A Predictive Energy-Efficient Technique to Support Object-Tracking Sensor Networks

In recent years, we have witnessed an increasing interest in deploying wireless sensor networks (WSNs) for real-life applications. However, before WSNs become a commodity, several challenging issues remain to be resolved. Object-tracking sensor network (OTSN)-based applications are widely viewed as being among the most interesting applications of WSNs. OTSN is mainly used to track certain objects in a monitored area and to report their location to the application's users. However, OTSNs are well known for their energy consumption when compared with other WSN applications. In this paper, we propose a prediction-based tracking technique using sequential patterns (PTSPs) designed to achieve significant reductions in the energy dissipated by the OTSNs while maintaining acceptable missing rate levels. PTSP is tested against basic tracking techniques to determine the appropriateness of PTSP under various circumstances. Our experimental results have shown that PTSP outperforms all the other basic tracking techniques and exhibits significant amounts of savings in terms of the entire network's energy consumption.

I. Introduction

Major advances in creating cost-effective, energy-efficient, and versatile microelectromechanical systems (MEMS) over the past few years has significantly contributed to the vast amount of research and development projects related to the field of wireless sensor networks (WSNs) and smart sensors. The sensor node is a very small device that represents the building blocks of the WSN. These nodes are being produced at a very low cost and yet with high levels of sophistication in terms of computing power, energy consumption savings, and multipurpose functionalities when compared with earlier generations of sensor nodes. WSNs are created by deploying a large number of sensor nodes in a certain area, which is usually called the monitored region, for monitoring purposes. These nodes are interconnected and are used together as a monitoring and reporting device to acquire specific types of data as desired by the application requirements [1]–[3], [19].