Using drones to inspect bridges and electric grid towers, mounting a search and rescue operation for a child lost in the woods, hosting a backcountry ski event for a weekend, and providing critical communication and application capabilities for forward military operations – These are just a few situations where there is a need to deploy a modern compute and communication infrastructure very rapidly in areas with poor network coverage. These situations require the ability to provide connectivity for mobile phones, cameras, drones, and other connected devices. These devices need to offload compute-intensive operations that cannot be performed on-device. They also require access to sophisticated applications, possibly proprietary, with too large a footprint to even run partially on-device. Until recent breakthroughs in a wide variety of open technologies, implementing these use cases has required custom hardware and software, proprietary network technologies, communication spectrum licenses, and the expertise to integrate a solution. These breakthroughs enable a new model – the Just-in-Time (JIT) Cloudlet – a highly integrated, lightweight, low power platform built from common off-the-shelf (COTS) technologies that provides a standalone private mobile network provisioned with applications for specific use cases. This technical report describes the motivation, requirements, and enablers to build a JIT Cloudlet. It also describes our architecture, implementation, and results for a JIT Cloudlet prototype created at the Carnegie Mellon University Living Edge Lab. This prototype, based around open-source software and COTS hardware can be the base for development platform for application developers and integrators to deliver solutions for the use cases above and many others.

*Arm, Inc.

30 pages

Return to: SCS Technical Report Collection
School of Computer Science

This page maintained by reports@cs.cmu.edu