ID	原文	译文
44486	在模拟实验中，将其与 Dijkstra 算法进行比较，数据结果显示路径选择结果满足 QoS 要求，算法可行有效。	Comparing with Dijkstra algorithm in the simulation, the result of the experiment shows that the algorithm achieves QoS requirement and is feasible.
44487	针对有效区分分组丢失类别问题，提出了一种端到端多参数度量自适应拥塞控制算法——TCP-NBayes算法。	The traditional TCP protocol attributes frequent random packet loss in the network to congestion, which greatly reduces network performance. Aiming at effectively distinguishing the packet loss category and improving the network transmission performance problem, an end-to-end multi-parameter metric adaptive congestion control strategy is proposed.
44488	然后基于朴素贝叶斯理论建立区分无线随机丢失和拥塞丢失的鉴别模型。	TCP-NBayes, based on the naive Bayesian theory in machine learning, establishes the distinction between wireless random loss and identification model for congestion loss.
44489	仿真实验表明该算法分类准确度最高可达 95%，与其他算法相比，其友好性与公平性表现良好，对网络性能有很大的改善。	Simulation experiments show that the classification accuracy of this method is up to 95%. Compared with other algorithms, the friendliness and fairness are good, and the network performance is greatly improved.
44490	针对经典的最大流 Dinic 算法反复沿着无效路径搜索造成的时间浪费问题，提出了一种基于有效反向网络的最大流算法。	In the classical max flow Dinic algorithm, repeated search along the invalid path causes time wastage. A maximum flow algorithm based on effective reverse network was proposed.
44491	算法修改了汇点的深度定义，在计算节点深度过程中构建了有效反向网络，从汇点出发搜索增广路径，降低了节点深度计算的次数，同时避免了反复搜索无效路径。	The algorithm modified the depth definition of the sink point, constructed an effective reverse network in the process of calculating the node depth, and searched for the augmented path from the sink point. The times of node depth calculations is reduced, and the repeated searches along invalid paths is avoided.
44492	实验结果表明，基于有效反向网络的最大流算法的求解速度优于 Dinic 算法。	The experimental results show that the maximum flow algorithm based on effective reverse network in time performance has a greater advantage than Dinic algorithm.
44493	随着以可编程协议无关报文处理语言（P4，programming protocol-independent packet processors）为主要编程语言的可编程数据平面的兴起，给网络遥测领域带来了新的发展机遇。	With the rise of programmable data plane with P4 as the main programming language, it brings new opportunities for network telemetry.
44494	带内网络遥测（INT, In-band network telemetry）就是其中一种具有代表性的能够探测到设备级遥测数据的被动遥测技术。	INT is one of the typical passive telemetry techniques that can detect device-level telemetry data.
44495	然而 INT 的探测范围受到探测点部署位置的限制，难以获取全局网络视图。	However, the detection scope of INT is limited by the deploy field of vantage points. Therefore, it is hard to achieve the global network view.