摘要
能耗和延迟是无线传感器网络（WSN）中的介质访问控制（MAC）协议的主要问题,为此在现有时隙ALOHA协议的基础上,提出一种融合Q学习算法的新型MAC协议：QS-ALOHA。设定每个节点在帧中的每个时隙上,都有一个独立的Q值。根据传输结果,利用Q学习算法进行更新,并将具有高Q值的时隙优先选择来传输数据,以此减小网络中的传输冲突和数据重发。另外,提出了一种马尔可夫模型,证明了协议中学习过程的收敛性。仿真结果表明,该协议在能量效率、延迟和吞吐量方面具有优越的性能。
Energy consumption and delay are the main problem considered in the design of media access control（MAC） in wireless sensor network（WSN）. A new kind of MAC protocol： QS-ALOHA based on Q learning algorithm and existing slotted ALOHA protocol is proposed. Each node has an independent Q value on each time slot in the frame. The Q learning algorithm is used to update the Q value according to the results of the transmission, and the time slot with a high Q value will be chosen priority to transmit data, so as to reduce the network transmission collisions and data retransmission. In addition, a Markov model is proposed to prove the convergence of the learning process. Simulation results show that the proposed protocol has excellent performance in terms of energy efficiency, delay and throughput.
作者
陈思
翟岩
张治斌
CHEN Si;ZHAI Yan;ZHANG Zhi-bin(a.Department of Information Technology;b.Center of Modem Education,Zhengzhou Vocational College of Finance and Taxation,Zhengzhou 450048,Chin;2.School of Computer Science and Technology,Henan University of Technology,Jiaozuo 454000,China)
出处
《控制工程》
CSCD
北大核心
2018年第9期1765-1770,共6页
Control Engineering of China
基金
河南省软科学研究计划资助项目(No.102400450034)
