Partition-aware centrality measures for connectivity restoration in mobile sensor networks

Mobile sensor networks (MSNs) often operate unattended in environments where human intervention is limited. To sustain network operations, network connectivity must be maintained at all times. However, the network can be partitioned due to random node failures. To tolerate such failures in a reactive manner, network topology can be restructured through node mobility. Minimising the mobility cost requires addressing two different challenges. First, identifying nodes to be relocated. Second, determining target locations for movement. We address the first problem by presenting three different partition-aware centrality measures based on closeness centrality, geometric centrality, and harmonic centrality. To determine the movement target, we consider the former locations of the upstream nodes so that simultaneous node failures can be tolerated with limited data collection scope. The approaches that we present in this paper not only ensure recovery but also minimise the recovery cost so that the network lifetime is extended.