Agile Migration for Fast-moving Mobile Devices (May 2018 - Current)

TBD; stay tuned!

RAVEN: Redundancy-Aided Vehicular Networking (Jan. 2016 - Apr. 2018)

Increasingly, vehicles sold today are connected cars: they offer vehicle-to-infrastructure connectivity through built-in WiFi and cellular, and they provide mobile hotspots for devices in the vehicle. We first study the connection quality available to connected cars today, focusing specifically on user-facing, latency-sensitive applications. We find that network latency varies significantly and unpredictably at short time scales and that high tail latency substantially degrades user experience. However, we also find an increase in coverage options available, primarily due to commercial WiFi hotspots, and that variations in latency across network options are not well-correlated. These results suggest that the principled use of redundant transmission across multiple wireless networks can improve the performance of latency-sensitive applications.

TeSLA: Thermal Service Level Agreement (May 2015 - Dec. 2015)

Rapid advances in the mobile processors show a promise in running compute-intensive applications on resource-constrained mobile devices. The mobile apps, however, face significant challenges in obtaining the full potential of those processors, especially when performance sustainability and computational sprinting for the apps are absolutely crucial. In a fanless environment, a software throttling mechanism, called ThermalEngine, by vendors comes into the play to cool down the processors, by which apps severely suffer from unpredictable performance. Our research is to develop an abstraction of Thermal Service Level Agreement (TeSLA) between underlying mobile system and apps, to guarantee sustained and expectable performance from mobile apps’ perspective and to deliver computational sprinting with the peak performance on demand.

SOUL: Sensors of Ubiquitous Life (Aug. 2014 - May 2015)

  Interacting with sensors presents numerous challenges, particularly for
  applications running on resource-constrained platforms like smartphones or
  tablets. The vSensor abstractions provide such applications with ease of use
  for today's multitude of sensors. vSensors not only assist with sensor use,
  but also interact with nearby and cloud resources to make available to
  applications the resources required for processing sensor-acquired data and
  controlling actuators, thus permitting them to scale in sensor usage. The
  vSensor abstraction's Android implementation offers globally transparent,
  uniform access to the ambient sensors in the environment in which apps
  operate, supporting both unmodified apps and those with vSensor awareness.

Applications in Personal Cloud (May 2014 - Aug. 2014)

Pcloud introduces a new runtime layer working on top of this improved
  Stratus. Unlike Stratus, Pcloud uses the service virtualization concept, so an
  application is now a set of services connected via API. Moreover, the runtime
  is responsible to allocate resources for virtual platforms to run each service
  of an application. Since Pcloud deals with cloud resources, it monitors
  trade-off between local and cloud in terms of latency.