Assessing the impact of dynamic power management on the functionality and the performance of battery-powered appliances

In this paper we provide an incremental methodology to assess the effect of the introduction of a dynamic power manager in a mobile embedded computing device. The methodology consists of two phases. In the first phase, we verify whether the introduction of the dynamic power manager alters the functionality of the system. We show that this can be accomplished by employing standard techniques based on equivalence checking for noninterference analysis. In the second phase, we quantify the effectiveness of the introduction of the dynamic power manager in terms of power consumption and overall system efficiency. This is carried out by enriching the functional model of the system with information about the performance aspects of the system, and by comparing the values of the power consumption and the overall system efficiency obtained from the solution of the performance model with and without dynamic power manager. To this purpose, first we employ a more abstract performance model based on the Markovian assumption, then we use a more realistic performance model - to be validated against the Markovian one - where general probability distributions are considered. The methodology is illustrated by means of its application to the study of a remote procedure call mechanism - through which a battery-powered device is used by some application requesting information - and of a streaming video service - which is accessed by a mobile client equipped with a power-manageable network interface card.