会议专题

An Energy-Efficient Resource Allocation Strategy for Vehicular Networks

  Vehicular networks have drawn many researchers'attention for the reason that vehicular networks can change the op-eration of vehicles into a safer and greener state.Resource allocation is one of important problems in vehicular network-s.In this paper,to achieve a good trade-off between energy efficiency and transmission latency,a novel resource alloca-tion method is proposed based on actor-critic reinforcemen-t learning approach.As known,actor-critic reinforcement learning is an acknowledged solution for the problem with continuous valued state and action variables.Further,consid-ering that edge computing technology for vehicular networks,the architecture of fog radio access network(F-RAN)is ex-ploited to formulate the resource allocation problem in this paper.By adopting fog computing,the transmission delay is decreased because the F-RAN nodes with computing abili-ty,are very close to vehicles so that the related information message does not need to be transmitted through the whole vehicular network.Further,to increase access capacity,the proposed method is deployed into non-orthogonal multiple access(NOMA)system.

Actor-critic reinforcement learning resource allocation non-orthogonal multiple access(NOMA)

Zhuoheng Li Jian Liu Yueyun Chen

School of Computer and Communication Engineering,University of Science and Technology Beijing

国际会议

2019国图灵大会(ACM Turing Celebration conference-China 2019 )

成都

英文

763-770

2019-05-17(万方平台首次上网日期,不代表论文的发表时间)