SDN网络管理仿真数据

整体数据由西南交通大学于2021年1月产生，该成果针对SDN网络，首先通过分析流表项生存时间对攻击检测的意义，设计了基于流表项属性的检测启动与调度算法，达到自适应地调整每个流表项的检测周期，降低由攻击检测带来的额外网络开销的目的，经同行评议后发表于Journal of Information Security and Applications期刊上。实验产生的数据使用Python处理绘制。支撑论文“ADVICE: Towards adaptive scheduling for data collection and DDoS detection in SDN”。The overall dataset was generated by Southwest Jiaotong University in January 2021. This work focuses on Software-Defined Networking (SDN) networks. First, by analyzing the significance of flow entry lifetime for attack detection, we designed a detection initiation and scheduling algorithm based on flow entry attributes, which can adaptively adjust the detection cycle for each flow entry to reduce the additional network overhead caused by attack detection. It was published in the Journal of Information Security and Applications after peer review. The data generated from the experiments were processed and visualized using Python. This dataset supports the paper titled "ADVICE: Towards adaptive scheduling for data collection and DDoS detection in SDN".

搜集汇总

背景与挑战

背景概述

该数据集由西南交通大学于2021年生成，专注于SDN网络的仿真管理，通过设计自适应检测算法来优化流表项分析，以减少攻击检测带来的网络开销。数据支撑了发表在Journal of Information Security and Applications上的相关论文，包含多种格式文件，总大小为7.16MB。