An Energy-Aware Programming Approach for Mobile Application Development Guided by a Fine-Grained Energy Model

Abstract: Energy efficiency has a significant influence on user experience of battery-driven devices such as smartphones and tablets. It is shown that software optimization plays an important role in reducing energy consumption of system. However, in mobile devices, the conventional nature of compiler considers not only energy-efficiency but also limited memory usage and real-time response to user inputs, which largely limits the compiler's positive impact on energy-saving. As a result, the code optimization relies more on developers. In this paper, we propose an energy-aware programming approach, which is guided by an operation-based source-code-level energy model. And this approach is placed at the end of software engineering life cycle to avoid distracting developers from guaranteeing the correctness of system. The experimental result shows that our approach is able to save from 6.4% to 50.2% of the overall energy consumption depending on different scenarios.