【摘要】 在对分布式云环境下的海量数据进行查询的过程中,容易出现带宽有限、能量有限、链路频繁断接的特点,导致传统的查询方法由于采用自适应分发数据机制来减少数据的通信量,不能有效实现海量数据查询,提出一种基于查询节点动态轮换的分布式环境下海量数据有效查询方法,将分布式云计算环境下的网络看作是一个带权的无向图,给出分布式云计算环境下单位数据传输时延计算公式,分析了系统模型及海量数据查询的问题描述。将每次剩余能量最高的节点作为查询节点,当接收到一个查询请求时,各节点需感应同时采集该节点所覆盖区域的数据源,对其进行计算、处理等操作,获取趋于请求的结果集,每个节点沿各自路径将数据传输至查询节点,在传输的过程中,各节点将接收到的数据进行融合处理。仿真实验结果表明,所提方法具有很高的查询命中率。更多还原

【Abstract】 The huge amounts of data in a distributed cloud environment in the process of query, it’s easy to have a limited bandwidth, limited energy, link the characteristics of a breakout, frequently lead to the traditional query method with adaptive data distribution mechanism to reduce the traffic data, cannot effectively realize the huge amounts of data query, in this paper, a dynamic query node based on rotation under the distributed environment of huge amounts of data query methods effectively, will be distributed in cloud computing environment of the network as a weighted undirected graph, gives a distributed cloud environment formula of unit of data transmission delay, analyzes the system model and huge amounts of data query problem description.Every time will be the highest residual energy of nodes as a query node,When receives a query request, each node needs to sensor nodes covered area on the acquisition data sources at the same time, the calculation and processing operations, such as access to the request of the result set, each node along their path to transmit data to query node, in the process of transmission, each node will receive the data fusion processing.The simulation results show that the proposed method has high query shooting.更多还原