Energy-Efficient Task Offloading Frameworks For Mixed Reality And Extended Reality In Edge AI Environments

Author

Mahin Khan Mahadi, Prairie View A&M University

Date of Award

12-2025

Document Type

Thesis

Degree Name

Master of Science

Degree Discipline

Electrical Engineering

Abstract

Mixed Reality (MR) and Extended Reality (XR) technologies are increasingly integrated into real-time applications such as remote maintenance, spatial navigation, and immersive learning. However, the computational intensity of deep learning workloads, especially object detection models like YOLO, poses significant challenges for wearable XR devices with limited processing power and battery life. To address these challenges, this thesis presents a comprehensive study of adaptive offloading strategies that optimize task execution between XR devices and edge servers.

We first proposed the Binary Spatial Allocation Framework (BSAF), which introduced a real-time binary decision mechanism for XR systems. The BSAF framework evaluates scene complexity, network conditions, and system constraints to dynamically select either local execution on HoloLens 2 or edge execution using high-precision YOLOv11 models. A closed-form utility model was developed to balance accuracy, latency, and energy consumption, and Lagrangian relaxation was employed to maintain constraint feasibility. Experimental results across 100 XR scenes showed that BSAF reduced latency by up to 20% and energy usage by 36% compared to full offloading, while preserving over 90% detection accuracy.

To further enhance adaptability, we proposed SPARL-CBF, a Safe Partial Offloading framework that integrates Model-Based Reinforcement Learning (MBRL) with Control Barrier Functions (CBFs). Unlike binary strategies, SPARL-CBF learns a continuous offloading policy that dynamically adjusts task partitioning based on runtime system states such as battery level, bandwidth, and CPU load. CBFs ensure real-time constraint satisfaction by projecting unsafe actions back into feasible regions. Implemented using Proximal Policy Optimization (PPO) and deployed on a live edge-XR testbed, SPARL-CBF achieved over 94% accuracy, reduces latency, and prolongs device battery life by intelligently modulating the offloading ratio. Together, BSAF and SPARL-CBF offer a unified, constraint-aware framework for intelligent task offloading in XR systems. This thesis provides mathematical formulations, system implementations, and empirical evaluations that demonstrate how adaptive offloading can significantly improve energy efficiency and responsiveness in edge-assisted XR environments. The proposed approaches lay the groundwork for scalable, real-time XR applications in emerging domains such as healthcare, smart cities, and the metaverse.

Index Terms-- augmented reality, computer vision, deep learning, edge computing, mixed reality.

Committee Chair/Advisor

Daniel Doe

Committee Co-Chair

Lijun Qian

Committee Member

Xiangfang Li

Publisher

Prairie View A&M University

Rights

© 2021 Prairie View A & M University

Date of Digitization

12/10/2025

Contributing Institution

J. B . Coleman Library

City of Publication

Prairie View

MIME Type

Application/PDF

Recommended Citation

Mahadi, M. (2025). Energy-Efficient Task Offloading Frameworks For Mixed Reality And Extended Reality In Edge AI Environments. Retrieved from https://digitalcommons.pvamu.edu/pvamu-theses/1658