基于深度强化学习的服务功能链跨域映射算法  

Cross-domain mapping algorithm of service function chain based on deep reinforcement learning

作　　者：朱国晖 李庆 梁申麟 Zhu Guohui;Li Qing;Liang Shenlin(School of Communication&Information Engineering,Xi’an University of Posts&Telecommunications,Xi’an 710121,China)

机构地区：[1]西安邮电大学通信与信息工程学院,西安710121

出　　处：《计算机应用研究》2021年第6期1834-1837,1842,共5页Application Research of Computers

基　　金：国家自然科学基金资助项目(61371087)。

摘　　要：在域内部分信息隔离场景下,针对SFC映射对传输时延和资源开销的影响,提出一种基于深度强化学习的服务功能链跨域映射算法。首先提出一个集中式编排架构,在此架构下上层控制器利用全网格聚合技术来构建抽象拓扑,降低域间映射复杂度;其次将SFC请求分割问题建模为马尔可夫决策过程,使得虚拟网络功能均衡地分配到各个域中;最后以域间传输时延以及映射资源开销为奖励函数构建深度强化学习网络,通过训练完成域间映射,如果域内映射失败则采用反馈机制提高SFC请求接受率。仿真结果表明,该算法有效地减小了传输时延和资源开销,同时提高了请求接受率。This paper proposed a cross-domain mapping algorithm of service function chain based on deep reinforcement learning in view of the influence of SFC mapping on transmission delay and resource cost in the partial information isolation.Firstly,this paper constructed a centralized choreography architecture,which the upper controller utilized the full mesh aggregation technology to construct the abstract topology and reduced the complexity of mapping between domains.Secondly,this paper modeled the SFC request partition problem as Markov decision process,so that virtual network function could evenly distribute in each domain.Finally,this paper constructed the deep reinforcement learning network when taking the inter-domain transmission delay and mapping resource cost as reward function,and completed the inter-domain mapping by training.If the intra-domain mapping fails,used the feedback mechanism to improve the acceptance rate of SFC requests.Simulation results show that the proposed algorithm can effectively reduce the transmission delay and resource cost.Meanwhile,it can improve the request acceptance rate.

关 键 词：多网络域 服务功能链 深度强化学习 反馈机制 

分 类 号：TP393[自动化与计算机技术—计算机应用技术]