Estimation and analysis of embedded operating system energy consumption

With the progress of low-power research on embedded systems, the estimation and analysis of the energy consumption of operating system becomes a hot topic. This paper presents a quantitative approach to estimate and analyze the energy consumption of embedded operating system (EOS). In this approach, EOS and applications are executed on two cooperated simulators. Instruction execution energy is estimated using a cycle-accurate micro-architecture power model. We propose an OS energy consumption estimation model based on software functionality and structure. The approach can calculate the energy consumption for functions, routines, services and kernel execution paths in an EOS, and can identify the key modules and factors impacting the system energy consumption. Our experiments show that the proposed approach improves the accuracy and efficiency of energy estimation of EOS significantly. The estimation results can be used to quantitatively analyze and optimize the energy consumption of EOS and applications.EI02209-2153