Distributed Change Detection via Average Consensus over Networks
This work addresses the problem of real-time monitoring in sensor networks, offering a fully distributed solution with theoretical guarantees.
The paper proposes a distributed change-point detection algorithm using average consensus, where sensors exchange CUSUM statistics locally. Theoretical bounds show it matches centralized performance under mild conditions, and experiments demonstrate effectiveness for asynchronous changes.
Distributed change-point detection has been a fundamental problem when performing real-time monitoring using sensor-networks. We propose a distributed detection algorithm, where each sensor only exchanges CUSUM statistic with their neighbors based on the average consensus scheme, and an alarm is raised when local consensus statistic exceeds a pre-specified global threshold. We provide theoretical performance bounds showing that the performance of the fully distributed scheme can match the centralized algorithms under some mild conditions. Numerical experiments demonstrate the good performance of the algorithm especially in detecting asynchronous changes.