FPSelector: A Flexible Path Selector for Mobile Augmented Reality Offloading
Saved in:
| Title: | FPSelector: A Flexible Path Selector for Mobile Augmented Reality Offloading |
|---|---|
| Authors: | Zhu, Yuanwei, Huang, Yakun, Qiao, Xiuquan, Liu, Xiaoli, Su, Xiang, Brunstrom, Anna, 1967, Alay, Özgü, Tarkoma, Sasu |
| Source: | IEEE Transactions on Mobile Computing. 24(9):8423-8440 |
| Subject Terms: | Feature extraction, Three-dimensional displays, Navigation, Dynamic scheduling, Cameras, Servers, Pose estimation, Mobile computing, Mars, Computational modeling, Mobile augmented reality, computation offloading, multipath transport, reinforcement learning, resource-awareness, Computer Science, Datavetenskap |
| Description: | Mobile Augmented Reality (MAR) applications pose unique challenges due to computation intensity, constrained device resources, and high interactive rendering requirements. The emergence of 5G and edge computing offers opportunities to offload computation to the edge and cloud, indirectly enhancing the computing capability and usage duration of MAR devices. However, existing general task offloading and multipath transmission techniques do not address the challenges in offloading path selection with multiple edges, dynamic resource competition awareness, and spatial computation with strong task dependencies. This paper contributes FPSelector, a flexible path selector for MAR offloading. We present a two-tier MAR-specific offloading scheme with multiple edge nodes. In offloading decisions, we design a reinforcement learning model to generate the selection policy for each packet of an AR data stream. This model incorporates an action masking mechanism, a comprehensive reward function, and state features complemented by a resource prediction module, making FPSelector aware of dynamic heterogeneous environments. Moreover, we propose an online learning strategy to facilitate real-time selection. To validate its efficacy, we compare FPSelector's performance against leading schedulers under various scenarios, demonstrating a notable reduction of 9.9% and 9.6% in overall completion time for 4 K and 8 K video-based MAR applications compared to its closest competitor. |
| File Description: | electronic |
| Access URL: | https://urn.kb.se/resolve?urn=urn:nbn:se:kau:diva-106772 https://doi.org/10.1109/TMC.2025.3556473 |
| Database: | SwePub |
Full Text Finder 
Nájsť tento článok vo Web of Science | Abstract: | Mobile Augmented Reality (MAR) applications pose unique challenges due to computation intensity, constrained device resources, and high interactive rendering requirements. The emergence of 5G and edge computing offers opportunities to offload computation to the edge and cloud, indirectly enhancing the computing capability and usage duration of MAR devices. However, existing general task offloading and multipath transmission techniques do not address the challenges in offloading path selection with multiple edges, dynamic resource competition awareness, and spatial computation with strong task dependencies. This paper contributes FPSelector, a flexible path selector for MAR offloading. We present a two-tier MAR-specific offloading scheme with multiple edge nodes. In offloading decisions, we design a reinforcement learning model to generate the selection policy for each packet of an AR data stream. This model incorporates an action masking mechanism, a comprehensive reward function, and state features complemented by a resource prediction module, making FPSelector aware of dynamic heterogeneous environments. Moreover, we propose an online learning strategy to facilitate real-time selection. To validate its efficacy, we compare FPSelector's performance against leading schedulers under various scenarios, demonstrating a notable reduction of 9.9% and 9.6% in overall completion time for 4 K and 8 K video-based MAR applications compared to its closest competitor. |
|---|---|
| ISSN: | 15361233 15580660 |
| DOI: | 10.1109/TMC.2025.3556473 |