi et al. | A hybrid algorithm for preserving energy and delay routing in mobile ad-hoc networks | |
| CN101127714A (en) | A route management method and device for wireless mesh network | |
| WO2019119346A1 (en) | Method and network device for determining communication path | |
| CN102334313B (en) | Network location recognition system and terminal location recognition device | |
| CN106330731A (en) | Wireless Ad hoc network multicast tree establishing method | |
| CN105847150B (en) | It is a kind of wirelessly with the wired mixed logic dynamic selection method of power carrier | |
| JP2013168883A (en) | Communication device | |
| Radhakrishnan et al. | Cost effective energy efficient scheme for mobile adhoc network | |
| Jin et al. | MANET for Disaster Relief based on NDN | |
| CN105072586A (en) | Management method for forwarding of broadcast message in embedded wireless ad hoc network | |
| Sheu et al. | A distributed IP address assignment scheme in ad hoc networks | |
| Leão et al. | Latency and network lifetime trade-off in geographic multicast routing for multi-sink wireless sensor networks | |
| Gong et al. | A distributed algorithm to construct multicast trees in WSNs: An approximate steiner tree approach | |
| JP4219366B2 (en) | Method and system for constructing multipoint link interactive environment | |
| CN106992930B (en) | A kind of opportunistic network routing method based on approach frequency | |
| CN105281832B (en) | Neighbor discovering method in a kind of ultraviolet optical-fiber network |
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 | ||
| CF01 | Termination of patent right due to non-payment of annual fee | ||
| CF01 | Termination of patent right due to non-payment of annual fee |
Granted publication date: 20200327 Termination date: 20211031 |