ABSTRACT
This chapter introduces a new algorithm for online dynamic voltage scaling for discrete voltages. Lightweight embedded systems are often low-profile, small, unobtrusive, portable processing elements with limited power resources, which typically incorporate sensing, processing, and communication. The popularity of the battery power systems has encouraged research in the area of energy minimization. Embedded systems are deployed in a large range of real-time applications such as space, defense, medicine, and even consumer products. In embedded systems, redundancy can be achieved through multiple copies of software and multiple copies of hardware and computational units. The first step in evaluating the reliability of a given task allocation instance is analyzing the ability to compute the connectivity of the network. The slack time in real-time embedded systems can be used to reduce the power consumption of the system through voltage or frequency scaling. The chapter concludes with a review of reliability concerns in real-time embedded systems and summarizes the proposed reliability optimization techniques.
