SDN Clustering Dataset

Future 6G networks will consist of fully soft-warized networks that incorporate in-network intelligence for self-management. However, this intelligent management will require massive data mining, analytics, and processing. Therefore, we need resources like quantum technologies to help achieve 6G key performance indicators. We use Quantum Machine Learning (QML) to solve the controller placement problem for a multi-controller Software Defined Network (SDN). Network delay depends on the controller’s position. Thus, it is critical to choose controllers at locations that minimize latency between the controllers and their associated switches. By using different types of datasets (uniformly distributed and Gaussian distributed datasets), the experimental results indicate that QML can accelerate the computational query of SDN clustering as compared to classical machine learning (like K-means) with comparable latency. To the best of our knowledge, this is the first work thatapplies QML to solve SDN’s controller placement problem.未来的第六代移动通信（6G）网络将由全软件化网络构成，此类网络融合了网络内智能以实现自主管理。然而，此类智能管理需依托大规模数据挖掘、分析与处理。因此，我们亟需量子技术等资源以达成6G关键性能指标。本研究采用量子机器学习（Quantum Machine Learning, QML）求解多控制器软件定义网络（Software Defined Network, SDN）的控制器放置问题。网络时延取决于控制器的部署位置，因此选择可最小化控制器与其关联交换机间时延的位置部署控制器至关重要。通过使用两类不同数据集——均匀分布数据集与高斯分布数据集，实验结果表明，相较于经典机器学习（如K均值聚类），量子机器学习可在时延性能相当的前提下，加速SDN聚类的计算查询流程。据我们所知，本研究是首次将量子机器学习应用于求解SDN控制器放置问题的工作。