论文部分内容阅读
针对Skyline计算中,需要处理的数据量大,处理时间较长的问题,引入P2P网络,将数据计算的压力分摊至各网络节点.预处理中,合理采用数据映射方式,增加同一节点数据间的决定能力,减少本地计算量.在全局Skyline计算时,通过网络点对点传输,将各节点需计算数据量减少至最小.实验结果和理论分析表明,新算法可将Chord网络中,本地节点需要计算的数据量减至10%左右,当数据量较大,数据各维度间没有相关性,且网络传输较为正常时,算法具有明显优势.
In the calculation of Skyline, large amount of data to be processed and long processing time are introduced into the P2P network to spread the pressure of data calculation to each network node. In the preprocessing, data mapping is adopted reasonably to increase the data between the same node Determine the ability to reduce the amount of local computation.When the global Skyline calculation, through the network point-to-point transmission, the amount of data required to be reduced by each node to a minimum.Experimental results and theoretical analysis show that the new algorithm can be used in the Chord network, the local node needs to be calculated When the amount of data is reduced to about 10%, the algorithm has obvious advantages when the amount of data is large and there is no correlation between the data dimensions and the network transmission is normal.