Dynamic software deployment from clouds to mobile devices

摘要: With the functionality of mobile applications ever increasing, designers are often confronted with either resource limitations devices or network. As pointed out by recent work, application partitioning between and clouds, can be used to solve some these issues, improving performance and/or battery life. In this paper, we argue that static decisions made in existing work cannot leverage full potential partitioning. Thus, allow for variations execution environment, have developed a system dynamically adapts partition decisions. The works continuously profiling an updating its distributed deployment accommodate changes network bandwidth, CPU utilization, data loads. Using several real applications, show our approach provides gains as high 75% over traditional approaches achieves lower power consumption factor close 45%.