Scaling Geo-Distributed Network Function Chains: A Prediction and Learning Framework
Scaling Geo-Distributed Network Function Chains: A Prediction and Learning Framework
复制标题
DOI：
10.1109/jsac.2019.2927068
复制
发表时间：
2019-07
影响因子：
16.4
通讯作者：
Ziyue Luo;Chuan Wu;Zongpeng Li;W. Zhou
中科院分区：
文献类型：
--
作者：
Ziyue Luo;Chuan Wu;Zongpeng Li;W. Zhou
地理分布式虚拟网络功能（VNF）链接已经很有用，例如在5G网络中的网络切片和WAN中的网络流量处理中。根据实时流量速率灵活扩展VNF链是网络功能虚拟化的关键。设计有效的扩展算法是具有挑战性的，特别是对于地理分布的链，其中WAN流量引起的带宽成本和延迟很重要，但在做出扩展决策时难以处理。现有的研究大多采用比例设计中的优化算法。为了通过从经验中进行深入学习来做出更好的决策，本文提出了一种基于深度学习的框架，用于扩展地理分布的VNF链，探索流量变化的内在模式和随着时间的推移的良好部署策略。我们新颖地结合了联合收割机作为预测即将到来的流量的流量模型和深度强化学习（DRL）代理，使链布局决策。我们采用的Actor-Critic DRL算法的基础上的经验重放技术，以优化学习结果。跟踪驱动的仿真表明，有限的离线训练，我们的学习框架适应快速在线交通动态，并实现了较低的系统成本，相比现有的代表性算法。
Geo-distributed virtual network function (VNF) chaining has been useful, such as in network slicing in 5G networks and for network traffic processing in the WAN. Agile scaling of the VNF chains according to real-time traffic rates is the key in network function virtualization. Designing efficient scaling algorithms is challenging, especially for geo-distributed chains, where bandwidth costs and latencies incurred by the WAN traffic are important but difficult to handle in making scaling decisions. Existing studies have largely resorted to optimization algorithms in scaling design. Aiming at better decisions empowered by in-depth learning from experiences, this paper proposes a deep learning-based framework for scaling of the geo-distributed VNF chains, exploring inherent pattern of traffic variation and good deployment strategies over time. We novelly combine a recurrent neural network as the traffic model for predicting upcoming flow rates and a deep reinforcement learning (DRL) agent for making chain placement decisions. We adopt the experience replay technique based on the actor–critic DRL algorithm to optimize the learning results. Trace-driven simulation shows that with limited offline training, our learning framework adapts quickly to traffic dynamics online and achieves lower system costs, compared to the existing representative algorithms.