Virtualized Application Function Chaining: Maximizing the Wearable System Lifetime

TL;DR

This paper presents a resource-aware function allocation approach for wearable systems, significantly extending battery life by intelligently utilizing shared resources across devices through MILP optimization and heuristics.

Contribution

It introduces a novel resource pooling and function allocation framework for wearables, optimizing resource use to enhance system lifetime.

Findings

Achieves 40-50% increase in system battery life.

Demonstrates effectiveness of MILP-based resource allocation.

Validates approach through data-driven simulations.

Abstract

The number of smart devices wear and carry by users is growing rapidly which is driven by innovative new smart wearables and interesting service o erings. This has led to applications that utilize multiple devices around the body to provide immersive environments such as mixed reality. These applications rely on a number of di erent types of functions such as sensing, communication and various types of processing, that require considerable resources. Thus one of the major challenges in supporting of these applications is dependent on the battery lifetime of the devices that provide the necessary functionality. The battery lifetime can be extended by either incorporating a battery with larger capacity and/or by utilizing the available resources e ciently. However, the increases in battery capacity are not keeping up with the demand and larger batteries add to both the weight and size of the device. Thus, the focus of this paper is to improve the battery e ciency through intelligent resources utilization. We show that, when the same resource is available on multiple devices that form part of the wearable system, and or is in close proximity, it is possible consider them as a resource pool and further utilize them intelligently to improve the system lifetime. Speci cally, we formulate the function allocation algorithm as a Mixed Integer Linear Programming (MILP) optimization problem and propose an e cient heuristic solution. The experimental data driven simulation results show that approximately 40-50% system battery life improvement can be achieved with proper function allocation and orchestration.