首页|Deep Reinforcement Learning for Multi-user Resource Allocation of Wireless Body Area Network
Deep Reinforcement Learning for Multi-user Resource Allocation of Wireless Body Area Network
扫码查看
点击上方二维码区域，可以放大扫码查看
原文链接
NETL
Springer Nature
The development of wireless body area network technology allows it to be widely used in various fields such as medical monitoring， sports， and entertainment， but the lack of spectrum resources also makes the interference between networks worse。 Aiming at the optimization problem of multi-user resource allocation in wireless body area network， an allocation algorithm based on deep reinforcement learning is proposed。 Facing the unknown and complex dynamic network environment and co-frequency interference between channels， Q-learning can effectively improve communication efficiency with the advantages of strong adaptability and no need to model the external environment。 Regarding energy use efficiency as rewards and punishments by training agents constantly interacts with the external environment to gain experience， dynamically adjusting policy of allocation and decision， so as to obtain a nearly optimal allocation strategy。 The communication efficiency and performance are significantly improved with the algorithm proposed。
Wireless body area networkResource allocationDeep reinforcement learning
Xiuzhi Xu、Jiasong Mu、Tiantian Zhang
展开 >
Tianjin Normal University, TianJin 300387, China
International Conference on Communications, Signal Processing, and Systems
NETL
Springer Nature
