期刊
IEEE INTERNET OF THINGS JOURNAL
卷 7, 期 10, 页码 9278-9290出版社
IEEE-INST ELECTRICAL ELECTRONICS ENGINEERS INC
DOI: 10.1109/JIOT.2020.2988457
关键词
Adaptive simulated annealing; deep reinforcement learning (DRL); large-scale mobile-edge computing (MEC); stacked autoencoder
资金
- National Natural Science Foundation of China [41604117, 41904127, 41874148, 61701179, 61620106011, 61572389]
- Scientific Research Fund of Hunan Provincial Education Department in China [18A031]
- Hunan Provincial Science Technology Project Foundation [2018TP1018, 2018RS3065]
- U.K. EPSRC Project NIRVANA [EP/L026031/1]
- Degree AMP
- Postgraduate Education Reform Project of Hunan Normal University [18JG15]
- EPSRC [EP/L026031/1] Funding Source: UKRI
An online resource scheduling framework is proposed for minimizing the sum of weighted task latency for all the Internet-of-Things (IoT) users, by optimizing offloading decision, transmission power, and resource allocation in the largescale mobile-edge computing (MEC) system. Toward this end, a deep reinforcement learning (DRL)-based solution is proposed, which includes the following components. First, a related and regularized stacked autoencoder (2r-SAE) with unsupervised learning is applied to perform data compression and representation for high-dimensional channel quality information (CQI) data, which can reduce the state space for DRL. Second, we present an adaptive simulated annealing approach (ASA) as the action search method of DRL, in which an adaptive h-mutation is used to guide the search direction and an adaptive iteration is proposed to enhance the search efficiency during the DRL process. Third, a preserved and prioritized experience replay (2p-ER) is introduced to assist the DRL to train the policy network and find the optimal offloading policy. The numerical results are provided to demonstrate that the proposed algorithm can achieve near-optimal performance while significantly decreasing the computational time compared with existing benchmarks.
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