Analysis and Optimization of Embedded Software Energy Consumption on the Source Code and Algorithm Level

The energy consumption optimization of embedded systems can be undertaken in multiple levels of hardware and software. In this paper, based on the energy consumption measurement of embedded software, the generating reasons and influencing factors of embedded software energy consumption on the micro-structure and circuit level of hardware were analyzed firstly. Then, to reduce the energy consumption of embedded software, some measures were adopted to improve the software-related characteristics on the source code and algorithm level. Finally, a C program of typical "Eight Queens" puzzle was optimized with three methods of source code level, algorithm level and a mix of source code and algorithm level, the highest energy savings of embedded systems could achieve up to 93.1%, and experimental results demonstrated that the energy consumption optimization methods of embedded software were feasible and effective to minimize the energy consumption of embedded systems.