基于人工免疫和FARIMA模型的流量预测方法研究

The study of traffic prediction method based on artificial immune and FARIMA model

针对Internet迅速发展而造成的网络拥塞现象,基于人工免疫算法与FARIMA模型提出了一种新的流量预测方法PAIF(Prediction method based on Artificial Immune and FA-RIMA).该方法首先利用人工免疫算法建立了预测策略,并结合FARIMA模型预测结果进行融合,以此提高预测精度.其次,以实际数据进行仿真实验,深入研究了影响PAIF预测误差的因素,同时对比分析了单独使用FARIMA模型的情况.实验结果表明,PPAIF具有较好的适应性.

In order to mitigate network congestion caused by the rapid growth of Internet,a novel traffic prediction method PAIF（Prediction method based on Artificial Immune and FARIMA） is proposed by artificial immune and FARIMA model.In this algorithm,the prediction strategy is presented with artificial immune at first,and the prediction accuracy is improved with the fusion traffic which is predicted by FARIMA model.Then,a simulation with actual data was conducted to research on the influence factors of error for PAIF,and the predicted data of FARIMA model was compared in simulation.The result shows that PAIF has better adaptability.