Sensor Health Monitoring in Wireless Sensor Networks

摘要：

Wireless Sensor Network (WSN) has been widely used in information collection and monitoring applications. At the center of attention in these applications are data, which come from the sensor part of each WSN node. Sensor faults are common due to the sensor device itself and the harsh deployment environment. These faults may degrade the data quality from the very beginning and thus have a possible large influence on the final success of specific WSN application. Our work presented in this paper is to monitor the health status of sensors in WSN. Inspired by the latest development of time series data mining technology, a flexible approach is proposed for unspecific fault monitoring. Each deployed WSN node learns the frequent patterns periodically. Any sensor fault follows a pattern that is different from the nodes learned frequent patterns. The proposed method can find fault patterns efficiently. We show how this method works well in Castalia simulation environment.

关键词： fault detection linear pattern threshold wireless sensor networks

作者: Chongming Zhang Xi Zhou Chuanshan Gao Chunmei Wang Huafeng Wu

作者单位: Dept.of Electronics Engineering Shanghai Normal University Shanghai, China School of Computer Science Fudan University Shanghai, China Merchant Marine College Shanghai Maritime University Shanghai, China

会议类型: 国际会议

会议名称: 2009 WASE International Conference on Information Engineering(2009年国际信息工程会议)(ICIE 2009)

会议地点: 太原

会议语种:英文

页码: 337-341

在线出版日期: 2009-07-10（万方平台首次上网日期，不代表论文的发表时间）