CAJ | 학술논문

由于内存限制使得单机环境下的P2P流量识别方法只能对小规模数据集进行处理，并且基于朴素贝叶斯分类的识别方法所使用的属性特征均为人工选择，因此，识别率受到了限制并且缺乏客观性。基于以上问题分析提出了云计算环境下的朴素贝叶斯分类算法并改进了在云计算环境下属性约简算法，结合这两个算法实现了对加密P2P流量的细粒度识别。实验结果表明该方法可以高效处理大数据集网络流量，并且有很高的P2P流量识别率，同时结果也具备客观性。
유우내존한제사득단궤배경하적P2P류량식별방법지능대소규모수거집진행처리，병차기우박소패협사분류적식별방법소사용적속성특정균위인공선택，인차，식별솔수도료한제병차결핍객관성。기우이상문제분석제출료운계산배경하적박소패협사분류산법병개진료재운계산배경하속성약간산법，결합저량개산법실현료대가밀P2P류량적세립도식별。실험결과표명해방법가이고효처리대수거집망락류량，병차유흔고적P2P류량식별솔，동시결과야구비객관성。
Due to memory limitations, P2P traffic identification can only deal with small-scale data sets in a stand-alone environment. And all the attribute characteristics used in the P2P traffic identification based on Bayesian classification are artificial selected. Therefore, the recognition rate is both restricted and lack of objectivity. Based on the above analysis, a Naive Bayesian classification algorithm is proposed in the cloud computing environment, and then an attribute reduction algorithm is improved to adapt to the cloud computing environment. Finally, both above algorithms are combined to achieve fine-grained encrypted P2P traffic identification. The experimental results show that this method can efficiently process large data sets of network traffic, and the recognition rate of P2P flow is high, and the results are objective at the same time.