摘要
根据不同周期采样的网络流量数据及其变化趋势,流量预测可以分析网络的运行规律及其特性,定位网络瓶颈,在网络资源管理、拥塞控制和服务质量等方面有重要的应用价值。本文利用不同时间粒度上的真实互联网流量数据,采用时间序列方法对采样流量数据进行建模和预测,将拟合的数学模型与实际网络流量进行对比,发现基于分钟粒度的数据预测误差率在2%以内,可以有效的预测未来短期内的流量走向。
By the network traffic information and trend, traffic analysis can discover the running rule and inner characteristic effective- ly. Moreover, it can locate the performance bottle of network management. All of these can contribute to the application of resource management, congestion control and quality of service. In this paper, we investigate the real network traffic data at different time scale. Based on the time sequence method, a one - step predictive model is presented. Compared with the real data, it can be discovered that the error is within 2%.
出处
《网络新媒体技术》
2015年第5期57-64,共8页
Network New Media Technology
