User-Centered Context-Aware CPU/GPU Power Management for Interactive Applications on Smartphones

• Main Authors: Lin, Syuan-Yi, 林軒旖
• Other Authors: King, Chung-Ta
• Format: Others
• Language: en_US
• Published: 2018
• Online Access: http://ndltd.ncl.edu.tw/handle/jz274n

碩士 === 國立清華大學 === 資訊工程學系所 === 107 === With the increasing functionalities in smartphones, smartphones become an important part of our daily lives. Users can communicate, navigate, and check the updates of social media with smartphones anywhere at any time. However, due to the limit battery capacity, the power management has become a critical issue to the battery-driven smartphones. A number of existing works strike to balance the user’s quality of experience(QoE) and the energy saving. However, most of them are unaware of the impact of the user’s context to the user’s QoE, which cause the over- or under-provisioning hardware. To observe the correlation between the user’s contexts and the user’s QoE, we conducted an experiment with 8 subjects for two weeks. The results reveal that the demand for users’ QoE varies in different contexts, which inspire us to scale the system performance based on context information to optimize energy saving. In this thesis, we propose a governor which optimize the energy saving while maintaining the user’s QoE simultaneously in the different contexts. The evaluation shows the proposed governor can save power consumption up to 25% compared to the default governor while keeping the users felt satisfied with the quality of service.