摘要
针对电力视频业务的流量特性,提出一种基于差分自回归移动平均(ARIMA)模型的电力视频业务流量分析和预测方法.首先利用差分法对视频流量数据进行平稳化处理,然后依据数据序列的自相关函数和偏自相关函数确定模型参数,从而建立能够有效预测电力视频业务流量的分析模型.仿真实验表明,该方法充分考虑了电力视频业务流量的自相似性、周期性、突发性及趋势性等特点,有效提高了流量预测拟合的精度.
Given the characteristics of power video services,a power video traffic analysis and prediction method was proposed based on the autoregressive integrated moving average(ARIMA)model. First,the video traffic data went through the smoothing process through different methods. Then the model parameters were determined by the autocorrelation function and partial autocorrelation function of the data sequence. Thus an effective prediction power video traffic analysis model was established. Simulation results show that the model can meet the characteristics of self-similarity,periodicity,suddenness and trends in power video traffic,and has effectively improved the fitting precision of traffic projections.
出处
《天津大学学报(自然科学与工程技术版)》
EI
CAS
CSCD
北大核心
2015年第1期49-55,共7页
Journal of Tianjin University:Science and Technology
基金
国家自然科学基金资助项目(61172014)
国家国际科技合作与交流专项资助项目(2013DFA11040)
天津市自然科学基金重点资助项目(12JCZDJC21300)
关键词
电力视频业务
流量分析
ARIMA
自相似
power video service
traffic analysis
autoregressive integrated moving average(ARIMA)
selfsimilarity