TY - JOUR
T1 - When Deep Reinforcement Learning Meets 5G-Enabled Vehicular Networks
T2 - A Distributed Offloading Framework for Traffic Big Data
AU - Ning, Zhaolong
AU - Li, Ye
AU - Dong, Peiran
AU - Wang, Xiaojie
AU - Obaidat, Mohammad S.
AU - Hu, Xiping
AU - Guo, Lei
AU - Guo, Yi
AU - Huang, Jun
AU - Hu, Bin
N1 - Publisher Copyright:
© 2005-2012 IEEE.
PY - 2020/2
Y1 - 2020/2
N2 - The emerging 5G-enabled vehicular networks can satisfy various requirements of vehicles by traffic offloading. However, limited cellular spectrum and energy supplies restrict the development of 5G-enabled applications in vehicular networks. In this article, we construct an intelligent offloading framework for 5G-enabled vehicular networks, by jointly utilizing licensed cellular spectrum and unlicensed channels. A cost minimization problem is formulated by considering the latency constraint of users and is further decomposed into two subproblems due to its complexity. For the first subproblem, a two-sided matching algorithm is proposed to schedule the unlicensed spectrum. Then, a deep-reinforcement-learning-based method is investigated for the second one, where the system state is simplified to realize distributed traffic offloading. Real-world traces of taxies are leveraged to illustrate the effectiveness of our solution.
AB - The emerging 5G-enabled vehicular networks can satisfy various requirements of vehicles by traffic offloading. However, limited cellular spectrum and energy supplies restrict the development of 5G-enabled applications in vehicular networks. In this article, we construct an intelligent offloading framework for 5G-enabled vehicular networks, by jointly utilizing licensed cellular spectrum and unlicensed channels. A cost minimization problem is formulated by considering the latency constraint of users and is further decomposed into two subproblems due to its complexity. For the first subproblem, a two-sided matching algorithm is proposed to schedule the unlicensed spectrum. Then, a deep-reinforcement-learning-based method is investigated for the second one, where the system state is simplified to realize distributed traffic offloading. Real-world traces of taxies are leveraged to illustrate the effectiveness of our solution.
KW - 5G-enabled vehicular networks
KW - Deep reinforcement learning (DRL)
KW - distributed offloading
KW - traffic big data
UR - http://www.scopus.com/inward/record.url?scp=85078702346&partnerID=8YFLogxK
U2 - 10.1109/TII.2019.2937079
DO - 10.1109/TII.2019.2937079
M3 - Article
AN - SCOPUS:85078702346
SN - 1551-3203
VL - 16
SP - 1352
EP - 1361
JO - IEEE Transactions on Industrial Informatics
JF - IEEE Transactions on Industrial Informatics
IS - 2
M1 - 8809673
ER -
