Timely Group Updating
share
We consider two closely related problems: anomaly detection in sensor networks and testing for infections in human populations. In both problems, we have n nodes (sensors, humans), and each node exhibits an event of interest (anomaly, infection) with probability p. We want to keep track of the anomaly/infection status of all nodes at a central location. We develop a group updating scheme, akin to group testing, which updates a central location about the status of each member of the population by appropriately grouping their individual status. Unlike group testing, which uses the expected number of tests as a metric, in group updating, we use the expected age of information at the central location as a metric. We determine the optimal group size to minimize the age of information. We show that, when p is small, the proposed group updating policy yields smaller age compared to a sequential updating policy.
READ FULL TEXT