欢迎您！东篱公司
退出
-
申报数据库
-
立项数据库
-
成果数据库
-
项目获奖数据库
中文摘要：
高速网络中及时准确地识别大流量对象对网络测量、控制和管理有重要的意义.该文提出了一种基于两级LRU机制的大流检测算法并分析了新算法中的参数与平均误差之间的关系.新算法通过增加一级用于过滤小流的LRU提高测量准确性.算法分析表明：新算法具有10Gbps的线速处理能力.该文基于实际互联网数据进行了实验对比,结果显示：与现有算法相比,新算法具有更高的测量准确性和实用性.
英文摘要：
Identifying large flows promptly and accurately is important for network measurement,network control and net- work management. This paper presents a new algorithm based on Dual-LRU mechanism and analyzes the relationship between the parameters and the average error. The proposed algorithm utilizes another LRU to filter the small flows and improve the accuracy of large flow identifications.An analysis demonstrates that the new algorithm can support the 10Gbps line-speed processing. Experi- ments are also conducted based on real network traces. Results show that the proposed algorithm is more accurate and practicable than existing algorithms.
同期刊论文项目
同项目期刊论文
位置：