期刊
IEEE INTERNET OF THINGS JOURNAL
卷 9, 期 2, 页码 1053-1067出版社
IEEE-INST ELECTRICAL ELECTRONICS ENGINEERS INC
DOI: 10.1109/JIOT.2021.3078514
关键词
Collaboration; Reinforcement learning; Task analysis; Computational modeling; Distributed databases; Edge computing; Data models; Federated learning (FL); joint collaboration; mixed policies; mobile-edge computing (MEC); multiagent deep reinforcement learning (RL); multimodal learning
资金
- Beijing Natural Science Foundation [4202030]
This paper introduces the application of mobile-edge computing (MEC) in distributed communication-computing systems and proposes a joint collaboration framework based on multimodal deep reinforcement learning. The proposed algorithm combines edge federated learning mode with multiagent actor-critic RL, improving the system performance in terms of average system age and training process stability.
As an emerging technique, mobile-edge computing (MEC) introduces a new scheme for various distributed communication-computing systems, such as industrial Internet of Things (IoT), vehicular communication, smart city, etc. In this work, we mainly focus on the timeliness of the MEC systems where the freshness of the data and computation tasks is significant. First, we formulate a kind of age-sensitive MEC models and define the average Age-of-Information (AoI) minimization problems of interests. Then, a novel mixed-policy-based multimodal deep reinforcement learning (RL) framework, called heterogeneous multiagent actor-critic (H-MAAC), is proposed as a paradigm for joint collaboration in the investigated MEC systems, where edge devices and center controller learn the interactive strategies through their own observations. To improve the system performance, we develop the corresponding online algorithm by introducing the edge federated learning mode into the multiagent cooperation whose advantages on learning convergence can be guaranteed theoretically. To the best of our knowledge, it is the first joint MEC collaboration algorithm that combines the edge federated mode with the multiagent actor-critic RL. Furthermore, we evaluate the proposed approach and compare it with popular RL-based methods. As a result, the proposed algorithm not only outperforms the baselines on average system age, but also promotes the stability of training process. Besides, the simulation outcomes provide several insights for collaboration designs over MEC systems.
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