Deep Q-Learning Based Computation Offloading Strategy for Mobile Edge Computing

To reduce the transmission latency and mitigate the backhaul burden of the centralized cloud-based network services, the mobile edge computing (MEC) has been drawing increased attention from both industry and academia recently. This paper focuses on mobile users' computation offloading problem...

Full description

Saved in:
Bibliographic Details
Published in:Computers, materials & continua materials & continua, 2019-01, Vol.59 (1), p.89-104
Main Authors: Wei, Yifei, Wang, Zhaoying, Guo, Da, Yu, F Richard
Format: Article
Language:English
Subjects:
Algorithms
Artificial neural networks
Cellular communication
Cloud computing
Computation offloading
Computer simulation
Decision making
Edge computing
Machine learning
Mobile computing
Network latency
Optimization
Wireless networks
Citations: Items that cite this one
Online Access:Get full text
Tags: Add Tag
No Tags, Be the first to tag this record!
Description
Summary:To reduce the transmission latency and mitigate the backhaul burden of the centralized cloud-based network services, the mobile edge computing (MEC) has been drawing increased attention from both industry and academia recently. This paper focuses on mobile users' computation offloading problem in wireless cellular networks with mobile edge computing for the purpose of optimizing the computation offloading decision making policy. Since wireless network states and computing requests have stochastic properties and the environment's dynamics are unknown, we use the model-free reinforcement learning (RL) framework to formulate and tackle the computation offloading problem. Each mobile user learns through interactions with the environment and the estimate of its performance in the form of value function, then it chooses the overhead-aware optimal computation offloading action (local computing or edge computing) based on its state. The state spaces are high-dimensional in our work and value function is unrealistic to estimate. Consequently, we use deep reinforcement learning algorithm, which combines RL method Q-learning with the deep neural network (DNN) to approximate the value functions for complicated control applications, and the optimal policy will be obtained when the value function reaches convergence. Simulation results showed that the effectiveness of the proposed method in comparison with baseline methods in terms of total overheads of all mobile users.
ISSN:1546-2226
1546-2218
1546-2226
DOI:10.32604/cmc.2019.04836