Design and implementation of low power Android mobile sink based on load prediction

• DOI: 10.1504/ijcat.2016.075513
• Publication Date: 2016-03-29T11:01:11Z
• Authors: Yaqiu Liu; Shuangman Wu; Weipeng Jing
• Keywords: 0211 other engineering and technologies; 02 engineering and technology; 7. Clean energy

To reduce the power consumption of mobile sink node, a new state PER_NOTIFICATION is added to standard Android system. Therefore, USB devices can be or removed from system by sys file interface according users' specific demand, realising more fine-grained management. In addition, an improved CPU load prediction algorithm SAWDLP proposed replace default one in on-demand governor. With SAWDLP, accurate done and then appropriate frequency chosen consumption. Experimental results show that works well managing devices. The gets 85.20% higher accuracy 0.40% lower comparison PAST algorithm, accomplishing goal low design run time extension.