No abstract

Soldiers and front-line personnel operating in tactical environments increasingly make use of handheld devices to help with tasks such as face recognition, language translation, decision-making, and mission planning. These resourceconstrained edge environments are characterized by dynamic context, limited computing resources, high levels of stress, and intermittent network connectivity. Cyber-foraging is the leverage of external resource-rich surrogates to augment the capabilities of resource-limited devices. In cloudlet-based cyber-foraging, resource-intensive computation and data is offloaded to cloudlets. Forward-deployed, discoverable, virtual-machine-based tactical cloudlets can be hosted on vehicles or other platforms to provide infrastructure to offload computation, provide forward data staging for a mission, perform data filtering to remove unnecessary data from streams intended for dismounted users, and serve as collection points for data heading for enterprise repositories. This paper describes tactical cloudlets and presents experimentation results for five different cloudlet provisioning mechanisms. The goal is to demonstrate that cyber-foraging in tactical environments is possible by moving cloud computing concepts and technologies closer to the edge so that tactical cloudlets, even if disconnected from the enterprise, can provide capabilities that can lead to enhanced situational awareness and decision making at the edge.

No abstract

Abstract.Handheld mobile technology is reaching first responders 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 and we must consider that 1) mobile devices offer less computational power than a conventional desktop or server computer, 2) computation-intensive tasks take a heavy toll on 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 paper presents a reference architecture for mobile devices that exploits cloudlets-VM-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.