CN102932486A - Method of dividing network structure in unstructured distributive P2P (peer-to-peer) network - Google Patents
Method of dividing network structure in unstructured distributive P2P (peer-to-peer) network Download PDFInfo
- Publication number
- CN102932486A CN102932486A CN2012104881803A CN201210488180A CN102932486A CN 102932486 A CN102932486 A CN 102932486A CN 2012104881803 A CN2012104881803 A CN 2012104881803A CN 201210488180 A CN201210488180 A CN 201210488180A CN 102932486 A CN102932486 A CN 102932486A
- Authority
- CN
- China
- Prior art keywords
- node
- network
- nodes
- inefficacy
- cur
- 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.)
- Pending
Links
- 238000000034 method Methods 0.000 title claims abstract description 50
- 230000008569 process Effects 0.000 claims abstract description 8
- 238000007781 pre-processing Methods 0.000 claims abstract description 4
- 238000012804 iterative process Methods 0.000 claims description 6
- 238000012163 sequencing technique Methods 0.000 claims description 2
- 238000013507 mapping Methods 0.000 description 4
- 230000008859 change Effects 0.000 description 3
- 238000010586 diagram Methods 0.000 description 3
- 238000013459 approach Methods 0.000 description 2
- 238000011161 development Methods 0.000 description 2
- 238000005516 engineering process Methods 0.000 description 2
- 238000012986 modification Methods 0.000 description 2
- 230000004048 modification Effects 0.000 description 2
- 238000012545 processing Methods 0.000 description 2
- 230000009471 action Effects 0.000 description 1
- 239000012141 concentrate Substances 0.000 description 1
- 238000007796 conventional method Methods 0.000 description 1
- 230000002950 deficient Effects 0.000 description 1
- 230000000694 effects Effects 0.000 description 1
- 230000003993 interaction Effects 0.000 description 1
- 238000005065 mining Methods 0.000 description 1
- 238000002203 pretreatment Methods 0.000 description 1
- 238000011160 research Methods 0.000 description 1
- 238000004088 simulation Methods 0.000 description 1
Images
Abstract
The invention discloses a method of dividing a network structure in an unstructured distributive P2P (peer-to-peer) network. The method comprises the following three steps: step 1, obtaining a P2P network topological structure, wherein the topological structure N=(V,E) consists of a plurality of nodes in the network and connections between the nodes; step 2, preprocessing process on the topological structure: if two failed nodes are connected directly, creating a virtual node newly to replace the two nodes; and step 3: division of the network structure: using the updated topological structure in step 2, with each failed node as a regional center, dividing the network structure in a flooding manner. As to each node in the network, the node is designated to a nearest region, and the node is affected when the corresponding central node fails.
Description
Technical field
The present invention relates to a kind of method of in destructuring distributed P 2 P network, dividing network configuration, related to network configuration division, computer software technical field, can be used for network upheaval or the disaster of avoiding some node fails of P2P network to cause.
Background technology
Along with the development of computer technology, increasing computer system is rendered as latticed form.
The P2P network according to the mapping relations between topology of networks and the storage positions of files, roughly can be divided into three kinds as a kind of typical network: centralized P2P network, structuring distributed P 2 P network, destructuring distributed P 2 P network.
Centralized P2P network refers to have in the network one and concentrates the server of preserving network File deposit position catalogue, and such as Napster, there is the single point failure problem in this network.The distributed P 2 P network is relative with centralized P2P network, does not have the LIST SERVER of concentrating in the network.The distributed P 2 P network can Further Division be structuring distributed P 2 P network again, such as Freenet and non-structure distribution formula P2P network, such as Gnutella, " structuring " refers to, file leaves special node in, and namely there are mapping relations in the deposit position of topology of networks and file; In non-structural P 2 P network, can not obtain according to network topology structure the deposit position of file, each node need to be taked inundation formula method: inquire about its all neighbours and could finally obtain file.
P2P network of network structure is paid close attention in existing a lot of research, but when seldom having the network topology structure of care to change, how to utilize the network of network structure to evade topologies change to the impact of network.Because the dynamic characteristic of network environment, some node may lose efficacy in the network, caused network topology structure to change.In centralized P2P network, if LIST SERVER lost efficacy, whole network can collapse, and if certain common node lost efficacy, other nodes is almost had no impact.In structuring distributed P 2 P network, if the special node fails of those of storing documents, network also can collapse, and similarly, other common node lost efficacy and can not have much impact to network.But in destructuring distributed P 2 P network, because the inundation form is adopted in the inquiry of file usually, a certain node fails can cause its all neighbor node inquiries to be broken down, and these neighbor nodes can affect again the neighbor node of himself.
In destructuring distributed P 2 P network, it is a kind of special to exist, and double-deck unstructured P2P network is such as KaZaA." bilayer " refers to that the node in the network is marked as two classifications, common node and super-peer, each super-peer links to each other with a plurality of common node, and super-peer is safeguarded the directory information of these common node, and each common node can only link to each other with a super-peer.This network is identical in essence with structuring distributed P 2 P network, and does not need to use inundation formula method, and therefore, the method is not suitable for this network.
Summary of the invention
The network upheaval that causes for inefficacy node in the destructuring distributed P 2 P network in the prior art, the defective of the coverage of the node of can't determining to lose efficacy provides a kind of method of dividing network configuration in destructuring distributed P 2 P network.
The invention provides a kind of method of in destructuring distributed P 2 P network, dividing network configuration:
The present invention divides community structure in destructuring distributed P 2 P network method comprises three steps:
Step 1: obtain the P2P network topology structure, topological structure N=(V, E) is by connecting to form between the some nodes in the network and these nodes.Part node in the node set is marked as the inefficacy node, and other nodes are common node.
Step 2: the preprocessing process of topological structure: if two inefficacy nodes directly link to each other, newly create a virtual nodes and replace this two nodes.
If two inefficacy nodes directly link to each other, these two inefficacy nodes have more public neighbours, the constraint that can only belong to a zone according to algorithm and each node of inundation formula, these nodes finally can only be divided in one of them zone, the minority node is only arranged, although the inefficacy node of this regional center has in fact also affected these public neighbours in another zone.The method creates virtual regional center, replaces directly continuous inefficacy node, and public neighbours are divided in zone corresponding to this virtual regional center.Upgrade topological structure N=(V, E), as the foundation of dividing network configuration in the step 3.
Need to distinguish in two kinds of situation when upgrading topological structure here: one, a certain two the inefficacy nodes of node and this that do not lose efficacy all link to each other; Two, only link to each other with one of them inefficacy node.In the topological structure after upgrading, this node that do not lose efficacy all links to each other with the virtual region center, and in situation one, originally two limits become a limit of upgrading in the rear topological structure in the topological structure, and the radix of set E need to subtract 1; In situation two, upgrade the front and rear side number and remain unchanged.
Step 3: the division of network configuration: utilize the topological structure after upgrading in the step 2, take each inefficacy node as regional center, the division network configuration of inundation formula.For each node in the network, it is divided into nearest zone, can affect it during the respective center node fails.
Particularly, for each regional center
Its corresponding influence area N
i, and corresponding two variable Cur_nodes
iAnd Cur_neighbors
i, Cur_nodes
iRepresentative has just been determined in last round of iterative process belongs to influence area N
iNode set, with Cur_nodes
iIn in the neighbor node that directly links to each other of all nodes, the node set that not yet is assigned to arbitrary zone has consisted of Cur_neighbors
i, need in the epicycle iterative process, determine.With Cur_nodes
iBe initialized as
Because initial each regional center
Corresponding influence area N
iOnly comprise himself, then will with
The node initialization Cur_neighbors that directly links to each other
i, and distribute to regional N
i, so first round iteration finishes.When beginning, use Cur_neighbors in every iteration of taking turns
iIn node initialization Cur_nodes
i, calculate Cur_neighbors
i, repeat above process, until common node set V
oIn all nodes all be assigned to a certain zone.
The node that affects when each node all is regarded as respective regions center inefficacy node leave in the network configuration that obtains.For the zone under the virtual region center, on the one hand, the node in logically should the zone is by a plurality of inefficacy nodes impacts corresponding to this virtual region center; On the other hand, physically also can only belong to the constraint in a zone without prejudice to each node.
What need to further specify is, according to the processing procedure of inundation formula, and a certain common node
May be two regional centers
With
Neighbours, and the length of shortest path is identical.Only belong to the constraint in a zone for satisfying a node, distribute this node according to computation sequence, that is, this node is divided into
With
In the zone of the correspondence that subscript is less in these two regional centers.For certain node and the situation that a plurality of regional centers link to each other and shortest path is identical, take identical measure.
The node that affects when each node all is regarded as respective regions centre junction point failure in the network configuration that obtains.For the zone under the virtual region center, on the one hand, the node in logically should the zone is by a plurality of inefficacy nodes impacts corresponding to this virtual region center; On the other hand, physically also can only belong to the constraint in a zone without prejudice to each node.
The method as regional center, and does not consider that a node belongs to the situation in a plurality of zones with the inefficacy node, takes the algorithm of inundation formula, and method network configuration simple and that divide has realistic meaning.
Some node is marked as the inefficacy node in the topological structure.Here, the inefficacy node can be that network environment fluctuation is left or failed node when larger, also can be the system manager for avoiding risk, the simulation that some common node is carried out, thereby upheaval even the disaster of before its real inefficacy, taking certain measure to avoid network to occur.
Therefore, in destructuring distributed P 2 P network, be the disaster of avoiding node fails to cause, the system manager need to know in advance, if some node fails in the network, which node around can affecting.Based on this, we proposed one with the inefficacy node as regional center, divide the method for network configuration, the node that the node in the gained network configuration in each zone affects when being considered to this regional center node fails, the method has simply but effectively been simulated reality.
According to the mapping relations between P2P network topology structure and the storage positions of files, can be divided into centralized P2P network, structuring distributed P 2 P network, destructuring distributed P 2 P network.Have a kind of double-deck P2P network in the destructuring distributed P 2 P network, the method is only applicable to destructuring distributed P 2 P network, and does not consider double-deck P2P network.In destructuring distributed P 2 P network, network topology structure and storage positions of files do not have mapping relations, and new node can add at any time, and node original in the network also can leave arbitrarily; Each node need to be taked the method for inundation formula: inquire about all neighbor nodes, just can obtain storage positions of files.If some node fails can impact other nodes in the network, the method that the method takes to divide network configuration is determined the coverage of each node.
Compared with prior art, effect of the present invention is embodied in: the inefficacy node as known regional center, is carried out the division of network configuration, avoided seeking in the conventional method complex process at subnet center, method is simple.For so that the division of network configuration has reality justice more, original topology structure to network is carried out preliminary treatment, so that the node that is affected simultaneously by a plurality of inefficacy nodes is divided in the virtual region, both satisfied the constraint that each node can only belong to a zone, more objective again.
Description of drawings
Fig. 1 is the destructuring distributed P 2 P topology of networks of the embodiment of the invention.
Fig. 2 is that the embodiment of the invention is upgraded the topological structure schematic diagram.
Fig. 3 is that the inundation formula method of the embodiment of the invention is used schematic diagram.
Fig. 4 is logical process schematic diagram of the present invention.
Embodiment:
The invention discloses a kind ofly in distributed, structureless equity (Peer to Peer, P2P) network, determine that some node fails on the method for the impact of node on every side, belongs to computer software technical field.Thought of the present invention is: at first, and with the node of each inefficacy in the P2P network center as involved area; Then, from each regional center, adopt the method for inundation formula, determine the zone that its neighbours are affiliated, all nodes in each zone all are affected when the centre junction point failure of respective regions.Method of the present invention comprises following several step: obtain the step of P2P network topology structure and regional center, in conjunction with the pre-treatment step of the inefficacy node that directly links to each other, based on the inundation formula iterative processing step of regional center.The present invention divides network configuration with the coverage of inefficacy node as standard, uses inundation formula method, has simplified the complexity that network configuration is divided.
As shown in Figure 4, the invention discloses a kind of method of in destructuring distributed P 2 P network, dividing network configuration, with each inefficacy node in the destructuring distributed P 2 P network as the involved area center, determine the affiliated zone of neighbor node of inefficacy node, all nodes in each zone all are considered as the node that is affected when the respective center node fails, may further comprise the steps:
Step 1: obtain the P2P network topology structure; The topological structure of destructuring distributed P 2 P network N is comprised of the set E on limit between a node set V and the node, is described as N=(V, E), V=(V
l, V
o), wherein, V
lInefficacy node set among the expression node set V, V
oNot inefficacy node set among the expression node set V.
Step 2: the preprocessing process of topological structure: if there are any two inefficacy nodes directly to link to each other, newly create a virtual nodes and replace this two nodes, and upgrade topological structure as the foundation of dividing network configuration in the step 3; If any two inefficacy nodes directly do not link to each other, then directly carry out step 3.If the inefficacy node directly links to each other more than two, create a virtual regional center, replace the inefficacy node that directly links to each other and upgrade the P2P network topology structure, the neighbor node of these inefficacy nodes all is divided in influence area corresponding to this virtual regional center.
Step 3: divide network configuration, according to the topological structure in the step 2, take each inefficacy node as regional center, adopt inundation formula method to divide network configuration.
Inefficacy node set V
lIn each inefficacy node as a regional center, take the method for inundation formula to divide network configuration, namely set up an influence area for each regional center, at first will be assigned to the neighbor node that this node that lost efficacy directly links to each other in this influence area, then will be assigned in this influence area with the neighbor node that directly links to each other of these neighbor nodes, iteration distributes, until the node set V that do not lose efficacy
oIn all nodes all be assigned in the influence area.
Each node can only be assigned to an influence area, if a node links to each other with inefficacy node more than two, this node is assigned in the zone apart from the failure node of its shortest path, if the length of shortest path is identical, gather V according to the center failure node of regional at failure node
oIn sequencing, this node is divided into influence area under first inefficacy node.
In the step 3, for each regional center
Its corresponding influence area N
i, and corresponding set Cur_nodes
iWith set Cur_neighbors
i, set Cur_nodes
iBelong to influence area N for what in last round of iterative process, determine
iNode set; Set Cur_neighbors
iFor with node set Cur_nodes
iIn not yet be assigned to the node set in arbitrary zone, set Cur_neighbors in the neighbor node that directly links to each other of all nodes
iIn the epicycle iteration, determine;
To gather Cur_nodes
iBe initialized as
Will with
The node that directly links to each other is initialized as Cur_neighbors
i, and distribute to influence area N
i, first round iteration finishes;
In every iteration of taking turns when beginning, with set Cur_neighbors
iIn node initialization set Cur_nodes
i, set of computations Cur_neighbors
i, iteration is until the node set V that do not lose efficacy
oIn all nodes all be assigned to a zone, then network configuration is divided complete.
Embodiment
Fig. 1 is an example of destructuring distributed P 2 P network, is used for illustrating better the inventive method.The Essential Environment of this example comes from the application of Distributed Services combination that S.Hu and V.MuthuSamy's occur in " Distributed automatic servicecomposition in large-scale systems (Proceedings of the second international conference ondistributed event-based systems; pp.233-244,2008) ".Wherein, core network adopts the distributed post customized network that occurs in E.Fidler and H.A.Jacobsen " The PADRES DistributedPublish/Subscribe System (Proceedings of the Feature Interactions in Telecommunication andSoftware Systems, 2005) ".Example in topology of networks employing J.Zhou and W.Dou " A Qos-Aware Service Selection Approach on P2P network for DynamicCross-Organizational Workflow Development (Web Information Systems and Mining; pp.289-298,2009) ".
In the network shown in Figure 1, the network periphery is ISP and client user, and the ISP gets involved network by the service broker; The client user is by the request broker access network.Because the central server of service registration functionality is not provided, each ISP need to whole network issue log-on message, specifically carry out with the inundation formula when registration service.When certain user asks to obtain to have the service of some function, send request to the request broker that is attached thereto, this is asked according to content-based routing table in the network at the network repeating, until satisfy the ISP of this request to Danone.
Supposed in this publishing of customized network certain node fails, if this node links to each other with a request broker, all can be failed from this user's request; If this node links to each other with a service broker, this service broker also can not registration service, therefore, needs to determine in advance the coverage of certain node fails in the network, for further action is ready.
The following describes the coverage of how coming to determine for destructuring distributed P 2 P network shown in Figure 1 the inefficacy node with this method.
As shown in Figure 2, suppose that node B1, B2, B3 lost efficacy, in this scene, wherein, node B1 directly links to each other with B2, and this topology of networks of preliminary treatment at first then with a virtual node Vir_node replacement, upgrades corresponding limit to B1 and B2 simultaneously.Dotted line represents the limit that changes in the renewal process among Fig. 2, and the node in the ellipse of with dashed lines mark then is regarded as regional center.
Next, need to determine the coverage of virtual nodes Vir_node and node B3, the influence area corresponding node Vir_node is designated as N
1, the influence area that B3 is corresponding is designated as N
2, at initial phase, Vir_node distributes to N
1, B3 distributes to N
2, Cur_nodes
1={ Vir_node}, Cur_nodes
2=B3},
First round iterative process is assigned to Cur_neighbors to the node that directly links to each other respectively
1And Cur_neighbors
2Take turns iterative process when beginning in after this each, make Cur_nodes
1=Cur_neighbors
1, Cur_nodes
2=Cur_neighbors
2Stopping criterion for iteration is that all nodes all are divided into regional N
1Perhaps N
2In, thereby obtain result shown in Figure 3.Wherein, use N
1The limit of mark has formed regional N
1The border, represent the coverage of Vir_node, use N
2The limit of mark has formed regional N
2The border, represent the coverage of B3, the node of impact when their reality represents respectively B1, B2 and B3 and lost efficacy.Node B4 and B5 are two special nodes, B4 directly links to each other with Vir_node and B3, and shortest path strength length all is 1, the agreement that only belongs to an influence area in order to satisfy each node, according to computation sequence, be divided into the Vir_node affiliated area, B5 directly links to each other with Vir_node and B3, and shortest path strength length all is 2, in like manner it is assigned to the Vir_node affiliated area.
The invention provides a kind of method of in destructuring distributed P 2 P network, dividing network configuration; method and the approach of this technical scheme of specific implementation are a lot; the above only is preferred implementation of the present invention; should be understood that; for those skilled in the art; under the prerequisite that does not break away from the principle of the invention, can also make some improvements and modifications, these improvements and modifications also should be considered as protection scope of the present invention.In the present embodiment not clear and definite each part all available prior art realized.
Claims (6)
1. method of in destructuring distributed P 2 P network, dividing network configuration, it is characterized in that, with each inefficacy node in the destructuring distributed P 2 P network as the involved area center, determine the affiliated zone of neighbor node of inefficacy node, all nodes in each zone all are considered as the node that is affected when the respective center node fails, may further comprise the steps:
Step 1: obtain the P2P network topology structure;
Step 2: the preprocessing process of topological structure: if there are any two inefficacy nodes directly to link to each other, newly create a virtual nodes and replace this two nodes, and upgrade topological structure as the foundation of dividing network configuration in the step 3; If any two inefficacy nodes directly do not link to each other, then directly carry out step 3;
Step 3: divide network configuration, according to the topological structure in the step 2, take each inefficacy node as regional center, adopt inundation formula method to divide network configuration.
2. a kind of method of in destructuring distributed P 2 P network, dividing network configuration according to claim 1, it is characterized in that, the topological structure of destructuring distributed P 2 P network N is comprised of the set E on limit between a node set V and the node, be described as N=(V, E), V=(V
l, V
o), wherein, V
lInefficacy node set among the expression node set V, V
oNot inefficacy node set among the expression node set V.
3. a kind of method of dividing network configuration in destructuring distributed P 2 P network according to claim 2 is characterized in that, inefficacy node set V
lIn each inefficacy node as a regional center, take the method for inundation formula to divide network configuration, namely set up an influence area for each regional center, at first will be assigned to the neighbor node that this node that lost efficacy directly links to each other in this influence area, then will be assigned in this influence area with the neighbor node that directly links to each other of these neighbor nodes, iteration distributes, until the node set V that do not lose efficacy
oIn all nodes all be assigned in the influence area.
4. a kind of method of in destructuring distributed P 2 P network, dividing network configuration according to claim 3, it is characterized in that, each node can only be assigned to an influence area, if a node links to each other with inefficacy node more than two, this node is assigned in the zone apart from the failure node of its shortest path, if the length of shortest path is identical, gather V according to the center failure node of regional at failure node
oIn sequencing, this node is divided into influence area under first inefficacy node.
5. a kind of method of in destructuring distributed P 2 P network, dividing network configuration according to claim 4, it is characterized in that, if the inefficacy node directly links to each other more than two, create a virtual regional center, replace the inefficacy node that directly links to each other and upgrade the P2P network topology structure, the neighbor node of these inefficacy nodes all is divided in influence area corresponding to this virtual regional center.
6. a kind of method of dividing network configuration in destructuring distributed P 2 P network according to claim 5 is characterized in that, in the step 3, for each regional center
Its corresponding influence area N
i, and corresponding set Cur_nodes
iWith set Cur_neighbors
i, set Cur_nodes
iBelong to influence area N for what in last round of iterative process, determine
iNode set; Set Cur_neighbors
iFor with node set Cur_nodes
iIn not yet be assigned to the node set in arbitrary zone, set Cur_neighbors in the neighbor node that directly links to each other of all nodes
iIn the epicycle iteration, determine;
To gather Cur_nodes
iBe initialized as
Will with
The node that directly links to each other is initialized as Cur_neighbors
i, and distribute to influence area N
i, first round iteration finishes;
In every iteration of taking turns when beginning, with set Cur_neighbors
iIn node initialization set Cur_nodes
i, set of computations Cur_neighbors
i, iteration is until the node set V that do not lose efficacy
oIn all nodes all be assigned to a zone, then network configuration is divided complete.
Priority Applications (1)
| Application Number | Priority Date | Filing Date | Title |
|---|---|---|---|
| CN2012104881803A CN102932486A (en) | 2012-11-26 | 2012-11-26 | Method of dividing network structure in unstructured distributive P2P (peer-to-peer) network |
Applications Claiming Priority (1)
| Application Number | Priority Date | Filing Date | Title |
|---|---|---|---|
| CN2012104881803A CN102932486A (en) | 2012-11-26 | 2012-11-26 | Method of dividing network structure in unstructured distributive P2P (peer-to-peer) network |
Publications (1)
| Publication Number | Publication Date |
|---|---|
| CN102932486A true CN102932486A (en) | 2013-02-13 |
Family
ID=47647182
Family Applications (1)
| Application Number | Title | Priority Date | Filing Date |
|---|---|---|---|
| CN2012104881803A Pending CN102932486A (en) | 2012-11-26 | 2012-11-26 | Method of dividing network structure in unstructured distributive P2P (peer-to-peer) network |
Country Status (1)
| Country | Link |
|---|---|
| CN (1) | CN102932486A (en) |
Cited By (3)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN105915602A (en) * | 2016-04-13 | 2016-08-31 | 华南理工大学 | Community-detection-algorithm-based P2P network scheduling method and system |
| CN110161900A (en) * | 2019-04-25 | 2019-08-23 | 中国人民解放军火箭军工程大学 | The wearable remote control operation platform of one remote operation |
| CN113179336A (en) * | 2021-06-30 | 2021-07-27 | 正链科技(深圳)有限公司 | Distributed peer-to-peer network system facing hundred million-magnitude large-scale cluster |
Citations (3)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| US20080098121A1 (en) * | 2006-10-23 | 2008-04-24 | Nec (China) Co., Ltd. | P2p sip enabled multimedia network communication system |
| CN101170578A (en) * | 2007-11-30 | 2008-04-30 | 北京理工大学 | Hierarchical peer-to-peer network structure and constructing method based on syntax similarity |
| CN101442479A (en) * | 2007-11-22 | 2009-05-27 | 华为技术有限公司 | Method, equipment and system for updating route in P2P peer-to-peer after node failure |
-
2012
- 2012-11-26 CN CN2012104881803A patent/CN102932486A/en active Pending
Patent Citations (3)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| US20080098121A1 (en) * | 2006-10-23 | 2008-04-24 | Nec (China) Co., Ltd. | P2p sip enabled multimedia network communication system |
| CN101442479A (en) * | 2007-11-22 | 2009-05-27 | 华为技术有限公司 | Method, equipment and system for updating route in P2P peer-to-peer after node failure |
| CN101170578A (en) * | 2007-11-30 | 2008-04-30 | 北京理工大学 | Hierarchical peer-to-peer network structure and constructing method based on syntax similarity |
Non-Patent Citations (1)
| Title |
|---|
| LIU MENG等: "A Practical Method for Detecting Community Structures in Decentralized and Unstructured P2P Networks", 《2012 SECOND INTERNATIONAL CONFERENCE ON CLOUD AND GREEN COMPUTING》 * |
Cited By (6)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN105915602A (en) * | 2016-04-13 | 2016-08-31 | 华南理工大学 | Community-detection-algorithm-based P2P network scheduling method and system |
| CN105915602B (en) * | 2016-04-13 | 2020-11-13 | 华南理工大学 | Dispatching method and system based on community detection algorithm P2P network |
| CN110161900A (en) * | 2019-04-25 | 2019-08-23 | 中国人民解放军火箭军工程大学 | The wearable remote control operation platform of one remote operation |
| CN110161900B (en) * | 2019-04-25 | 2021-04-27 | 中国人民解放军火箭军工程大学 | Remote operation's wearing formula remote control operation platform |
| CN113179336A (en) * | 2021-06-30 | 2021-07-27 | 正链科技(深圳)有限公司 | Distributed peer-to-peer network system facing hundred million-magnitude large-scale cluster |
| CN113179336B (en) * | 2021-06-30 | 2021-09-07 | 正链科技(深圳)有限公司 | Distributed peer-to-peer network system facing hundred million-magnitude large-scale cluster |
Similar Documents
| Publication | Publication Date | Title |
|---|---|---|
| Kuhn et al. | Towards worst-case churn resistant peer-to-peer systems | |
| CN103095727B (en) | P2p resource location method | |
| Selimi et al. | Distributed storage and service discovery for heterogeneous community network clouds | |
| CN102932486A (en) | Method of dividing network structure in unstructured distributive P2P (peer-to-peer) network | |
| Guo et al. | Quasi-kautz digraphs for peer-to-peer networks | |
| Teng et al. | A self-similar super-peer overlay construction scheme for super large-scale P2P applications | |
| Lai et al. | A scalable multi-attribute hybrid overlay for range queries on the cloud | |
| Shen et al. | CCLBR: Congestion control-based load balanced routing in unstructured P2P systems | |
| Girdzijauskas et al. | Fuzzynet: Ringless routing in a ring-like structured overlay | |
| Abe | Blockchain storage load balancing among dht clustered nodes | |
| Gueye et al. | A self-adaptive structuring for large-scale P2P Grid environment: design and simulation analysis | |
| D’Alessandro Costa et al. | Performance analysis of a locality-aware BitTorrent protocol in enterprise networks | |
| CN107734008A (en) | Method, apparatus, node device and the storage medium of a kind of troubleshooting in data-storage system | |
| Ou et al. | GTPP: General truncated pyramid peer-to-peer architecture over structured DHT networks | |
| JP5761759B2 (en) | Node participation processing apparatus, method, and program | |
| Sharifkhani et al. | A review of new advances in resource discovery approaches in unstructured P2P networks | |
| López Chavira et al. | Distributed rewiring model for complex networking: The effect of local rewiring rules on final structural properties | |
| Fischer et al. | Resilient and underlay-aware P2P live-streaming | |
| Jia et al. | Designs and Evaluation of a Tracker in P2P Networks | |
| JP2015207906A (en) | Network construction method and network construction device | |
| Rajasekhar et al. | A scalable and robust qos architecture for wifi p2p networks | |
| Binh et al. | All capacities modular cost survivable network design problem using genetic algorithm with completely connection encoding | |
| Lehmann et al. | Random graphs, small-worlds and scale-free networks | |
| Tang et al. | Review of content distribution network architectures | |
| Dobre | A cluster-enhanced fault tolerant peer-to-peer systems |
Legal Events
| Date | Code | Title | Description |
|---|---|---|---|
| C06 | Publication | ||
| PB01 | Publication | ||
| C10 | Entry into substantive examination | ||
| SE01 | Entry into force of request for substantive examination | ||
| C05 | Deemed withdrawal (patent law before 1993) | ||
| WD01 | Invention patent application deemed withdrawn after publication |
Application publication date: 20130213 |