面向延迟容忍服务的高能效传输策略

Energy Efficient Transmission Strategy for Delay Tolerance Services

近年来随着互联网技术与应用的快速发展,互联网用户、无线终端设备急剧增多,对于能源的消耗也在不断增加。如何在保证通信业务质量的前提下,降低能量消耗成为了亟待解决的问题。对此,研究了能源效率(Energy-Efficiency,EE)与延迟容忍(Delay Tolerable,DT)服务时延之间的关系。针对离散信道运用了动态统计规划(Statistical Dynamic Programming,SDP)的方法。针对连续信道引入了近似动态统计规划(Approximate Statistical Dynamic Programming,ASDP)的方法。针对没有任何先验信息的情况引入了Q-Learning算法。仿真结果显示,在离散信道中,DT服务可以有效降低传输信息的能耗;但是在连续信道中,DT服务在信道状态较好的条件下并不会明显提升EE。通过仿真结果发现,对于连续信道状态采用Q-Learning算法可以很好地实现传输功率的调整,实现EE的提高。

In recent years,with the rapid development of Internet technology and application,Internet users and wireless terminal equipment are increasing rapidly and energy consumption is also increasing.How to reduce energy consumption on the premise of ensuring communication service quality has become an urgent problem to be solved.The relationship between Energy-Efficiency(EE)and Delay Tolerance(DT)services is studied.Firstly,Statistical Dynamic Programming(SDP)is used for discrete channels.Secondly,Approximate Statistical Dynamic Programming(ASDP)is introduced for continuous channel.Thirdly,the Q-Learning algorithm is introduced in the case of no prior information.The simulation results show that DT service can effectively reduce the energy consumption of information transmission in discrete channels.But in continuous channel,DT service does not significantly improve EE under the condition of good channel status.The simulation results show that Q-Learning algorithm can be used to adjust the transmission power and improve EE.