Energy-efficient distributed approach for clustering-based fault detection and diagnosis in image sensor networks

This study proposes an algorithm for the design of a distributed protocol for detecting and diagnosing permanent faults in wireless image sensor networks (WISNs). This work explicitly takes into account the possibility of faults in different sections of the image sensor node and communication channel. The fault diagnosis is achieved by disseminating local decision made at each node. Theoretical analysis and simulation results show that high level (>0.95) of diagnosis accuracy can be achieved for a wide range of fault rates. Correctness and complexity proofs are provided, and they show that the proposed algorithm performs better than the existing protocols from both communication and energy complexity perspective. Analytical study shows that time complexity is O(n_c) and message complexity O(n) for an n-node WISN where n_c is the number of cluster heads.