Cloud Computing at the Tactical Edge
October 2012 • Technical Note
Soumya Simanta, Grace Lewis, Edwin J. Morris, Kiryong Ha (Carnegie Mellon School of Computer Science), Mahadev Satyanarayanan (Carnegie Mellon University)
This technical note presents a strategy to overcome the challenges of obtaining sufficient computation power to run applications needed for warfighting and disaster relief missions. It discusses the use of cloudlets-- localized, stateless servers running one or more virtual machines--on which soldiers can offload resource-intensive computations from their handheld mobile devices.
Software Engineering Institute
CMU/SEI Report Number
DOI (Digital Object Identifier):10.1184/R1/6572231.v1
Handheld mobile technology is reaching first responders, disaster-relief workers, and soldiers in the field to aid in various tasks, such as speech and image recognition, natural-language processing, decision making, and mission planning. However, these applications are computation intensive, so it is necessary to consider that (1) mobile devices offer less computational power than conventional desktop or server computers, (2) computation-intensive tasks consume large amounts of battery power, and (3) networks in hostile environments, such as those experienced by first responders and soldiers in the field, are often unreliable, and bandwidth is limited and inconsistent. While there has been considerable research in code offload to the cloud to enhance computation and battery life, most of this work assumes reliable connectivity between the mobile device and the cloud—an invalid assumption in hostile environments. This technical note presents a reference architecture for mobile devices that exploits cloudlets—virtual-machine-based, code-offload elements—that are in single-hop proximity to the mobile devices that they serve. Two implementations of this reference architecture are presented, along with an analysis of architecture tradeoffs.