基于深度强化学习的C+L波段弹性光网络频谱分配算法  

Spectrum allocation algorithm for C+L band elastic optical networks based on deep reinforcement learning

作　　者：晏丹 冯楠 左晓博 沈凌飞 任丹萍[1,2] 胡劲华[1,2] 赵继军[1,2] YAN Dan;FENG Nan;ZUO Xiaobo;SHEN Lingfei;REN Danping;HU Jinhua;ZHAO Jijun(School of Informatiation and Electrical Engineering,Hebei University of Engineering,Handan Hebei 056038,China;Hebei Key Laboratory of Security and Protection Information Sensing and Processing,Hebei University of Engineering,Handan Hebei 056038,China;The 54th Research Institute of CETC,Shijiazhuang 050081,China;Hebei Key Laboratory of Photonic Information Technology and Application,Shijiazhuang 050081,China)

机构地区：[1]河北工程大学信息与电气工程学院,河北邯郸056038 [2]河北工程大学河北省安防信息感知与处理重点实验室,河北邯郸056038 [3]中国电子科技集团公司第五十四研究所,石家庄050081 [4]河北省光子信息技术与应用重点实验室,石家庄050081

出　　处：《光通信技术》2024年第3期23-29,共7页Optical Communication Technology

基　　金：河北省硕士在读研究生创新能力培养资助项目(CXZZSS2024101)资助。

摘　　要：针对C+L波段弹性光网络中受激喇曼散射(SRS)效应导致物理层损伤加剧的问题,提出一种基于深度强化学习(DRL)自适应调制格式的频谱分配算法,在路由阶段,采用K最短路由算法为业务请求预计算K条最短备选路径;在波段、调制格式与频谱分配阶段,采用DRL进行智能化决策,并结合了2种奖励函数,以降低网络阻塞率并提高频谱使用效率。仿真结果表明,该算法能够有效降低阻塞率并提高频谱利用率。Aiming at the problem of intensified physical layer damage caused by stimulated Raman scattering(SRS)effect in C+L band elastic optical networks,a spectrum allocation algorithm based on deep reinforcement learning(DRL)adaptive modulation format is proposed.In the routing stage,the-shortest routing algorithm is used to pre calculate shortest candidate paths for business requests.In the stages of band,modulation format,and spectrum allocation,DRL is used for intelligent deci sion-making,and two reward functions are combined to reduce network blocking rate and improve spectrum utilization effi ciency.The simulation results show that the algorithm can effectively reduce blocking rate and improve spectrum utilization.

关 键 词：C+L波段弹性光网络 路由与频谱分配 受激喇曼散射效应 深度强化学习 奖励设计 

分 类 号：TN929.1[电子电信—通信与信息系统]