基于深度自编码器的WSN数据融合算法  

Data aggregation in WSN based on deep self-encoder

作　　者：潘琢金 秦蓓 罗振 杨华 PAN Zhuo-jin;QIN Bei;LUO Zhen;YANG Hua(School of Computer Science, Shenyang Aerospace University, Shenyang 110136, China)

机构地区：[1]沈阳航空航天大学计算机学院,辽宁沈阳110136

出　　处：《计算机工程与设计》2018年第5期1214-1218,共5页Computer Engineering and Design

基　　金：航空科学基金项目(2014ZC54012);辽宁省自然科学基金项目(2013024002);辽宁省教育厅基金项目(L201626)

摘　　要：无线传感器网络(WSN)资源有限,为减少数据在传输过程中的能量消耗,提出一种基于深度自编码器的WSN数据融合算法(DESAEDA)。构造深度自编码器(DESAE)并在汇聚节点完成训练,将训练好的参数传给相应的传感器节点。提出两种数据融合模型,将采集到的原始数据通过网络模型,提取得到少量特征数据,将其发送到汇聚节点,减少数据传输量。仿真结果表明,与LEACH算法相比,该算法能够显著减少能量消耗,延长网络生命周期,更适于处理较大规模网络。To reduce the energy consumption of data transmission in limited resource of wireless sensor networks,a WSN data fusion algorithm based on depth self-coder（DESAEDA）was proposed.The depth self-encoder（DESAE）was constructed and the training was completed at the sink node,and the trained parameters were passed to the corresponding sensor nodes.Two kinds of data fusion models were proposed,in which the raw data were extracted through the network model to obtain a small amount of feature data,and they were sent to the convergence node,reducing the amount of data transmission.Simulation results show that compared with the LEACH algorithm,the algorithm can significantly reduce the energy consumption,extending the network life cycle,and it is more suitable for dealing large scale networks.

关 键 词：无线传感器网络 数据融合 深度自编码器 特征数据 生命周期 

分 类 号：TP393[自动化与计算机技术—计算机应用技术]