ID 原文 译文
52407 网络应用的发展造成接入网流量复杂多样，对接入网数据流量的精细化管控成为业务运营方和管理者的紧迫需求，网络流量的识别与监控对保障网络安全具有越来越重要的作用。 The development of network applications makes the access network traffic complex and diverse. Fine control of access network data traffic has become an urgent need for service operators and managers.
52408 在对以太网无源光网络流量识别系统需求分析的基础上，给出一种基于现场可编程门阵列 (FPGA) 的流量识别系统串接前端的硬件架构，并详细介绍了其中关键匹配引擎模块的设计方案。 Based on the requirement analysis in Ethernet Passive Optical Network (EPON) traffic identification system, a hardware architecture based on Field Programmable Gate Array (FPGA) is presented. The key design scheme of matching engine module is introduced in detail.
52409 经过测试，原型系统能够在不引入较大时延的情况下，对10Gbit/s EPON线路数据帧前64字节固定字段进行线速流量识别， The test results show that the prototype system can identify the first 64 bytes fixed fields of 10Gbit/s EPON line data frame in line speed without introducing significant latency.
52410 完成对以太网数据的匹配与串接管控操作，为后端分析系统进一步解析数据流量提供有效的支撑。 It also completes the matching of Ethernet network data and control, and provides effective support for the back-end analysis system for further data parsing.
52411 基于时间窗的告警事务集选取直接影响告警关联规则挖掘的有效性，同时，智能光网络告警的内在关联性使其具备一定的聚类关系， The selection of alarm transaction set based on time window directly affects the effectiveness of alarm association rule mining, and the internal correlation of Automatically Switched Optical Network (ASON) alarm makes it have a certain clustering relationship.
52412 据此提出一种基于业务时间窗选取的告警聚类及关联方法。 Therefore, we propose a alarm clustering and correlation method based on business time window selection.
52413 首先根据网络业务配置情况对多网元告警进行聚类， The multi-network alarm is first clustered according to the network business configuration.
52414 然后通过确定告警增长期进行时间窗划分，生成关联性更强的告警事务集， Then the time window is divided to generate a more strongly correlated alarm transaction set by determining the alarm growth period.
52415 并进一步挖掘告警关联规则。 Finally, we also investigate the alarm association rules.
52416 该方法能够适应智能光网络多平面和多网元告警内在关联的特点，可有效压缩告警事务集，提高告警关联规则的准确度，为后续故障诊断提供支撑。 This method can adapt to the characteristics of multi-plane and multi-network alarm internal correlation of intelligent optical network, which has the advantages of effectively compressing the alarm transaction set, higher accuracy of alarm association rules, and support for subsequent fault diagnosis.