Adaptive sampling for sensor networks

Abstract

A distributed data-stream architecture finds application in sensor networks for monitoring environment and activities. In such a network, large numbers of sensors deliver continuous data to a central server. The rate at which the data is sampled at each sensor affects the communication resource and the computational load at the central server. In this paper, we propose a novel adaptive sampling technique where the sampling rate at each sensor adapts to the streaming-data characteristics. Our approach employs a Kalman-Filter (KF)-based estimation technique wherein the sensor can use the KF estimation error to adaptively adjust its sampling rate within a given range, autonomously. When the desired sampling rate violates the range, a new sampling rate is requested from the server. The server allocates new sampling rates under the constraint of available resources such that KF estimation error over all the active streaming sensors is minimized. Through empirical studies, we demonstrate the flexibility and effectiveness of our model.