XR Offloading Across Multiple Time Scales: The Roles of Power, Temperature, and Energy

TL;DR

This paper presents TAO, a temperature-aware offloading strategy for XR wearables that optimizes computational offloading across multiple time scales, reducing costs while respecting power, thermal, and energy constraints.

Contribution

It introduces a novel stochastic offloading model considering power, temperature, and energy over different time scales, and proposes the TAO strategy to optimize offloading decisions.

Findings

TAO reduces offloading cost by over 35% compared to existing methods.

TAO effectively manages power, thermal, and energy constraints in XR wearables.

Performance validated using COMSOL models of real-world devices.

Abstract

Extended reality (XR) devices, commonly known as wearables, must handle significant computational loads under tight latency constraints. To meet these demands, they rely on a combination of on-device processing and edge offloading. This letter focuses on offloading strategies for wearables by considering their impact across three time scales: instantaneous power consumption, short-term temperature fluctuations, and long-term battery duration. We introduce a comprehensive system model that captures these temporal dynamics, and propose a stochastic and stationary offloading strategy, called TAO (for temperature-aware offloading), designed to minimize the offloading cost while adhering to power, thermal, and energy constraints. Our performance evaluation, leveraging COMSOL models of real-world wearables, confirms that TAO reduces offloading cost by over 35% compared to state-of-the-art approaches, without violating the wearable operational limits.