Toward ultra low-power hardware specialization of a Wireless Sensor Network node

Research in micro-electro-mechanical systems (MEMS) technology, wireless communications, and digital electronics has enabled the future emergence of Wireless Sensor Networks (WSN). These systems consist of low-cost and low-power sensor nodes that communicate efficiently over short distances. It has been shown that power consumption is the biggest design constraint for such systems. Currently, WSN nodes are being designed using low-power micro-controllers. However, their power dissipation is still orders of magnitude too high. In this paper, we propose an approach to hardware specialization that uses power-gated distributed hardware tasks. We target control-oriented tasks running on WSN nodes and present, as a case study, a temperature monitoring application. Our approach is validated experimentally and shows prominent power gains over software implementation on a low-power micro-controller such as the MSP430.