SBIR Phase II: Enabling Techologies for Energy-Centric Mobile App Design to Extend Mobile Device Battery Life

The broader impact/commercial potential of this Small Business Innovation Research (SBIR) Phase II project will result from it having far-reaching societal, commercial, and technological impact. (1) Initial research by the Principal Investigator on analyzing the energy drain of AngryBirds has demonstrated the severe energy inefficiency of popular mobile apps in today's app market. The importance of this work is heightened by smartphones being an important enabler of Internet access for disadvantaged people in both developed and developing countries, and hence being an important tool in overcoming the "digital divide". (2) Commercially, the project will foster a paradigm shift in the mobile app industry ($101B industry in 2020) from the current feature-centric to energy-aware app design. Such a paradigm shift will have a significant, long lasting impact on the app industry. Energy-efficient apps lead to longer battery life, which in turn leads to longer user engagement time, which ultimately translates into millions of dollars of increased mobile revenue as all major businesses are shifting towards mobile. Hence this SBIR project will lead to a marketable product. (3) Technically, the proposed work will extend the performance profiling technology that is foundational to the software industry into the energy dimension, which is critical to the mobile software industry. This Small Business Innovation Research (SBIR) Phase II project will develop the industry's first app energy management (AEM) solution to help app developers reduce app battery drain, and extend the battery life of billions of smartphones. The research objectives are (1) to develop advanced energy debugging techniques that can automatically identify energy drain opportunities from legitimate energy hotspots; and (2) to develop an SDK-based app energy monitoring system for monitoring app energy drain when running on consumer phones in the open market. These objectives pose significant technical challenges. While similar challenges on performance metrics (such as running time) have been well studied for traditional software, in particular in high-performance computing, in this project the company is expanding them to the energy dimension for the mobile app industry, which has not been attempted before. The company will develop novel machine-learning based solutions to learn, classify, and auto-detect energy optimization opportunities. As a result it expects to develop the first set of solutions to these fundamental challenges in optimizing the energy drain of millions of mobile apps in the app market.