Published December 15, 2019 | Version v1
Conference paper

Distributed Change Detection in Streaming Graph Signals

Description

Detecting abrupt changes in streaming graph signals is relevant in a variety of applications ranging from energy and water supplies, to environmental monitoring. In this paper, we address this problem when anomalies activate localized groups of nodes in a network. We introduce an online change-point detection algorithm, which is fully distributed across nodes to monitor large-scale dynamic networks. We analyze the detection statistics for controlling the probability of a global type 1 error. Finally we illustrate the detection and localization performance with simulated data. This work was funded by the French government labelled PIA program under its IDEX UCAJEDI project (ANR-15-IDEX-0001).

Abstract

International audience

Additional details

Created:
December 3, 2022
Modified:
December 1, 2023