ID	原文	译文
4133	为提高运营商数据中心流量调度能力，同时考虑网络结构和网络流量两方面因素，设计了一种软件定义网络（SDN）架构数据中心的流量分析预测在线调度机制。	To improve traffic scheduling capabilities in network provider data centers, both network structure and net-work traffic flow were considered at the same time. The analysis prediction and online scheduling mechanism was pro-posed in data center based on software defined networking (SDN).
4134	针对数据中心流量调度的多维、多约束和多模态问题，提出基于斐波那契树优化（FTO）算法的流量调度策略，将 FTO 算法嵌入分析预测和在线调度 2 个阶段，发挥FTO 算法全局局部交替迭代寻优和多模特性，得到流量调度的最优解和多个有价值的次优解。	Aiming at the multi-dimensional, multi-constrainedand multi-modal problems of traffic flow scheduling in data centers, the traffic flow scheduling strategy based on Fibo-nacci tree optimization (FTO) algorithm was proposed. FTO algorithm was embedded into two stages of analysis predic-tion and online scheduling, took it advantage of global local alternating and multi-model optimization characteristics, theoptimal solution and suboptimal solutions of traffic scheduling had been got at one time.
4135	模拟平台验证表明，FTO 流量调度策略能够对数据中心流量进行合理调度，有效提升运营商数据中心网络的负载均衡能力。	The emulator result shows that,the FTO traffic scheduling strategy can schedule traffic in data centers reasonably, which improves the load balancingcapability of network providers' data centers effectively.
4136	为解决现有网络流量异常检测方法需要投喂大量数据且泛化能力较差的问题，提出了基于样本增强的网络恶意流量智能检测方法。	To address the problem that the existing methods of network traffic anomaly detection not only need a largenumber of training sets, but also have poor generalization ability, an intelligent detection method on network malicioustraffic based on sample enhancement was proposed.
4137	所提方法从训练集中提取关键词，且基于关键词回避策略对训练集进行样本增强，提高了方法提取文本特征的能力。	The key words were extracted from the training set and the sample of the training set was enhanced based on the strategy of key word avoidance, and the ability for the method to extract thetext features from the training set was improved.
4138	实验结果表明，所提方法通过小型训练数据集即可提高网络流量异常检测模型的准确率与跨数据集检测能力，相较于其他方法，在显著降低计算复杂度的同时得到了更佳的检测能力。	The experimental results show that, the accuracy of network trafficanomaly detection model and cross dataset can be significantly improved by small training set. Compared with other me-thods, the proposed method can reduce the computational complexity and achieve better detection ability.
4139	针对 IP 跳变技术导致数据分组处理时延高、开销大的问题，基于数据平面开发套件设计并实现了一种多层次网络部署结构的主动防御网关系统。	Aiming at the problems of high packet processing delay and high overhead caused by IP hopping, active de-fense gateway system with multi-layer network deployment structure was designed and implemented based on the dataplane development kit (DPDK).
4140	首先，基于 DPDK 快速转发框架优化了系统的转发和处理性能；	Firstly, based on the DPDK fast forwarding framework, forwarding and processing per-formance of the system were optimized.
4141	其次，针对具有 3 种不同类型 IP 地址的动态化随机映射网关，设计了高效的 IP 地址分配算法以及具有不可预测性的 IP地址变换算法。	Secondly, for the dynamic random mapping gateway with three different types ofIP addresses, an efficient IP address allocation algorithm and an unpredictable IP address conversion algorithm were de-signed.
4142	实验结果表明，所设计的系统在有效减少嗅探攻击信息获取速率的同时，大幅提升了动态跳变导致的处理时延大的问题。	The experimental results show that the designed system can effectively reduce the rate of information acquisitionof sniffing attack, while greatly improving the processing delay caused by dynamic hopping.