无线传感器网络中一种基于能效的入侵检测算法-3N算法研究

Reaserch on Energy-Efficiency Intrusion Detection Algorithm(3N Algorithm) in Wireless Sensor Networks

识别异常行为是无线传感器网络进行入侵检测的一项重要任务,当识别异常时应使网络的通信开销和能量消耗达到最小.文中提出了一种基于分簇的分布式异常检测算法-3N算法.首先对传感器的测量值进行分簇,再向其它节点传送分簇信息之前对簇进行融合.仿真结果表明,这种分布式方法与集中式方法的检测精度相当,但通信开销大大减少.

Identifying misbehaviors is an important task for intrusion detection in wireless sensor networks. The communication overhead and energy consumption should reach the minimum value to the greatest extent in the network when identifying misbehaviors. Our approach to this problem is based on a distributed, cluster-based anomaly detection algorithm, namely 3N algorithm. We minimize the communication overhead by clustering the sensor measurements and merging clusters before sending a description of the clusters to the other nodes. Results show that distributed scheme achieves comparable accuracy compared to a centralized scheme with a significant reduction in communication overhead.