A data-driven approach to increasing the lifetime of IoT sensor nodes

Abstract

Abstract Data transmission accounts for significant energy consumption in wireless sensor networks where streaming data is generated by the sensors. This impedes their use in many settings, including livestock monitoring over large pastures (which forms our target application). We present Ambrosia, a lightweight protocol that utilizes a window-based timeseries forecasting mechanism for data reduction. Ambrosia employs a configurable error threshold to ensure that the accuracy of end applications is unaffected by the data transfer reduction. Experimental evaluations using LoRa and BLE on a real livestock monitoring deployment demonstrate 60% reduction in data transmission and a 2 $$\times$$ × increase in battery lifetime.