基于强化学习的FANET自适应MAC协议  

Adaptive MAC protocol based on reinforcement learning for FANET

作　　者：闫涛 赵一帆 高明虎 陈虎 唐嘉宁 YAN Tao;ZHAO Yi-fan;GAO Ming-hu;CHEN Hu;TANG Jia-ning(College of Electrical Information Engineering,Yunnan Minzu University,Kunming 650504,China)

机构地区：[1]云南民族大学电气信息工程学院,云南昆明650504

出　　处：《计算机工程与设计》2024年第9期2613-2619,共7页Computer Engineering and Design

基　　金：国家自然科学基金项目(61963038)。

摘　　要：针对预设的单一媒体接入控制(MAC)协议难以满足飞行自组织网络(FANET)多样化业务需求的问题,提出一种基于Q Learning的FANET自适应MAC协议(FQL-AMAC)。使用两种基准协议联合控制,根据当前网络条件自动选择并切换至服务质量(QoS)显著的MAC协议。优化单个网络性能指标实现QoS局部最优,采用熵值法融合吞吐量、延迟并提出综合性能指标构建奖励函数,以趋近QoS全局最优。实验结果表明,FQL-AMAC能有效选择最佳协议运行,吞吐量、延迟和综合性能表现优于现有协议。To solve the problem that the preset single media access control(MAC)protocol is difficult to meet the diversified service requirements of FANET,an adaptive MAC protocol based on Q Learning for FANET(FQL-AMAC)was proposed.The joint control of the two benchmark protocols was used to automatically select and switch to the MAC protocol with significant quality of service(QoS)according to the current network conditions.A single network performance index was optimized to achieve the local optimum of QoS,and the entropy method was used to fuse the throughput and delay,and the comprehensive performance index was proposed to construct the reward function,so as to approach the global optimum of QoS.The results show that FQL-AMAC can effectively select the best protocol to run,and the performances of throughput,delay and comprehensive performance are better than that of the existing protocols.

关 键 词：飞行自组织网络 媒体接入控制 多样化业务 自适应选择 Q Learning 熵值法 综合性能 

分 类 号：TN929.5[电子电信—通信与信息系统]