Mystique: User-Level Adaptation for Real-Time Video Analytics in Edge Networks via Meta-RL
IEEE Transactions on Mobile Computing · 2025-05 · 24 (5) · 3615-3632
DOI: 10.1109/tmc.2024.3514088 ↗Kurz gefasst
Fachartikel in der Zeitschrift IEEE Transactions on Mobile Computing, 2025-05. Verfasst von Xiaohang Shi und 12 weiteren Autor:innen. Die Arbeit wurde bisher 7-mal zitiert (Crossref) und nennt 57 Literaturangaben. Gefördert von: Science and Technology Project of State Grid Company, Ltd, Research on data aggregation and dynamic interaction technology of enterprise-level real-time measurement data center, Nanjing University-China Mobile Communications Group Company, Ltd.
Abstract (Originalsprache)
Deep neural network (DNN)-based real-time video analytics service, as a core module for numerous crucial applications such as augmented reality (AR), has garnered increasing research attention, where mobile edge computing (MEC) is often leveraged to mitigate its real-time processing burden on resource-constrained user devices. For Quality of Experience (QoE) optimization, latest works employ reinforcement learning (RL)-based methods to adaptively adjust configurations (e.g., resolution and frame rate), yet still presenting significant challenges. Firstly, we observe a substantial diversity in QoE patterns among users. Given that existing methods integrate a fixed QoE pattern in parameter training, it is intuitive to customize a policy network for each user. However, this necessitates significant training investment, failing to support on-the-fly deployment for new users. Secondly, given the dual dynamics from both the network and video content in edge video analytics system, existing methods often fall into the dilemma of fitting newly emerged and diverse system states with offline-trained fixed parameters. While it is promising to employ online learning algorithms, most of them struggle to catch up with the high dynamics. We hence propose Mystique. In real-time edge video analytics domain, it is the first meta-RL-based user-level configuration adaptation framework. Mystique establishes an initial model in offline meta training with model-agnostic meta-learning (MAML), enabling swift online adaptation to new users and system states through limited gradient updates from initial parameters. Comprehensive experiments illustrate that Mystique can improve QoE by 42% on average compared to prior works.
Förderung
- Science and Technology Project of State Grid Company, Ltd
- Research on data aggregation and dynamic interaction technology of enterprise-level real-time measurement data center
- Nanjing University-China Mobile Communications Group Company, Ltd
Zitieren
APA
Shi, X., Zhang, S., Liu, M., Meng, L., Wei, L., Gu, Y., Liu, K., Cheng, H., Song, Y., Tang, L., Zhu, A., Chen, N., & Qian, Z. (2025). Mystique: User-Level Adaptation for Real-Time Video Analytics in Edge Networks via Meta-RL. IEEE Transactions on Mobile Computing, 24(5), 3615-3632. https://doi.org/10.1109/tmc.2024.3514088
Vancouver
Shi X, Zhang S, Liu M, Meng L, Wei L, Gu Y, et al. Mystique: User-Level Adaptation for Real-Time Video Analytics in Edge Networks via Meta-RL. IEEE Transactions on Mobile Computing. 2025;24(5):3615-3632. doi:10.1109/tmc.2024.3514088
BibTeX
@article{Shi2025,
author = {Shi, Xiaohang and Zhang, Sheng and Liu, Meizhao and Meng, Lingkun and Wei, Liu and Gu, Yingcheng and Liu, Kai and Cheng, Huanyu and Song, Yu and Tang, Lei and Zhu, Andong and Chen, Ning and Qian, Zhuzhong},
title = {Mystique: User-Level Adaptation for Real-Time Video Analytics in Edge Networks via Meta-RL},
journal = {IEEE Transactions on Mobile Computing},
year = {2025},
volume = {24},
number = {5},
pages = {3615--3632},
doi = {10.1109/tmc.2024.3514088}
}
EUVIMED