Dynamic monitoring frequency for energy-efficient data collection in Internet of Things
Jelena Čulić Gambiroža, Toni Mastelić, Ivana Nižetić Kosović, Mario Čagalj
Abstract
With growth of Internet of Things, number of connected sensors increases as well, along with data being collected by those sensors. Most sensors are battery powered and commonly collect data in short and equally spaced time periods resulting with large amount of redundant and often irrelevant data. In this paper, we propose a dynamic monitoring frequency (DMF) algorithm that aims at collecting data only when sensor readings change by more than a predefined value between consecutive readings. Thus, a sensor is turned on only when a change in monitored phenomenon value exceeds a predefined threshold. Two algorithms are analyzed, namely statistical and machine learning. DMF shows notable performance, resulting either with up to ∼70% less missed readings, or it collects up to ∼40% less data compared to the baseline algorithm that collects data with static monitoring frequency.