Outlier detection in wireless sensor networks using distributed principalcomponent analysis

Outlier detection is an important task for intrusion detection and fault diagnosis in wireless sensor networks(WSNs). Outliers in sensed data may be caused due to compromised or malfunctioning sensor nodes. In thispaper, we propose a centralized and a distributed approach based on the principal component analysis (PCA)for outlier detection in WSNs. In the distributed approach, we partition the network into multiple groups ofsensor nodes. Each group has a group head and several member nodes. Every member node uses a fixedwidthclustering algorithm and sends a description of its local sensed data to the group head. The group headthen applies a distributed PCA to establish a global normal pattern and detect outliers. This pattern is periodicallyupdated using weighted coefficients. We compare the performance of the centralized and distributedapproaches based on the real sensed data collected by 54 Mica2Dot sensors deployed in Intel Berkeley ResearchLab. The experimental results show that the distributed approach reduces both communication overheadand energy consumption, while achieving comparable accuracy.

Keywords:

Wireless sensor network , Outlier detection , Principal component analysis