WO2013104231A1 - 一种网络负荷控制方法及登记服务器 - Google Patents

一种网络负荷控制方法及登记服务器 Download PDF

Info

Publication number
WO2013104231A1
WO2013104231A1 PCT/CN2012/086560 CN2012086560W WO2013104231A1 WO 2013104231 A1 WO2013104231 A1 WO 2013104231A1 CN 2012086560 W CN2012086560 W CN 2012086560W WO 2013104231 A1 WO2013104231 A1 WO 2013104231A1
Authority
WO
WIPO (PCT)
Prior art keywords
node
target area
load
registration server
network
Prior art date
Application number
PCT/CN2012/086560
Other languages
English (en)
French (fr)
Inventor
陶峑郡
王炜
吴建华
Original Assignee
中兴通讯股份有限公司
Priority date (The priority date is an assumption and is not a legal conclusion. Google has not performed a legal analysis and makes no representation as to the accuracy of the date listed.)
Filing date
Publication date
Application filed by 中兴通讯股份有限公司 filed Critical 中兴通讯股份有限公司
Priority to EP12865297.1A priority Critical patent/EP2790362B1/en
Priority to US14/371,561 priority patent/US20150009812A1/en
Publication of WO2013104231A1 publication Critical patent/WO2013104231A1/zh

Links

Classifications

    • HELECTRICITY
    • H04ELECTRIC COMMUNICATION TECHNIQUE
    • H04LTRANSMISSION OF DIGITAL INFORMATION, e.g. TELEGRAPHIC COMMUNICATION
    • H04L47/00Traffic control in data switching networks
    • H04L47/10Flow control; Congestion control
    • H04L47/12Avoiding congestion; Recovering from congestion
    • H04L47/122Avoiding congestion; Recovering from congestion by diverting traffic away from congested entities
    • HELECTRICITY
    • H04ELECTRIC COMMUNICATION TECHNIQUE
    • H04LTRANSMISSION OF DIGITAL INFORMATION, e.g. TELEGRAPHIC COMMUNICATION
    • H04L67/00Network arrangements or protocols for supporting network services or applications
    • H04L67/01Protocols
    • H04L67/10Protocols in which an application is distributed across nodes in the network
    • H04L67/1001Protocols in which an application is distributed across nodes in the network for accessing one among a plurality of replicated servers
    • H04L67/1004Server selection for load balancing
    • H04L67/1008Server selection for load balancing based on parameters of servers, e.g. available memory or workload
    • HELECTRICITY
    • H04ELECTRIC COMMUNICATION TECHNIQUE
    • H04LTRANSMISSION OF DIGITAL INFORMATION, e.g. TELEGRAPHIC COMMUNICATION
    • H04L47/00Traffic control in data switching networks
    • H04L47/10Flow control; Congestion control
    • H04L47/11Identifying congestion
    • HELECTRICITY
    • H04ELECTRIC COMMUNICATION TECHNIQUE
    • H04LTRANSMISSION OF DIGITAL INFORMATION, e.g. TELEGRAPHIC COMMUNICATION
    • H04L67/00Network arrangements or protocols for supporting network services or applications
    • H04L67/01Protocols
    • H04L67/10Protocols in which an application is distributed across nodes in the network
    • H04L67/1001Protocols in which an application is distributed across nodes in the network for accessing one among a plurality of replicated servers
    • H04L67/1004Server selection for load balancing
    • HELECTRICITY
    • H04ELECTRIC COMMUNICATION TECHNIQUE
    • H04LTRANSMISSION OF DIGITAL INFORMATION, e.g. TELEGRAPHIC COMMUNICATION
    • H04L67/00Network arrangements or protocols for supporting network services or applications
    • H04L67/01Protocols
    • H04L67/10Protocols in which an application is distributed across nodes in the network
    • H04L67/104Peer-to-peer [P2P] networks
    • HELECTRICITY
    • H04ELECTRIC COMMUNICATION TECHNIQUE
    • H04LTRANSMISSION OF DIGITAL INFORMATION, e.g. TELEGRAPHIC COMMUNICATION
    • H04L67/00Network arrangements or protocols for supporting network services or applications
    • H04L67/01Protocols
    • H04L67/10Protocols in which an application is distributed across nodes in the network
    • H04L67/104Peer-to-peer [P2P] networks
    • H04L67/1044Group management mechanisms 
    • H04L67/1051Group master selection mechanisms
    • HELECTRICITY
    • H04ELECTRIC COMMUNICATION TECHNIQUE
    • H04LTRANSMISSION OF DIGITAL INFORMATION, e.g. TELEGRAPHIC COMMUNICATION
    • H04L67/00Network arrangements or protocols for supporting network services or applications
    • H04L67/01Protocols
    • H04L67/10Protocols in which an application is distributed across nodes in the network
    • H04L67/104Peer-to-peer [P2P] networks
    • H04L67/1044Group management mechanisms 
    • H04L67/1053Group management mechanisms  with pre-configuration of logical or physical connections with a determined number of other peers
    • HELECTRICITY
    • H04ELECTRIC COMMUNICATION TECHNIQUE
    • H04LTRANSMISSION OF DIGITAL INFORMATION, e.g. TELEGRAPHIC COMMUNICATION
    • H04L67/00Network arrangements or protocols for supporting network services or applications
    • H04L67/01Protocols
    • H04L67/10Protocols in which an application is distributed across nodes in the network
    • H04L67/104Peer-to-peer [P2P] networks
    • H04L67/1044Group management mechanisms 
    • H04L67/1053Group management mechanisms  with pre-configuration of logical or physical connections with a determined number of other peers
    • H04L67/1055Group management mechanisms  with pre-configuration of logical or physical connections with a determined number of other peers involving connection limits
    • HELECTRICITY
    • H04ELECTRIC COMMUNICATION TECHNIQUE
    • H04LTRANSMISSION OF DIGITAL INFORMATION, e.g. TELEGRAPHIC COMMUNICATION
    • H04L67/00Network arrangements or protocols for supporting network services or applications
    • H04L67/01Protocols
    • H04L67/10Protocols in which an application is distributed across nodes in the network
    • H04L67/104Peer-to-peer [P2P] networks
    • H04L67/1061Peer-to-peer [P2P] networks using node-based peer discovery mechanisms
    • H04L67/1065Discovery involving distributed pre-established resource-based relationships among peers, e.g. based on distributed hash tables [DHT] 

Definitions

  • the present invention relates to the field of communications, and in particular, to a network load control method and a registration server.
  • P2P peer-to-peer or peer-to-peer
  • SIP Session Initialization
  • FIG 1 is a schematic diagram of a P2P core network architecture of the related art, where: P2P overlay network 101 is different from various types.
  • a logical network of role peers also referred to herein as nodes).
  • the peer node 102 in the P2P overlay network is a basic component of the P2P overlay network and is a node capable of providing storage and delivery services for other nodes in the same P2P overlay network.
  • the non-P2P terminal device 103 is a terminal device that supports the P2P overlay network and does not support any P2P protocol, and only supports the SIP protocol.
  • the P2P terminal device 104 is a terminal device that supports both the P2P protocol and the IP protocol in the P2P overlay network. Considering that the general terminal device, especially the handheld terminal device, has weak capabilities, in many cases, in practice In the deployment, the P2P terminal device only accesses the P2P overlay network as a P2P client, and does not assume the functions of a server such as storage and transmission.
  • the access node 105 is an access node of a terminal device such as a non-P2P terminal device 103 and a P2P terminal device 104. In consideration of the needs of the telecommunication operation, both the P2P terminal and the non-P2P terminal must access the P2P overlay through the nearest access node.
  • the access node when the access node acts as an access node of a non-P2P terminal, it also acts as a proxy node, and is responsible for stacking the SIP protocol and P2P used by the non-P2P terminal.
  • the intranet internal routing SIP uses the conversion of the protocol, and when the node acts as the access node of the P2P terminal, only the message needs to be relayed.
  • the registration server 106 is responsible for joining the management of the peer-to-peer network node and adding the peer-to-peer network assignment node identifier to the node.
  • Load Balancing 107 Server 107 is responsible for collecting P2P network node load.
  • the peer nodes 102 implement dynamic real-time backup of data between nodes according to a distributed hash algorithm (DHT).
  • DHT distributed hash algorithm
  • FIG. 2 is a schematic flow chart of a conventional network overload control, in which a forward node is a message sender, a backward node is a message receiver, and a current node senses that the backward node is overloaded, and the forward node is proportional according to an overload policy. Discard or send a message back to the node.
  • the specific process is as follows:
  • Step 201 The forward node senses that the backward node is overloaded
  • the manner in which the forward node senses the backward node load generally includes: the backward node notification, the load balancing server notification, and the inference according to the message delay.
  • Step 202 According to the overload policy, the forward node discards or sends a message to the backward node according to a predetermined proportion according to the overload degree of the backward node, so as to reduce the load of the backward node.
  • the advantages of the P2P network cannot be reflected, and the instability of the P2P network is expanded.
  • the advantage of the P2P network is that the quantity is exchanged for high quality, and the stability of a single node is more traditional than The performance of a single node on the network is poor. When the network is under heavy load, it is easier to form a resource overload. If the traditional overload control method is used, the connection rate of the P2P network is much lower than that of the traditional one. The internet.
  • the embodiment of the invention provides a network load control method and a registration server, which can implement load control on a P2P network without lowering the P2P network connection rate.
  • adding a node in the target area includes:
  • the registration server invokes a standby node, adds the spare node to the target area, or selects a node from a network area outside the target area, and adds the selected node to the target area.
  • adding the standby node to the target area includes:
  • the registration server wakes up the standby node, and after receiving the join network request message sent by the standby node, assigns a node identifier to the standby node, and the allocated node identifier enables the standby node to join the network.
  • the target area shares the bearer of the target area address space to decompose the load of the target area.
  • selecting a node from the network area outside the target area, and adding the selected node to the target area includes:
  • the registration server selects one or more nodes whose load is lower than the reference load of the target area from the network area outside the target area or selects one or more nodes whose load is lower than the first load threshold;
  • the registration server notifies the selected node to rejoin the network, and after receiving the join network request message sent by the selected node, assigns a node identifier to the selected node, and the assigned node identifier makes the selected node join the network.
  • the bearer of the target area address space is shared for the target area to decompose the load of the target area.
  • the reference load when the reference load includes a plurality of nodes in the target area, it is an average load or a minimum load of nodes in the target area; when the target area includes a node, it is included The load of the node.
  • the standby node is in an idle state or a dormant state, and listens to the wakeup of the registration server, and after listening to the wakeup of the registration server, enters a working state, and sends a join network request message to the registration server. Node.
  • the step of the registration server being informed that the target area is overloaded includes:
  • the load control node determines whether the load of the target area is higher than a second load threshold. If it is higher, it determines that a load adjustment needs to be initiated, and sends a load adjustment request to the registration server; or, at the load control node and the When the registration server is set up, the registration server senses The load of the target area is determined whether the load of the target area is higher than the second load threshold.
  • the target area includes one or more nodes
  • the load control node notifies the registration server of the node identifier of the node included in the target area in the load adjustment request.
  • the manner in which the load control node notifies the node identifier of the node included in the target area to the registration server in the load adjustment request includes one or more of the following, including:
  • the load control node records a node identifier of a single node in the load adjustment request; the load control node records a node identifier range in the load adjustment request, where the node identifier range represents one node or represents a node identifier continuous Multiple nodes.
  • the node pointed to by the end node identifier is indicated.
  • the load control node is a node that currently has a service, or is a load balancing server, or a functional unit disposed in the registration server.
  • the embodiment of the invention further provides another network load control method, including:
  • the registration server knows that the load of the target area is lower than the third load threshold, the node is selected from the target area, and the selected node is exited from the target area.
  • the selected node is exited from the target area, including:
  • the registration server notifies the selected node to be returned as a standby node.
  • the standby node is in an idle state or a dormant state, and listens to the wakeup of the registration server, and after listening to the wakeup of the registration server, enters a working state, and sends a join network request message to the registration server. Node.
  • a registration server includes: a load monitoring unit and a load control unit, where:
  • the load monitoring unit is configured to monitor a load of the target area
  • the load control unit is configured to add a node in the target area after the load monitoring unit learns that the target area is overloaded.
  • the load control unit is configured to invoke a standby node, add the standby node to the target area, or select a node from a network area outside the target area, and select the selected node. Joined into the target area.
  • the load control unit includes: a node management subunit and an identifier assignment subunit, wherein: the node management subunit is configured to wake up the standby node, and receive a join network request message sent by the standby node;
  • the identifier allocation subunit is configured to: after the node management subunit receives the join network request message sent by the standby node, assign a node identifier to the standby node, where the allocated node identifier makes the standby node After joining the network, the bearer of the target area address space is shared for the target area to decompose the load of the target area.
  • the load control unit comprises: a node management subunit and an identifier assignment subunit, wherein:
  • the node management subunit is configured to select one or more nodes whose load is lower than a reference load of the target area from a network area other than the target area or select one or more loads to be lower than a first load threshold Node, notifying the selected node to rejoin the network, and receiving the join network request message sent by the selected node;
  • the identifier allocation subunit is configured to: after the node management subunit receives the join network request message sent by the standby node, assign a node identifier to the selected node, and the allocated node identifier makes the selected node After joining the network, the bearer of the target area address space is shared for the target area to decompose the load of the target area.
  • An embodiment of the present invention further provides another registration server, including: a load monitoring unit and a load control unit, where:
  • the load monitoring unit is configured to monitor a load of the target area
  • the load control unit is configured to, when the load monitoring unit learns that the load of the target area is lower than the third load threshold, select a node from the target area, and exit the selected node from the target area.
  • the load control unit comprises a node management subunit, wherein:
  • the node management subunit configured to select a node from the target area, to notify the selected The node is returned as a standby node.
  • the P2P network is load-controlled by adding or leaving the reserved standby node to the target network, or by adjusting the node identifier, so that the connection rate of the P2P network can be not reduced.
  • FIG. 1 is a structural diagram of a P2P core network in related art
  • FIG. 2 is a flow chart of a method for network overload control in the related art
  • FIG. 5 are flowcharts of a network load control method according to an embodiment of the present invention.
  • FIG. 6 is a structural diagram of a registration server according to an embodiment of the present invention.
  • the load control node senses that the load of the target area is higher than the second load threshold set by the operator, sends a message to the registration server, requests to adjust the network load, and the registration server joins the node in the target area; When the load of the target area is lower than the third load threshold, the load control node requests to adjust the network load, and the registration server selects a node from the target area and exits the selected node from the target area.
  • the load control node may be a node in the P2P network where the service occurs.
  • the node where the service occurs refers to a common node in the peer-to-peer network, or a load balancing server. If the registration server aggregates the load control node, the load control node does not need to be A request message is sent to the registration server, and the load adjustment is requested, and the adjustment is directly performed by the registration server.
  • FIG. 3 is a network load control method according to an embodiment of the present invention, including:
  • Step 301 The load control node senses the target area, determines whether the load of the target area is higher than the set second load threshold, to determine whether the load adjustment needs to be initiated, and if necessary, executing step 302;
  • the second load threshold is for the average load or peak load of the network for a certain period of time.
  • the load control node is a node that currently has a service, or is a load balancing server, or The functional unit set in the registration server, that is, the load control node is combined with the registration server.
  • the target area includes one or more nodes, and the load control node may record the node identifier of the single node in the load adjustment request; and/or record the node identification range in the load adjustment request, where the node identification range represents one node or represents the node identifier phase Multiple nodes in succession. Indicates the node pointed to by the end node identifier when the two end node identifiers are the same before and after the node ID range.
  • Step 303 The registration server invokes the standby node to the standby node pool, wakes up the invoked standby node, and notifies the standby node to join the target area, so as to reduce the load of the target network area.
  • the standby node is in an idle state or a sleep state, and listens to the wakeup of the registration server. After listening to the wakeup of the registration server, it enters a working state, and sends a node joining the network request message to the registration server.
  • Step 304 The standby node starts, and sends a join network request message to the registration server.
  • ID node identifier
  • the registration server determines the node identifier assigned to the standby node based on the node identifier of the node included in the target area.
  • the registration server allocates node identities using different allocation methods of the Network Distributed Algorithm (DHT).
  • Step 306 Return the assigned node ID to the standby node.
  • DHT Network Distributed Algorithm
  • Step 307 The standby node joins the target area by using the assigned node ID to decompose the network load of the target area.
  • the registration server after receiving the load adjustment request of the load control server, the registration server selects a node with a light load to adjust to the target area, and includes:
  • Steps 401 to 402 are the same as steps 301 to 302;
  • Step 403 The registration server selects one or more nodes whose load is lower than the reference load of the target area from the network area outside the target area or selects one or more nodes whose load is lower than the first load threshold;
  • the reference load contains multiple nodes in the target area, it is the average load or the lowest load of the nodes in the target area; when one node is included in the target area, it is the load of the included nodes.
  • the registration server can query the load balancing server for the load of the nodes in the network.
  • Step 404 The registration server sends a network adjustment request message to the selected node to notify the selected node to rejoin the network.
  • Step 405 The selected node exits the network.
  • Step 406 The selected node sends a join network request message to the registration server, and re-adds the network.
  • Step 407 The registration server receives the join network request message of the selected node, and assigns a node identifier to the selected node.
  • the assigned node identifier enables the selected node to share the bearer of the target area address space for the target area after joining the network. To decompose the load on the target area;
  • the registration server determines the node identifier assigned to the selected node based on the node identifier of the node included in the target area.
  • the registration server allocates node identities using different allocation methods of the Network Distributed Algorithm (DHT).
  • Step 408 Return the assigned node ID to the selected node.
  • DHT Network Distributed Algorithm
  • Step 409 The selected node joins the target area by using the assigned node ID to decompose the network load of the target area.
  • FIG. 5 is another embodiment of the network load control method according to the embodiment.
  • the load control node senses that the load reduction of the target area is lower than the third load threshold, the load control node sends a network adjustment request to the registration server, and the registration server selects the node to exit the target and degrades.
  • the standby node include:
  • Step 501 The load control node senses the target area, and when the load of the target area is lower than the set third load threshold, step 502 is performed;
  • the third load threshold is for the average load of a certain time period of the network.
  • Step 502 The load control node sends a load adjustment request to the registration server, and notifies the registration server of the node identifier of the node included in the target area in the request;
  • the target area includes one or more nodes, and the load control node may record the node identifier of the single node in the load adjustment request; and/or record the node identification range in the load adjustment request, where the node identification range represents one node or represents the node identifier phase Multiple nodes in succession. Indicates the node pointed to by the end node identifier when the two end node identifiers are the same before and after the node ID range.
  • Step 503 The registration server selects one or more nodes from the target area to exit the service and enter the standby state.
  • Step 504 The registration server sends an exit network request to the selected node.
  • Step 505 The selected node exits the network and enters the standby state.
  • the backup status means that the node is in an idle or dormant state, and periodically listens to the registration request of the registration server.
  • the embodiment further provides a registration server, including: a load monitoring unit and a load control unit, where:
  • a load monitoring unit configured to monitor the load of the target area
  • the load control unit is configured to add a node to the target area after the load monitoring unit learns that the target area is overloaded.
  • the load control unit is configured to call the standby node, add the standby node to the target area, or select a node from the network area outside the target area, and add the selected node to the target area.
  • the load control unit includes: a node management subunit and an identifier assignment subunit, wherein: the node management subunit is configured to wake up the standby node, and receive a join network request message sent by the standby node;
  • the identifier allocation subunit is configured to allocate a node identifier to the standby node after the node management subunit receives the join network request message sent by the standby node, and the allocated node identifier enables the standby node to share the target area address for the target area after joining the network.
  • the node management subunit is configured to select one or more nodes that are lower than the reference load of the target area from the network area outside the target area or select one or more loads lower than the first load. a node of the threshold, notifying the selected node to rejoin the network, and receiving the join network request message sent by the selected node;
  • the identifier allocation subunit is configured to: after the node management subunit receives the join network request message sent by the standby node, assign a node identifier to the selected node, and the allocated node identifier makes the selected node be the target area after joining the network.
  • the bearer of the target area address space is shared to decompose the load of the target area.
  • Another registration server of this embodiment includes: a load monitoring unit and a load control unit, wherein:
  • a load monitoring unit configured to monitor the load of the target area
  • the load control unit is configured to, when the load monitoring unit knows that the load of the target area is lower than the third load threshold, select a node from the target area, and exit the selected node from the target area.
  • the load control unit includes a node management subunit, wherein: the node management subunit is configured to select a node from the target area, and notify the selected node to return to the standby node.
  • the P2P network is load-controlled by adding or leaving the reserved standby node to the target network, or by adjusting the node identification, so that the connection rate of the P2P network can be not reduced.

Abstract

一种网络负荷控制方法及登记服务器,该方法包括:登记服务器在获知目标区域过负载后,在所述目标区域中加入节点;或者登记服务器在获知目标区域的负荷低于负荷门限时,从所述目标区域中选择节点,将所选择的节点退出所述目标区域。

Description

一种网络负荷控制方法及登记服务器
技术领域
本发明涉及通讯领域,尤其是涉及一种网络负荷控制方法及登记服务器。
背景技术
目前, 对等互联或点对点 (Peer-to-Peer, P2P )在文件交换、 分布式计 算和服务共享等方面已经充分显示出了其强大的技术优势, 但是, P2P的应 用主要还是集中在 Internet (英特网)应用中, 在传统电信网络中尚未大规模 应用。 考虑到目前以及将来电信网络中, 会话控制的主流是 SIP (会话初始 化)协议, 因此, 将 P2P技术引入到电信网中, 必须能保证 SIP协议在 P2P 网络中的应用, 同时需要能够运行各类典型业务。
基于以上考虑, 目前业界的很多机构都在致力于研究如何将 P2P技术引 入到电信网络中来, 图 1是相关技术的一种 P2P核心网架构示意图, 其中: P2P叠加网 101由各类担负不同角色的对等体(本文中也称为节点)组 成的一张逻辑网络。
P2P叠加网中的对等节点 102为 P2P叠加网中的基本组成部分, 是能够 为同一 P2P叠加网中的其它节点提供存储和传送服务的节点。
非 P2P终端设备 103为接入到 P2P叠加网的不支持任何 P2P协议,仅支 持 SIP协议的终端设备。
P2P终端设备 104为接入到 P2P叠加网中的既支持 P2P协议,也支持 IP 协议的终端设备; 考虑到一般终端设备,特别是手持式终端设备的能力较弱, 所以很多情况下,在实际部署中, P2P终端设备仅作为 P2P客户端接入到 P2P 叠加网中, 并不承担存储、 传送等服务器的功能。
接入节点 105为非 P2P终端设备 103和 P2P终端设备 104等终端设备的 接入节点, 考虑到电信营运的需要, 包括 P2P终端与非 P2P终端都必须通过 就近的接入节点接入到 P2P叠加网中, 当该接入节点作为非 P2P终端的接入 节点时, 同时作为代理节点, 负责将非 P2P终端所釆用的 SIP协议与 P2P叠 加网内部路由 SIP所釆用协议的转换, 而当该节点作为 P2P终端的接入节点 时, 仅需要对消息进行中继。
登记服务器 106负责对等网网络节点加入管理, 为节点加入对等网络分 配节点标识。
负荷均衡 Λ良务器 107负责收集 P2P网络节点负荷。
在 P2P叠加网中, 对等节点 102之间根据分布式哈希算法( DHT ) , 实 现节点之间数据相互动态实时备份。
图 2是传统网络过负荷控制的流程示意图,其中前向节点为消息发送方, 后向节点为消息接收方, 当前向节点感知到后向节点过负荷, 前向节点根据 过负荷策略, 按比例丟弃或者向后向节点发送消息, 具体流程如下:
步骤 201 : 前向节点感知到后向节点过负荷;
前向节点感知后向节点负荷的方式一般包括: 后向节点告知、 负荷均衡 服务器告知和根据消息延迟推断等。
步骤 202: 前向节点根据过负荷策略, 根据后向节点过负荷程度, 按照 既定的比例丟弃或者发送消息给后向节点, 以减少后向节点的负荷。
如果将上述传统网络的过负荷控制方法应用到 P2P网络, 无法体现 P2P 网络的优势, 反而扩大 P2P网络的不稳定性, P2P网络的优势是以数量换取 高质量, 单个节点的稳定性要比传统网络单节点的性能要差, 在网络高负荷 运作时候, 更容易形成资源过负荷, 如果按照传统的过负荷控制方式, 会导 致在高负荷的时候, P2P网络的接通率要大大低于传统网络。
发明内容
本发明实施例提供一种网络负荷控制方法及登记服务器, 能够在不降低 P2P网络接通率的情况下实现对 P2P网络的负荷控制。
本发明实施例的一种网络负荷控制方法, 包括:
登记服务器在获知目标区域过负载后, 在所述目标区域中加入节点。 较佳地, 在所述目标区域中加入节点, 包括:
所述登记服务器调用备用节点,将所述备用节点加入到所述目标区域中, 或者从所述目标区域之外的网络区域中选择节点, 将所选择的节点加入到所 述目标区域中。
较佳地, 将所述备用节点加入到所述目标区域, 包括:
所述登记服务器唤醒所述备用节点, 在接收到所述备用节点发送的加入 网络请求消息后, 为所述备用节点分配节点标识, 所分配的节点标识使所述 备用节点在加入网络后为所述目标区域分担目标区域地址空间的承载, 以分 解所述目标区域的负荷。
较佳地, 从所述目标区域之外的网络区域中选择节点, 将所选择的节点 加入到所述目标区域中, 包括:
所述登记服务器从所述目标区域之外的网络区域中选择一个或多个负荷 低于所述目标区域的参考负荷的节点或选择一个或多个负荷低于第一负荷门 限的节点; 所述登记服务器通知所选择的节点重新加入网络, 并在接收到所选择的 节点发送的加入网络请求消息后, 为所选择的节点分配节点标识, 所分配的 节点标识使所选择的节点在加入网络后为所述目标区域分担目标区域地址空 间的承载, 以分解所述目标区域的负荷。
较佳地, 所述参考负荷在所述目标区域中包含多个节点时, 为所述目标 区域中的节点的平均负荷或最低负荷; 在所述目标区域中包含一个节点时, 为所包含的节点的负荷。
较佳地, 所述备用节点为处于空闲状态或者休眠状态, 并监听所述登记 服务器的唤醒, 在监听到所述登记服务器的唤醒后, 进入工作状态, 向所述 登记服务器发送加入网络请求消息的节点。
较佳地, 所述登记服务器获知目标区域过负载的步骤, 包括:
负荷控制节点判断所述目标区域的负荷是否高于第二负荷门限, 如果高 于, 则确定需要发起负荷调整, 向所述登记服务器发送负荷调整请求; 或者, 在所述负荷控制节点与所述登记服务器合设时, 所述登记服务器感知所 述目标区域的负荷, 判断所述目标区域的负荷是否高于第二负荷门限。
较佳地, 所述目标区域中包含一个或多个节点, 所述负荷控制节点在所 述负荷调整请求中将所述目标区域中包含的节点的节点标识通知给所述登记 服务器。
较佳地, 所述负荷控制节点在所述负荷调整请求中将所述目标区域中包 含的节点的节点标识通知给所述登记服务器的方式包含以下一种或多种, 包 括:
所述负荷控制节点在所述负荷调整请求中记录单个节点的节点标识; 所述负荷控制节点在所述负荷调整请求中记录节点标识范围, 所述节点 标识范围表示一个节点或表示节点标识相连续的多个节点。
较佳地, 在所述节点标识范围的前后两个端节点标识相同时, 表示所述 端节点标识指向的节点。
较佳地, 所述负荷控制节点为当前发生业务的节点, 或者为负荷均衡服 务器, 或者为设置在所述登记服务器中的功能单元。
本发明实施例还提供另一种网络负荷控制方法, 包括:
登记服务器在获知目标区域的负荷低于第三负荷门限时, 从所述目标区 域中选择节点, 将所选择的节点退出所述目标区域。
较佳地, 将所选择的节点退出所述目标区域, 包括:
所述登记服务器通知所选择的节点退还为备用节点。
较佳地, 所述备用节点为处于空闲状态或者休眠状态, 并监听所述登记 服务器的唤醒, 在监听到所述登记服务器的唤醒后, 进入工作状态, 向所述 登记服务器发送加入网络请求消息的节点。
本发明实施例的一种登记服务器, 包括: 负荷监控单元和负荷控制单元, 其中:
所述负荷监控单元, 设置为监控目标区域的负荷;
所述负荷控制单元,设置为在所述负荷监控单元获知目标区域过负载后, 在所述目标区域中加入节点。 较佳地, 所述负荷控制单元, 是设置为调用备用节点, 将所述备用节点 加入到所述目标区域中, 或者从所述目标区域之外的网络区域中选择节点, 将所选择的节点加入到所述目标区域中。
较佳地, 所述负荷控制单元包括: 节点管理子单元和标识分配子单元, 其中: 所述节点管理子单元, 设置为唤醒所述备用节点, 接收所述备用节点发 送的加入网络请求消息;
所述标识分配子单元, 设置为在所述节点管理子单元接收到所述备用节 点发送的加入网络请求消息后, 为所述备用节点分配节点标识, 所分配的节 点标识使所述备用节点在加入网络后为所述目标区域分担目标区域地址空间 的承载, 以分解所述目标区域的负荷。
较佳地, 所述负荷控制单元包括: 节点管理子单元和标识分配子单元, 其中:
所述节点管理子单元, 设置为从所述目标区域之外的网络区域中选择一 个或多个负荷低于所述目标区域的参考负荷的节点或选择一个或多个负荷低 于第一负荷门限的节点, 通知所选择的节点重新加入网络, 并接收所选择的 节点发送的加入网络请求消息;
所述标识分配子单元, 设置为在所述节点管理子单元接收到所述备用节 点发送的加入网络请求消息后, 为所选择的节点分配节点标识, 所分配的节 点标识使所选择的节点在加入网络后为所述目标区域分担目标区域地址空间 的承载, 以分解所述目标区域的负荷。 本发明实施例还提供另一种登记服务器, 包括: 负荷监控单元和负荷控 制单元, 其中:
所述负荷监控单元, 设置为监控目标区域的负荷;
所述负荷控制单元, 设置为在所述负荷监控单元获知目标区域的负荷低 于第三负荷门限时, 从所述目标区域中选择节点, 将所选择的节点退出所述 目标区域。
较佳地, 所述负荷控制单元包括节点管理子单元, 其中:
所述节点管理子单元, 设置为从所述目标区域中选择节点, 通知所选择 的节点退还为备用节点。
综上所述, 本发明实施例通过将预留的备用节点加入或退出目标网络, 或者通过节点标识调整的方式, 对 P2P网络进行负荷控制, 能够不降低 P2P 网络的接通率。 附图概述
图 1为相关技术中 P2P核心网的架构图;
图 2为相关技术中网络过负荷控制的方法的流程图;
图 3〜图 5为本发明实施方式的网络负荷控制方法的流程图;
图 6为本发明实施方式的登记服务器的架构图。
本发明的较佳实施方式
本实施方式中, 在 P2P网络中, 负荷控制节点感知到目标区域的负荷高 于运营商设置的第二负荷门限,发消息通知登记服务器,请求调整网络负荷, 登记服务器在目标区域中加入节点; 负荷控制节点在目标区域的负荷低于第 三负荷门限时, 请求调整网络负荷, 登记服务器从目标区域中选择节点, 将 所选择的节点退出目标区域。 负荷控制节点可以是 P2P网络中的一个发生业 务的节点, 这里的发生业务的节点指对等网络中的普通节点, 或者是负荷均 衡服务器, 如果登记服务器集合负荷控制节点, 则无需由负荷控制节点向登 记服务器发送请求消息, 请求负荷调整, 由登记服务器器直接进行调整。
图 3为本实施方式的网络负荷控制方法, 包括:
步骤 301 : 负荷控制节点感知目标区域, 判断目标区域的负荷是否高于 设置的第二负荷门限, 以确定是否需要发起负荷调整, 如果需要, 则执行步 骤 302;
第二负荷门限针对的是网络的某个时间段的平均负荷或者负荷峰值。 负荷控制节点为当前发生业务的节点, 或者为负荷均衡服务器, 或者为 设置在登记服务器中的功能单元, 即: 负荷控制节点与登记服务器合设。 步骤 302: 负荷控制节点向登记服务器发送负荷调整请求, 在请求中将 目标区域中包含的节点的节点标识通知给登记服务器;
目标区域中包含一个或多个节点, 负荷控制节点可以在负荷调整请求中 记录单个节点的节点标识; 和 /或在负荷调整请求中记录节点标识范围, 节点 标识范围表示一个节点或表示节点标识相连续的多个节点。 在节点标识范围 的前后两个端节点标识相同时, 表示端节点标识指向的节点。
步骤 303: 登记服务器向备用节点池调用备用节点, 唤醒所调用的备用 节点, 通知备用节点加入到目标区域, 以降低目标网络区域的负荷;
备用节点为处于空闲状态或者休眠状态, 并监听登记服务器的唤醒, 在 监听到登记服务器的唤醒后, 进入工作状态, 向登记服务器发送加入网络请 求消息的节点。
步骤 304: 备用节点启动, 并向登记服务器发出加入网络请求消息; 步骤 305: 登记服务器收到备用节点的加入网络请求消息, 为备用节点 分配节点标识(ID ) , 所分配的节点标识使备用节点在加入网络后为目标区 域分担目标区域地址空间的承载, 以分解目标区域的负荷;
登记服务器根据目标区域中包含的节点的节点标识确定为备用节点分配 的节点标识。
登记服务器釆用网络分布式算法(DHT )的不同分配方式分配节点标识。 步骤 306: 返回分配的节点 ID给备用节点;
步骤 307: 备用节点使用所分配的节点 ID加入到目标区域, 以分解目标 区域的网络负荷。
图 4是本实施方式的网络负荷控制方法的另一实现方式, 在该实现方式 中, 登记服务器在收到负荷控制服务器的负荷调整请求后, 选择负荷较轻的 节点调整到目标区域, 包括:
步骤 401~402同步骤 301~302; 步骤 403 : 登记服务器从目标区域之外的网络区域中选择一个或多个负 荷低于目标区域的参考负荷的节点或选择一个或多个负荷低于第一负荷门限 的节点;
参考负荷在目标区域中包含多个节点时, 为目标区域中的节点的平均负 荷或最低负荷; 在目标区域中包含一个节点时, 为所包含的节点的负荷。
登记服务器可以向负荷均衡服务器查询网络中节点的负荷。
步骤 404: 登记服务器向所选择的节点发送网络调整请求消息, 通知所 选择的节点重新加入网络; 步骤 405: 所选择的节点退出网络;
步骤 406: 所选择的节点向登记服务器发送加入网络请求消息, 重新加 入网络;
步骤 407: 登记服务器收到所选择的节点的加入网络请求消息, 为所选 择的节点分配节点标识, 所分配的节点标识使所选择的节点在加入网络后为 目标区域分担目标区域地址空间的承载, 以分解目标区域的负荷;
登记服务器根据目标区域中包含的节点的节点标识确定为所选择的节点 分配的节点标识。
登记服务器釆用网络分布式算法(DHT )的不同分配方式分配节点标识。 步骤 408: 返回分配的节点 ID给所选择的节点;
步骤 409: 所选择的节点使用所分配的节点 ID加入到目标区域, 以分解 目标区域的网络负荷。
图 5是本实施方式的网络负荷控制方法的另一实施例, 负荷控制节点感 知目标区域的负荷减轻低于第三负荷门限, 则向登记服务器发送网络调整请 求, 登记服务器选择节点退出目标, 退化为备用节点, 包括:
步骤 501 : 负荷控制节点感知目标区域, 在目标区域的负荷低于设置的 第三负荷门限时, 执行步骤 502;
第三负荷门限针对的是网络的某个时间段的平均负荷。 步骤 502: 负荷控制节点向登记服务器发送负荷调整请求, 在请求中将 目标区域中包含的节点的节点标识通知给登记服务器;
目标区域中包含一个或多个节点, 负荷控制节点可以在负荷调整请求中 记录单个节点的节点标识; 和 /或在负荷调整请求中记录节点标识范围, 节点 标识范围表示一个节点或表示节点标识相连续的多个节点。 在节点标识范围 的前后两个端节点标识相同时, 表示端节点标识指向的节点。
步骤 503 : 登记服务器从目标区域中选择一个或者多个节点退出服务, 进入备用状态;
步骤 504: 登记服务器向所选择的节点发送退出网络请求;
步骤 505: 所选择的节点退出网络, 并进入备用状态。
这里的备份状态指节点处于空闲或者休眠状态, 定时监听登记服务器的 激活请求。
如图 6所示, 本实施方式还提供了一种登记服务器, 包括: 负荷监控单 元和负荷控制单元, 其中:
负荷监控单元, 设置为监控目标区域的负荷;
负荷控制单元, 设置为在负荷监控单元获知目标区域过负载后, 在目标 区域中加入节点。
负荷控制单元, 设置为调用备用节点, 将备用节点加入到目标区域中, 或者从目标区域之外的网络区域中选择节点, 将所选择的节点加入到目标区 域中。
负荷控制单元包括: 节点管理子单元和标识分配子单元, 其中: 节点管理子单元, 设置为唤醒备用节点, 接收备用节点发送的加入网络 请求消息;
标识分配子单元, 设置为在节点管理子单元接收到备用节点发送的加入 网络请求消息后, 为备用节点分配节点标识, 所分配的节点标识使备用节点 在加入网络后为目标区域分担目标区域地址空间的承载, 以分解目标区域的 负荷。 在另一实现方式中, 节点管理子单元, 设置为从目标区域之外的网络区 域中选择一个或多个负荷低于目标区域的参考负荷的节点或选择一个或多个 负荷低于第一负荷门限的节点, 通知所选择的节点重新加入网络, 并接收所 选择的节点发送的加入网络请求消息;
标识分配子单元, 设置为在节点管理子单元接收到备用节点发送的加入 网络请求消息后, 为所选择的节点分配节点标识, 所分配的节点标识使所选 择的节点在加入网络后为目标区域分担目标区域地址空间的承载, 以分解目 标区域的负荷。
本实施方式的另一登记服务器, 包括: 负荷监控单元和负荷控制单元, 其中:
负荷监控单元, 设置为监控目标区域的负荷;
负荷控制单元, 设置为在负荷监控单元获知目标区域的负荷低于第三负 荷门限时, 从目标区域中选择节点, 将所选择的节点退出目标区域。
负荷控制单元包括节点管理子单元, 其中: 节点管理子单元, 设置为从 目标区域中选择节点, 通知所选择的节点退还为备用节点。
本领域普通技术人员可以理解上述方法中的全部或部分步骤可通过程序 来指令相关硬件完成, 所述程序可以存储于计算机可读存储介质中, 如只读 存储器、 磁盘或光盘等。 可选地, 上述实施例的全部或部分步骤也可以使用 一个或多个集成电路来实现。 相应地, 上述实施例中的各模块 /单元可以釆用 硬件的形式实现, 也可以釆用软件功能模块的形式实现。 本发明不限制于任 何特定形式的硬件和软件的结合。
当然, 本发明还可有其他多种实施例, 在不背离本发明精神及其实质的 但这些相应的改变和变形都应属于本发明所附的权利要求的保护范围。
工业实用性
本发明实施例通过将预留的备用节点加入或退出目标网络, 或者通过节点标 识调整的方式, 对 P2P网络进行负荷控制, 能够不降低 P2P网络的接通率。

Claims

权 利 要 求 书
1、 一种网络负荷控制方法, 其包括:
登记服务器在获知目标区域过负载后, 在所述目标区域中加入节点。
2、 如权利要求 1 所述的方法, 其中, 在所述目标区域中加入节点的步 骤, 包括:
所述登记服务器调用备用节点,将所述备用节点加入到所述目标区域中, 或者从所述目标区域之外的网络区域中选择节点, 将所选择的节点加入到所 述目标区域中。
3、 如权利要求 2 所述的方法, 其中, 将所述备用节点加入到所述目标 区域的步骤, 包括:
所述登记服务器唤醒所述备用节点, 在接收到所述备用节点发送的加入 网络请求消息后, 为所述备用节点分配节点标识, 所分配的节点标识使所述 备用节点在加入网络后为所述目标区域分担目标区域地址空间的承载, 以分 解所述目标区域的负荷。
4、 如权利要求 2 所述的方法, 其中, 从所述目标区域之外的网络区域 中选择节点, 将所选择的节点加入到所述目标区域中的步骤, 包括:
所述登记服务器从所述目标区域之外的网络区域中选择一个或多个负荷 低于所述目标区域的参考负荷的节点或选择一个或多个负荷低于第一负荷门 限的节点; 所述登记服务器通知所选择的节点重新加入网络, 并在接收到所选择的 节点发送的加入网络请求消息后, 为所选择的节点分配节点标识, 所分配的 节点标识使所选择的节点在加入网络后为所述目标区域分担目标区域地址空 间的承载, 以分解所述目标区域的负荷。
5、 如权利要求 4 所述的方法, 其中: 在所述目标区域中包含多个节点 时, 所述参考负荷为所述目标区域中的节点的平均负荷或最低负荷; 在所述 目标区域中包含一个节点时, 所述参考负荷为所包含的节点的负荷。
6、 如权利要求 2 所述的方法, 其中: 所述备用节点为处于空闲状态或 者休眠状态, 并监听所述登记服务器的唤醒, 在监听到所述登记服务器的唤 醒后, 进入工作状态, 向所述登记服务器发送加入网络请求消息的节点。
7、 如权利要求 1 所述的方法, 其中, 所述登记服务器获知目标区域过 负载的步骤, 包括:
负荷控制节点判断所述目标区域的负荷是否高于第二负荷门限, 如果高 于, 则确定需要发起负荷调整, 向所述登记服务器发送负荷调整请求; 或者, 在所述负荷控制节点与所述登记服务器合设时, 所述登记服务器感知所 述目标区域的负荷, 判断所述目标区域的负荷是否高于第二负荷门限。
8、 如权利要求 7 所述的方法, 其中: 所述目标区域中包含一个或多个 节点, 所述负荷控制节点在所述负荷调整请求中将所述目标区域中包含的节 点的节点标识通知给所述登记服务器。
9、 如权利要求 8 所述的方法, 其中, 所述负荷控制节点在所述负荷调 整请求中将所述目标区域中包含的节点的节点标识通知给所述登记服务器 的, 包括:
所述负荷控制节点在所述负荷调整请求中记录单个节点的节点标识; 或 者
所述负荷控制节点在所述负荷调整请求中记录节点标识范围, 所述节点 标识范围表示一个节点或表示节点标识相连续的多个节点。
10、 如权利要求 9所述的方法, 其中: 在所述节点标识范围的前后两个 端节点标识相同时, 表示所述端节点标识指向的节点。
11、 如权利要求 1所述的方法, 其中: 所述负荷控制节点为当前发生业 务的节点, 或者为负荷均衡服务器, 或者为设置在所述登记服务器中的功能 单元。
12、 一种网络负荷控制方法, 其包括:
登记服务器在获知目标区域的负荷低于第三负荷门限时, 从所述目标区 域中选择节点, 将所选择的节点退出所述目标区域。
13、 如权利要求 12 所述的方法, 其中, 将所选择的节点退出所述目标 区域的步骤, 包括:
所述登记服务器通知所选择的节点退还为备用节点。
14、 如权利要求 13 所述的方法, 其中: 所述备用节点为处于空闲状态 或者休眠状态, 并监听所述登记服务器的唤醒, 在监听到所述登记服务器的 唤醒后, 进入工作状态, 向所述登记服务器发送加入网络请求消息的节点。
15、 一种登记服务器, 其包括: 负荷监控单元和负荷控制单元, 其中: 所述负荷监控单元, 设置为监控目标区域的负荷;
所述负荷控制单元,设置为在所述负荷监控单元获知目标区域过负载后, 在所述目标区域中加入节点。
16、 如权利要求 15所述的登记服务器, 其中:
所述负荷控制单元, 是设置为: 调用备用节点, 将所述备用节点加入到 所述目标区域中, 或者从所述目标区域之外的网络区域中选择节点, 将所选 择的节点加入到所述目标区域中。
17、 如权利要求 16所述的登记服务器, 其中, 所述负荷控制单元包括: 节点管理子单元和标识分配子单元, 其中:
所述节点管理子单元, 设置为唤醒所述备用节点, 接收所述备用节点发 送的加入网络请求消息;
所述标识分配子单元, 设置为在所述节点管理子单元接收到所述备用节 点发送的加入网络请求消息后, 为所述备用节点分配节点标识, 所分配的节 点标识使所述备用节点在加入网络后为所述目标区域分担目标区域地址空间 的承载, 以分解所述目标区域的负荷。
18、 如权利要求 16所述的登记服务器, 其中, 所述负荷控制单元包括: 节点管理子单元和标识分配子单元, 所述节点管理子单元, 设置为从所述目标区域之外的网络区域中选择一 个或多个负荷低于所述目标区域的参考负荷的节点或选择一个或多个负荷低 于第一负荷门限的节点, 通知所选择的节点重新加入网络, 并接收所选择的 节点发送的加入网络请求消息;
所述标识分配子单元, 设置为在所述节点管理子单元接收到所述备用节 点发送的加入网络请求消息后, 为所选择的节点分配节点标识, 所分配的节 点标识使所选择的节点在加入网络后为所述目标区域分担目标区域地址空间 的承载, 以分解所述目标区域的负荷。
19、 一种登记服务器, 其包括: 负荷监控单元和负荷控制单元, 其中: 所述负荷监控单元, 设置为监控目标区域的负荷;
所述负荷控制单元, 设置为在所述负荷监控单元获知目标区域的负荷低 于第三负荷门限时, 从所述目标区域中选择节点, 将所选择的节点退出所述 目标区域。
20、 如权利要求 19 所述的登记服务器, 其中, 所述负荷控制单元包括 节点管理子单元, 其中:
所述节点管理子单元, 设置为从所述目标区域中选择节点, 通知所选择的节 点退还为备用节点。
PCT/CN2012/086560 2012-01-11 2012-12-13 一种网络负荷控制方法及登记服务器 WO2013104231A1 (zh)

Priority Applications (2)

Application Number Priority Date Filing Date Title
EP12865297.1A EP2790362B1 (en) 2012-01-11 2012-12-13 Network load control method and registration server
US14/371,561 US20150009812A1 (en) 2012-01-11 2012-12-13 Network load control method and registration server

Applications Claiming Priority (2)

Application Number Priority Date Filing Date Title
CN201210007024.0 2012-01-11
CN2012100070240A CN103209136A (zh) 2012-01-11 2012-01-11 一种网络负荷控制方法及登记服务器

Publications (1)

Publication Number Publication Date
WO2013104231A1 true WO2013104231A1 (zh) 2013-07-18

Family

ID=48756225

Family Applications (1)

Application Number Title Priority Date Filing Date
PCT/CN2012/086560 WO2013104231A1 (zh) 2012-01-11 2012-12-13 一种网络负荷控制方法及登记服务器

Country Status (4)

Country Link
US (1) US20150009812A1 (zh)
EP (1) EP2790362B1 (zh)
CN (1) CN103209136A (zh)
WO (1) WO2013104231A1 (zh)

Families Citing this family (2)

* Cited by examiner, † Cited by third party
Publication number Priority date Publication date Assignee Title
WO2015042773A1 (zh) * 2013-09-24 2015-04-02 华为技术有限公司 一种接入点配置方法和控制器
KR102359886B1 (ko) 2015-07-07 2022-02-09 삼성디스플레이 주식회사 표시 패널 구동 장치, 이를 이용한 표시 패널 구동 방법 및 이를 포함하는 표시 장치

Citations (3)

* Cited by examiner, † Cited by third party
Publication number Priority date Publication date Assignee Title
CN1614928A (zh) * 2003-11-06 2005-05-11 国际商业机器公司 操作服务器群集的方法和系统
CN101686172A (zh) * 2008-09-27 2010-03-31 华为技术有限公司 一种网关节点的选择方法、系统和设备
CN101729390A (zh) * 2008-10-22 2010-06-09 中国移动通信集团公司 分布式哈希表dht网络及其构建方法、节点

Family Cites Families (32)

* Cited by examiner, † Cited by third party
Publication number Priority date Publication date Assignee Title
US4756019A (en) * 1986-08-27 1988-07-05 Edmund Szybicki Traffic routing and automatic network management system for telecommunication networks
US20010034752A1 (en) * 2000-01-26 2001-10-25 Prompt2U Inc. Method and system for symmetrically distributed adaptive matching of partners of mutual interest in a computer network
US7174390B2 (en) * 2001-04-20 2007-02-06 Egenera, Inc. Address resolution protocol system and method in a virtual network
GB0119145D0 (en) * 2001-08-06 2001-09-26 Nokia Corp Controlling processing networks
JP2003131960A (ja) * 2001-10-26 2003-05-09 Hitachi Ltd データ中継方法
US7984110B1 (en) * 2001-11-02 2011-07-19 Hewlett-Packard Company Method and system for load balancing
US7734726B2 (en) * 2001-11-27 2010-06-08 International Business Machines Corporation System and method for dynamically allocating processing on a network amongst multiple network servers
US20040260745A1 (en) * 2003-06-18 2004-12-23 Gage Christopher A. S. Load balancer performance using affinity modification
US8738804B2 (en) * 2004-01-08 2014-05-27 International Business Machines Corporation Supporting transactions in a data network using router information
JP4371056B2 (ja) * 2005-01-07 2009-11-25 ブラザー工業株式会社 ノード装置、ネットワーク参加処理プログラム、及びネットワーク参加処理方法等
US20060212584A1 (en) * 2005-03-15 2006-09-21 Qian Xiang Shi Ji (Beijing) Technology Development Co. Ltd. Method and system for accelerating downloading of web page content by a peer-to-peer network
TWI330022B (en) * 2006-11-06 2010-09-01 Inst Information Industry Method and computer program product for a new node joining a peer to peer network and computer readable medium and the network thereof
US7844839B2 (en) * 2006-12-07 2010-11-30 Juniper Networks, Inc. Distribution of network communications based on server power consumption
CN100531098C (zh) * 2007-03-13 2009-08-19 华为技术有限公司 一种对等网络系统及重叠网间节点的互通方法
US8780917B2 (en) * 2007-03-14 2014-07-15 James Roger Hargrave System, method and computer readable medium for communication on a Zigbee network
CN101431463B (zh) * 2007-11-09 2014-07-09 华为技术有限公司 一种接纳控制方法、装置和相关通信系统
US7940696B2 (en) * 2007-12-20 2011-05-10 International Business Macines Corporation Remotely booting computing nodes in a switching domain
US8583810B2 (en) * 2008-01-04 2013-11-12 Red Hat, Inc. Session affinity cache and manager
JP5125679B2 (ja) * 2008-03-27 2013-01-23 日本電気株式会社 負荷分散装置及び方法とプログラム
CN101262369B (zh) * 2008-03-28 2011-05-11 华为技术有限公司 调度服务器的主备实现方法及调度服务器
US8631134B2 (en) * 2008-07-30 2014-01-14 Visa U.S.A. Inc. Network architecture for secure data communications
JP5589847B2 (ja) * 2008-10-27 2014-09-17 日本電気株式会社 基地局、無線通信システム、基地局の制御方法、無線通信方法、および基地局の制御プログラム
US7848355B2 (en) * 2008-10-30 2010-12-07 International Business Machines Corporation Resource allocation in peer-to-peer streaming
US8296434B1 (en) * 2009-05-28 2012-10-23 Amazon Technologies, Inc. Providing dynamically scaling computing load balancing
EP2514140A4 (en) * 2009-12-18 2017-02-22 Hewlett-Packard Enterprise Development LP Proxy agents in a network
US8169936B2 (en) * 2009-12-22 2012-05-01 Motorola Solutions, Inc. Decoupled cascaded mixers architechture and related methods
US8224971B1 (en) * 2009-12-28 2012-07-17 Amazon Technologies, Inc. Using virtual networking devices and routing information to initiate external actions
US9084208B2 (en) * 2010-02-15 2015-07-14 Telefonaktiebolaget L M Ericsson (Publ) Energy-efficient network methods and apparatus
US8266204B2 (en) * 2010-03-15 2012-09-11 Microsoft Corporation Direct addressability and direct server return
CN102377635B (zh) * 2010-08-06 2014-01-01 北京乾唐视联网络科技有限公司 一种城域网通信方法及通信系统
US8767737B2 (en) * 2011-11-30 2014-07-01 Industrial Technology Research Institute Data center network system and packet forwarding method thereof
TWI501603B (zh) * 2011-12-19 2015-09-21 Ind Tech Res Inst 在機器類型通信網路中對機器類型通信裝置分組之方法以及通信方法

Patent Citations (3)

* Cited by examiner, † Cited by third party
Publication number Priority date Publication date Assignee Title
CN1614928A (zh) * 2003-11-06 2005-05-11 国际商业机器公司 操作服务器群集的方法和系统
CN101686172A (zh) * 2008-09-27 2010-03-31 华为技术有限公司 一种网关节点的选择方法、系统和设备
CN101729390A (zh) * 2008-10-22 2010-06-09 中国移动通信集团公司 分布式哈希表dht网络及其构建方法、节点

Also Published As

Publication number Publication date
EP2790362A1 (en) 2014-10-15
EP2790362B1 (en) 2018-07-25
EP2790362A4 (en) 2014-12-31
US20150009812A1 (en) 2015-01-08
CN103209136A (zh) 2013-07-17

Similar Documents

Publication Publication Date Title
KR20090069312A (ko) 리소스 공급을 위한 방법, 시스템, 및 에지 서버
RU2475992C2 (ru) Способы и устройство для оптимального участия устройств одноранговой оверлейной сети
US20080267144A1 (en) System and method for managing broadcast and/or multicast based communication sessions for mobile nodes
US20060045100A1 (en) Method for improving quality-of-service management in networks
WO2008110054A1 (fr) Système de réseau pair a pair, nœud de proximité, et procédé de communication pour les nœuds parmi les réseaux de recouvrement
WO2010127618A1 (zh) 一种实现流媒体内容服务的系统和方法
WO2011113289A1 (zh) 一种业务路由方法和业务网络
WO2010028590A1 (zh) 地址列表的提供方法、对等网络及其调度方法
WO2011120256A1 (zh) 均衡负载的方法、系统及相应设备
EP3095229B1 (en) Method and nodes for configuring a communication path for a media service
JP5372140B2 (ja) ネットワークを管理するための方法及び装置
US8650309B2 (en) Cascading architecture for audio and video streams
EP3496432B1 (en) Efficient multicast transmission
WO2009127132A1 (zh) 报文分发方法、设备及系统
US20110078312A1 (en) Method and system for monitoring incoming connection requests in a Peer-to-Peer network
WO2009117946A1 (zh) 调度服务器的主备实现方法及调度服务器
WO2010096989A1 (zh) 一种用于发现p2p流量优化服务的方法、装置和系统
KR101517380B1 (ko) 멀티캐스팅을 요청하고, 멀티캐스팅 요청들을 처리하고 이러한 처리를 보조하기 위한 방법 및 디바이스
WO2013104231A1 (zh) 一种网络负荷控制方法及登记服务器
WO2011015094A1 (zh) 对等网络管理系统及其实现管理的方法
CN101340457B (zh) 一种不依赖于中心服务器的对等网络启动方法和系统
CN101378392A (zh) 一种p2p环境下资源查询的方法和装置
EP2216940A1 (en) Method, system and device for switching source
EP2259507B1 (en) Method and device for controlling a node to join in a peer-to-peer network
WO2010069219A1 (zh) 一种p2p系统及种子查询方法

Legal Events

Date Code Title Description
121 Ep: the epo has been informed by wipo that ep was designated in this application

Ref document number: 12865297

Country of ref document: EP

Kind code of ref document: A1

WWE Wipo information: entry into national phase

Ref document number: 14371561

Country of ref document: US

Ref document number: 2012865297

Country of ref document: EP

NENP Non-entry into the national phase

Ref country code: DE