Topics: Smartphone apps, web and Internet apps
Authors: Philip Lundrigan, Mojgan Khaledi, Makito Kano, Naveen Subramanyam and Sneha Kumar Kasera (University of Utah, USA)
Presenter bio:
Philip Lundrigan received the B.S. degree (with honors) in
Computer Engineering from Brigham Young University in 2012. He is
pursing the Ph.D. degree in Computer Science from the University of
Utah. His current research interests include mobile networks, mobile
computing, and wireless network management.
Abstract: We design and build a system we call mobiLivUp, that utilizes nearby
smartphones to improve live wide-area video upstreaming. In mobiLivUp,
to distribute the video to nearby devices, the video streaming device
creates a small wireless network using Wi-Fi Direct. Other devices then
connect to this network. Parts of the video stream are sent to these
connected devices, which then upload their parts to a location in the
wide-area network using their cellular connections. We develop
algorithms and methods to effectively distribute video data to nearby
nodes and for incentivizing cooperation from these nodes. We test our
system through trace-driven simulation and implementation in various
settings. Our experiments show that, in general, mobiLivUp increases the
aggregate video throughput, depending on the number of nodes forwarding
data and their data rates.
