面向智能通信的深度强化学习方法  

Deep Reinforcement Learning for Intelligent Communications

作　　者：谭俊杰 梁应敞 TAN Jun-jie;LIANG Ying-chang(National Key Laboratory of Science and Technology on Communications,University of Electronic Science and Technology of China Chengdu 611731)

机构地区：[1]电子科技大学通信抗干扰技术国家级重点实验室,成都611731

出　　处：《电子科技大学学报》2020年第2期169-181,共13页Journal of University of Electronic Science and Technology of China

基　　金：国家自然科学基金(61631005,U1801261);国家重点研发计划(2018YFB1801105)。

摘　　要：在如今信息爆炸的时代,无线通信终端的激增导致无线通信网络规模剧增。同时,人们日益提高的通信需求使无线通信网络必须通过精准的按需服务来充分利用有限的资源。这二者使得传统人工建模并优化求解的网络管理方法在未来将会遇到瓶颈。幸运的是,人工智能和机器学习的出现为解决这一问题提供了新的途径。作为一种数据驱动的机器学习方法,深度强化学习能够直接学习动态环境规律并得到最优决策。因此,深度强化学习能赋予网络依据自身环境进行自我优化管理的能力,令智能通信将成为可能。本文从资源管理、接入控制以及网络维护三方面介绍了深度强化学习在无线通信上的应用,以此说明深度强化学习是实现智能通信的有效途径。In the era of data explosion,the rapid growth of mobile devices makes the size of wireless networks increase tremendously.Meanwhile,people are having higher demands for wireless communications,which requires the networks to provide precisely on-demand services in order to exploit the limited resource.Due to the above two reasons,the traditional modeling-and-optimizing methods for network management will meet the performance bottleneck in the future.Fortunately,the appearance of artificial intelligence and machine learning provides a new solution to this issue.As a data-driven machine learning technique,deep reinforcement learning can directly learn the pattern of dynamic environments and use it to make optimal decisions.Hence,deep reinforcement learning enables wireless networks to manage and optimize themselves based on their environments,which makes it possible to realize intelligent communications.This paper introduces the application of deep reinforcement learning on wireless communications from the aspects of resource management,access control,and network maintenance,and illustrates that deep reinforcement learning is an effective approach to realizing intelligent communications.

关 键 词：深度强化学习 异构网络 智能通信 智能网络管理 

分 类 号：TN929.5[电子电信—通信与信息系统]