Seamless Resources Sharing in Wearable Networks by Application Function Virtualization

TL;DR

This paper introduces AFV, an architecture for dynamic function virtualization in wearable networks, enabling adaptive resource sharing and improving energy efficiency and user experience.

Contribution

The paper presents AFV, a novel architecture that automates function virtualization and scheduling across wearable devices, simplifying app development and enhancing resource utilization.

Findings

AFV reduces energy consumption in wearable networks.

AFV improves user experience through adaptive function invocation.

Implementation on Android demonstrates feasibility and benefits.

Abstract

The prevalence of smart wearable devices is increasing exponentially and we are witnessing a wide variety of fascinating new services that leverage the capabilities of these wearables. Wearables are truly changing the way mobile computing is deployed and mobile applications are being developed. It is possible to leverage the capabilities such as connectivity, processing, and sensing of wearable devices in an adaptive manner for efficient resource usage and information accuracy within the personal area network. We show that application developers are not yet taking advantage of these cross-device capabilities, however, instead using wearables as passive sensors or simple end displays to provide notifications to the user. We thus design AFV (Application Function Virtualization), an architecture enabling automated dynamic function virtualization and scheduling across devices in a personal area network, simplifying the development of the apps that are adaptive to context changes. AFV provides a simple set of APIs hiding complex architectural tasks from app developers whilst continuously monitoring the user, device and network context, to enable the adaptive invocation of functions across devices. We show the feasibility of our design by implementing AFV on Android, and the benefits for the user in terms of resource efficiency, especially in saving energy consumption, and quality of experience with multiple use cases.