期刊
IEEE TRANSACTIONS ON MOBILE COMPUTING
卷 22, 期 11, 页码 6663-6675出版社
IEEE COMPUTER SOC
DOI: 10.1109/TMC.2022.3197706
关键词
Deep reinforcement learning; multi-access edge computing; partial observable markov decision process; service migration
The research proposes a novel learning-driven method with a user-centric approach to address service migration in dynamic MEC environments. By modeling the problem as a Partially Observable Markov Decision Process (POMDP), a new encoder network combining LSTM and an embedding matrix is designed for effective information extraction, and a tailored off-policy actor-critic algorithm is proposed for efficient training.
Multi-access Edge Computing (MEC) is an emerging computing paradigm that extends cloud computing to the network edge to support resource-intensive applications on mobile devices. As a crucial problem in MEC, service migration needs to decide how to migrate user services for maintaining the Quality-of-Service when users roam between MEC servers with limited coverage and capacity. However, finding an optimal migration policy is intractable due to the dynamic MEC environment and user mobility. Many existing studies make centralized migration decisions based on complete system-level information, which is time-consuming and also lacks desirable scalability. To address these challenges, we propose a novel learning-driven method, which is user-centric and can make effective online migration decisions by utilizing incomplete system-level information. Specifically, the service migration problem is modeled as a Partially Observable Markov Decision Process (POMDP). To solve the POMDP, we design a new encoder network that combines a Long Short-Term Memory (LSTM) and an embedding matrix for effective extraction of hidden information, and further propose a tailored off-policy actor-critic algorithm for efficient training. The extensive experimental results based on real-world mobility traces demonstrate that this new method consistently outperforms both the heuristic and state-of-the-art learning-driven algorithms and can achieve near-optimal results on various MEC scenarios.
作者
我是这篇论文的作者
点击您的名字以认领此论文并将其添加到您的个人资料中。
推荐
暂无数据