会员体验
专利管家(专利管理)
工作空间(专利管理)
风险监控(情报监控)
数据分析(专利分析)
侵权分析(诉讼无效)
联系我们
交流群
官方交流:
QQ群: 891211   
微信请扫码    >>>
现在联系顾问~
热词
    • 3. 发明授权
    • Connection management in peer-to-peer content distribution clouds
    • 对等内容分发云中的连接管理
    • US07849196B2
    • 2010-12-07
    • US12097946
    • 2006-12-04
    • Christos GkantsidisJohn MillerManuel CostaPablo Rodriguez RodriguezStuart Ranson
    • Christos GkantsidisJohn MillerManuel CostaPablo Rodriguez RodriguezStuart Ranson
    • G06F15/173
    • H04L67/104H04L67/06H04L67/1085
    • A topology management process is implemented which involves removing or “tearing down” connections between nodes in certain situations in order to try to replace those connections with more optimal ones. Idle connections are torn down unless those are in a “notify” state; a notify state being one in which a request for content has been made to a neighbour but that neighbour has no available content as yet. Idle connections in a notify state are torn down only if they remain idle for a longer time than that required before an idle connection is torn down. To avoid problems caused by clusters of node forming and of loners being unable to join the cloud, network churn algorithms are taught. These involve requiring nodes to drop connections when specified conditions are met. Relative content distribution between connections is monitored and this information used to influence selection of those connections to drop.
    • 实现了拓扑管理过程,其涉及在某些情况下删除或“拆除”节点之间的连接,以便尝试用更优选的连接替换这些连接。 空闲连接被拆除,除非它们处于“通知”状态; 通知状态是向邻居做出对内容的请求的通知状态,但是该邻居还没有可用的内容。 通知状态下的空闲连接只有在空闲连接断开之前保持空闲时间较长的时间才会被拆除。 为了避免由于节点形成的簇和不能加入云的孤岛造成的问题,教授了网络流失算法。 这些涉及要求节点在满足指定条件时删除连接。 监视连接之间的相对内容分配,并将此信息用于影响这些连接的选择。
    • 4. 发明申请
    • Connection Management in Peer-to-Peer Content Distribution Clouds
    • 对等内容分发云中的连接管理
    • US20080294779A1
    • 2008-11-27
    • US12097946
    • 2006-12-04
    • Christos GkantsidisJohn MillerManuel CostaPablo Rodriguez RodriguezStuart Ranson
    • Christos GkantsidisJohn MillerManuel CostaPablo Rodriguez RodriguezStuart Ranson
    • G06F15/173
    • H04L67/104H04L67/06H04L67/1085
    • A topology management process is implemented which involves removing or “tearing down” connections between nodes in certain situations in order to try to replace those connections with more optimal ones. Idle connections are torn down unless those are in a “notify” state; a notify state being one in which a request for content has been made to a neighbour but that neighbour has no available content as yet. Idle connections in a notify state are torn down only if they remain idle for a longer time than that required before an idle connection is torn down. To avoid problems caused by clusters of node forming and of loners being unable to join the cloud, network churn algorithms are taught. These involve requiring nodes to drop connections when specified conditions are met. Relative content distribution between connections is monitored and this information used to influence selection of those connections to drop.
    • 实现了拓扑管理过程,其涉及在某些情况下删除或“拆除”节点之间的连接,以便尝试用更优选的连接替换这些连接。 空闲连接被拆除,除非它们处于“通知”状态; 通知状态是向邻居做出对内容的请求的通知状态,但是该邻居还没有可用的内容。 通知状态下的空闲连接只有在空闲连接断开之前保持空闲时间较长的时间才会被拆除。 为了避免由于节点形成的簇和不能加入云的孤岛造成的问题,教授了网络流失算法。 这些涉及要求节点在满足指定条件时删除连接。 监视连接之间的相对内容分配,并将此信息用于影响这些连接的选择。